diff options
Diffstat (limited to '')
68 files changed, 6736 insertions, 2271 deletions
diff --git a/libnetdata/Makefile.am b/libnetdata/Makefile.am index f01a1d34..333155aa 100644 --- a/libnetdata/Makefile.am +++ b/libnetdata/Makefile.am @@ -8,9 +8,11 @@ SUBDIRS = \ aral \ avl \ buffer \ + buffered_reader \ clocks \ completion \ config \ + datetime \ dictionary \ ebpf \ eval \ @@ -19,6 +21,7 @@ SUBDIRS = \ json \ july \ health \ + line_splitter \ locks \ log \ onewayalloc \ @@ -31,10 +34,12 @@ SUBDIRS = \ string \ threads \ url \ + uuid \ worker_utilization \ tests \ $(NULL) dist_noinst_DATA = \ README.md \ + gorilla/README.md \ $(NULL) diff --git a/libnetdata/buffer/buffer.c b/libnetdata/buffer/buffer.c index feee72fc..64f9cce4 100644 --- a/libnetdata/buffer/buffer.c +++ b/libnetdata/buffer/buffer.c @@ -81,6 +81,7 @@ void buffer_snprintf(BUFFER *wb, size_t len, const char *fmt, ...) va_list args; va_start(args, fmt); + // vsnprintfz() returns the number of bytes actually written - after possible truncation wb->len += vsnprintfz(&wb->buffer[wb->len], len, fmt, args); va_end(args); @@ -89,53 +90,39 @@ void buffer_snprintf(BUFFER *wb, size_t len, const char *fmt, ...) // the buffer is \0 terminated by vsnprintfz } -void buffer_vsprintf(BUFFER *wb, const char *fmt, va_list args) -{ +inline void buffer_vsprintf(BUFFER *wb, const char *fmt, va_list args) { if(unlikely(!fmt || !*fmt)) return; - size_t wrote = 0, need = 2, space_remaining = 0; + size_t full_size_bytes = 0, need = 2, space_remaining = 0; do { - need += space_remaining * 2; + need += full_size_bytes + 2; - netdata_log_debug(D_WEB_BUFFER, "web_buffer_sprintf(): increasing web_buffer at position %zu, size = %zu, by %zu bytes (wrote = %zu)\n", wb->len, wb->size, need, wrote); buffer_need_bytes(wb, need); space_remaining = wb->size - wb->len - 1; - wrote = (size_t) vsnprintfz(&wb->buffer[wb->len], space_remaining, fmt, args); + // Use the copy of va_list for vsnprintf + va_list args_copy; + va_copy(args_copy, args); + // vsnprintf() returns the number of bytes required, even if bigger than the buffer provided + full_size_bytes = (size_t) vsnprintf(&wb->buffer[wb->len], space_remaining, fmt, args_copy); + va_end(args_copy); - } while(wrote >= space_remaining); + } while(full_size_bytes >= space_remaining); - wb->len += wrote; + wb->len += full_size_bytes; - // the buffer is \0 terminated by vsnprintf + wb->buffer[wb->len] = '\0'; + buffer_overflow_check(wb); } void buffer_sprintf(BUFFER *wb, const char *fmt, ...) { - if(unlikely(!fmt || !*fmt)) return; - va_list args; - size_t wrote = 0, need = 2, space_remaining = 0; - - do { - need += space_remaining * 2; - - netdata_log_debug(D_WEB_BUFFER, "web_buffer_sprintf(): increasing web_buffer at position %zu, size = %zu, by %zu bytes (wrote = %zu)\n", wb->len, wb->size, need, wrote); - buffer_need_bytes(wb, need); - - space_remaining = wb->size - wb->len - 1; - - va_start(args, fmt); - wrote = (size_t) vsnprintfz(&wb->buffer[wb->len], space_remaining, fmt, args); - va_end(args); - - } while(wrote >= space_remaining); - - wb->len += wrote; - - // the buffer is \0 terminated by vsnprintf + va_start(args, fmt); + buffer_vsprintf(wb, fmt, args); + va_end(args); } // generate a javascript date, the fastest possible way... @@ -301,12 +288,15 @@ void buffer_json_initialize(BUFFER *wb, const char *key_quote, const char *value strncpyz(wb->json.key_quote, key_quote, BUFFER_QUOTE_MAX_SIZE); strncpyz(wb->json.value_quote, value_quote, BUFFER_QUOTE_MAX_SIZE); - wb->json.options = options; wb->json.depth = (int8_t)(depth - 1); _buffer_json_depth_push(wb, BUFFER_JSON_OBJECT); if(add_anonymous_object) buffer_fast_strcat(wb, "{", 1); + else + options |= BUFFER_JSON_OPTIONS_NON_ANONYMOUS; + + wb->json.options = options; wb->content_type = CT_APPLICATION_JSON; buffer_no_cacheable(wb); @@ -316,9 +306,14 @@ void buffer_json_finalize(BUFFER *wb) { while(wb->json.depth >= 0) { switch(wb->json.stack[wb->json.depth].type) { case BUFFER_JSON_OBJECT: - buffer_json_object_close(wb); + if (wb->json.depth == 0) + if (!(wb->json.options & BUFFER_JSON_OPTIONS_NON_ANONYMOUS)) + buffer_json_object_close(wb); + else + _buffer_json_depth_pop(wb); + else + buffer_json_object_close(wb); break; - case BUFFER_JSON_ARRAY: buffer_json_array_close(wb); break; diff --git a/libnetdata/buffer/buffer.h b/libnetdata/buffer/buffer.h index 26efe007..88d3f028 100644 --- a/libnetdata/buffer/buffer.h +++ b/libnetdata/buffer/buffer.h @@ -72,6 +72,7 @@ typedef enum __attribute__ ((__packed__)) { BUFFER_JSON_OPTIONS_DEFAULT = 0, BUFFER_JSON_OPTIONS_MINIFY = (1 << 0), BUFFER_JSON_OPTIONS_NEWLINE_ON_ARRAY_ITEMS = (1 << 1), + BUFFER_JSON_OPTIONS_NON_ANONYMOUS = (1 << 2), } BUFFER_JSON_OPTIONS; typedef struct web_buffer { @@ -93,6 +94,8 @@ typedef struct web_buffer { } json; } BUFFER; +#define CLEAN_BUFFER _cleanup_(buffer_freep) BUFFER + #define buffer_cacheable(wb) do { (wb)->options |= WB_CONTENT_CACHEABLE; if((wb)->options & WB_CONTENT_NO_CACHEABLE) (wb)->options &= ~WB_CONTENT_NO_CACHEABLE; } while(0) #define buffer_no_cacheable(wb) do { (wb)->options |= WB_CONTENT_NO_CACHEABLE; if((wb)->options & WB_CONTENT_CACHEABLE) (wb)->options &= ~WB_CONTENT_CACHEABLE; (wb)->expires = 0; } while(0) @@ -134,6 +137,10 @@ BUFFER *buffer_create(size_t size, size_t *statistics); void buffer_free(BUFFER *b); void buffer_increase(BUFFER *b, size_t free_size_required); +static inline void buffer_freep(BUFFER **bp) { + if(bp) buffer_free(*bp); +} + void buffer_snprintf(BUFFER *wb, size_t len, const char *fmt, ...) PRINTFLIKE(3, 4); void buffer_vsprintf(BUFFER *wb, const char *fmt, va_list args); void buffer_sprintf(BUFFER *wb, const char *fmt, ...) PRINTFLIKE(2,3); @@ -209,6 +216,13 @@ static inline void buffer_fast_rawcat(BUFFER *wb, const char *txt, size_t len) { buffer_overflow_check(wb); } +static inline void buffer_putc(BUFFER *wb, char c) { + buffer_need_bytes(wb, 2); + wb->buffer[wb->len++] = c; + wb->buffer[wb->len] = '\0'; + buffer_overflow_check(wb); +} + static inline void buffer_fast_strcat(BUFFER *wb, const char *txt, size_t len) { if(unlikely(!txt || !*txt || !len)) return; @@ -282,6 +296,19 @@ static inline void buffer_strncat(BUFFER *wb, const char *txt, size_t len) { buffer_overflow_check(wb); } +static inline void buffer_memcat(BUFFER *wb, const void *mem, size_t bytes) { + if(unlikely(!mem)) return; + + buffer_need_bytes(wb, bytes + 1); + + memcpy(&wb->buffer[wb->len], mem, bytes); + + wb->len += bytes; + wb->buffer[wb->len] = '\0'; + + buffer_overflow_check(wb); +} + static inline void buffer_json_strcat(BUFFER *wb, const char *txt) { if(unlikely(!txt || !*txt)) return; @@ -809,8 +836,13 @@ static inline void buffer_json_member_add_boolean(BUFFER *wb, const char *key, b static inline void buffer_json_member_add_array(BUFFER *wb, const char *key) { buffer_print_json_comma_newline_spacing(wb); - buffer_print_json_key(wb, key); - buffer_fast_strcat(wb, ":[", 2); + if (key) { + buffer_print_json_key(wb, key); + buffer_fast_strcat(wb, ":[", 2); + } + else + buffer_fast_strcat(wb, "[", 1); + wb->json.stack[wb->json.depth].count++; _buffer_json_depth_push(wb, BUFFER_JSON_ARRAY); @@ -860,6 +892,13 @@ static inline void buffer_json_add_array_item_uint64(BUFFER *wb, uint64_t value) wb->json.stack[wb->json.depth].count++; } +static inline void buffer_json_add_array_item_boolean(BUFFER *wb, bool value) { + buffer_print_json_comma_newline_spacing(wb); + + buffer_strcat(wb, value ? "true" : "false"); + wb->json.stack[wb->json.depth].count++; +} + static inline void buffer_json_add_array_item_time_t(BUFFER *wb, time_t value) { buffer_print_json_comma_newline_spacing(wb); @@ -959,12 +998,14 @@ typedef enum __attribute__((packed)) { RRDF_FIELD_OPTS_STICKY = (1 << 2), // the field should be sticky RRDF_FIELD_OPTS_FULL_WIDTH = (1 << 3), // the field should get full width RRDF_FIELD_OPTS_WRAP = (1 << 4), // the field should wrap - RRDR_FIELD_OPTS_DUMMY = (1 << 5), // not a presentable field + RRDF_FIELD_OPTS_DUMMY = (1 << 5), // not a presentable field + RRDF_FIELD_OPTS_EXPANDED_FILTER = (1 << 6), // show the filter expanded } RRDF_FIELD_OPTIONS; typedef enum __attribute__((packed)) { RRDF_FIELD_TYPE_NONE, RRDF_FIELD_TYPE_INTEGER, + RRDF_FIELD_TYPE_BOOLEAN, RRDF_FIELD_TYPE_STRING, RRDF_FIELD_TYPE_DETAIL_STRING, RRDF_FIELD_TYPE_BAR_WITH_INTEGER, @@ -982,6 +1023,9 @@ static inline const char *rrdf_field_type_to_string(RRDF_FIELD_TYPE type) { case RRDF_FIELD_TYPE_INTEGER: return "integer"; + case RRDF_FIELD_TYPE_BOOLEAN: + return "boolean"; + case RRDF_FIELD_TYPE_STRING: return "string"; @@ -1112,7 +1156,7 @@ static inline const char *rrdf_field_summary_to_string(RRDF_FIELD_SUMMARY summar } typedef enum __attribute__((packed)) { - RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_FILTER_NONE = 0, RRDF_FIELD_FILTER_RANGE, RRDF_FIELD_FILTER_MULTISELECT, RRDF_FIELD_FILTER_FACET, @@ -1173,8 +1217,9 @@ buffer_rrdf_table_add_field(BUFFER *wb, size_t field_id, const char *key, const buffer_json_member_add_boolean(wb, "full_width", options & RRDF_FIELD_OPTS_FULL_WIDTH); buffer_json_member_add_boolean(wb, "wrap", options & RRDF_FIELD_OPTS_WRAP); + buffer_json_member_add_boolean(wb, "default_expanded_filter", options & RRDF_FIELD_OPTS_EXPANDED_FILTER); - if(options & RRDR_FIELD_OPTS_DUMMY) + if(options & RRDF_FIELD_OPTS_DUMMY) buffer_json_member_add_boolean(wb, "dummy", true); } buffer_json_object_close(wb); diff --git a/libnetdata/buffered_reader/Makefile.am b/libnetdata/buffered_reader/Makefile.am new file mode 100644 index 00000000..161784b8 --- /dev/null +++ b/libnetdata/buffered_reader/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/libnetdata/buffered_reader/README.md b/libnetdata/buffered_reader/README.md new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/libnetdata/buffered_reader/README.md diff --git a/libnetdata/buffered_reader/buffered_reader.c b/libnetdata/buffered_reader/buffered_reader.c new file mode 100644 index 00000000..7cd17abf --- /dev/null +++ b/libnetdata/buffered_reader/buffered_reader.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" diff --git a/libnetdata/buffered_reader/buffered_reader.h b/libnetdata/buffered_reader/buffered_reader.h new file mode 100644 index 00000000..4db57cd2 --- /dev/null +++ b/libnetdata/buffered_reader/buffered_reader.h @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_BUFFERED_READER_H +#define NETDATA_BUFFERED_READER_H + +struct buffered_reader { + ssize_t read_len; + ssize_t pos; + char read_buffer[PLUGINSD_LINE_MAX + 1]; +}; + +static inline void buffered_reader_init(struct buffered_reader *reader) { + reader->read_buffer[0] = '\0'; + reader->read_len = 0; + reader->pos = 0; +} + +typedef enum { + BUFFERED_READER_READ_OK = 0, + BUFFERED_READER_READ_FAILED = -1, + BUFFERED_READER_READ_BUFFER_FULL = -2, + BUFFERED_READER_READ_POLLERR = -3, + BUFFERED_READER_READ_POLLHUP = -4, + BUFFERED_READER_READ_POLLNVAL = -5, + BUFFERED_READER_READ_POLL_UNKNOWN = -6, + BUFFERED_READER_READ_POLL_TIMEOUT = -7, + BUFFERED_READER_READ_POLL_FAILED = -8, +} buffered_reader_ret_t; + + +static inline buffered_reader_ret_t buffered_reader_read(struct buffered_reader *reader, int fd) { +#ifdef NETDATA_INTERNAL_CHECKS + if(reader->read_buffer[reader->read_len] != '\0') + fatal("read_buffer does not start with zero"); +#endif + + char *read_at = reader->read_buffer + reader->read_len; + ssize_t remaining = sizeof(reader->read_buffer) - reader->read_len - 1; + + if(unlikely(remaining <= 0)) + return BUFFERED_READER_READ_BUFFER_FULL; + + ssize_t bytes_read = read(fd, read_at, remaining); + if(unlikely(bytes_read <= 0)) + return BUFFERED_READER_READ_FAILED; + + reader->read_len += bytes_read; + reader->read_buffer[reader->read_len] = '\0'; + + return BUFFERED_READER_READ_OK; +} + +static inline buffered_reader_ret_t buffered_reader_read_timeout(struct buffered_reader *reader, int fd, int timeout_ms, bool log_error) { + errno = 0; + struct pollfd fds[1]; + + fds[0].fd = fd; + fds[0].events = POLLIN; + + int ret = poll(fds, 1, timeout_ms); + + if (ret > 0) { + /* There is data to read */ + if (fds[0].revents & POLLIN) + return buffered_reader_read(reader, fd); + + else if(fds[0].revents & POLLERR) { + if(log_error) + netdata_log_error("PARSER: read failed: POLLERR."); + return BUFFERED_READER_READ_POLLERR; + } + else if(fds[0].revents & POLLHUP) { + if(log_error) + netdata_log_error("PARSER: read failed: POLLHUP."); + return BUFFERED_READER_READ_POLLHUP; + } + else if(fds[0].revents & POLLNVAL) { + if(log_error) + netdata_log_error("PARSER: read failed: POLLNVAL."); + return BUFFERED_READER_READ_POLLNVAL; + } + + if(log_error) + netdata_log_error("PARSER: poll() returned positive number, but POLLIN|POLLERR|POLLHUP|POLLNVAL are not set."); + return BUFFERED_READER_READ_POLL_UNKNOWN; + } + else if (ret == 0) { + if(log_error) + netdata_log_error("PARSER: timeout while waiting for data."); + return BUFFERED_READER_READ_POLL_TIMEOUT; + } + + if(log_error) + netdata_log_error("PARSER: poll() failed with code %d.", ret); + return BUFFERED_READER_READ_POLL_FAILED; +} + +/* Produce a full line if one exists, statefully return where we start next time. + * When we hit the end of the buffer with a partial line move it to the beginning for the next fill. + */ +static inline bool buffered_reader_next_line(struct buffered_reader *reader, BUFFER *dst) { + buffer_need_bytes(dst, reader->read_len - reader->pos + 2); + + size_t start = reader->pos; + + char *ss = &reader->read_buffer[start]; + char *se = &reader->read_buffer[reader->read_len]; + char *ds = &dst->buffer[dst->len]; + char *de = &ds[dst->size - dst->len - 2]; + + if(ss >= se) { + *ds = '\0'; + reader->pos = 0; + reader->read_len = 0; + reader->read_buffer[reader->read_len] = '\0'; + return false; + } + + // copy all bytes to buffer + while(ss < se && ds < de && *ss != '\n') { + *ds++ = *ss++; + dst->len++; + } + + // if we have a newline, return the buffer + if(ss < se && ds < de && *ss == '\n') { + // newline found in the r->read_buffer + + *ds++ = *ss++; // copy the newline too + dst->len++; + + *ds = '\0'; + + reader->pos = ss - reader->read_buffer; + return true; + } + + reader->pos = 0; + reader->read_len = 0; + reader->read_buffer[reader->read_len] = '\0'; + return false; +} + +#endif //NETDATA_BUFFERED_READER_H diff --git a/libnetdata/clocks/clocks.c b/libnetdata/clocks/clocks.c index 489e9685..adbad045 100644 --- a/libnetdata/clocks/clocks.c +++ b/libnetdata/clocks/clocks.c @@ -7,8 +7,14 @@ static clockid_t clock_boottime_to_use = CLOCK_MONOTONIC; static clockid_t clock_monotonic_to_use = CLOCK_MONOTONIC; -usec_t clock_monotonic_resolution = 1000; -usec_t clock_realtime_resolution = 1000; +// the default clock resolution is 1ms +#define DEFAULT_CLOCK_RESOLUTION_UT ((usec_t)0 * USEC_PER_SEC + (usec_t)1 * USEC_PER_MS) + +// the max clock resolution is 10ms +#define MAX_CLOCK_RESOLUTION_UT ((usec_t)0 * USEC_PER_SEC + (usec_t)10 * USEC_PER_MS) + +usec_t clock_monotonic_resolution = DEFAULT_CLOCK_RESOLUTION_UT; +usec_t clock_realtime_resolution = DEFAULT_CLOCK_RESOLUTION_UT; #ifndef HAVE_CLOCK_GETTIME inline int clock_gettime(clockid_t clk_id __maybe_unused, struct timespec *ts) { @@ -50,9 +56,24 @@ static void test_clock_boottime(void) { } static usec_t get_clock_resolution(clockid_t clock) { - struct timespec ts; - clock_getres(clock, &ts); - return ts.tv_sec * USEC_PER_SEC + ts.tv_nsec * NSEC_PER_USEC; + struct timespec ts = { 0 }; + + if(clock_getres(clock, &ts) == 0) { + usec_t ret = (usec_t)ts.tv_sec * USEC_PER_SEC + (usec_t)ts.tv_nsec / NSEC_PER_USEC; + if(!ret && ts.tv_nsec > 0 && ts.tv_nsec < NSEC_PER_USEC) + return (usec_t)1; + + else if(ret > MAX_CLOCK_RESOLUTION_UT) { + nd_log(NDLS_DAEMON, NDLP_ERR, "clock_getres(%d) returned %"PRIu64" usec is out of range, using defaults for clock resolution.", (int)clock, ret); + return DEFAULT_CLOCK_RESOLUTION_UT; + } + + return ret; + } + else { + nd_log(NDLS_DAEMON, NDLP_ERR, "clock_getres(%d) failed, using defaults for clock resolution.", (int)clock); + return DEFAULT_CLOCK_RESOLUTION_UT; + } } // perform any initializations required for clocks @@ -66,14 +87,6 @@ void clocks_init(void) { clock_monotonic_resolution = get_clock_resolution(clock_monotonic_to_use); clock_realtime_resolution = get_clock_resolution(CLOCK_REALTIME); - - // if for any reason these are zero, netdata will crash - // since we use them as modulo to calculations - if(!clock_realtime_resolution) - clock_realtime_resolution = 1000; - - if(!clock_monotonic_resolution) - clock_monotonic_resolution = 1000; } inline time_t now_sec(clockid_t clk_id) { @@ -91,7 +104,7 @@ inline usec_t now_usec(clockid_t clk_id) { netdata_log_error("clock_gettime(%d, ×pec) failed.", clk_id); return 0; } - return (usec_t)ts.tv_sec * USEC_PER_SEC + (ts.tv_nsec % NSEC_PER_SEC) / NSEC_PER_USEC; + return (usec_t)ts.tv_sec * USEC_PER_SEC + (usec_t)(ts.tv_nsec % NSEC_PER_SEC) / NSEC_PER_USEC; } inline int now_timeval(clockid_t clk_id, struct timeval *tv) { @@ -113,6 +126,10 @@ inline time_t now_realtime_sec(void) { return now_sec(CLOCK_REALTIME); } +inline msec_t now_realtime_msec(void) { + return now_usec(CLOCK_REALTIME) / USEC_PER_MS; +} + inline usec_t now_realtime_usec(void) { return now_usec(CLOCK_REALTIME); } @@ -275,7 +292,7 @@ void heartbeat_statistics(usec_t *min_ptr, usec_t *max_ptr, usec_t *average_ptr, inline void heartbeat_init(heartbeat_t *hb) { hb->realtime = 0ULL; - hb->randomness = 250 * USEC_PER_MS + ((now_realtime_usec() * clock_realtime_resolution) % (250 * USEC_PER_MS)); + hb->randomness = (usec_t)250 * USEC_PER_MS + ((usec_t)(now_realtime_usec() * clock_realtime_resolution) % (250 * USEC_PER_MS)); hb->randomness -= (hb->randomness % clock_realtime_resolution); netdata_mutex_lock(&heartbeat_alignment_mutex); @@ -298,8 +315,10 @@ usec_t heartbeat_next(heartbeat_t *hb, usec_t tick) { // TODO: The heartbeat tick should be specified at the heartbeat_init() function usec_t tmp = (now_realtime_usec() * clock_realtime_resolution) % (tick / 2); - error_limit_static_global_var(erl, 10, 0); - error_limit(&erl, "heartbeat randomness of %"PRIu64" is too big for a tick of %"PRIu64" - setting it to %"PRIu64"", hb->randomness, tick, tmp); + nd_log_limit_static_global_var(erl, 10, 0); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_NOTICE, + "heartbeat randomness of %"PRIu64" is too big for a tick of %"PRIu64" - setting it to %"PRIu64"", + hb->randomness, tick, tmp); hb->randomness = tmp; } @@ -325,13 +344,19 @@ usec_t heartbeat_next(heartbeat_t *hb, usec_t tick) { if(unlikely(now < next)) { errno = 0; - error_limit_static_global_var(erl, 10, 0); - error_limit(&erl, "heartbeat clock: woke up %"PRIu64" microseconds earlier than expected (can be due to the CLOCK_REALTIME set to the past).", next - now); + nd_log_limit_static_global_var(erl, 10, 0); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_NOTICE, + "heartbeat clock: woke up %"PRIu64" microseconds earlier than expected " + "(can be due to the CLOCK_REALTIME set to the past).", + next - now); } else if(unlikely(now - next > tick / 2)) { errno = 0; - error_limit_static_global_var(erl, 10, 0); - error_limit(&erl, "heartbeat clock: woke up %"PRIu64" microseconds later than expected (can be due to system load or the CLOCK_REALTIME set to the future).", now - next); + nd_log_limit_static_global_var(erl, 10, 0); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_NOTICE, + "heartbeat clock: woke up %"PRIu64" microseconds later than expected " + "(can be due to system load or the CLOCK_REALTIME set to the future).", + now - next); } if(unlikely(!hb->realtime)) { diff --git a/libnetdata/clocks/clocks.h b/libnetdata/clocks/clocks.h index 5b88a457..2beb14ed 100644 --- a/libnetdata/clocks/clocks.h +++ b/libnetdata/clocks/clocks.h @@ -117,6 +117,7 @@ usec_t now_realtime_usec(void); int now_monotonic_timeval(struct timeval *tv); time_t now_monotonic_sec(void); +msec_t now_realtime_msec(void); usec_t now_monotonic_usec(void); int now_monotonic_high_precision_timeval(struct timeval *tv); time_t now_monotonic_high_precision_sec(void); diff --git a/libnetdata/config/appconfig.h b/libnetdata/config/appconfig.h index b3a09024..214a15ed 100644 --- a/libnetdata/config/appconfig.h +++ b/libnetdata/config/appconfig.h @@ -217,4 +217,4 @@ typedef struct _connector_instance { _CONNECTOR_INSTANCE *add_connector_instance(struct section *connector, struct section *instance); -#endif /* NETDATA_CONFIG_H */ +#endif /* NETDATA_CONFIG_H */
\ No newline at end of file diff --git a/libnetdata/datetime/Makefile.am b/libnetdata/datetime/Makefile.am new file mode 100644 index 00000000..161784b8 --- /dev/null +++ b/libnetdata/datetime/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/libnetdata/datetime/README.md b/libnetdata/datetime/README.md new file mode 100644 index 00000000..ba236631 --- /dev/null +++ b/libnetdata/datetime/README.md @@ -0,0 +1,11 @@ +<!-- +title: "Datetime" +custom_edit_url: https://github.com/netdata/netdata/edit/master/libnetdata/datetime/README.md +sidebar_label: "Datetime" +learn_topic_type: "Tasks" +learn_rel_path: "Developers/libnetdata" +--> + +# Datetime + +Formatting dates and timestamps. diff --git a/libnetdata/datetime/iso8601.c b/libnetdata/datetime/iso8601.c new file mode 100644 index 00000000..8e3f4e02 --- /dev/null +++ b/libnetdata/datetime/iso8601.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +size_t iso8601_datetime_ut(char *buffer, size_t len, usec_t now_ut, ISO8601_OPTIONS options) { + if(unlikely(!buffer || len == 0)) + return 0; + + time_t t = (time_t)(now_ut / USEC_PER_SEC); + struct tm *tmp, tmbuf; + + if(options & ISO8601_UTC) + // Use gmtime_r for UTC time conversion. + tmp = gmtime_r(&t, &tmbuf); + else + // Use localtime_r for local time conversion. + tmp = localtime_r(&t, &tmbuf); + + if (unlikely(!tmp)) { + buffer[0] = '\0'; + return 0; + } + + // Format the date and time according to the ISO 8601 format. + size_t used_length = strftime(buffer, len, "%Y-%m-%dT%H:%M:%S", tmp); + if (unlikely(used_length == 0)) { + buffer[0] = '\0'; + return 0; + } + + if(options & ISO8601_MILLISECONDS) { + // Calculate the remaining microseconds + int milliseconds = (int) ((now_ut % USEC_PER_SEC) / USEC_PER_MS); + if(milliseconds && len - used_length > 4) + used_length += snprintfz(buffer + used_length, len - used_length, ".%03d", milliseconds); + } + else if(options & ISO8601_MICROSECONDS) { + // Calculate the remaining microseconds + int microseconds = (int) (now_ut % USEC_PER_SEC); + if(microseconds && len - used_length > 7) + used_length += snprintfz(buffer + used_length, len - used_length, ".%06d", microseconds); + } + + if(options & ISO8601_UTC) { + if(used_length + 1 < len) { + buffer[used_length++] = 'Z'; + buffer[used_length] = '\0'; // null-terminate the string. + } + } + else { + // Calculate the timezone offset in hours and minutes from UTC. + long offset = tmbuf.tm_gmtoff; + int hours = (int) (offset / 3600); // Convert offset seconds to hours. + int minutes = (int) ((offset % 3600) / 60); // Convert remainder to minutes (keep the sign for minutes). + + // Check if timezone is UTC. + if(hours == 0 && minutes == 0) { + // For UTC, append 'Z' to the timestamp. + if(used_length + 1 < len) { + buffer[used_length++] = 'Z'; + buffer[used_length] = '\0'; // null-terminate the string. + } + } + else { + // For non-UTC, format the timezone offset. Omit minutes if they are zero. + if(minutes == 0) { + // Check enough space is available for the timezone offset string. + if(used_length + 3 < len) // "+hh\0" + used_length += snprintfz(buffer + used_length, len - used_length, "%+03d", hours); + } + else { + // Check enough space is available for the timezone offset string. + if(used_length + 6 < len) // "+hh:mm\0" + used_length += snprintfz(buffer + used_length, len - used_length, + "%+03d:%02d", hours, abs(minutes)); + } + } + } + + return used_length; +} diff --git a/libnetdata/datetime/iso8601.h b/libnetdata/datetime/iso8601.h new file mode 100644 index 00000000..ce480096 --- /dev/null +++ b/libnetdata/datetime/iso8601.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_ISO8601_H +#define NETDATA_ISO8601_H + +typedef enum __attribute__((__packed__)) { + ISO8601_UTC = (1 << 0), + ISO8601_LOCAL_TIMEZONE = (1 << 1), + ISO8601_MILLISECONDS = (1 << 2), + ISO8601_MICROSECONDS = (1 << 3), +} ISO8601_OPTIONS; + +#define ISO8601_MAX_LENGTH 64 +size_t iso8601_datetime_ut(char *buffer, size_t len, usec_t now_ut, ISO8601_OPTIONS options); + +#endif //NETDATA_ISO8601_H diff --git a/libnetdata/datetime/rfc3339.c b/libnetdata/datetime/rfc3339.c new file mode 100644 index 00000000..157e340d --- /dev/null +++ b/libnetdata/datetime/rfc3339.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#include "rfc3339.h" + +size_t rfc3339_datetime_ut(char *buffer, size_t len, usec_t now_ut, size_t fractional_digits, bool utc) { + if (!buffer || len == 0) + return 0; + + time_t t = (time_t)(now_ut / USEC_PER_SEC); + struct tm *tmp, tmbuf; + + if (utc) + tmp = gmtime_r(&t, &tmbuf); + else + tmp = localtime_r(&t, &tmbuf); + + if (!tmp) { + buffer[0] = '\0'; + return 0; + } + + size_t used_length = strftime(buffer, len, "%Y-%m-%dT%H:%M:%S", tmp); + if (used_length == 0) { + buffer[0] = '\0'; + return 0; + } + + if (fractional_digits >= 0 && fractional_digits <= 9) { + int fractional_part = (int)(now_ut % USEC_PER_SEC); + if (fractional_part && len - used_length > fractional_digits + 1) { + char format[] = ".%01d"; + format[3] = (char)('0' + fractional_digits); + + // Adjust fractional part + fractional_part /= (int)pow(10, 6 - fractional_digits); + + used_length += snprintf(buffer + used_length, len - used_length, + format, fractional_part); + } + } + + if (utc) { + if (used_length + 1 < len) { + buffer[used_length++] = 'Z'; + buffer[used_length] = '\0'; + } + } + else { + long offset = tmbuf.tm_gmtoff; + int hours = (int)(offset / 3600); + int minutes = abs((int)((offset % 3600) / 60)); + + if (used_length + 7 < len) { // Space for "+HH:MM\0" + used_length += snprintf(buffer + used_length, len - used_length, "%+03d:%02d", hours, minutes); + } + } + + return used_length; +} + +usec_t rfc3339_parse_ut(const char *rfc3339, char **endptr) { + struct tm tm = { 0 }; + int tz_hours = 0, tz_mins = 0; + char *s; + usec_t timestamp, usec = 0; + + // Use strptime to parse up to seconds + s = strptime(rfc3339, "%Y-%m-%dT%H:%M:%S", &tm); + if (!s) + return 0; // Parsing error + + // Parse fractional seconds if present + if (*s == '.') { + char *next; + usec = strtoul(s + 1, &next, 10); + int digits_parsed = (int)(next - (s + 1)); + + if (digits_parsed < 1 || digits_parsed > 9) + return 0; // parsing error + + static const usec_t fix_usec[] = { + 1000000, // 0 digits (not used) + 100000, // 1 digit + 10000, // 2 digits + 1000, // 3 digits + 100, // 4 digits + 10, // 5 digits + 1, // 6 digits + 10, // 7 digits + 100, // 8 digits + 1000, // 9 digits + }; + usec = digits_parsed <= 6 ? usec * fix_usec[digits_parsed] : usec / fix_usec[digits_parsed]; + + s = next; + } + + // Check and parse timezone if present + int tz_offset = 0; + if (*s == '+' || *s == '-') { + // Parse the hours:mins part of the timezone + + if (!isdigit(s[1]) || !isdigit(s[2]) || s[3] != ':' || + !isdigit(s[4]) || !isdigit(s[5])) + return 0; // Parsing error + + char tz_sign = *s; + tz_hours = (s[1] - '0') * 10 + (s[2] - '0'); + tz_mins = (s[4] - '0') * 10 + (s[5] - '0'); + + tz_offset = tz_hours * 3600 + tz_mins * 60; + tz_offset *= (tz_sign == '+' ? 1 : -1); + + s += 6; // Move past the timezone part + } + else if (*s == 'Z') + s++; + else + return 0; // Invalid RFC 3339 format + + // Convert to time_t (assuming local time, then adjusting for timezone later) + time_t epoch_s = mktime(&tm); + if (epoch_s == -1) + return 0; // Error in time conversion + + timestamp = (usec_t)epoch_s * USEC_PER_SEC + usec; + timestamp -= tz_offset * USEC_PER_SEC; + + if(endptr) + *endptr = s; + + return timestamp; +} diff --git a/libnetdata/datetime/rfc3339.h b/libnetdata/datetime/rfc3339.h new file mode 100644 index 00000000..88ebb3ec --- /dev/null +++ b/libnetdata/datetime/rfc3339.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_RFC3339_H +#define NETDATA_RFC3339_H + +#define RFC3339_MAX_LENGTH 36 +size_t rfc3339_datetime_ut(char *buffer, size_t len, usec_t now_ut, size_t fractional_digits, bool utc); +usec_t rfc3339_parse_ut(const char *rfc3339, char **endptr); + +#endif //NETDATA_RFC3339_H diff --git a/libnetdata/datetime/rfc7231.c b/libnetdata/datetime/rfc7231.c new file mode 100644 index 00000000..4925ed2c --- /dev/null +++ b/libnetdata/datetime/rfc7231.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +inline size_t rfc7231_datetime(char *buffer, size_t len, time_t now_t) { + if (unlikely(!buffer || !len)) + return 0; + + struct tm *tmp, tmbuf; + + // Use gmtime_r for UTC time conversion. + tmp = gmtime_r(&now_t, &tmbuf); + + if (unlikely(!tmp)) { + buffer[0] = '\0'; + return 0; + } + + // Format the date and time according to the RFC 7231 format. + size_t ret = strftime(buffer, len, "%a, %d %b %Y %H:%M:%S GMT", tmp); + if (unlikely(ret == 0)) + buffer[0] = '\0'; + + return ret; +} + +size_t rfc7231_datetime_ut(char *buffer, size_t len, usec_t now_ut) { + return rfc7231_datetime(buffer, len, (time_t) (now_ut / USEC_PER_SEC)); +} diff --git a/libnetdata/datetime/rfc7231.h b/libnetdata/datetime/rfc7231.h new file mode 100644 index 00000000..5ba93053 --- /dev/null +++ b/libnetdata/datetime/rfc7231.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_RFC7231_H +#define NETDATA_RFC7231_H + +#define RFC7231_MAX_LENGTH 30 +size_t rfc7231_datetime(char *buffer, size_t len, time_t now_t); +size_t rfc7231_datetime_ut(char *buffer, size_t len, usec_t now_ut); + +#endif //NETDATA_RFC7231_H diff --git a/libnetdata/dictionary/dictionary.c b/libnetdata/dictionary/dictionary.c index 2d5313c3..45922abf 100644 --- a/libnetdata/dictionary/dictionary.c +++ b/libnetdata/dictionary/dictionary.c @@ -422,7 +422,7 @@ static inline void DICTIONARY_ENTRIES_MINUS1(DICTIONARY *dict) { size_t entries; (void)entries; if(unlikely(is_dictionary_single_threaded(dict))) { dict->version++; - entries = dict->entries++; + entries = dict->entries--; } else { __atomic_fetch_add(&dict->version, 1, __ATOMIC_RELAXED); @@ -2627,7 +2627,7 @@ static char **dictionary_unittest_generate_names(size_t entries) { char **names = mallocz(sizeof(char *) * entries); for(size_t i = 0; i < entries ;i++) { char buf[25 + 1] = ""; - snprintfz(buf, 25, "name.%zu.0123456789.%zu!@#$%%^&*(),./[]{}\\|~`", i, entries / 2 + i); + snprintfz(buf, sizeof(buf) - 1, "name.%zu.0123456789.%zu!@#$%%^&*(),./[]{}\\|~`", i, entries / 2 + i); names[i] = strdupz(buf); } return names; @@ -2637,7 +2637,7 @@ static char **dictionary_unittest_generate_values(size_t entries) { char **values = mallocz(sizeof(char *) * entries); for(size_t i = 0; i < entries ;i++) { char buf[25 + 1] = ""; - snprintfz(buf, 25, "value-%zu-0987654321.%zu%%^&*(),. \t !@#$/[]{}\\|~`", i, entries / 2 + i); + snprintfz(buf, sizeof(buf) - 1, "value-%zu-0987654321.%zu%%^&*(),. \t !@#$/[]{}\\|~`", i, entries / 2 + i); values[i] = strdupz(buf); } return values; @@ -3253,13 +3253,13 @@ static void *unittest_dict_thread(void *arg) { char buf [256 + 1]; for (int i = 0; i < 1000; i++) { - snprintfz(buf, 256, "del/flush test %d", i); + snprintfz(buf, sizeof(buf) - 1, "del/flush test %d", i); dictionary_set(tu->dict, buf, NULL, 0); tu->stats.ops.inserts++; } for (int i = 0; i < 1000; i++) { - snprintfz(buf, 256, "del/flush test %d", i); + snprintfz(buf, sizeof(buf) - 1, "del/flush test %d", i); dictionary_del(tu->dict, buf); tu->stats.ops.deletes++; } diff --git a/libnetdata/dyn_conf/README.md b/libnetdata/dyn_conf/README.md index 6c812740..17d059b0 100644 --- a/libnetdata/dyn_conf/README.md +++ b/libnetdata/dyn_conf/README.md @@ -1,6 +1,6 @@ # Netdata Dynamic Configuration -Purpose of Netdata Dynamic Configuration is to allow configuration of select Netdata plugins and options through the +Purpose of Netdata Dynamic Configuration is to allow configuration of select Netdata plugins and options through the Netdata API and by extension by UI. ## HTTP API documentation @@ -9,159 +9,180 @@ Netdata API and by extension by UI. For summary of all jobs and their statuses (for all children that stream to parent) use the following URL: -| Method | Endpoint | Description | -|:-------:|-------------------------------|------------------------------------------------------------| -| **GET** | `api/v2/job_statuses` | list of Jobs | -| **GET** | `api/v2/job_statuses?grouped` | list of Jobs (hierarchical, grouped by host/plugin/module) | +| Method | Endpoint | Description | +|:-------:|-------------------------------|------------------------------------------------------------| +| **GET** | `api/v2/job_statuses` | list of Jobs | +| **GET** | `api/v2/job_statuses?grouped` | list of Jobs (hierarchical, grouped by host/plugin/module) | ### Dyncfg API ### Top level -| Method | Endpoint | Description | -|:-------:|------------------|-----------------------------------------| -| **GET** | `/api/v2/config` | registered Plugins (sent DYNCFG_ENABLE) | +| Method | Endpoint | Description | +|:-------:|------------------|-----------------------------------------| +| **GET** | `/api/v2/config` | registered Plugins (sent DYNCFG_ENABLE) | ### Plugin level -| Method | Endpoint | Description | -|:-------:|-----------------------------------|------------------------------| -| **GET** | `/api/v2/config/[plugin]` | Plugin config | -| **PUT** | `/api/v2/config/[plugin]` | update Plugin config | -| **GET** | `/api/v2/config/[plugin]/modules` | Modules registered by Plugin | -| **GET** | `/api/v2/config/[plugin]/schema` | Plugin config schema | +| Method | Endpoint | Description | +|:-------:|-----------------------------------|------------------------------| +| **GET** | `/api/v2/config/[plugin]` | Plugin config | +| **PUT** | `/api/v2/config/[plugin]` | update Plugin config | +| **GET** | `/api/v2/config/[plugin]/modules` | Modules registered by Plugin | +| **GET** | `/api/v2/config/[plugin]/schema` | Plugin config schema | ### Module level -| Method | Endpoint | Description | -|:-------:|-----------------------------------------------|---------------------------| -| **GET** | `/api/v2/config/<plugin>/[module]` | Module config | -| **PUT** | `/api/v2/config/[plugin]/[module]` | update Module config | -| **GET** | `/api/v2/config/[plugin]/[module]/jobs` | Jobs registered by Module | -| **GET** | `/api/v2/config/[plugin]/[module]/job_schema` | Job config schema | -| **GET** | `/api/v2/config/[plugin]/[module]/schema` | Module config schema | +| Method | Endpoint | Description | +|:-------:|-----------------------------------------------|---------------------------| +| **GET** | `/api/v2/config/<plugin>/[module]` | Module config | +| **PUT** | `/api/v2/config/[plugin]/[module]` | update Module config | +| **GET** | `/api/v2/config/[plugin]/[module]/jobs` | Jobs registered by Module | +| **GET** | `/api/v2/config/[plugin]/[module]/job_schema` | Job config schema | +| **GET** | `/api/v2/config/[plugin]/[module]/schema` | Module config schema | ### Job level - only for modules where `module_type == job_array` -| Method | Endpoint | Description | -|:----------:|------------------------------------------|--------------------------------| -| **GET** | `/api/v2/config/[plugin]/[module]/[job]` | Job config | -| **PUT** | `/api/v2/config/[plugin]/[module]/[job]` | update Job config | -| **POST** | `/api/v2/config/[plugin]/[module]/[job]` | create Job | -| **DELETE** | `/api/v2/config/[plugin]/[module]/[job]` | delete Job (created by Dyncfg) | +| Method | Endpoint | Description | +|:----------:|------------------------------------------|--------------------------------| +| **GET** | `/api/v2/config/[plugin]/[module]/[job]` | Job config | +| **PUT** | `/api/v2/config/[plugin]/[module]/[job]` | update Job config | +| **POST** | `/api/v2/config/[plugin]/[module]/[job]` | create Job | +| **DELETE** | `/api/v2/config/[plugin]/[module]/[job]` | delete Job (created by Dyncfg) | -## AGENT<->PLUGIN interface documentation +## Internal Plugins API -### 1. DYNCFG_ENABLE +TBD + +## External Plugins API + +### Commands plugins can use + +#### DYNCFG_ENABLE Plugin signifies to agent its ability to use new dynamic config and the name it wishes to use by sending -``` -plugin->agent: -============= -DYNCFG_ENABLE [plugin_url_name] -``` +``` +DYNCFG_ENABLE [{PLUGIN_NAME}] +``` -This can be sent only once per lifetime of the plugin (at startup or later) sending it multiple times is considered a +This can be sent only once per lifetime of the plugin (at startup or later) sending it multiple times is considered a protocol violation and plugin might get terminated. -After this command is sent the plugin has to be ready to accept all the new commands/keywords related to dynamic + +After this command is sent the plugin has to be ready to accept all the new commands/keywords related to dynamic configuration (this command lets agent know this plugin is dyncfg capable and wishes to use dyncfg functionality). -After this command agent can call +#### DYNCFG_RESET -``` -agent->plugin: -============= -FUNCTION_PAYLOAD [UUID] 1 "set_plugin_config" -the new configuration -blah blah blah -FUNCTION_PAYLOAD_END - -plugin->agent: -============= -FUNCTION_RESULT_BEGIN [UUID] [(1/0)(accept/reject)] [text/plain] 5 -FUNCTION_RESULT_END -``` +Sending this, will reset the internal state of the agent, considering this a `DYNCFG_ENABLE`. -to set the new config which can be accepted/rejected by plugin by sending answer for this FUNCTION as it would with any -other regular function. +``` +DYNCFG_RESET +``` -The new `FUNCTION_PAYLOAD` command differs from regular `FUNCTION` command exclusively in its ability to send bigger -payloads (configuration file contents) to the plugin (not just parameters list). -Agent can also call (after `DYNCFG_ENABLE`) +#### DYNCFG_REGISTER_MODULE ``` -Agent->plugin: -============= -FUNCTION [UID] 1 "get_plugin_config" - -Plugin->agent: -============= -FUNCTION_RESULT_BEGIN [UID] 1 text/plain 5 -{ - "the currently used config from plugin" : "nice" -} -FUNCTION_RESULT_END +DYNCFG_REGISTER_MODULE {MODULE_NAME} {MODULE_TYPE} ``` -and +Module has to choose one of following types at registration: + +- `single` - module itself has configuration but does not accept any jobs *(this is useful mainly for internal netdata + configurable things like webserver etc.)* + +- `job_array` - module itself **can** *(not must)* have configuration and it has an array of jobs which can be added, + modified and deleted. **this is what plugin developer needs in most cases** + +After a module has been registered agent can call `set_module_config`, `get_module_config` and `get_module_config_schema`. + +When `MODULE_TYPE` is `job_array` the agent may also send `set_job_config`, `get_job_config` and `get_job_config_schema`. + +#### DYNCFG_REGISTER_JOB + +The plugin can use `DYNCFG_REGISTER_JOB` to register its own configuration jobs. It should not register jobs configured +via DYNCFG (doing so, the agent will shutdown the plugin). + ``` -Agent->plugin: -============= -FUNCTION [UID] 1 "get_plugin_config_schema" - -Plugin->agent: -============= -FUNCTION_RESULT_BEGIN [UID] 1 text/plain 5 -{ - "the schema of plugin configuration" : "splendid" -} -FUNCTION_RESULT_END +DYNCFG_REGISTER_JOB {MODULE_NAME} {JOB_NAME} {JOB_TYPE} {FLAGS} ``` -Plugin can also register zero, one or more configurable modules using: +Where: + +- `MODULE_NAME` is the name of the module. +- `JOB_NAME` is the name of the job. +- `JOB_TYPE` is either `stock` or `autodiscovered`. +- `FLAGS`, just send zero. + +#### REPORT_JOB_STATUS ``` -plugin->agent: -============= -DYNCFG_REGISTER_MODULE [module_url_name] (job_array|single) +REPORT_JOB_STATUS {MODULE_NAME} {JOB_NAME} {STATUS} {STATE} ["REASON"] ``` -modules can be added any time during plugins lifetime (you are not required to add them all at startup). +Note the REASON parameter is optional and can be entirelly ommited (for example when state is OK there is no need to send any reason). -### 2. DYNCFG_REGISTER_MODULE +Where: -Module has to choose one of following types at registration: +- `MODULE_NAME` is the name of the module. +- `JOB_NAME` is the name of the job. +- `STATUS` is one of `stopped`, `running`, or `error`. +- `STATE`, just send zero. +- `REASON` is a message describing the status. In case you don't want to send any reason string it is preferable to omit this parameter altogether (as opposed to sending empty string `""`). -- `single` - module itself has configuration but does not accept any jobs *(this is useful mainly for internal netdata - configurable things like webserver etc.)* -- `job_array` - module itself **can** *(not must)* have configuration and it has an array of jobs which can be added, - modified and deleted. **this is what plugin developer needs in most cases** -After module has been registered agent can call +### Commands plugins must serve + +Once a plugin calls `DYNCFG_ENABLE`, the must be able to handle these calls. -- `set_module_config [module]` FUNCTION_PAYLOAD -- `get_module_config [module]` FUNCTION -- `get_module_config_schema [module]` FUNCTION +function|parameters|prerequisites|request payload|response payload| +:---:|:---:|:---:|:---:|:---:| +`set_plugin_config`|none|`DYNCFG_ENABLE`|plugin configuration|none| +`get_plugin_config`|none|`DYNCFG_ENABLE`|none|plugin configuration| +`get_plugin_config_schema`|none|`DYNCFG_ENABLE`|none|plugin configuration schema| +`set_module_config`|`module_name`|`DYNCFG_REGISTER_MODULE`|module configuration|none| +`get_module_config`|`module_name`|`DYNCFG_REGISTER_MODULE`|none|module configuration| +`get_module_config_schema`|`module_name`|`DYNCFG_REGISTER_MODULE`|none|module configuration schema| +`set_job_config`|`module_name`, `job_name`|`DYNCFG_REGISTER_MODULE`|job configuration|none| +`get_job_config`|`module_name`, `job_name`|`DYNCFG_REGISTER_MODULE`|none|job configuration| +`get_job_config_schema`|`module_name`, `job_name`|`DYNCFG_REGISTER_MODULE`|none|job configuration schema| -with same syntax as `set_plugin_config` and `get_plugin_config`. In case of `set` command the plugin has ability to -reject the new configuration pushed to it. +All of them work like this: -In a case the module was registered as `job_array` type following commands can be used to manage jobs: +If the request payload is `none`, then the request looks like this: -### 3. Job interface for job_array modules +```bash +FUNCTION {TRANSACTION_UUID} {TIMEOUT_SECONDS} "{function} {parameters}" +``` + +When there is payload, the request looks like this: + +```bash +FUNCTION_PAYLOAD {TRANSACTION_UUID} {TIMEOUT_SECONDS} "{function} {parameters}" +<payload> +FUNCTION_PAYLOAD_END +``` + +In all cases, the response is like this: + +```bash +FUNCTION_RESULT_BEGIN {TRANSACTION_UUID} {HTTP_RESPONSE_CODE} "{CONTENT_TYPE}" {EXPIRATION_TIMESTAMP} +<payload> +FUNCTION_RESULT_END +``` +Where: +- `TRANSACTION_UUID` is the same UUID received with the request. +- `HTTP_RESPONSE_CODE` is either `0` (rejected) or `1` (accepted). +- `CONTENT_TYPE` should reflect the `payload` returned. +- `EXPIRATION_TIMESTAMP` can be zero. -- `get_job_config_schema [module]` - FUNCTION -- `get_job_config [module] [job]` - FUNCTION -- `set_job_config [module] [job]` - FUNCTION_PAYLOAD -- `delete_job_name [module] [job]` - FUNCTION -### 4. Streaming +## DYNCFG with streaming -When above commands are transferred trough streaming additionally `plugin_name` is prefixed as first parameter. This is +When above commands are transferred trough streaming additionally `plugin_name` is prefixed as first parameter. This is done to allow routing to appropriate plugin @child. -As a plugin developer you don't need to concern yourself with this detail as that parameter is stripped when sent to the +As a plugin developer you don't need to concern yourself with this detail as that parameter is stripped when sent to the plugin *(and added when sent trough streaming)* automagically. diff --git a/libnetdata/dyn_conf/dyn_conf.h b/libnetdata/dyn_conf/dyn_conf.h index f6a5fe49..d584343b 100644 --- a/libnetdata/dyn_conf/dyn_conf.h +++ b/libnetdata/dyn_conf/dyn_conf.h @@ -112,7 +112,7 @@ static inline const char* job_type2str(enum job_type type) } } -static inline enum job_type str2job_type(const char *type_name) +static inline enum job_type dyncfg_str2job_type(const char *type_name) { if (strcmp(type_name, "stock") == 0) return JOB_TYPE_STOCK; diff --git a/libnetdata/ebpf/ebpf.c b/libnetdata/ebpf/ebpf.c index 1bd45ef2..99f23b9c 100644 --- a/libnetdata/ebpf/ebpf.c +++ b/libnetdata/ebpf/ebpf.c @@ -1367,6 +1367,8 @@ void ebpf_load_addresses(ebpf_addresses_t *fa, int fd) char *fcnt = procfile_lineword(ff, l, 2); uint32_t hash = simple_hash(fcnt); if (fa->hash == hash && !strcmp(fcnt, fa->function)) { + char *type = procfile_lineword(ff, l, 2); + fa->type = type[0]; if (fd > 0) { char addr[128]; snprintf(addr, 127, "0x%s", procfile_lineword(ff, l, 0)); diff --git a/libnetdata/ebpf/ebpf.h b/libnetdata/ebpf/ebpf.h index 6708f669..9218cb9d 100644 --- a/libnetdata/ebpf/ebpf.h +++ b/libnetdata/ebpf/ebpf.h @@ -148,6 +148,7 @@ typedef struct ebpf_addresses { uint32_t hash; // We use long as address, because it matches system length unsigned long addr; + uint32_t type; } ebpf_addresses_t; extern char *ebpf_user_config_dir; diff --git a/libnetdata/endian.h b/libnetdata/endian.h new file mode 100644 index 00000000..66f75cb1 --- /dev/null +++ b/libnetdata/endian.h @@ -0,0 +1,32 @@ +#ifndef LIBNETDATA_ENDIAN_H +#define LIBNETDATA_ENDIAN_H + +/** compatibility header for endian.h + * This is a simple compatibility shim to convert + * BSD/Linux endian macros to the Mac OS X equivalents. + * It is public domain. + * */ + +#ifndef __APPLE__ +#error "This header file (endian.h) is MacOS X specific.\n" +#endif /* __APPLE__ */ + + +#include <libkern/OSByteOrder.h> + +#define htobe16(x) OSSwapHostToBigInt16(x) +#define htole16(x) OSSwapHostToLittleInt16(x) +#define be16toh(x) OSSwapBigToHostInt16(x) +#define le16toh(x) OSSwapLittleToHostInt16(x) + +#define htobe32(x) OSSwapHostToBigInt32(x) +#define htole32(x) OSSwapHostToLittleInt32(x) +#define be32toh(x) OSSwapBigToHostInt32(x) +#define le32toh(x) OSSwapLittleToHostInt32(x) + +#define htobe64(x) OSSwapHostToBigInt64(x) +#define htole64(x) OSSwapHostToLittleInt64(x) +#define be64toh(x) OSSwapBigToHostInt64(x) +#define le64toh(x) OSSwapLittleToHostInt64(x) + +#endif /* LIBNETDATA_ENDIAN_H */ diff --git a/libnetdata/eval/eval.c b/libnetdata/eval/eval.c index 236be932..a1ac4483 100644 --- a/libnetdata/eval/eval.c +++ b/libnetdata/eval/eval.c @@ -384,7 +384,7 @@ static inline void print_parsed_as_constant(BUFFER *out, NETDATA_DOUBLE n) { } char b[100+1], *s; - snprintfz(b, 100, NETDATA_DOUBLE_FORMAT, n); + snprintfz(b, sizeof(b) - 1, NETDATA_DOUBLE_FORMAT, n); s = &b[strlen(b) - 1]; while(s > b && *s == '0') { diff --git a/libnetdata/facets/facets.c b/libnetdata/facets/facets.c index e72cb732..4a5f5442 100644 --- a/libnetdata/facets/facets.c +++ b/libnetdata/facets/facets.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-3.0-or-later #include "facets.h" -#define HISTOGRAM_COLUMNS 150 // the target number of points in a histogram +#define FACETS_HISTOGRAM_COLUMNS 150 // the target number of points in a histogram #define FACETS_KEYS_WITH_VALUES_MAX 200 // the max number of keys that can be facets #define FACETS_KEYS_IN_ROW_MAX 500 // the max number of keys in a row -#define FACETS_KEYS_HASHTABLE_ENTRIES 127 -#define FACETS_VALUES_HASHTABLE_ENTRIES 31 +#define FACETS_KEYS_HASHTABLE_ENTRIES 15 +#define FACETS_VALUES_HASHTABLE_ENTRIES 15 + +static inline void facets_reset_key(FACET_KEY *k); // ---------------------------------------------------------------------------- @@ -30,14 +32,12 @@ static const uint8_t id_encoding_characters_reverse[256] = { ['6'] = 60, ['7'] = 61, ['8'] = 62, ['9'] = 63 }; -__attribute__((constructor)) void initialize_facets_id_encoding_characters_reverse(void) { - -} - #define FACET_STRING_HASH_SIZE 12 #define FACETS_HASH XXH64_hash_t #define FACETS_HASH_FUNCTION(src, len) XXH3_64bits(src, len) #define FACETS_HASH_ZERO (FACETS_HASH)0 +#define FACETS_HASH_UNSAMPLED (FACETS_HASH)(UINT64_MAX - 1) +#define FACETS_HASH_ESTIMATED (FACETS_HASH)UINT64_MAX static inline void facets_hash_to_str(FACETS_HASH num, char *out) { out[11] = '\0'; @@ -99,76 +99,47 @@ static inline bool is_valid_string_hash(const char *s) { } // ---------------------------------------------------------------------------- +// hashtable for FACET_VALUE -typedef uint64_t SIMPLE_HASHTABLE_HASH; -#define SIMPLE_HASHTABLE_HASH_SECOND_HASH_SHIFTS 32 - -typedef struct simple_hashtable_slot { - SIMPLE_HASHTABLE_HASH hash; - void *data; -} SIMPLE_HASHTABLE_SLOT; +// cleanup hashtable defines +#undef SIMPLE_HASHTABLE_SORT_FUNCTION +#undef SIMPLE_HASHTABLE_VALUE_TYPE +#undef SIMPLE_HASHTABLE_NAME +#undef NETDATA_SIMPLE_HASHTABLE_H -typedef struct simple_hashtable { - size_t size; - SIMPLE_HASHTABLE_SLOT *hashtable; -} SIMPLE_HASHTABLE; - -static void simple_hashtable_init(SIMPLE_HASHTABLE *ht, size_t size) { - ht->size = size; - ht->hashtable = callocz(ht->size, sizeof(*ht->hashtable)); -} - -static void simple_hashtable_free(SIMPLE_HASHTABLE *ht) { - freez(ht->hashtable); - ht->hashtable = NULL; - ht->size = 0; -} - -static inline SIMPLE_HASHTABLE_SLOT *simple_hashtable_get_slot(SIMPLE_HASHTABLE *ht, SIMPLE_HASHTABLE_HASH hash) { - // IMPORTANT: - // If the hashtable supported deletions, we would need to have a special slot.data value - // to mark deleted values and assume they are occupied during lookup, but empty during insert. - // But for our case, we don't need it, since we never delete items from the hashtable. - - size_t slot = hash % ht->size; - if(!ht->hashtable[slot].data || ht->hashtable[slot].hash == hash) - return &ht->hashtable[slot]; - - slot = ((hash >> SIMPLE_HASHTABLE_HASH_SECOND_HASH_SHIFTS) + 1) % ht->size; - // Linear probing until we find it - while (ht->hashtable[slot].data && ht->hashtable[slot].hash != hash) - slot = (slot + 1) % ht->size; // Wrap around if necessary - - return &ht->hashtable[slot]; -} - -static void simple_hashtable_resize_double(SIMPLE_HASHTABLE *ht) { - SIMPLE_HASHTABLE_SLOT *old = ht->hashtable; - size_t old_size = ht->size; - - ht->size = (ht->size * 2) + 1; - ht->hashtable = callocz(ht->size, sizeof(*ht->hashtable)); - for(size_t i = 0 ; i < old_size ; i++) { - if(!old[i].data) - continue; +struct facet_value; +// #define SIMPLE_HASHTABLE_SORT_FUNCTION compare_facet_value +#define SIMPLE_HASHTABLE_VALUE_TYPE struct facet_value +#define SIMPLE_HASHTABLE_NAME _VALUE +#include "../simple_hashtable.h" - SIMPLE_HASHTABLE_SLOT *slot = simple_hashtable_get_slot(ht, old[i].hash); - *slot = old[i]; - } +// ---------------------------------------------------------------------------- +// hashtable for FACET_KEY - freez(old); -} +// cleanup hashtable defines +#undef SIMPLE_HASHTABLE_SORT_FUNCTION +#undef SIMPLE_HASHTABLE_VALUE_TYPE +#undef SIMPLE_HASHTABLE_NAME +#undef NETDATA_SIMPLE_HASHTABLE_H +struct facet_key; +// #define SIMPLE_HASHTABLE_SORT_FUNCTION compare_facet_key +#define SIMPLE_HASHTABLE_VALUE_TYPE struct facet_key +#define SIMPLE_HASHTABLE_NAME _KEY +#include "../simple_hashtable.h" // ---------------------------------------------------------------------------- typedef struct facet_value { FACETS_HASH hash; const char *name; + const char *color; uint32_t name_len; bool selected; bool empty; + bool unsampled; + bool estimated; uint32_t rows_matching_facet_value; uint32_t final_facet_value_counter; @@ -181,14 +152,19 @@ typedef struct facet_value { } FACET_VALUE; typedef enum { - FACET_KEY_VALUE_NONE = 0, - FACET_KEY_VALUE_UPDATED = (1 << 0), - FACET_KEY_VALUE_EMPTY = (1 << 1), - FACET_KEY_VALUE_COPIED = (1 << 2), + FACET_KEY_VALUE_NONE = 0, + FACET_KEY_VALUE_UPDATED = (1 << 0), + FACET_KEY_VALUE_EMPTY = (1 << 1), + FACET_KEY_VALUE_UNSAMPLED = (1 << 2), + FACET_KEY_VALUE_ESTIMATED = (1 << 3), + FACET_KEY_VALUE_COPIED = (1 << 4), } FACET_KEY_VALUE_FLAGS; #define facet_key_value_updated(k) ((k)->current_value.flags & FACET_KEY_VALUE_UPDATED) #define facet_key_value_empty(k) ((k)->current_value.flags & FACET_KEY_VALUE_EMPTY) +#define facet_key_value_unsampled(k) ((k)->current_value.flags & FACET_KEY_VALUE_UNSAMPLED) +#define facet_key_value_estimated(k) ((k)->current_value.flags & FACET_KEY_VALUE_ESTIMATED) +#define facet_key_value_empty_or_unsampled_or_estimated(k) ((k)->current_value.flags & (FACET_KEY_VALUE_EMPTY|FACET_KEY_VALUE_UNSAMPLED|FACET_KEY_VALUE_ESTIMATED)) #define facet_key_value_copied(k) ((k)->current_value.flags & FACET_KEY_VALUE_COPIED) struct facet_key { @@ -210,7 +186,7 @@ struct facet_key { bool enabled; uint32_t used; FACET_VALUE *ll; - SIMPLE_HASHTABLE ht; + SIMPLE_HASHTABLE_VALUE ht; } values; struct { @@ -227,6 +203,14 @@ struct facet_key { } empty_value; struct { + FACET_VALUE *v; + } unsampled_value; + + struct { + FACET_VALUE *v; + } estimated_value; + + struct { facet_dynamic_row_t cb; void *data; } dynamic; @@ -261,7 +245,7 @@ struct facets { struct { size_t count; FACET_KEY *ll; - SIMPLE_HASHTABLE ht; + SIMPLE_HASHTABLE_KEY ht; } keys; struct { @@ -324,6 +308,8 @@ struct facets { struct { size_t evaluated; size_t matched; + size_t unsampled; + size_t estimated; size_t created; size_t reused; } rows; @@ -331,7 +317,6 @@ struct facets { struct { size_t registered; size_t unique; - size_t hashtable_increases; } keys; struct { @@ -339,16 +324,21 @@ struct facets { size_t transformed; size_t dynamic; size_t empty; + size_t unsampled; + size_t estimated; size_t indexed; size_t inserts; size_t conflicts; - size_t hashtable_increases; } values; struct { size_t searches; } fts; } operations; + + struct { + DICTIONARY *used_hashes_registry; + } report; }; usec_t facets_row_oldest_ut(FACETS *facets) { @@ -386,7 +376,7 @@ static inline bool facets_key_is_facet(FACETS *facets, FACET_KEY *k); static inline void FACETS_VALUES_INDEX_CREATE(FACET_KEY *k) { k->values.ll = NULL; k->values.used = 0; - simple_hashtable_init(&k->values.ht, FACETS_VALUES_HASHTABLE_ENTRIES); + simple_hashtable_init_VALUE(&k->values.ht, FACETS_VALUES_HASHTABLE_ENTRIES); } static inline void FACETS_VALUES_INDEX_DESTROY(FACET_KEY *k) { @@ -402,7 +392,7 @@ static inline void FACETS_VALUES_INDEX_DESTROY(FACET_KEY *k) { k->values.used = 0; k->values.enabled = false; - simple_hashtable_free(&k->values.ht); + simple_hashtable_destroy_VALUE(&k->values.ht); } static inline const char *facets_key_get_value(FACET_KEY *k) { @@ -449,17 +439,17 @@ static inline void FACET_VALUE_ADD_CONFLICT(FACET_KEY *k, FACET_VALUE *v, const } static inline FACET_VALUE *FACET_VALUE_GET_FROM_INDEX(FACET_KEY *k, FACETS_HASH hash) { - SIMPLE_HASHTABLE_SLOT *slot = simple_hashtable_get_slot(&k->values.ht, hash); - return slot->data; + SIMPLE_HASHTABLE_SLOT_VALUE *slot = simple_hashtable_get_slot_VALUE(&k->values.ht, hash, true); + return SIMPLE_HASHTABLE_SLOT_DATA(slot); } static inline FACET_VALUE *FACET_VALUE_ADD_TO_INDEX(FACET_KEY *k, const FACET_VALUE * const tv) { - SIMPLE_HASHTABLE_SLOT *slot = simple_hashtable_get_slot(&k->values.ht, tv->hash); + SIMPLE_HASHTABLE_SLOT_VALUE *slot = simple_hashtable_get_slot_VALUE(&k->values.ht, tv->hash, true); - if(slot->data) { + if(SIMPLE_HASHTABLE_SLOT_DATA(slot)) { // already exists - FACET_VALUE *v = slot->data; + FACET_VALUE *v = SIMPLE_HASHTABLE_SLOT_DATA(slot); FACET_VALUE_ADD_CONFLICT(k, v, tv); return v; } @@ -467,12 +457,21 @@ static inline FACET_VALUE *FACET_VALUE_ADD_TO_INDEX(FACET_KEY *k, const FACET_VA // we have to add it FACET_VALUE *v = mallocz(sizeof(*v)); - slot->hash = tv->hash; - slot->data = v; + simple_hashtable_set_slot_VALUE(&k->values.ht, slot, tv->hash, v); memcpy(v, tv, sizeof(*v)); - DOUBLE_LINKED_LIST_APPEND_ITEM_UNSAFE(k->values.ll, v, prev, next); + if(v->estimated || v->unsampled) { + if(k->values.ll && k->values.ll->estimated) { + FACET_VALUE *estimated = k->values.ll; + DOUBLE_LINKED_LIST_INSERT_ITEM_AFTER_UNSAFE(k->values.ll, estimated, v, prev, next); + } + else + DOUBLE_LINKED_LIST_PREPEND_ITEM_UNSAFE(k->values.ll, v, prev, next); + } + else + DOUBLE_LINKED_LIST_APPEND_ITEM_UNSAFE(k->values.ll, v, prev, next); + k->values.used++; if(!v->selected) @@ -490,12 +489,53 @@ static inline FACET_VALUE *FACET_VALUE_ADD_TO_INDEX(FACET_KEY *k, const FACET_VA k->facets->operations.values.inserts++; - if(unlikely(k->values.used > k->values.ht.size / 2)) { - simple_hashtable_resize_double(&k->values.ht); - k->facets->operations.values.hashtable_increases++; + return v; +} + +static inline void FACET_VALUE_ADD_UNSAMPLED_VALUE_TO_INDEX(FACET_KEY *k) { + static const FACET_VALUE tv = { + .hash = FACETS_HASH_UNSAMPLED, + .name = FACET_VALUE_UNSAMPLED, + .name_len = sizeof(FACET_VALUE_UNSAMPLED) - 1, + .unsampled = true, + .color = "offline", + }; + + k->current_value.hash = FACETS_HASH_UNSAMPLED; + + if(k->unsampled_value.v) { + FACET_VALUE_ADD_CONFLICT(k, k->unsampled_value.v, &tv); + k->current_value.v = k->unsampled_value.v; } + else { + FACET_VALUE *v = FACET_VALUE_ADD_TO_INDEX(k, &tv); + v->unsampled = true; + k->unsampled_value.v = v; + k->current_value.v = v; + } +} - return v; +static inline void FACET_VALUE_ADD_ESTIMATED_VALUE_TO_INDEX(FACET_KEY *k) { + static const FACET_VALUE tv = { + .hash = FACETS_HASH_ESTIMATED, + .name = FACET_VALUE_ESTIMATED, + .name_len = sizeof(FACET_VALUE_ESTIMATED) - 1, + .estimated = true, + .color = "generic", + }; + + k->current_value.hash = FACETS_HASH_ESTIMATED; + + if(k->estimated_value.v) { + FACET_VALUE_ADD_CONFLICT(k, k->estimated_value.v, &tv); + k->current_value.v = k->estimated_value.v; + } + else { + FACET_VALUE *v = FACET_VALUE_ADD_TO_INDEX(k, &tv); + v->estimated = true; + k->estimated_value.v = v; + k->current_value.v = v; + } } static inline void FACET_VALUE_ADD_EMPTY_VALUE_TO_INDEX(FACET_KEY *k) { @@ -503,6 +543,7 @@ static inline void FACET_VALUE_ADD_EMPTY_VALUE_TO_INDEX(FACET_KEY *k) { .hash = FACETS_HASH_ZERO, .name = FACET_VALUE_UNSET, .name_len = sizeof(FACET_VALUE_UNSET) - 1, + .empty = true, }; k->current_value.hash = FACETS_HASH_ZERO; @@ -527,6 +568,9 @@ static inline void FACET_VALUE_ADD_CURRENT_VALUE_TO_INDEX(FACET_KEY *k) { tv.name = facets_key_get_value(k); tv.name_len = facets_key_get_value_length(k); tv.hash = FACETS_HASH_FUNCTION(tv.name, tv.name_len); + tv.empty = false; + tv.estimated = false; + tv.unsampled = false; k->current_value.v = FACET_VALUE_ADD_TO_INDEX(k, &tv); k->facets->operations.values.indexed++; @@ -567,7 +611,7 @@ static inline void FACETS_KEYS_INDEX_CREATE(FACETS *facets) { facets->keys.count = 0; facets->keys_with_values.used = 0; - simple_hashtable_init(&facets->keys.ht, FACETS_KEYS_HASHTABLE_ENTRIES); + simple_hashtable_init_KEY(&facets->keys.ht, FACETS_KEYS_HASHTABLE_ENTRIES); } static inline void FACETS_KEYS_INDEX_DESTROY(FACETS *facets) { @@ -586,12 +630,12 @@ static inline void FACETS_KEYS_INDEX_DESTROY(FACETS *facets) { facets->keys.count = 0; facets->keys_with_values.used = 0; - simple_hashtable_free(&facets->keys.ht); + simple_hashtable_destroy_KEY(&facets->keys.ht); } static inline FACET_KEY *FACETS_KEY_GET_FROM_INDEX(FACETS *facets, FACETS_HASH hash) { - SIMPLE_HASHTABLE_SLOT *slot = simple_hashtable_get_slot(&facets->keys.ht, hash); - return slot->data; + SIMPLE_HASHTABLE_SLOT_KEY *slot = simple_hashtable_get_slot_KEY(&facets->keys.ht, hash, true); + return SIMPLE_HASHTABLE_SLOT_DATA(slot); } bool facets_key_name_value_length_is_selected(FACETS *facets, const char *key, size_t key_length, const char *value, size_t value_length) { @@ -670,26 +714,20 @@ static inline FACET_KEY *FACETS_KEY_CREATE(FACETS *facets, FACETS_HASH hash, con static inline FACET_KEY *FACETS_KEY_ADD_TO_INDEX(FACETS *facets, FACETS_HASH hash, const char *name, size_t name_length, FACET_KEY_OPTIONS options) { facets->operations.keys.registered++; - SIMPLE_HASHTABLE_SLOT *slot = simple_hashtable_get_slot(&facets->keys.ht, hash); + SIMPLE_HASHTABLE_SLOT_KEY *slot = simple_hashtable_get_slot_KEY(&facets->keys.ht, hash, true); - if(unlikely(!slot->data)) { + if(unlikely(!SIMPLE_HASHTABLE_SLOT_DATA(slot))) { // we have to add it FACET_KEY *k = FACETS_KEY_CREATE(facets, hash, name, name_length, options); - slot->hash = hash; - slot->data = k; - - if(facets->keys.count > facets->keys.ht.size / 2) { - simple_hashtable_resize_double(&facets->keys.ht); - facets->operations.keys.hashtable_increases++; - } + simple_hashtable_set_slot_KEY(&facets->keys.ht, slot, hash, k); return k; } // already in the index - FACET_KEY *k = slot->data; + FACET_KEY *k = SIMPLE_HASHTABLE_SLOT_DATA(slot); facet_key_set_name(k, name, name_length); @@ -716,6 +754,10 @@ bool facets_key_name_is_facet(FACETS *facets, const char *key) { // ---------------------------------------------------------------------------- +size_t facets_histogram_slots(FACETS *facets) { + return facets->histogram.slots; +} + static usec_t calculate_histogram_bar_width(usec_t after_ut, usec_t before_ut) { // Array of valid durations in seconds static time_t valid_durations_s[] = { @@ -731,7 +773,7 @@ static usec_t calculate_histogram_bar_width(usec_t after_ut, usec_t before_ut) { usec_t bar_width_ut = 1 * USEC_PER_SEC; for (int i = array_size - 1; i >= 0; --i) { - if (duration_ut / (valid_durations_s[i] * USEC_PER_SEC) >= HISTOGRAM_COLUMNS) { + if (duration_ut / (valid_durations_s[i] * USEC_PER_SEC) >= FACETS_HISTOGRAM_COLUMNS) { bar_width_ut = valid_durations_s[i] * USEC_PER_SEC; break; } @@ -788,17 +830,7 @@ void facets_set_timeframe_and_histogram_by_name(FACETS *facets, const char *key_ facets_set_timeframe_and_histogram_by_id(facets, hash_str, after_ut, before_ut); } -static inline void facets_histogram_update_value(FACETS *facets, usec_t usec) { - if(!facets->histogram.enabled || - !facets->histogram.key || - !facets->histogram.key->values.enabled || - !facet_key_value_updated(facets->histogram.key) || - usec < facets->histogram.after_ut || - usec > facets->histogram.before_ut) - return; - - FACET_VALUE *v = facets->histogram.key->current_value.v; - +static inline uint32_t facets_histogram_slot_at_time_ut(FACETS *facets, usec_t usec, FACET_VALUE *v) { if(unlikely(!v->histogram)) v->histogram = callocz(facets->histogram.slots, sizeof(*v->histogram)); @@ -815,11 +847,177 @@ static inline void facets_histogram_update_value(FACETS *facets, usec_t usec) { if(unlikely(slot >= facets->histogram.slots)) slot = facets->histogram.slots - 1; + return slot; +} + +static inline void facets_histogram_update_value_slot(FACETS *facets, usec_t usec, FACET_VALUE *v) { + uint32_t slot = facets_histogram_slot_at_time_ut(facets, usec, v); v->histogram[slot]++; } +static inline void facets_histogram_update_value(FACETS *facets, usec_t usec) { + if(!facets->histogram.enabled || + !facets->histogram.key || + !facets->histogram.key->values.enabled || + !facet_key_value_updated(facets->histogram.key) || + usec < facets->histogram.after_ut || + usec > facets->histogram.before_ut) + return; + + FACET_VALUE *v = facets->histogram.key->current_value.v; + facets_histogram_update_value_slot(facets, usec, v); +} + +static usec_t overlap_duration_ut(usec_t start1, usec_t end1, usec_t start2, usec_t end2) { + usec_t overlap_start = MAX(start1, start2); + usec_t overlap_end = MIN(end1, end2); + + if (overlap_start < overlap_end) + return overlap_end - overlap_start; + else + return 0; // No overlap +} + +void facets_update_estimations(FACETS *facets, usec_t from_ut, usec_t to_ut, size_t entries) { + if(unlikely(!facets->histogram.enabled)) + return; + + if(unlikely(!overlap_duration_ut(facets->histogram.after_ut, facets->histogram.before_ut, from_ut, to_ut))) + return; + + facets->operations.rows.evaluated += entries; + facets->operations.rows.matched += entries; + facets->operations.rows.estimated += entries; + + if (!facets->histogram.enabled || + !facets->histogram.key || + !facets->histogram.key->values.enabled) + return; + + if (from_ut < facets->histogram.after_ut) + from_ut = facets->histogram.after_ut; + + if (to_ut > facets->histogram.before_ut) + to_ut = facets->histogram.before_ut; + + if (!facets->histogram.key->estimated_value.v) + FACET_VALUE_ADD_ESTIMATED_VALUE_TO_INDEX(facets->histogram.key); + + FACET_VALUE *v = facets->histogram.key->estimated_value.v; + + size_t slots = 0; + size_t total_ut = to_ut - from_ut; + ssize_t remaining_entries = (ssize_t)entries; + size_t slot = facets_histogram_slot_at_time_ut(facets, from_ut, v); + for(; slot < facets->histogram.slots ;slot++) { + usec_t slot_start_ut = facets->histogram.after_ut + slot * facets->histogram.slot_width_ut; + usec_t slot_end_ut = slot_start_ut + facets->histogram.slot_width_ut; + + if(slot_start_ut > to_ut) + break; + + usec_t overlap_ut = overlap_duration_ut(from_ut, to_ut, slot_start_ut, slot_end_ut); + + size_t slot_entries = (overlap_ut * entries) / total_ut; + v->histogram[slot] += slot_entries; + remaining_entries -= (ssize_t)slot_entries; + slots++; + } + + // Check if all entries are assigned + // This should always be true if the distribution is correct + internal_fatal(remaining_entries < 0 || remaining_entries >= (ssize_t)(slots), + "distribution of estimations is not accurate - there are %zd remaining entries", + remaining_entries); +} + +void facets_row_finished_unsampled(FACETS *facets, usec_t usec) { + facets->operations.rows.evaluated++; + facets->operations.rows.matched++; + facets->operations.rows.unsampled++; + + if(!facets->histogram.enabled || + !facets->histogram.key || + !facets->histogram.key->values.enabled || + usec < facets->histogram.after_ut || + usec > facets->histogram.before_ut) + return; + + if(!facets->histogram.key->unsampled_value.v) + FACET_VALUE_ADD_UNSAMPLED_VALUE_TO_INDEX(facets->histogram.key); + + FACET_VALUE *v = facets->histogram.key->unsampled_value.v; + facets_histogram_update_value_slot(facets, usec, v); + + facets_reset_key(facets->histogram.key); +} + +static const char *facets_key_name_cached(FACET_KEY *k, DICTIONARY *used_hashes_registry) { + if(k->name) { + if(used_hashes_registry && !k->default_selected_for_values) { + char hash_str[FACET_STRING_HASH_SIZE]; + facets_hash_to_str(k->hash, hash_str); + dictionary_set(used_hashes_registry, hash_str, (void *)k->name, strlen(k->name) + 1); + } + + return k->name; + } + + // key has no name + const char *name = "[UNAVAILABLE_FIELD]"; + + if(used_hashes_registry) { + char hash_str[FACET_STRING_HASH_SIZE]; + facets_hash_to_str(k->hash, hash_str); + const char *s = dictionary_get(used_hashes_registry, hash_str); + if(s) name = s; + } + + return name; +} + +static const char *facets_key_value_cached(FACET_KEY *k, FACET_VALUE *v, DICTIONARY *used_hashes_registry) { + if(v->empty || v->estimated || v->unsampled) + return v->name; + + if(v->name && v->name_len) { + if(used_hashes_registry && !k->default_selected_for_values && v->selected) { + char hash_str[FACET_STRING_HASH_SIZE]; + facets_hash_to_str(v->hash, hash_str); + dictionary_set(used_hashes_registry, hash_str, (void *)v->name, v->name_len + 1); + } + + return v->name; + } + + // key has no name + const char *name = "[unavailable field]"; + + if(used_hashes_registry) { + char hash_str[FACET_STRING_HASH_SIZE]; + facets_hash_to_str(v->hash, hash_str); + const char *s = dictionary_get(used_hashes_registry, hash_str); + if(s) name = s; + } + + return name; +} + +static inline void facets_key_value_transformed(FACETS *facets, FACET_KEY *k, FACET_VALUE *v, BUFFER *dst, FACETS_TRANSFORMATION_SCOPE scope) { + buffer_flush(dst); + + if(v->empty || v->unsampled || v->estimated) + buffer_strcat(dst, v->name); + else if(k->transform.cb && k->transform.view_only) { + buffer_contents_replace(dst, v->name, v->name_len); + k->transform.cb(facets, dst, scope, k->transform.data); + } + else + buffer_strcat(dst, facets_key_value_cached(k, v, facets->report.used_hashes_registry)); +} + static inline void facets_histogram_value_names(BUFFER *wb, FACETS *facets __maybe_unused, FACET_KEY *k, const char *key, const char *first_key) { - BUFFER *tb = NULL; + CLEAN_BUFFER *tb = buffer_create(0, NULL); buffer_json_member_add_array(wb, key); { @@ -832,23 +1030,30 @@ static inline void facets_histogram_value_names(BUFFER *wb, FACETS *facets __may if (unlikely(!v->histogram)) continue; - if(!v->empty && k->transform.cb && k->transform.view_only) { - if(!tb) - tb = buffer_create(0, NULL); - - buffer_contents_replace(tb, v->name, v->name_len); - k->transform.cb(facets, tb, FACETS_TRANSFORM_HISTOGRAM, k->transform.data); - buffer_json_add_array_item_string(wb, buffer_tostring(tb)); - } - else - buffer_json_add_array_item_string(wb, v->name); + facets_key_value_transformed(facets, k, v, tb, FACETS_TRANSFORM_HISTOGRAM); + buffer_json_add_array_item_string(wb, buffer_tostring(tb)); } foreach_value_in_key_done(v); } } buffer_json_array_close(wb); // key +} - buffer_free(tb); +static inline void facets_histogram_value_colors(BUFFER *wb, FACETS *facets __maybe_unused, FACET_KEY *k, const char *key) { + buffer_json_member_add_array(wb, key); + { + if(k && k->values.enabled) { + FACET_VALUE *v; + foreach_value_in_key(k, v) { + if (unlikely(!v->histogram)) + continue; + + buffer_json_add_array_item_string(wb, v->color); + } + foreach_value_in_key_done(v); + } + } + buffer_json_array_close(wb); // key } static inline void facets_histogram_value_units(BUFFER *wb, FACETS *facets __maybe_unused, FACET_KEY *k, const char *key) { @@ -954,6 +1159,8 @@ static inline void facets_histogram_value_con(BUFFER *wb, FACETS *facets __maybe } static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) { + CLEAN_BUFFER *tmp = buffer_create(0, NULL); + size_t dimensions = 0; uint32_t min = UINT32_MAX, max = 0, sum = 0, count = 0; @@ -995,6 +1202,7 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) buffer_json_member_add_object(wb, "summary"); { + // summary.nodes buffer_json_member_add_array(wb, "nodes"); { buffer_json_add_array_item_object(wb); // node @@ -1041,6 +1249,7 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) } buffer_json_array_close(wb); // nodes + // summary.contexts buffer_json_member_add_array(wb, "contexts"); { buffer_json_add_array_item_object(wb); // context @@ -1078,6 +1287,7 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) } buffer_json_array_close(wb); // contexts + // summary.instances buffer_json_member_add_array(wb, "instances"); { buffer_json_add_array_item_object(wb); // instance @@ -1109,17 +1319,20 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) } buffer_json_array_close(wb); // instances + // summary.dimensions buffer_json_member_add_array(wb, "dimensions"); if(dimensions && k && k->values.enabled) { size_t pri = 0; FACET_VALUE *v; + foreach_value_in_key(k, v) { if(unlikely(!v->histogram)) continue; buffer_json_add_array_item_object(wb); // dimension { - buffer_json_member_add_string(wb, "id", v->name); + facets_key_value_transformed(facets, k, v, tmp, FACETS_TRANSFORM_HISTOGRAM); + buffer_json_member_add_string(wb, "id", buffer_tostring(tmp)); buffer_json_member_add_object(wb, "ds"); { buffer_json_member_add_uint64(wb, "sl", 1); @@ -1275,7 +1488,7 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) char title[1024 + 1] = "Events Distribution"; FACET_KEY *kt = FACETS_KEY_GET_FROM_INDEX(facets, facets->histogram.hash); if(kt && kt->name) - snprintfz(title, 1024, "Events Distribution by %s", kt->name); + snprintfz(title, sizeof(title) - 1, "Events Distribution by %s", kt->name); buffer_json_member_add_string(wb, "title", title); buffer_json_member_add_time_t(wb, "update_every", facets->histogram.slot_width_ut / USEC_PER_SEC); @@ -1293,6 +1506,7 @@ static void facets_histogram_generate(FACETS *facets, FACET_KEY *k, BUFFER *wb) facets_histogram_value_names(wb, facets, k, "ids", NULL); facets_histogram_value_names(wb, facets, k, "names", NULL); + facets_histogram_value_colors(wb, facets, k, "colors"); facets_histogram_value_units(wb, facets, k, "units"); buffer_json_member_add_object(wb, "sts"); @@ -1525,6 +1739,30 @@ void facets_set_additional_options(FACETS *facets, FACETS_OPTIONS options) { // ---------------------------------------------------------------------------- +static inline void facets_key_set_unsampled_value(FACETS *facets, FACET_KEY *k) { + if(likely(!facet_key_value_updated(k) && facets->keys_in_row.used < FACETS_KEYS_IN_ROW_MAX)) + facets->keys_in_row.array[facets->keys_in_row.used++] = k; + + k->current_value.flags |= FACET_KEY_VALUE_UPDATED | FACET_KEY_VALUE_UNSAMPLED; + + facets->operations.values.registered++; + facets->operations.values.unsampled++; + + // no need to copy the UNSET value + // empty values are exported as empty + k->current_value.raw = NULL; + k->current_value.raw_len = 0; + k->current_value.b->len = 0; + k->current_value.flags &= ~FACET_KEY_VALUE_COPIED; + + if(unlikely(k->values.enabled)) + FACET_VALUE_ADD_UNSAMPLED_VALUE_TO_INDEX(k); + else { + k->key_found_in_row++; + k->key_values_selected_in_row++; + } +} + static inline void facets_key_set_empty_value(FACETS *facets, FACET_KEY *k) { if(likely(!facet_key_value_updated(k) && facets->keys_in_row.used < FACETS_KEYS_IN_ROW_MAX)) facets->keys_in_row.array[facets->keys_in_row.used++] = k; @@ -1554,7 +1792,7 @@ static inline void facets_key_check_value(FACETS *facets, FACET_KEY *k) { facets->keys_in_row.array[facets->keys_in_row.used++] = k; k->current_value.flags |= FACET_KEY_VALUE_UPDATED; - k->current_value.flags &= ~FACET_KEY_VALUE_EMPTY; + k->current_value.flags &= ~(FACET_KEY_VALUE_EMPTY|FACET_KEY_VALUE_UNSAMPLED|FACET_KEY_VALUE_ESTIMATED); facets->operations.values.registered++; @@ -1568,7 +1806,7 @@ static inline void facets_key_check_value(FACETS *facets, FACET_KEY *k) { // if(strstr(buffer_tostring(k->current_value), "fprintd") != NULL) // found = true; - if(facets->query && !facet_key_value_empty(k) && ((k->options & FACET_KEY_OPTION_FTS) || facets->options & FACETS_OPTION_ALL_KEYS_FTS)) { + if(facets->query && !facet_key_value_empty_or_unsampled_or_estimated(k) && ((k->options & FACET_KEY_OPTION_FTS) || facets->options & FACETS_OPTION_ALL_KEYS_FTS)) { facets->operations.fts.searches++; facets_key_value_copy_to_buffer(k); switch(simple_pattern_matches_extract(facets->query, buffer_tostring(k->current_value.b), NULL, 0)) { @@ -1679,7 +1917,7 @@ static FACET_ROW *facets_row_create(FACETS *facets, usec_t usec, FACET_ROW *into .empty = true, }; - if(facet_key_value_updated(k) && !facet_key_value_empty(k)) { + if(facet_key_value_updated(k) && !facet_key_value_empty_or_unsampled_or_estimated(k)) { t.tmp = facets_key_get_value(k); t.tmp_len = facets_key_get_value_length(k); t.empty = false; @@ -1758,6 +1996,12 @@ static inline bool facets_is_entry_within_anchor(FACETS *facets, usec_t usec) { return true; } +bool facets_row_candidate_to_keep(FACETS *facets, usec_t usec) { + return !facets->base || + (usec >= facets->base->prev->usec && usec <= facets->base->usec && facets_is_entry_within_anchor(facets, usec)) || + facets->items_to_return < facets->max_items_to_return; +} + static void facets_row_keep(FACETS *facets, usec_t usec) { facets->operations.rows.matched++; @@ -1885,9 +2129,10 @@ bool facets_row_finished(FACETS *facets, usec_t usec) { for(size_t p = 0; p < entries ;p++) { FACET_KEY *k = facets->keys_with_values.array[p]; - if(!facet_key_value_updated(k)) + if(!facet_key_value_updated(k)) { // put the FACET_VALUE_UNSET value into it facets_key_set_empty_value(facets, k); + } total_keys++; @@ -1935,7 +2180,7 @@ bool facets_row_finished(FACETS *facets, usec_t usec) { // ---------------------------------------------------------------------------- // output -static const char *facets_severity_to_string(FACET_ROW_SEVERITY severity) { +const char *facets_severity_to_string(FACET_ROW_SEVERITY severity) { switch(severity) { default: case FACET_ROW_SEVERITY_NORMAL: @@ -2104,7 +2349,7 @@ static uint32_t facets_sort_and_reorder_values(FACET_KEY *k) { if(!k->values.enabled || !k->values.ll || !k->values.used) return 0; - if(!k->transform.cb || !(k->facets->options & FACETS_OPTION_SORT_FACETS_ALPHABETICALLY)) + if(!k->transform.cb || !k->transform.view_only || !(k->facets->options & FACETS_OPTION_SORT_FACETS_ALPHABETICALLY)) return facets_sort_and_reorder_values_internal(k); // we have a transformation and has to be sorted alphabetically @@ -2128,8 +2373,7 @@ static uint32_t facets_sort_and_reorder_values(FACET_KEY *k) { values[used].name_len = v->name_len; used++; - buffer_contents_replace(tb, v->name, v->name_len); - k->transform.cb(k->facets, tb, FACETS_TRANSFORM_FACET_SORT, k->transform.data); + facets_key_value_transformed(k->facets, k, v, tb, FACETS_TRANSFORM_FACET_SORT); v->name = strdupz(buffer_tostring(tb)); v->name_len = buffer_strlen(tb); } @@ -2167,55 +2411,9 @@ void facets_table_config(BUFFER *wb) { buffer_json_object_close(wb); // pagination } -static const char *facets_json_key_name_string(FACET_KEY *k, DICTIONARY *used_hashes_registry) { - if(k->name) { - if(used_hashes_registry && !k->default_selected_for_values) { - char hash_str[FACET_STRING_HASH_SIZE]; - facets_hash_to_str(k->hash, hash_str); - dictionary_set(used_hashes_registry, hash_str, (void *)k->name, strlen(k->name) + 1); - } - - return k->name; - } - - // key has no name - const char *name = "[UNAVAILABLE_FIELD]"; - - if(used_hashes_registry) { - char hash_str[FACET_STRING_HASH_SIZE]; - facets_hash_to_str(k->hash, hash_str); - const char *s = dictionary_get(used_hashes_registry, hash_str); - if(s) name = s; - } - - return name; -} - -static const char *facets_json_key_value_string(FACET_KEY *k, FACET_VALUE *v, DICTIONARY *used_hashes_registry) { - if(v->name && v->name_len) { - if(used_hashes_registry && !k->default_selected_for_values && v->selected) { - char hash_str[FACET_STRING_HASH_SIZE]; - facets_hash_to_str(v->hash, hash_str); - dictionary_set(used_hashes_registry, hash_str, (void *)v->name, v->name_len + 1); - } - - return v->name; - } - - // key has no name - const char *name = "[unavailable field]"; - - if(used_hashes_registry) { - char hash_str[FACET_STRING_HASH_SIZE]; - facets_hash_to_str(v->hash, hash_str); - const char *s = dictionary_get(used_hashes_registry, hash_str); - if(s) name = s; - } - - return name; -} - void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) { + facets->report.used_hashes_registry = used_hashes_registry; + if(!(facets->options & FACETS_OPTION_DATA_ONLY)) { facets_table_config(wb); facets_accepted_parameters_to_json_array(facets, wb, true); @@ -2239,7 +2437,7 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) } if(show_facets) { - BUFFER *tb = NULL; + CLEAN_BUFFER *tb = buffer_create(0, NULL); FACET_KEY *k; foreach_key_in_facets(facets, k) { if(!k->values.enabled) @@ -2252,7 +2450,9 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) buffer_json_add_array_item_object(wb); // key { buffer_json_member_add_string(wb, "id", hash_to_static_string(k->hash)); - buffer_json_member_add_string(wb, "name", facets_json_key_name_string(k, used_hashes_registry)); + buffer_json_member_add_string(wb, "name", facets_key_name_cached(k + , facets->report.used_hashes_registry + )); if(!k->order) k->order = facets->order++; buffer_json_member_add_uint64(wb, "order", k->order); @@ -2264,21 +2464,15 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) if((facets->options & FACETS_OPTION_DONT_SEND_EMPTY_VALUE_FACETS) && v->empty) continue; + if(v->unsampled || v->estimated) + continue; + buffer_json_add_array_item_object(wb); { buffer_json_member_add_string(wb, "id", hash_to_static_string(v->hash)); - if(!v->empty && k->transform.cb && k->transform.view_only) { - if(!tb) - tb = buffer_create(0, NULL); - - buffer_contents_replace(tb, v->name, v->name_len); - k->transform.cb(facets, tb, FACETS_TRANSFORM_FACET, k->transform.data); - buffer_json_member_add_string(wb, "name", buffer_tostring(tb)); - } - else - buffer_json_member_add_string(wb, "name", facets_json_key_value_string(k, v, used_hashes_registry)); - + facets_key_value_transformed(facets, k, v, tb, FACETS_TRANSFORM_FACET); + buffer_json_member_add_string(wb, "name", buffer_tostring(tb)); buffer_json_member_add_uint64(wb, "count", v->final_facet_value_counter); buffer_json_member_add_uint64(wb, "order", v->order); } @@ -2291,7 +2485,6 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) buffer_json_object_close(wb); // key } foreach_key_in_facets_done(k); - buffer_free(tb); buffer_json_array_close(wb); // facets } } @@ -2325,7 +2518,7 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) NULL, RRDF_FIELD_SUMMARY_COUNT, RRDF_FIELD_FILTER_NONE, - RRDR_FIELD_OPTS_DUMMY, + RRDF_FIELD_OPTS_DUMMY, NULL); FACET_KEY *k; @@ -2345,6 +2538,9 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) if (k->options & FACET_KEY_OPTION_MAIN_TEXT) options |= RRDF_FIELD_OPTS_FULL_WIDTH | RRDF_FIELD_OPTS_WRAP; + if (k->options & FACET_KEY_OPTION_EXPANDED_FILTER) + options |= RRDF_FIELD_OPTS_EXPANDED_FILTER; + const char *hash_str = hash_to_static_string(k->hash); buffer_rrdf_table_add_field( @@ -2356,8 +2552,7 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) RRDF_FIELD_SORT_FIXED, NULL, RRDF_FIELD_SUMMARY_COUNT, - (k->options & FACET_KEY_OPTION_NEVER_FACET) ? RRDF_FIELD_FILTER_NONE - : RRDF_FIELD_FILTER_FACET, + (k->options & FACET_KEY_OPTION_NEVER_FACET) ? RRDF_FIELD_FILTER_NONE : RRDF_FIELD_FILTER_FACET, options, FACET_VALUE_UNSET); } foreach_key_in_facets_done(k); @@ -2503,6 +2698,8 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) if(show_items) { buffer_json_member_add_uint64(wb, "evaluated", facets->operations.rows.evaluated); buffer_json_member_add_uint64(wb, "matched", facets->operations.rows.matched); + buffer_json_member_add_uint64(wb, "unsampled", facets->operations.rows.unsampled); + buffer_json_member_add_uint64(wb, "estimated", facets->operations.rows.estimated); buffer_json_member_add_uint64(wb, "returned", facets->items_to_return); buffer_json_member_add_uint64(wb, "max_to_return", facets->max_items_to_return); buffer_json_member_add_uint64(wb, "before", facets->operations.skips_before); @@ -2533,21 +2730,51 @@ void facets_report(FACETS *facets, BUFFER *wb, DICTIONARY *used_hashes_registry) buffer_json_object_close(wb); // rows buffer_json_member_add_object(wb, "keys"); { + size_t resizes = 0, searches = 0, collisions = 0, used = 0, size = 0, count = 0; + count++; + used += facets->keys.ht.used; + size += facets->keys.ht.size; + resizes += facets->keys.ht.resizes; + searches += facets->keys.ht.searches; + collisions += facets->keys.ht.collisions; + buffer_json_member_add_uint64(wb, "registered", facets->operations.keys.registered); buffer_json_member_add_uint64(wb, "unique", facets->operations.keys.unique); - buffer_json_member_add_uint64(wb, "hashtable_increases", facets->operations.keys.hashtable_increases); + buffer_json_member_add_uint64(wb, "hashtables", count); + buffer_json_member_add_uint64(wb, "hashtable_used", used); + buffer_json_member_add_uint64(wb, "hashtable_size", size); + buffer_json_member_add_uint64(wb, "hashtable_searches", searches); + buffer_json_member_add_uint64(wb, "hashtable_collisions", collisions); + buffer_json_member_add_uint64(wb, "hashtable_resizes", resizes); } buffer_json_object_close(wb); // keys buffer_json_member_add_object(wb, "values"); { + size_t resizes = 0, searches = 0, collisions = 0, used = 0, size = 0, count = 0; + for(FACET_KEY *k = facets->keys.ll; k ; k = k->next) { + count++; + used += k->values.ht.used; + size += k->values.ht.size; + resizes += k->values.ht.resizes; + searches += k->values.ht.searches; + collisions += k->values.ht.collisions; + } + buffer_json_member_add_uint64(wb, "registered", facets->operations.values.registered); buffer_json_member_add_uint64(wb, "transformed", facets->operations.values.transformed); buffer_json_member_add_uint64(wb, "dynamic", facets->operations.values.dynamic); buffer_json_member_add_uint64(wb, "empty", facets->operations.values.empty); + buffer_json_member_add_uint64(wb, "unsampled", facets->operations.values.unsampled); + buffer_json_member_add_uint64(wb, "estimated", facets->operations.values.estimated); buffer_json_member_add_uint64(wb, "indexed", facets->operations.values.indexed); buffer_json_member_add_uint64(wb, "inserts", facets->operations.values.inserts); buffer_json_member_add_uint64(wb, "conflicts", facets->operations.values.conflicts); - buffer_json_member_add_uint64(wb, "hashtable_increases", facets->operations.values.hashtable_increases); + buffer_json_member_add_uint64(wb, "hashtables", count); + buffer_json_member_add_uint64(wb, "hashtable_used", used); + buffer_json_member_add_uint64(wb, "hashtable_size", size); + buffer_json_member_add_uint64(wb, "hashtable_searches", searches); + buffer_json_member_add_uint64(wb, "hashtable_collisions", collisions); + buffer_json_member_add_uint64(wb, "hashtable_resizes", resizes); } buffer_json_object_close(wb); // values buffer_json_member_add_object(wb, "fts"); diff --git a/libnetdata/facets/facets.h b/libnetdata/facets/facets.h index 75972561..8364d861 100644 --- a/libnetdata/facets/facets.h +++ b/libnetdata/facets/facets.h @@ -6,6 +6,8 @@ #include "../libnetdata.h" #define FACET_VALUE_UNSET "-" +#define FACET_VALUE_UNSAMPLED "[unsampled]" +#define FACET_VALUE_ESTIMATED "[estimated]" typedef enum __attribute__((packed)) { FACETS_ANCHOR_DIRECTION_FORWARD, @@ -31,6 +33,7 @@ typedef enum __attribute__((packed)) { FACET_KEY_OPTION_RICH_TEXT = (1 << 7), FACET_KEY_OPTION_REORDER = (1 << 8), // give the key a new order id on first encounter FACET_KEY_OPTION_TRANSFORM_VIEW = (1 << 9), // when registering the transformation, do it only at the view, not on all data + FACET_KEY_OPTION_EXPANDED_FILTER = (1 << 10), // the presentation should have this filter expanded by default } FACET_KEY_OPTIONS; typedef enum __attribute__((packed)) { @@ -84,11 +87,16 @@ void facets_accepted_param(FACETS *facets, const char *param); void facets_rows_begin(FACETS *facets); bool facets_row_finished(FACETS *facets, usec_t usec); +void facets_row_finished_unsampled(FACETS *facets, usec_t usec); +void facets_update_estimations(FACETS *facets, usec_t from_ut, usec_t to_ut, size_t entries); +size_t facets_histogram_slots(FACETS *facets); + FACET_KEY *facets_register_key_name(FACETS *facets, const char *key, FACET_KEY_OPTIONS options); void facets_set_query(FACETS *facets, const char *query); void facets_set_items(FACETS *facets, uint32_t items); void facets_set_anchor(FACETS *facets, usec_t start_ut, usec_t stop_ut, FACETS_ANCHOR_DIRECTION direction); void facets_enable_slice_mode(FACETS *facets); +bool facets_row_candidate_to_keep(FACETS *facets, usec_t usec); FACET_KEY *facets_register_facet_id(FACETS *facets, const char *key_id, FACET_KEY_OPTIONS options); void facets_register_facet_id_filter(FACETS *facets, const char *key_id, char *value_id, FACET_KEY_OPTIONS options); @@ -115,4 +123,6 @@ uint32_t facets_rows(FACETS *facets); void facets_table_config(BUFFER *wb); +const char *facets_severity_to_string(FACET_ROW_SEVERITY severity); + #endif diff --git a/libnetdata/functions_evloop/functions_evloop.c b/libnetdata/functions_evloop/functions_evloop.c index 3fcd70aa..044556ac 100644 --- a/libnetdata/functions_evloop/functions_evloop.c +++ b/libnetdata/functions_evloop/functions_evloop.c @@ -64,6 +64,12 @@ static void *rrd_functions_worker_globals_worker_main(void *arg) { pthread_mutex_unlock(&wg->worker_mutex); if(acquired) { + ND_LOG_STACK lgs[] = { + ND_LOG_FIELD_TXT(NDF_REQUEST, j->cmd), + ND_LOG_FIELD_END(), + }; + ND_LOG_STACK_PUSH(lgs); + last_acquired = true; j = dictionary_acquired_item_value(acquired); j->cb(j->transaction, j->cmd, j->timeout, &j->cancelled); @@ -208,3 +214,10 @@ void functions_evloop_add_function(struct functions_evloop_globals *wg, const ch we->default_timeout = default_timeout; DOUBLE_LINKED_LIST_APPEND_ITEM_UNSAFE(wg->expectations, we, prev, next); } + +void functions_evloop_cancel_threads(struct functions_evloop_globals *wg){ + for(size_t i = 0; i < wg->workers ; i++) + netdata_thread_cancel(wg->worker_threads[i]); + + netdata_thread_cancel(wg->reader_thread); +} diff --git a/libnetdata/functions_evloop/functions_evloop.h b/libnetdata/functions_evloop/functions_evloop.h index ee0f72cb..e5e83e95 100644 --- a/libnetdata/functions_evloop/functions_evloop.h +++ b/libnetdata/functions_evloop/functions_evloop.h @@ -46,12 +46,15 @@ #define PLUGINSD_KEYWORD_EXIT "EXIT" +#define PLUGINSD_KEYWORD_SLOT "SLOT" // to change the length of this, update pluginsd_extract_chart_slot() too + #define PLUGINS_FUNCTIONS_TIMEOUT_DEFAULT 10 // seconds typedef void (*functions_evloop_worker_execute_t)(const char *transaction, char *function, int timeout, bool *cancelled); struct functions_evloop_worker_job; struct functions_evloop_globals *functions_evloop_init(size_t worker_threads, const char *tag, netdata_mutex_t *stdout_mutex, bool *plugin_should_exit); void functions_evloop_add_function(struct functions_evloop_globals *wg, const char *function, functions_evloop_worker_execute_t cb, time_t default_timeout); +void functions_evloop_cancel_threads(struct functions_evloop_globals *wg); #define pluginsd_function_result_begin_to_buffer(wb, transaction, code, content_type, expires) \ diff --git a/libnetdata/gorilla/README.md b/libnetdata/gorilla/README.md new file mode 100644 index 00000000..dc3718d1 --- /dev/null +++ b/libnetdata/gorilla/README.md @@ -0,0 +1,39 @@ +# Gorilla compression and decompression + +This provides an alternative way of representing values stored in database +pages. Instead of allocating and using a page of fixed size, ie. 4096 bytes, +the Gorilla implementation adds support for dynamically sized pages that +contain a variable number of Gorilla buffers. + +Each buffer takes 512 bytes and compresses incoming data using the Gorilla +compression: + +- The very first value is stored as it is. +- For each new value, Gorilla compression doesn't store the value itself. Instead, +it computes the difference (XOR) between the new value and the previous value. +- If the XOR result is zero (meaning the new value is identical to the previous +value), we store just a single bit set to `1`. +- If the XOR result is not zero (meaning the new value differs from the previous): + - We store a `0` bit to indicate the change. + - We compute the leading-zero count (LZC) of the XOR result, and compare it + with the previous LZC. If the two LZCs are equal we store a `1` bit. + - If the LZCs are different we use 5 bits to store the new LZC, and we store + the rest of the value (ie. without its LZC) in the buffer. + +A Gorilla page can have multiple Gorilla buffers. If the values of a metric +are highly compressible, just one Gorilla buffer is able to store all the values +that otherwise would require a regular 4096 byte page, ie. we can use just 512 +bytes instead. In the worst case scenario (for metrics whose values are not +compressible at all), a Gorilla page might end up having `9` Gorilla buffers, +consuming 4608 bytes. In practice, this is pretty rare and does not negate +the effect of compression for the metrics. + +When a gorilla page is full, ie. it contains 1024 slots/values, we serialize +the linked-list of gorilla buffers directly to disk. During deserialization, +eg. when performing a DBEngine query, the Gorilla page is loaded from the disk and +its linked-list entries are patched to point to the new memory allocated for +serving the query results. + +Overall, on a real-agent the Gorilla compression scheme reduces memory +consumption approximately by ~30%, which can be several GiB of RAM for parents +having hundreds, or even thousands of children streaming to them. diff --git a/libnetdata/gorilla/fuzzer.sh b/libnetdata/gorilla/fuzzer.sh index 9dfdec05..19098a61 100755 --- a/libnetdata/gorilla/fuzzer.sh +++ b/libnetdata/gorilla/fuzzer.sh @@ -11,4 +11,4 @@ clang++ \ -fsanitize=fuzzer \ -o gorilla_fuzzer gorilla.cc -./gorilla_fuzzer -workers=8 -jobs=8 +./gorilla_fuzzer -workers=12 -jobs=16 diff --git a/libnetdata/gorilla/gorilla.cc b/libnetdata/gorilla/gorilla.cc index af2f7400..e6138ce3 100644 --- a/libnetdata/gorilla/gorilla.cc +++ b/libnetdata/gorilla/gorilla.cc @@ -17,413 +17,344 @@ static constexpr size_t bit_size() noexcept return (sizeof(T) * CHAR_BIT); } -/* - * Low-level bitstream operations, allowing us to read/write individual bits. -*/ - -template<typename Word> -struct bit_stream_t { - Word *buffer; - size_t capacity; - size_t position; -}; - -template<typename Word> -static bit_stream_t<Word> bit_stream_new(Word *buffer, Word capacity) { - bit_stream_t<Word> bs; - - bs.buffer = buffer; - bs.capacity = capacity * bit_size<Word>(); - bs.position = 0; - - return bs; -} - -template<typename Word> -static bool bit_stream_write(bit_stream_t<Word> *bs, Word value, size_t nbits) { - assert(nbits > 0 && nbits <= bit_size<Word>()); - assert(bs->capacity >= (bs->position + nbits)); +static void bit_buffer_write(uint32_t *buf, size_t pos, uint32_t v, size_t nbits) +{ + assert(nbits > 0 && nbits <= bit_size<uint32_t>()); - if (bs->position + nbits > bs->capacity) { - return false; - } + const size_t index = pos / bit_size<uint32_t>(); + const size_t offset = pos % bit_size<uint32_t>(); - const size_t index = bs->position / bit_size<Word>(); - const size_t offset = bs->position % bit_size<Word>(); - bs->position += nbits; + pos += nbits; if (offset == 0) { - bs->buffer[index] = value; + buf[index] = v; } else { - const size_t remaining_bits = bit_size<Word>() - offset; + const size_t remaining_bits = bit_size<uint32_t>() - offset; // write the lower part of the value - const Word low_bits_mask = ((Word) 1 << remaining_bits) - 1; - const Word lowest_bits_in_value = value & low_bits_mask; - bs->buffer[index] |= (lowest_bits_in_value << offset); + const uint32_t low_bits_mask = ((uint32_t) 1 << remaining_bits) - 1; + const uint32_t lowest_bits_in_value = v & low_bits_mask; + buf[index] |= (lowest_bits_in_value << offset); if (nbits > remaining_bits) { // write the upper part of the value - const Word high_bits_mask = ~low_bits_mask; - const Word highest_bits_in_value = (value & high_bits_mask) >> (remaining_bits); - bs->buffer[index + 1] = highest_bits_in_value; + const uint32_t high_bits_mask = ~low_bits_mask; + const uint32_t highest_bits_in_value = (v & high_bits_mask) >> (remaining_bits); + buf[index + 1] = highest_bits_in_value; } } - - return true; } -template<typename Word> -static bool bit_stream_read(bit_stream_t<Word> *bs, Word *value, size_t nbits) { - assert(nbits > 0 && nbits <= bit_size<Word>()); - assert(bs->capacity >= (bs->position + nbits)); +static void bit_buffer_read(const uint32_t *buf, size_t pos, uint32_t *v, size_t nbits) +{ + assert(nbits > 0 && nbits <= bit_size<uint32_t>()); - if (bs->position + nbits > bs->capacity) { - return false; - } + const size_t index = pos / bit_size<uint32_t>(); + const size_t offset = pos % bit_size<uint32_t>(); - const size_t index = bs->position / bit_size<Word>(); - const size_t offset = bs->position % bit_size<Word>(); - bs->position += nbits; + pos += nbits; if (offset == 0) { - *value = (nbits == bit_size<Word>()) ? - bs->buffer[index] : - bs->buffer[index] & (((Word) 1 << nbits) - 1); + *v = (nbits == bit_size<uint32_t>()) ? + buf[index] : + buf[index] & (((uint32_t) 1 << nbits) - 1); } else { - const size_t remaining_bits = bit_size<Word>() - offset; + const size_t remaining_bits = bit_size<uint32_t>() - offset; // extract the lower part of the value if (nbits < remaining_bits) { - *value = (bs->buffer[index] >> offset) & (((Word) 1 << nbits) - 1); + *v = (buf[index] >> offset) & (((uint32_t) 1 << nbits) - 1); } else { - *value = (bs->buffer[index] >> offset) & (((Word) 1 << remaining_bits) - 1); + *v = (buf[index] >> offset) & (((uint32_t) 1 << remaining_bits) - 1); nbits -= remaining_bits; - *value |= (bs->buffer[index + 1] & (((Word) 1 << nbits) - 1)) << remaining_bits; + *v |= (buf[index + 1] & (((uint32_t) 1 << nbits) - 1)) << remaining_bits; } } - - return true; } -/* - * High-level Gorilla codec implementation -*/ - -template<typename Word> -struct bit_code_t { - bit_stream_t<Word> bs; - Word entries; - Word prev_number; - Word prev_xor; - Word prev_xor_lzc; -}; - -template<typename Word> -static void bit_code_init(bit_code_t<Word> *bc, Word *buffer, Word capacity) { - bc->bs = bit_stream_new(buffer, capacity); - - bc->entries = 0; - bc->prev_number = 0; - bc->prev_xor = 0; - bc->prev_xor_lzc = 0; - - // reserved two words: - // Buffer[0] -> number of entries written - // Buffer[1] -> number of bits written +gorilla_writer_t gorilla_writer_init(gorilla_buffer_t *gbuf, size_t n) +{ + gorilla_writer_t gw = gorilla_writer_t { + .head_buffer = gbuf, + .last_buffer = NULL, + .prev_number = 0, + .prev_xor_lzc = 0, + .capacity = 0 + }; - bc->bs.position += 2 * bit_size<Word>(); + gorilla_writer_add_buffer(&gw, gbuf, n); + return gw; } -template<typename Word> -static bool bit_code_read(bit_code_t<Word> *bc, Word *number) { - bit_stream_t<Word> *bs = &bc->bs; - - bc->entries++; +void gorilla_writer_add_buffer(gorilla_writer_t *gw, gorilla_buffer_t *gbuf, size_t n) +{ + gbuf->header.next = NULL; + gbuf->header.entries = 0; + gbuf->header.nbits = 0; - // read the first number - if (bc->entries == 1) { - bool ok = bit_stream_read(bs, number, bit_size<Word>()); - bc->prev_number = *number; - return ok; - } + uint32_t capacity = (n * bit_size<uint32_t>()) - (sizeof(gorilla_header_t) * CHAR_BIT); - // process same-number bit - Word is_same_number; - if (!bit_stream_read(bs, &is_same_number, 1)) { - return false; - } + gw->prev_number = 0; + gw->prev_xor_lzc = 0; + gw->capacity = capacity; - if (is_same_number) { - *number = bc->prev_number; - return true; - } + if (gw->last_buffer) + gw->last_buffer->header.next = gbuf; - // proceess same-xor-lzc bit - Word xor_lzc = bc->prev_xor_lzc; - - Word same_xor_lzc; - if (!bit_stream_read(bs, &same_xor_lzc, 1)) { - return false; - } + __atomic_store_n(&gw->last_buffer, gbuf, __ATOMIC_RELAXED); +} - if (!same_xor_lzc) { - if (!bit_stream_read(bs, &xor_lzc, (bit_size<Word>() == 32) ? 5 : 6)) { - return false; - } - } +uint32_t gorilla_writer_entries(const gorilla_writer_t *gw) { + uint32_t entries = 0; - // process the non-lzc suffix - Word xor_value = 0; - if (!bit_stream_read(bs, &xor_value, bit_size<Word>() - xor_lzc)) { - return false; - } + const gorilla_buffer_t *curr_gbuf = __atomic_load_n(&gw->head_buffer, __ATOMIC_SEQ_CST); + do { + const gorilla_buffer_t *next_gbuf = __atomic_load_n(&curr_gbuf->header.next, __ATOMIC_SEQ_CST); - *number = (bc->prev_number ^ xor_value); + entries += __atomic_load_n(&curr_gbuf->header.entries, __ATOMIC_SEQ_CST); - bc->prev_number = *number; - bc->prev_xor_lzc = xor_lzc; - bc->prev_xor = xor_value; + curr_gbuf = next_gbuf; + } while (curr_gbuf); - return true; + return entries; } -template<typename Word> -static bool bit_code_write(bit_code_t<Word> *bc, const Word number) { - bit_stream_t<Word> *bs = &bc->bs; - Word position = bs->position; - - bc->entries++; +bool gorilla_writer_write(gorilla_writer_t *gw, uint32_t number) +{ + gorilla_header_t *hdr = &gw->last_buffer->header; + uint32_t *data = gw->last_buffer->data; // this is the first number we are writing - if (bc->entries == 1) { - bc->prev_number = number; - return bit_stream_write(bs, number, bit_size<Word>()); - } - - // write true/false based on whether we got the same number or not. - if (number == bc->prev_number) { - return bit_stream_write(bs, static_cast<Word>(1), 1); - } else { - if (bit_stream_write(bs, static_cast<Word>(0), 1) == false) { + if (hdr->entries == 0) { + if (hdr->nbits + bit_size<uint32_t>() >= gw->capacity) return false; - } - } - - // otherwise: - // - compute the non-zero xor - // - find its leading-zero count - - Word xor_value = bc->prev_number ^ number; - // FIXME: Use SFINAE - Word xor_lzc = (bit_size<Word>() == 32) ? __builtin_clz(xor_value) : __builtin_clzll(xor_value); - Word is_xor_lzc_same = (xor_lzc == bc->prev_xor_lzc) ? 1 : 0; - - if (is_xor_lzc_same) { - // xor-lzc is same - if (bit_stream_write(bs, static_cast<Word>(1), 1) == false) { - goto RET_FALSE; - } - } else { - // xor-lzc is different - if (bit_stream_write(bs, static_cast<Word>(0), 1) == false) { - goto RET_FALSE; - } - - if (bit_stream_write(bs, xor_lzc, (bit_size<Word>() == 32) ? 5 : 6) == false) { - goto RET_FALSE; - } - } + bit_buffer_write(data, hdr->nbits, number, bit_size<uint32_t>()); - // write the bits of the XOR value without the LZC prefix - if (bit_stream_write(bs, xor_value, bit_size<Word>() - xor_lzc) == false) { - goto RET_FALSE; + __atomic_fetch_add(&hdr->nbits, bit_size<uint32_t>(), __ATOMIC_RELAXED); + __atomic_fetch_add(&hdr->entries, 1, __ATOMIC_RELAXED); + gw->prev_number = number; + return true; } - bc->prev_number = number; - bc->prev_xor_lzc = xor_lzc; - return true; - -RET_FALSE: - bc->bs.position = position; - return false; -} + // write true/false based on whether we got the same number or not. + if (number == gw->prev_number) { + if (hdr->nbits + 1 >= gw->capacity) + return false; -// only valid for writers -template<typename Word> -static bool bit_code_flush(bit_code_t<Word> *bc) { - bit_stream_t<Word> *bs = &bc->bs; + bit_buffer_write(data, hdr->nbits, static_cast<uint32_t>(1), 1); + __atomic_fetch_add(&hdr->nbits, 1, __ATOMIC_RELAXED); + __atomic_fetch_add(&hdr->entries, 1, __ATOMIC_RELAXED); + return true; + } - Word num_entries_written = bc->entries; - Word num_bits_written = bs->position; + if (hdr->nbits + 1 >= gw->capacity) + return false; + bit_buffer_write(data, hdr->nbits, static_cast<uint32_t>(0), 1); + __atomic_fetch_add(&hdr->nbits, 1, __ATOMIC_RELAXED); - // we want to write these at the beginning - bs->position = 0; + uint32_t xor_value = gw->prev_number ^ number; + uint32_t xor_lzc = (bit_size<uint32_t>() == 32) ? __builtin_clz(xor_value) : __builtin_clzll(xor_value); + uint32_t is_xor_lzc_same = (xor_lzc == gw->prev_xor_lzc) ? 1 : 0; - if (!bit_stream_write(bs, num_entries_written, bit_size<Word>())) { + if (hdr->nbits + 1 >= gw->capacity) return false; + bit_buffer_write(data, hdr->nbits, is_xor_lzc_same, 1); + __atomic_fetch_add(&hdr->nbits, 1, __ATOMIC_RELAXED); + + if (!is_xor_lzc_same) { + if (hdr->nbits + 1 >= gw->capacity) + return false; + bit_buffer_write(data, hdr->nbits, xor_lzc, (bit_size<uint32_t>() == 32) ? 5 : 6); + __atomic_fetch_add(&hdr->nbits, (bit_size<uint32_t>() == 32) ? 5 : 6, __ATOMIC_RELAXED); } - if (!bit_stream_write(bs, num_bits_written, bit_size<Word>())) { + // write the bits of the XOR'd value without the LZC prefix + if (hdr->nbits + (bit_size<uint32_t>() - xor_lzc) >= gw->capacity) return false; - } + bit_buffer_write(data, hdr->nbits, xor_value, bit_size<uint32_t>() - xor_lzc); + __atomic_fetch_add(&hdr->nbits, bit_size<uint32_t>() - xor_lzc, __ATOMIC_RELAXED); + __atomic_fetch_add(&hdr->entries, 1, __ATOMIC_RELAXED); - bs->position = num_bits_written; + gw->prev_number = number; + gw->prev_xor_lzc = xor_lzc; return true; } -// only valid for readers -template<typename Word> -static bool bit_code_info(bit_code_t<Word> *bc, Word *num_entries_written, - Word *num_bits_written) { - bit_stream_t<Word> *bs = &bc->bs; +gorilla_buffer_t *gorilla_writer_drop_head_buffer(gorilla_writer_t *gw) { + if (!gw->head_buffer) + return NULL; - assert(bs->position == 2 * bit_size<Word>()); - if (bs->capacity < (2 * bit_size<Word>())) { - return false; - } - - if (num_entries_written) { - *num_entries_written = bs->buffer[0]; - } - if (num_bits_written) { - *num_bits_written = bs->buffer[1]; - } - - return true; + gorilla_buffer_t *curr_head = gw->head_buffer; + gorilla_buffer_t *next_head = gw->head_buffer->header.next; + __atomic_store_n(&gw->head_buffer, next_head, __ATOMIC_RELAXED); + return curr_head; } -template<typename Word> -static size_t gorilla_encode(Word *dst, Word dst_len, const Word *src, Word src_len) { - bit_code_t<Word> bcw; +uint32_t gorilla_writer_nbytes(const gorilla_writer_t *gw) +{ + uint32_t nbits = 0; - bit_code_init(&bcw, dst, dst_len); + const gorilla_buffer_t *curr_gbuf = __atomic_load_n(&gw->head_buffer, __ATOMIC_SEQ_CST); + do { + const gorilla_buffer_t *next_gbuf = __atomic_load_n(&curr_gbuf->header.next, __ATOMIC_SEQ_CST); - for (size_t i = 0; i != src_len; i++) { - if (!bit_code_write(&bcw, src[i])) - return 0; - } + nbits += __atomic_load_n(&curr_gbuf->header.nbits, __ATOMIC_SEQ_CST); - if (!bit_code_flush(&bcw)) - return 0; + curr_gbuf = next_gbuf; + } while (curr_gbuf); - return src_len; + return (nbits + (CHAR_BIT - 1)) / CHAR_BIT; } -template<typename Word> -static size_t gorilla_decode(Word *dst, Word dst_len, const Word *src, Word src_len) { - bit_code_t<Word> bcr; +bool gorilla_writer_serialize(const gorilla_writer_t *gw, uint8_t *dst, uint32_t dst_size) { + const gorilla_buffer_t *curr_gbuf = gw->head_buffer; - bit_code_init(&bcr, (Word *) src, src_len); + do { + const gorilla_buffer_t *next_gbuf = curr_gbuf->header.next; - Word num_entries; - if (!bit_code_info(&bcr, &num_entries, (Word *) NULL)) { - return 0; - } - if (num_entries > dst_len) { - return 0; - } - - for (size_t i = 0; i != num_entries; i++) { - if (!bit_code_read(&bcr, &dst[i])) - return 0; - } + size_t bytes = GORILLA_BUFFER_SIZE; + if (bytes > dst_size) + return false; - return num_entries; -} + memcpy(dst, curr_gbuf, bytes); + dst += bytes; + dst_size -= bytes; -/* - * Low-level public API -*/ - -// 32-bit API + curr_gbuf = next_gbuf; + } while (curr_gbuf); -void bit_code_writer_u32_init(bit_code_writer_u32_t *bcw, uint32_t *buffer, uint32_t capacity) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcw; - bit_code_init(bc, buffer, capacity); + return true; } -bool bit_code_writer_u32_write(bit_code_writer_u32_t *bcw, const uint32_t number) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcw; - return bit_code_write(bc, number); -} +uint32_t gorilla_buffer_patch(gorilla_buffer_t *gbuf) { + gorilla_buffer_t *curr_gbuf = gbuf; + uint32_t n = curr_gbuf->header.entries; -bool bit_code_writer_u32_flush(bit_code_writer_u32_t *bcw) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcw; - return bit_code_flush(bc); -} + while (curr_gbuf->header.next) { + uint32_t *buf = reinterpret_cast<uint32_t *>(gbuf); + gbuf = reinterpret_cast<gorilla_buffer_t *>(&buf[GORILLA_BUFFER_SLOTS]); -void bit_code_reader_u32_init(bit_code_reader_u32_t *bcr, uint32_t *buffer, uint32_t capacity) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcr; - bit_code_init(bc, buffer, capacity); -} + assert(((uintptr_t) (gbuf) % sizeof(uintptr_t)) == 0 && + "Gorilla buffer not aligned to uintptr_t"); -bool bit_code_reader_u32_read(bit_code_reader_u32_t *bcr, uint32_t *number) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcr; - return bit_code_read(bc, number); -} + curr_gbuf->header.next = gbuf; + curr_gbuf = curr_gbuf->header.next; -bool bit_code_reader_u32_info(bit_code_reader_u32_t *bcr, uint32_t *num_entries_written, - uint32_t *num_bits_written) { - bit_code_t<uint32_t> *bc = (bit_code_t<uint32_t> *) bcr; - return bit_code_info(bc, num_entries_written, num_bits_written); + n += curr_gbuf->header.entries; + } + + return n; } -// 64-bit API +gorilla_reader_t gorilla_writer_get_reader(const gorilla_writer_t *gw) +{ + const gorilla_buffer_t *buffer = __atomic_load_n(&gw->head_buffer, __ATOMIC_SEQ_CST); -void bit_code_writer_u64_init(bit_code_writer_u64_t *bcw, uint64_t *buffer, uint64_t capacity) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcw; - bit_code_init(bc, buffer, capacity); -} + uint32_t entries = __atomic_load_n(&buffer->header.entries, __ATOMIC_SEQ_CST); + uint32_t capacity = __atomic_load_n(&buffer->header.nbits, __ATOMIC_SEQ_CST); -bool bit_code_writer_u64_write(bit_code_writer_u64_t *bcw, const uint64_t number) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcw; - return bit_code_write(bc, number); + return gorilla_reader_t { + .buffer = buffer, + .entries = entries, + .index = 0, + .capacity = capacity, + .position = 0, + .prev_number = 0, + .prev_xor_lzc = 0, + .prev_xor = 0, + }; } -bool bit_code_writer_u64_flush(bit_code_writer_u64_t *bcw) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcw; - return bit_code_flush(bc); -} +gorilla_reader_t gorilla_reader_init(gorilla_buffer_t *gbuf) +{ + uint32_t entries = __atomic_load_n(&gbuf->header.entries, __ATOMIC_SEQ_CST); + uint32_t capacity = __atomic_load_n(&gbuf->header.nbits, __ATOMIC_SEQ_CST); + + return gorilla_reader_t { + .buffer = gbuf, + .entries = entries, + .index = 0, + .capacity = capacity, + .position = 0, + .prev_number = 0, + .prev_xor_lzc = 0, + .prev_xor = 0, + }; +} + +bool gorilla_reader_read(gorilla_reader_t *gr, uint32_t *number) +{ + const uint32_t *data = gr->buffer->data; + + if (gr->index + 1 > gr->entries) { + // We don't have any more entries to return. However, the writer + // might have updated the buffer's entries. We need to check once + // more in case more elements were added. + gr->entries = __atomic_load_n(&gr->buffer->header.entries, __ATOMIC_SEQ_CST); + gr->capacity = __atomic_load_n(&gr->buffer->header.nbits, __ATOMIC_SEQ_CST); + + // if the reader's current buffer has not been updated, we need to + // check if it has a pointer to a next buffer. + if (gr->index + 1 > gr->entries) { + gorilla_buffer_t *next_buffer = __atomic_load_n(&gr->buffer->header.next, __ATOMIC_SEQ_CST); + + if (!next_buffer) { + // fprintf(stderr, "Consumed reader with %zu entries from buffer %p\n (No more buffers to read from)", gr->length, gr->buffer); + return false; + } + + // fprintf(stderr, "Consumed reader with %zu entries from buffer %p\n", gr->length, gr->buffer); + *gr = gorilla_reader_init(next_buffer); + return gorilla_reader_read(gr, number); + } + } -void bit_code_reader_u64_init(bit_code_reader_u64_t *bcr, uint64_t *buffer, uint64_t capacity) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcr; - bit_code_init(bc, buffer, capacity); -} + // read the first number + if (gr->index == 0) { + bit_buffer_read(data, gr->position, number, bit_size<uint32_t>()); -bool bit_code_reader_u64_read(bit_code_reader_u64_t *bcr, uint64_t *number) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcr; - return bit_code_read(bc, number); -} + gr->index++; + gr->position += bit_size<uint32_t>(); + gr->prev_number = *number; + return true; + } -bool bit_code_reader_u64_info(bit_code_reader_u64_t *bcr, uint64_t *num_entries_written, - uint64_t *num_bits_written) { - bit_code_t<uint64_t> *bc = (bit_code_t<uint64_t> *) bcr; - return bit_code_info(bc, num_entries_written, num_bits_written); -} + // process same-number bit + uint32_t is_same_number; + bit_buffer_read(data, gr->position, &is_same_number, 1); + gr->position++; -/* - * High-level public API -*/ + if (is_same_number) { + *number = gr->prev_number; + gr->index++; + return true; + } -// 32-bit API + // proceess same-xor-lzc bit + uint32_t xor_lzc = gr->prev_xor_lzc; -size_t gorilla_encode_u32(uint32_t *dst, size_t dst_len, const uint32_t *src, size_t src_len) { - return gorilla_encode(dst, (uint32_t) dst_len, src, (uint32_t) src_len); -} + uint32_t same_xor_lzc; + bit_buffer_read(data, gr->position, &same_xor_lzc, 1); + gr->position++; -size_t gorilla_decode_u32(uint32_t *dst, size_t dst_len, const uint32_t *src, size_t src_len) { - return gorilla_decode(dst, (uint32_t) dst_len, src, (uint32_t) src_len); -} + if (!same_xor_lzc) { + bit_buffer_read(data, gr->position, &xor_lzc, (bit_size<uint32_t>() == 32) ? 5 : 6); + gr->position += (bit_size<uint32_t>() == 32) ? 5 : 6; + } -// 64-bit API + // process the non-lzc suffix + uint32_t xor_value = 0; + bit_buffer_read(data, gr->position, &xor_value, bit_size<uint32_t>() - xor_lzc); + gr->position += bit_size<uint32_t>() - xor_lzc; -size_t gorilla_encode_u64(uint64_t *dst, size_t dst_len, const uint64_t *src, size_t src_len) { - return gorilla_encode(dst, (uint64_t) dst_len, src, (uint64_t) src_len); -} + *number = (gr->prev_number ^ xor_value); + + gr->index++; + gr->prev_number = *number; + gr->prev_xor_lzc = xor_lzc; + gr->prev_xor = xor_value; -size_t gorilla_decode_u64(uint64_t *dst, size_t dst_len, const uint64_t *src, size_t src_len) { - return gorilla_decode(dst, (uint64_t) dst_len, src, (uint64_t) src_len); + return true; } /* @@ -451,54 +382,69 @@ static std::vector<Word> random_vector(const uint8_t *data, size_t size) { return V; } -template<typename Word> -static void check_equal_buffers(Word *lhs, Word lhs_size, Word *rhs, Word rhs_size) { - assert((lhs_size == rhs_size) && "Buffers have different size."); +class Storage { +public: + gorilla_buffer_t *alloc_buffer(size_t words) { + uint32_t *new_buffer = new uint32_t[words](); + assert(((((uintptr_t) new_buffer) % 8u) == 0) && "Unaligned buffer..."); + Buffers.push_back(new_buffer); + return reinterpret_cast<gorilla_buffer_t *>(new_buffer); + } - for (size_t i = 0; i != lhs_size; i++) { - assert((lhs[i] == rhs[i]) && "Buffers differ"); + void free_buffers() { + for (uint32_t *buffer : Buffers) { + delete[] buffer; + } } -} + +private: + std::vector<uint32_t *> Buffers; +}; extern "C" int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size) { - // 32-bit tests - { - if (Size < 4) - return 0; - - std::vector<uint32_t> RandomData = random_vector<uint32_t>(Data, Size); - std::vector<uint32_t> EncodedData(10 * RandomData.capacity(), 0); - std::vector<uint32_t> DecodedData(10 * RandomData.capacity(), 0); - - size_t num_entries_written = gorilla_encode_u32(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()); - size_t num_entries_read = gorilla_decode_u32(DecodedData.data(), DecodedData.size(), - EncodedData.data(), EncodedData.size()); - - assert(num_entries_written == num_entries_read); - check_equal_buffers(RandomData.data(), (uint32_t) RandomData.size(), - DecodedData.data(), (uint32_t) RandomData.size()); + if (Size < 4) + return 0; + + std::vector<uint32_t> RandomData = random_vector<uint32_t>(Data, Size); + + Storage S; + size_t words_per_buffer = 8; + + /* + * write data + */ + gorilla_buffer_t *first_buffer = S.alloc_buffer(words_per_buffer); + gorilla_writer_t gw = gorilla_writer_init(first_buffer, words_per_buffer); + + for (size_t i = 0; i != RandomData.size(); i++) { + bool ok = gorilla_writer_write(&gw, RandomData[i]); + if (ok) + continue; + + // add new buffer + gorilla_buffer_t *buffer = S.alloc_buffer(words_per_buffer); + gorilla_writer_add_buffer(&gw, buffer, words_per_buffer); + + ok = gorilla_writer_write(&gw, RandomData[i]); + assert(ok && "Could not write data to new buffer!!!"); } - // 64-bit tests - { - if (Size < 8) - return 0; - std::vector<uint64_t> RandomData = random_vector<uint64_t>(Data, Size); - std::vector<uint64_t> EncodedData(10 * RandomData.capacity(), 0); - std::vector<uint64_t> DecodedData(10 * RandomData.capacity(), 0); + /* + * read data + */ + gorilla_reader_t gr = gorilla_writer_get_reader(&gw); - size_t num_entries_written = gorilla_encode_u64(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()); - size_t num_entries_read = gorilla_decode_u64(DecodedData.data(), DecodedData.size(), - EncodedData.data(), EncodedData.size()); + for (size_t i = 0; i != RandomData.size(); i++) { + uint32_t number = 0; + bool ok = gorilla_reader_read(&gr, &number); + assert(ok && "Failed to read number from gorilla buffer"); - assert(num_entries_written == num_entries_read); - check_equal_buffers(RandomData.data(), (uint64_t) RandomData.size(), - DecodedData.data(), (uint64_t) RandomData.size()); + assert((number == RandomData[i]) + && "Read wrong number from gorilla buffer"); } + S.free_buffers(); return 0; } @@ -523,17 +469,20 @@ static void BM_EncodeU32Numbers(benchmark::State& state) { std::vector<uint32_t> EncodedData(10 * RandomData.capacity(), 0); for (auto _ : state) { - benchmark::DoNotOptimize( - gorilla_encode_u32(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()) - ); + gorilla_writer_t gw = gorilla_writer_init( + reinterpret_cast<gorilla_buffer_t *>(EncodedData.data()), + EncodedData.size()); + + for (size_t i = 0; i != RandomData.size(); i++) + benchmark::DoNotOptimize(gorilla_writer_write(&gw, RandomData[i])); + benchmark::ClobberMemory(); } state.SetItemsProcessed(NumItems * state.iterations()); state.SetBytesProcessed(NumItems * state.iterations() * sizeof(uint32_t)); } -BENCHMARK(BM_EncodeU32Numbers); +BENCHMARK(BM_EncodeU32Numbers)->ThreadRange(1, 16)->UseRealTime(); static void BM_DecodeU32Numbers(benchmark::State& state) { std::random_device rd; @@ -547,74 +496,27 @@ static void BM_DecodeU32Numbers(benchmark::State& state) { std::vector<uint32_t> EncodedData(10 * RandomData.capacity(), 0); std::vector<uint32_t> DecodedData(10 * RandomData.capacity(), 0); - gorilla_encode_u32(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()); - - for (auto _ : state) { - benchmark::DoNotOptimize( - gorilla_decode_u32(DecodedData.data(), DecodedData.size(), - EncodedData.data(), EncodedData.size()) - ); - benchmark::ClobberMemory(); - } - - state.SetItemsProcessed(NumItems * state.iterations()); - state.SetBytesProcessed(NumItems * state.iterations() * sizeof(uint32_t)); -} -// Register the function as a benchmark -BENCHMARK(BM_DecodeU32Numbers); - -static void BM_EncodeU64Numbers(benchmark::State& state) { - std::random_device rd; - std::mt19937 mt(rd()); - std::uniform_int_distribution<uint64_t> dist(0x0, 0x0000FFFF); + gorilla_writer_t gw = gorilla_writer_init( + reinterpret_cast<gorilla_buffer_t *>(EncodedData.data()), + EncodedData.size()); - std::vector<uint64_t> RandomData; - for (size_t idx = 0; idx != 1024; idx++) { - RandomData.push_back(dist(mt)); - } - std::vector<uint64_t> EncodedData(10 * RandomData.capacity(), 0); + for (size_t i = 0; i != RandomData.size(); i++) + gorilla_writer_write(&gw, RandomData[i]); for (auto _ : state) { - benchmark::DoNotOptimize( - gorilla_encode_u64(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()) - ); - benchmark::ClobberMemory(); - } + gorilla_reader_t gr = gorilla_reader_init(reinterpret_cast<gorilla_buffer_t *>(EncodedData.data())); - state.SetItemsProcessed(NumItems * state.iterations()); - state.SetBytesProcessed(NumItems * state.iterations() * sizeof(uint64_t)); -} -BENCHMARK(BM_EncodeU64Numbers); - -static void BM_DecodeU64Numbers(benchmark::State& state) { - std::random_device rd; - std::mt19937 mt(rd()); - std::uniform_int_distribution<uint64_t> dist(0x0, 0xFFFFFFFF); - - std::vector<uint64_t> RandomData; - for (size_t idx = 0; idx != 1024; idx++) { - RandomData.push_back(dist(mt)); - } - std::vector<uint64_t> EncodedData(10 * RandomData.capacity(), 0); - std::vector<uint64_t> DecodedData(10 * RandomData.capacity(), 0); - - gorilla_encode_u64(EncodedData.data(), EncodedData.size(), - RandomData.data(), RandomData.size()); + for (size_t i = 0; i != RandomData.size(); i++) { + uint32_t number = 0; + benchmark::DoNotOptimize(gorilla_reader_read(&gr, &number)); + } - for (auto _ : state) { - benchmark::DoNotOptimize( - gorilla_decode_u64(DecodedData.data(), DecodedData.size(), - EncodedData.data(), EncodedData.size()) - ); benchmark::ClobberMemory(); } state.SetItemsProcessed(NumItems * state.iterations()); - state.SetBytesProcessed(NumItems * state.iterations() * sizeof(uint64_t)); + state.SetBytesProcessed(NumItems * state.iterations() * sizeof(uint32_t)); } -// Register the function as a benchmark -BENCHMARK(BM_DecodeU64Numbers); +BENCHMARK(BM_DecodeU32Numbers)->ThreadRange(1, 16)->UseRealTime(); #endif /* ENABLE_BENCHMARK */ diff --git a/libnetdata/gorilla/gorilla.h b/libnetdata/gorilla/gorilla.h index 12bec42c..d57c07cf 100644 --- a/libnetdata/gorilla/gorilla.h +++ b/libnetdata/gorilla/gorilla.h @@ -11,47 +11,64 @@ extern "C" { #endif -/* - * Low-level public API -*/ +struct gorilla_buffer; -// 32-bit API +typedef struct { + struct gorilla_buffer *next; + uint32_t entries; + uint32_t nbits; +} gorilla_header_t; -typedef struct bit_code_writer_u32 bit_code_writer_u32_t; -typedef struct bit_code_reader_u32 bit_code_reader_u32_t; +typedef struct gorilla_buffer { + gorilla_header_t header; + uint32_t data[]; +} gorilla_buffer_t; -void bit_code_writer_u32_init(bit_code_writer_u32_t *bcw, uint32_t *buffer, uint32_t capacity); -bool bit_code_writer_u32_write(bit_code_writer_u32_t *bcw, const uint32_t number); -bool bit_code_writer_u32_flush(bit_code_writer_u32_t *bcw); +typedef struct { + gorilla_buffer_t *head_buffer; + gorilla_buffer_t *last_buffer; -void bit_code_reader_u32_init(bit_code_reader_u32_t *bcr, uint32_t *buffer, uint32_t capacity); -bool bit_code_reader_u32_read(bit_code_reader_u32_t *bcr, uint32_t *number); -bool bit_code_reader_u32_info(bit_code_reader_u32_t *bcr, uint32_t *num_entries_written, - uint64_t *num_bits_written); + uint32_t prev_number; + uint32_t prev_xor_lzc; -// 64-bit API + // in bits + uint32_t capacity; +} gorilla_writer_t; -typedef struct bit_code_writer_u64 bit_code_writer_u64_t; -typedef struct bit_code_reader_u64 bit_code_reader_u64_t; +typedef struct { + const gorilla_buffer_t *buffer; -void bit_code_writer_u64_init(bit_code_writer_u64_t *bcw, uint64_t *buffer, uint64_t capacity); -bool bit_code_writer_u64_write(bit_code_writer_u64_t *bcw, const uint64_t number); -bool bit_code_writer_u64_flush(bit_code_writer_u64_t *bcw); + // number of values + size_t entries; + size_t index; -void bit_code_reader_u64_init(bit_code_reader_u64_t *bcr, uint64_t *buffer, uint64_t capacity); -bool bit_code_reader_u64_read(bit_code_reader_u64_t *bcr, uint64_t *number); -bool bit_code_reader_u64_info(bit_code_reader_u64_t *bcr, uint64_t *num_entries_written, - uint64_t *num_bits_written); + // in bits + size_t capacity; // FIXME: this not needed on the reader's side + size_t position; -/* - * High-level public API -*/ + uint32_t prev_number; + uint32_t prev_xor_lzc; + uint32_t prev_xor; +} gorilla_reader_t; -size_t gorilla_encode_u32(uint32_t *dst, size_t dst_len, const uint32_t *src, size_t src_len); -size_t gorilla_decode_u32(uint32_t *dst, size_t dst_len, const uint32_t *src, size_t src_len); +gorilla_writer_t gorilla_writer_init(gorilla_buffer_t *gbuf, size_t n); +void gorilla_writer_add_buffer(gorilla_writer_t *gw, gorilla_buffer_t *gbuf, size_t n); +bool gorilla_writer_write(gorilla_writer_t *gw, uint32_t number); +uint32_t gorilla_writer_entries(const gorilla_writer_t *gw); -size_t gorilla_encode_u64(uint64_t *dst, size_t dst_len, const uint64_t *src, size_t src_len); -size_t gorilla_decode_u64(uint64_t *dst, size_t dst_len, const uint64_t *src, size_t src_len); +gorilla_reader_t gorilla_writer_get_reader(const gorilla_writer_t *gw); + +gorilla_buffer_t *gorilla_writer_drop_head_buffer(gorilla_writer_t *gw); + +uint32_t gorilla_writer_nbytes(const gorilla_writer_t *gw); +bool gorilla_writer_serialize(const gorilla_writer_t *gw, uint8_t *dst, uint32_t dst_size); + +uint32_t gorilla_buffer_patch(gorilla_buffer_t *buf); +gorilla_reader_t gorilla_reader_init(gorilla_buffer_t *buf); +bool gorilla_reader_read(gorilla_reader_t *gr, uint32_t *number); + +#define GORILLA_BUFFER_SLOTS 128 +#define GORILLA_BUFFER_SIZE (GORILLA_BUFFER_SLOTS * sizeof(uint32_t)) #ifdef __cplusplus } diff --git a/libnetdata/health/health.c b/libnetdata/health/health.c index f2dc46e3..2b3b8f7d 100644 --- a/libnetdata/health/health.c +++ b/libnetdata/health/health.c @@ -29,9 +29,13 @@ void health_silencers_add(SILENCER *silencer) { // Add the created instance to the linked list in silencers silencer->next = silencers->silencers; silencers->silencers = silencer; - netdata_log_debug(D_HEALTH, "HEALTH command API: Added silencer %s:%s:%s:%s", silencer->alarms, - silencer->charts, silencer->contexts, silencer->hosts - ); + netdata_log_debug( + D_HEALTH, + "HEALTH command API: Added silencer %s:%s:%s:%s", + silencer->alarms, + silencer->charts, + silencer->contexts, + silencer->hosts); } /** @@ -71,10 +75,6 @@ SILENCER *health_silencers_addparam(SILENCER *silencer, char *key, char *value) (hash == hash_host && !strcasecmp(key, HEALTH_HOST_KEY)) ) { silencer = create_silencer(); - if(!silencer) { - netdata_log_error("Cannot add a new silencer to Netdata"); - return NULL; - } } } @@ -160,10 +160,10 @@ int health_silencers_json_read_callback(JSON_ENTRY *e) * @return It returns 0 on success and -1 otherwise */ int health_initialize_global_silencers() { - silencers = mallocz(sizeof(SILENCERS)); - silencers->all_alarms=0; - silencers->stype=STYPE_NONE; - silencers->silencers=NULL; + silencers = mallocz(sizeof(SILENCERS)); + silencers->all_alarms = 0; + silencers->stype = STYPE_NONE; + silencers->silencers = NULL; return 0; } diff --git a/libnetdata/http/http_defs.h b/libnetdata/http/http_defs.h index 71bd442c..635f703e 100644 --- a/libnetdata/http/http_defs.h +++ b/libnetdata/http/http_defs.h @@ -3,6 +3,13 @@ #ifndef NETDATA_HTTP_DEFS_H #define NETDATA_HTTP_DEFS_H +#define HTTP_1_1 " HTTP/1.1" +#define HTTP_HDR_END "\r\n\r\n" +#define HTTP_ENDL "\r\n" + +// HTTP_CODES 1XX +#define HTTP_RESP_SWITCH_PROTO 101 + // HTTP_CODES 2XX Success #define HTTP_RESP_OK 200 diff --git a/libnetdata/inlined.h b/libnetdata/inlined.h index 9c07d97b..535b791e 100644 --- a/libnetdata/inlined.h +++ b/libnetdata/inlined.h @@ -426,13 +426,24 @@ static inline void sanitize_json_string(char *dst, const char *src, size_t dst_s } static inline bool sanitize_command_argument_string(char *dst, const char *src, size_t dst_size) { + if(dst_size) + *dst = '\0'; + // skip leading dashes - while (src[0] == '-') + while (*src == '-') src++; - // escape single quotes - while (src[0] != '\0') { - if (src[0] == '\'') { + while (*src != '\0') { + if (dst_size < 1) + return false; + + if (iscntrl(*src) || *src == '$') { + // remove control characters and characters that are expanded by bash + *dst++ = '_'; + dst_size--; + } + else if (*src == '\'' || *src == '`') { + // escape single quotes if (dst_size < 4) return false; @@ -440,14 +451,10 @@ static inline bool sanitize_command_argument_string(char *dst, const char *src, dst += 4; dst_size -= 4; - } else { - if (dst_size < 1) - return false; - - dst[0] = src[0]; - - dst += 1; - dst_size -= 1; + } + else { + *dst++ = *src; + dst_size--; } src++; @@ -456,6 +463,7 @@ static inline bool sanitize_command_argument_string(char *dst, const char *src, // make sure we have space to terminate the string if (dst_size == 0) return false; + *dst = '\0'; return true; @@ -531,10 +539,6 @@ static inline int read_single_base64_or_hex_number_file(const char *filename, un } } -static inline int uuid_memcmp(const uuid_t *uu1, const uuid_t *uu2) { - return memcmp(uu1, uu2, sizeof(uuid_t)); -} - static inline char *strsep_skip_consecutive_separators(char **ptr, char *s) { char *p = (char *)""; while (p && !p[0] && *ptr) p = strsep(ptr, s); diff --git a/libnetdata/libnetdata.c b/libnetdata/libnetdata.c index 159e8995..37319a88 100644 --- a/libnetdata/libnetdata.c +++ b/libnetdata/libnetdata.c @@ -42,7 +42,7 @@ void aral_judy_init(void) { for(size_t Words = 0; Words <= MAX_JUDY_SIZE_TO_ARAL; Words++) if(judy_sizes_config[Words]) { char buf[30+1]; - snprintfz(buf, 30, "judy-%zu", Words * sizeof(Word_t)); + snprintfz(buf, sizeof(buf) - 1, "judy-%zu", Words * sizeof(Word_t)); judy_sizes_aral[Words] = aral_create( buf, Words * sizeof(Word_t), @@ -1269,17 +1269,19 @@ char *fgets_trim_len(char *buf, size_t buf_size, FILE *fp, size_t *len) { return s; } +// vsnprintfz() returns the number of bytes actually written - after possible truncation int vsnprintfz(char *dst, size_t n, const char *fmt, va_list args) { if(unlikely(!n)) return 0; int size = vsnprintf(dst, n, fmt, args); dst[n - 1] = '\0'; - if (unlikely((size_t) size > n)) size = (int)n; + if (unlikely((size_t) size >= n)) size = (int)(n - 1); return size; } +// snprintfz() returns the number of bytes actually written - after possible truncation int snprintfz(char *dst, size_t n, const char *fmt, ...) { va_list args; @@ -1375,7 +1377,7 @@ static int is_virtual_filesystem(const char *path, char **reason) { return 0; } -int verify_netdata_host_prefix() { +int verify_netdata_host_prefix(bool log_msg) { if(!netdata_configured_host_prefix) netdata_configured_host_prefix = ""; @@ -1408,13 +1410,16 @@ int verify_netdata_host_prefix() { if(is_virtual_filesystem(path, &reason) == -1) goto failed; - if(netdata_configured_host_prefix && *netdata_configured_host_prefix) - netdata_log_info("Using host prefix directory '%s'", netdata_configured_host_prefix); + if (netdata_configured_host_prefix && *netdata_configured_host_prefix) { + if (log_msg) + netdata_log_info("Using host prefix directory '%s'", netdata_configured_host_prefix); + } return 0; failed: - netdata_log_error("Ignoring host prefix '%s': path '%s' %s", netdata_configured_host_prefix, path, reason); + if (log_msg) + netdata_log_error("Ignoring host prefix '%s': path '%s' %s", netdata_configured_host_prefix, path, reason); netdata_configured_host_prefix = ""; return -1; } @@ -1694,51 +1699,28 @@ char *find_and_replace(const char *src, const char *find, const char *replace, c return value; } -inline int pluginsd_isspace(char c) { - switch(c) { - case ' ': - case '\t': - case '\r': - case '\n': - case '=': - return 1; - default: - return 0; - } -} +BUFFER *run_command_and_get_output_to_buffer(const char *command, int max_line_length) { + BUFFER *wb = buffer_create(0, NULL); -inline int config_isspace(char c) { - switch (c) { - case ' ': - case '\t': - case '\r': - case '\n': - case ',': - return 1; + pid_t pid; + FILE *fp = netdata_popen(command, &pid, NULL); - default: - return 0; + if(fp) { + char buffer[max_line_length + 1]; + while (fgets(buffer, max_line_length, fp)) { + buffer[max_line_length] = '\0'; + buffer_strcat(wb, buffer); + } } -} - -inline int group_by_label_isspace(char c) { - if(c == ',' || c == '|') - return 1; - - return 0; -} - -bool isspace_map_pluginsd[256] = {}; -bool isspace_map_config[256] = {}; -bool isspace_map_group_by_label[256] = {}; - -__attribute__((constructor)) void initialize_is_space_arrays(void) { - for(int c = 0; c < 256 ; c++) { - isspace_map_pluginsd[c] = pluginsd_isspace((char) c); - isspace_map_config[c] = config_isspace((char) c); - isspace_map_group_by_label[c] = group_by_label_isspace((char) c); + else { + buffer_free(wb); + netdata_log_error("Failed to execute command '%s'.", command); + return NULL; } + + netdata_pclose(NULL, fp, pid); + return wb; } bool run_command_and_copy_output_to_stdout(const char *command, int max_line_length) { diff --git a/libnetdata/libnetdata.h b/libnetdata/libnetdata.h index c337b3b5..d2ecfa15 100644 --- a/libnetdata/libnetdata.h +++ b/libnetdata/libnetdata.h @@ -11,8 +11,8 @@ extern "C" { #include <config.h> #endif -#ifdef ENABLE_LZ4 -#define ENABLE_RRDPUSH_COMPRESSION 1 +#if defined(ENABLE_BROTLIENC) && defined(ENABLE_BROTLIDEC) +#define ENABLE_BROTLI 1 #endif #ifdef ENABLE_OPENSSL @@ -201,6 +201,8 @@ extern "C" { // ---------------------------------------------------------------------------- // netdata common definitions +#define _cleanup_(x) __attribute__((__cleanup__(x))) + #ifdef __GNUC__ #define GCC_VERSION (__GNUC__ * 10000 + __GNUC_MINOR__ * 100 + __GNUC_PATCHLEVEL__) #endif // __GNUC__ @@ -559,7 +561,7 @@ extern int enable_ksm; char *fgets_trim_len(char *buf, size_t buf_size, FILE *fp, size_t *len); -int verify_netdata_host_prefix(); +int verify_netdata_host_prefix(bool log_msg); int recursively_delete_dir(const char *path, const char *reason); @@ -681,108 +683,13 @@ static inline BITMAPX *bitmapX_create(uint32_t bits) { #define bitmap1024_get_bit(ptr, idx) bitmapX_get_bit((BITMAPX *)ptr, idx) #define bitmap1024_set_bit(ptr, idx, value) bitmapX_set_bit((BITMAPX *)ptr, idx, value) - -#define COMPRESSION_MAX_MSG_SIZE 0x4000 -#define PLUGINSD_LINE_MAX (COMPRESSION_MAX_MSG_SIZE - 1024) -int pluginsd_isspace(char c); -int config_isspace(char c); -int group_by_label_isspace(char c); - -extern bool isspace_map_pluginsd[256]; -extern bool isspace_map_config[256]; -extern bool isspace_map_group_by_label[256]; - -static inline size_t quoted_strings_splitter(char *str, char **words, size_t max_words, bool *isspace_map) { - char *s = str, quote = 0; - size_t i = 0; - - // skip all white space - while (unlikely(isspace_map[(uint8_t)*s])) - s++; - - if(unlikely(!*s)) { - words[i] = NULL; - return 0; - } - - // check for quote - if (unlikely(*s == '\'' || *s == '"')) { - quote = *s; // remember the quote - s++; // skip the quote - } - - // store the first word - words[i++] = s; - - // while we have something - while (likely(*s)) { - // if it is an escape - if (unlikely(*s == '\\' && s[1])) { - s += 2; - continue; - } - - // if it is a quote - else if (unlikely(*s == quote)) { - quote = 0; - *s = ' '; - continue; - } - - // if it is a space - else if (unlikely(quote == 0 && isspace_map[(uint8_t)*s])) { - // terminate the word - *s++ = '\0'; - - // skip all white space - while (likely(isspace_map[(uint8_t)*s])) - s++; - - // check for a quote - if (unlikely(*s == '\'' || *s == '"')) { - quote = *s; // remember the quote - s++; // skip the quote - } - - // if we reached the end, stop - if (unlikely(!*s)) - break; - - // store the next word - if (likely(i < max_words)) - words[i++] = s; - else - break; - } - - // anything else - else - s++; - } - - if (likely(i < max_words)) - words[i] = NULL; - - return i; -} - -#define quoted_strings_splitter_query_group_by_label(str, words, max_words) \ - quoted_strings_splitter(str, words, max_words, isspace_map_group_by_label) - -#define quoted_strings_splitter_config(str, words, max_words) \ - quoted_strings_splitter(str, words, max_words, isspace_map_config) - -#define quoted_strings_splitter_pluginsd(str, words, max_words) \ - quoted_strings_splitter(str, words, max_words, isspace_map_pluginsd) - -static inline char *get_word(char **words, size_t num_words, size_t index) { - if (unlikely(index >= num_words)) - return NULL; - - return words[index]; -} +#define COMPRESSION_MAX_CHUNK 0x4000 +#define COMPRESSION_MAX_OVERHEAD 128 +#define COMPRESSION_MAX_MSG_SIZE (COMPRESSION_MAX_CHUNK - COMPRESSION_MAX_OVERHEAD - 1) +#define PLUGINSD_LINE_MAX (COMPRESSION_MAX_MSG_SIZE - 768) bool run_command_and_copy_output_to_stdout(const char *command, int max_line_length); +struct web_buffer *run_command_and_get_output_to_buffer(const char *command, int max_line_length); typedef enum { OPEN_FD_ACTION_CLOSE, @@ -802,6 +709,8 @@ extern char *netdata_configured_host_prefix; #define XXH_INLINE_ALL #include "xxhash.h" +#include "uuid/uuid.h" + #include "libjudy/src/Judy.h" #include "july/july.h" #include "os.h" @@ -811,7 +720,11 @@ extern char *netdata_configured_host_prefix; #include "circular_buffer/circular_buffer.h" #include "avl/avl.h" #include "inlined.h" +#include "line_splitter/line_splitter.h" #include "clocks/clocks.h" +#include "datetime/iso8601.h" +#include "datetime/rfc3339.h" +#include "datetime/rfc7231.h" #include "completion/completion.h" #include "popen/popen.h" #include "simple_pattern/simple_pattern.h" @@ -820,7 +733,9 @@ extern char *netdata_configured_host_prefix; #endif #include "socket/socket.h" #include "config/appconfig.h" +#include "log/journal.h" #include "log/log.h" +#include "buffered_reader/buffered_reader.h" #include "procfile/procfile.h" #include "string/string.h" #include "dictionary/dictionary.h" diff --git a/libnetdata/line_splitter/Makefile.am b/libnetdata/line_splitter/Makefile.am new file mode 100644 index 00000000..161784b8 --- /dev/null +++ b/libnetdata/line_splitter/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/libnetdata/line_splitter/README.md b/libnetdata/line_splitter/README.md new file mode 100644 index 00000000..f811bb4b --- /dev/null +++ b/libnetdata/line_splitter/README.md @@ -0,0 +1,14 @@ +<!-- +title: "Log" +custom_edit_url: https://github.com/netdata/netdata/edit/master/libnetdata/log/README.md +sidebar_label: "Log" +learn_status: "Published" +learn_topic_type: "Tasks" +learn_rel_path: "Developers/libnetdata" +--> + +# Log + +The netdata log library supports debug, info, error and fatal error logging. +By default we have an access log, an error log and a collectors log. + diff --git a/libnetdata/line_splitter/line_splitter.c b/libnetdata/line_splitter/line_splitter.c new file mode 100644 index 00000000..a459d334 --- /dev/null +++ b/libnetdata/line_splitter/line_splitter.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + + +bool line_splitter_reconstruct_line(BUFFER *wb, void *ptr) { + struct line_splitter *spl = ptr; + if(!spl) return false; + + size_t added = 0; + for(size_t i = 0; i < spl->num_words ;i++) { + if(i) buffer_fast_strcat(wb, " ", 1); + + buffer_fast_strcat(wb, "'", 1); + const char *s = get_word(spl->words, spl->num_words, i); + buffer_strcat(wb, s?s:""); + buffer_fast_strcat(wb, "'", 1); + added++; + } + + return added > 0; +} + +inline int pluginsd_isspace(char c) { + switch(c) { + case ' ': + case '\t': + case '\r': + case '\n': + case '=': + return 1; + + default: + return 0; + } +} + +inline int config_isspace(char c) { + switch (c) { + case ' ': + case '\t': + case '\r': + case '\n': + case ',': + return 1; + + default: + return 0; + } +} + +inline int group_by_label_isspace(char c) { + if(c == ',' || c == '|') + return 1; + + return 0; +} + +bool isspace_map_pluginsd[256] = {}; +bool isspace_map_config[256] = {}; +bool isspace_map_group_by_label[256] = {}; + +__attribute__((constructor)) void initialize_is_space_arrays(void) { + for(int c = 0; c < 256 ; c++) { + isspace_map_pluginsd[c] = pluginsd_isspace((char) c); + isspace_map_config[c] = config_isspace((char) c); + isspace_map_group_by_label[c] = group_by_label_isspace((char) c); + } +} diff --git a/libnetdata/line_splitter/line_splitter.h b/libnetdata/line_splitter/line_splitter.h new file mode 100644 index 00000000..b5a59ad3 --- /dev/null +++ b/libnetdata/line_splitter/line_splitter.h @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_LINE_SPLITTER_H +#define NETDATA_LINE_SPLITTER_H + +#define PLUGINSD_MAX_WORDS 30 + +struct line_splitter { + size_t count; // counts number of lines + char *words[PLUGINSD_MAX_WORDS]; // an array of pointers for the words in this line + size_t num_words; // the number of pointers used in this line +}; + +bool line_splitter_reconstruct_line(BUFFER *wb, void *ptr); + +static inline void line_splitter_reset(struct line_splitter *line) { + line->num_words = 0; +} + +int pluginsd_isspace(char c); +int config_isspace(char c); +int group_by_label_isspace(char c); + +extern bool isspace_map_pluginsd[256]; +extern bool isspace_map_config[256]; +extern bool isspace_map_group_by_label[256]; + +static inline size_t quoted_strings_splitter(char *str, char **words, size_t max_words, bool *isspace_map) { + char *s = str, quote = 0; + size_t i = 0; + + // skip all white space + while (unlikely(isspace_map[(uint8_t)*s])) + s++; + + if(unlikely(!*s)) { + words[i] = NULL; + return 0; + } + + // check for quote + if (unlikely(*s == '\'' || *s == '"')) { + quote = *s; // remember the quote + s++; // skip the quote + } + + // store the first word + words[i++] = s; + + // while we have something + while (likely(*s)) { + // if it is an escape + if (unlikely(*s == '\\' && s[1])) { + s += 2; + continue; + } + + // if it is a quote + else if (unlikely(*s == quote)) { + quote = 0; + *s = ' '; + continue; + } + + // if it is a space + else if (unlikely(quote == 0 && isspace_map[(uint8_t)*s])) { + // terminate the word + *s++ = '\0'; + + // skip all white space + while (likely(isspace_map[(uint8_t)*s])) + s++; + + // check for a quote + if (unlikely(*s == '\'' || *s == '"')) { + quote = *s; // remember the quote + s++; // skip the quote + } + + // if we reached the end, stop + if (unlikely(!*s)) + break; + + // store the next word + if (likely(i < max_words)) + words[i++] = s; + else + break; + } + + // anything else + else + s++; + } + + if (likely(i < max_words)) + words[i] = NULL; + + return i; +} + +#define quoted_strings_splitter_query_group_by_label(str, words, max_words) \ + quoted_strings_splitter(str, words, max_words, isspace_map_group_by_label) + +#define quoted_strings_splitter_config(str, words, max_words) \ + quoted_strings_splitter(str, words, max_words, isspace_map_config) + +#define quoted_strings_splitter_pluginsd(str, words, max_words) \ + quoted_strings_splitter(str, words, max_words, isspace_map_pluginsd) + +static inline char *get_word(char **words, size_t num_words, size_t index) { + if (unlikely(index >= num_words)) + return NULL; + + return words[index]; +} + +#endif //NETDATA_LINE_SPLITTER_H diff --git a/libnetdata/log/Makefile.am b/libnetdata/log/Makefile.am index 161784b8..a02b8ebd 100644 --- a/libnetdata/log/Makefile.am +++ b/libnetdata/log/Makefile.am @@ -5,4 +5,5 @@ MAINTAINERCLEANFILES = $(srcdir)/Makefile.in dist_noinst_DATA = \ README.md \ + systemd-cat-native.md \ $(NULL) diff --git a/libnetdata/log/README.md b/libnetdata/log/README.md index f811bb4b..d9ed6437 100644 --- a/libnetdata/log/README.md +++ b/libnetdata/log/README.md @@ -7,8 +7,198 @@ learn_topic_type: "Tasks" learn_rel_path: "Developers/libnetdata" --> -# Log +# Netdata Logging -The netdata log library supports debug, info, error and fatal error logging. -By default we have an access log, an error log and a collectors log. +This document describes how Netdata generates its own logs, not how Netdata manages and queries logs databases. + +## Log sources + +Netdata supports the following log sources: + +1. **daemon**, logs generated by Netdata daemon. +2. **collector**, logs generated by Netdata collectors, including internal and external ones. +3. **access**, API requests received by Netdata +4. **health**, all alert transitions and notifications + +## Log outputs + +For each log source, Netdata supports the following output methods: + +- **off**, to disable this log source +- **journal**, to send the logs to systemd-journal. +- **syslog**, to send the logs to syslog. +- **system**, to send the output to `stderr` or `stdout` depending on the log source. +- **stdout**, to write the logs to Netdata's `stdout`. +- **stderr**, to write the logs to Netdata's `stderr`. +- **filename**, to send the logs to a file. + +For `daemon` and `collector` the default is `journal` when systemd-journal is available. +To decide if systemd-journal is available, Netdata checks: + +1. `stderr` is connected to systemd-journald +2. `/run/systemd/journal/socket` exists +3. `/host/run/systemd/journal/socket` exists (`/host` is configurable in containers) + +If any of the above is detected, Netdata will select `journal` for `daemon` and `collector` sources. + +All other sources default to a file. + +## Log formats + +| Format | Description | +|---------|--------------------------------------------------------------------------------------------------------| +| journal | journald-specific log format. Automatically selected when logging to systemd-journal. | +| logfmt | logs data as a series of key/value pairs. The default when logging to any output other than `journal`. | +| json | logs data in JSON format. | + +## Log levels + +Each time Netdata logs, it assigns a priority to the log. It can be one of this (in order of importance): + +| Level | Description | +|-----------|----------------------------------------------------------------------------------------| +| emergency | a fatal condition, Netdata will most likely exit immediately after. | +| alert | a very important issue that may affect how Netdata operates. | +| critical | a very important issue the user should know which, Netdata thinks it can survive. | +| error | an error condition indicating that Netdata is trying to do something, but it fails. | +| warning | something unexpected has happened that may or may not affect the operation of Netdata. | +| notice | something that does not affect the operation of Netdata, but the user should notice. | +| info | the default log level about information the user should know. | +| debug | these are more verbose logs that can be ignored. | + +## Logs Configuration + +In `netdata.conf`, there are the following settings: + +``` +[logs] + # logs to trigger flood protection = 1000 + # logs flood protection period = 60 + # facility = daemon + # level = info + # daemon = journal + # collector = journal + # access = /var/log/netdata/access.log + # health = /var/log/netdata/health.log +``` + +- `logs to trigger flood protection` and `logs flood protection period` enable logs flood protection for `daemon` and `collector` sources. It can also be configured per log source. +- `facility` is used only when Netdata logs to syslog. +- `level` defines the minimum [log level](#log-levels) of logs that will be logged. This setting is applied only to `daemon` and `collector` sources. It can also be configured per source. + +### Configuring log sources + +Each for the sources (`daemon`, `collector`, `access`, `health`), accepts the following: + +``` +source = {FORMAT},level={LEVEL},protection={LOG}/{PERIOD}@{OUTPUT} +``` + +Where: + +- `{FORMAT}`, is one of the [log formats](#log-formats), +- `{LEVEL}`, is the minimum [log level](#log-levels) to be logged, +- `{LOGS}` is the number of `logs to trigger flood protection` configured per output, +- `{PERIOD}` is the equivalent of `logs flood protection period` configured per output, +- `{OUTPUT}` is one of the `[log outputs](#log-outputs), + +All parameters can be omitted, except `{OUTPUT}`. If `{OUTPUT}` is the only given parameter, `@` can be omitted. + +### Logs rotation + +Netdata comes with `logrotate` configuration to rotate its log files periodically. + +The default is usually found in `/etc/logrotate.d/netdata`. + +Sending a `SIGHUP` to Netdata, will instruct it to re-open all its log files. + +## Log Fields + +Netdata exposes the following fields to its logs: + +| journal | logfmt | json | Description | +|:--------------------------------------:|:------------------------------:|:------------------------------:|:---------------------------------------------------------------------------------------------------------:| +| `_SOURCE_REALTIME_TIMESTAMP` | `time` | `time` | the timestamp of the event | +| `SYSLOG_IDENTIFIER` | `comm` | `comm` | the program logging the event | +| `ND_LOG_SOURCE` | `source` | `source` | one of the [log sources](#log-sources) | +| `PRIORITY`<br/>numeric | `level`<br/>text | `level`<br/>numeric | one of the [log levels](#log-levels) | +| `ERRNO` | `errno` | `errno` | the numeric value of `errno` | +| `INVOCATION_ID` | - | - | a unique UUID of the Netdata session, reset on every Netdata restart, inherited by systemd when available | +| `CODE_LINE` | - | - | the line number of of the source code logging this event | +| `CODE_FILE` | - | - | the filename of the source code logging this event | +| `CODE_FUNCTION` | - | - | the function name of the source code logging this event | +| `TID` | `tid` | `tid` | the thread id of the thread logging this event | +| `THREAD_TAG` | `thread` | `thread` | the name of the thread logging this event | +| `MESSAGE_ID` | `msg_id` | `msg_id` | see [message IDs](#message-ids) | +| `ND_MODULE` | `module` | `module` | the Netdata module logging this event | +| `ND_NIDL_NODE` | `node` | `node` | the hostname of the node the event is related to | +| `ND_NIDL_INSTANCE` | `instance` | `instance` | the instance of the node the event is related to | +| `ND_NIDL_CONTEXT` | `context` | `context` | the context the event is related to (this is usually the chart name, as shown on netdata dashboards | +| `ND_NIDL_DIMENSION` | `dimension` | `dimension` | the dimension the event is related to | +| `ND_SRC_TRANSPORT` | `src_transport` | `src_transport` | when the event happened during a request, this is the request transport | +| `ND_SRC_IP` | `src_ip` | `src_ip` | when the event happened during an inbound request, this is the IP the request came from | +| `ND_SRC_PORT` | `src_port` | `src_port` | when the event happened during an inbound request, this is the port the request came from | +| `ND_SRC_CAPABILITIES` | `src_capabilities` | `src_capabilities` | when the request came from a child, this is the communication capabilities of the child | +| `ND_DST_TRANSPORT` | `dst_transport` | `dst_transport` | when the event happened during an outbound request, this is the outbound request transport | +| `ND_DST_IP` | `dst_ip` | `dst_ip` | when the event happened during an outbound request, this is the IP the request destination | +| `ND_DST_PORT` | `dst_port` | `dst_port` | when the event happened during an outbound request, this is the port the request destination | +| `ND_DST_CAPABILITIES` | `dst_capabilities` | `dst_capabilities` | when the request goes to a parent, this is the communication capabilities of the parent | +| `ND_REQUEST_METHOD` | `req_method` | `req_method` | when the event happened during an inbound request, this is the method the request was received | +| `ND_RESPONSE_CODE` | `code` | `code` | when responding to a request, this this the response code | +| `ND_CONNECTION_ID` | `conn` | `conn` | when there is a connection id for an inbound connection, this is the connection id | +| `ND_TRANSACTION_ID` | `transaction` | `transaction` | the transaction id (UUID) of all API requests | +| `ND_RESPONSE_SENT_BYTES` | `sent_bytes` | `sent_bytes` | the bytes we sent to API responses | +| `ND_RESPONSE_SIZE_BYTES` | `size_bytes` | `size_bytes` | the uncompressed bytes of the API responses | +| `ND_RESPONSE_PREP_TIME_USEC` | `prep_ut` | `prep_ut` | the time needed to prepare a response | +| `ND_RESPONSE_SENT_TIME_USEC` | `sent_ut` | `sent_ut` | the time needed to send a response | +| `ND_RESPONSE_TOTAL_TIME_USEC` | `total_ut` | `total_ut` | the total time needed to complete a response | +| `ND_ALERT_ID` | `alert_id` | `alert_id` | the alert id this event is related to | +| `ND_ALERT_EVENT_ID` | `alert_event_id` | `alert_event_id` | a sequential number of the alert transition (per host) | +| `ND_ALERT_UNIQUE_ID` | `alert_unique_id` | `alert_unique_id` | a sequential number of the alert transition (per alert) | +| `ND_ALERT_TRANSITION_ID` | `alert_transition_id` | `alert_transition_id` | the unique UUID of this alert transition | +| `ND_ALERT_CONFIG` | `alert_config` | `alert_config` | the alert configuration hash (UUID) | +| `ND_ALERT_NAME` | `alert` | `alert` | the alert name | +| `ND_ALERT_CLASS` | `alert_class` | `alert_class` | the alert classification | +| `ND_ALERT_COMPONENT` | `alert_component` | `alert_component` | the alert component | +| `ND_ALERT_TYPE` | `alert_type` | `alert_type` | the alert type | +| `ND_ALERT_EXEC` | `alert_exec` | `alert_exec` | the alert notification program | +| `ND_ALERT_RECIPIENT` | `alert_recipient` | `alert_recipient` | the alert recipient(s) | +| `ND_ALERT_VALUE` | `alert_value` | `alert_value` | the current alert value | +| `ND_ALERT_VALUE_OLD` | `alert_value_old` | `alert_value_old` | the previous alert value | +| `ND_ALERT_STATUS` | `alert_status` | `alert_status` | the current alert status | +| `ND_ALERT_STATUS_OLD` | `alert_value_old` | `alert_value_old` | the previous alert value | +| `ND_ALERT_UNITS` | `alert_units` | `alert_units` | the units of the alert | +| `ND_ALERT_SUMMARY` | `alert_summary` | `alert_summary` | the summary text of the alert | +| `ND_ALERT_INFO` | `alert_info` | `alert_info` | the info text of the alert | +| `ND_ALERT_DURATION` | `alert_duration` | `alert_duration` | the duration the alert was in its previous state | +| `ND_ALERT_NOTIFICATION_TIMESTAMP_USEC` | `alert_notification_timestamp` | `alert_notification_timestamp` | the timestamp the notification delivery is scheduled | +| `ND_REQUEST` | `request` | `request` | the full request during which the event happened | +| `MESSAGE` | `msg` | `msg` | the event message | + + +### Message IDs + +Netdata assigns specific message IDs to certain events: + +- `ed4cdb8f1beb4ad3b57cb3cae2d162fa` when a Netdata child connects to this Netdata +- `6e2e3839067648968b646045dbf28d66` when this Netdata connects to a Netdata parent +- `9ce0cb58ab8b44df82c4bf1ad9ee22de` when alerts change state +- `6db0018e83e34320ae2a659d78019fb7` when notifications are sent + +You can view these events using the Netdata systemd-journal.plugin at the `MESSAGE_ID` filter, +or using `journalctl` like this: + +```bash +# query children connection +journalctl MESSAGE_ID=ed4cdb8f1beb4ad3b57cb3cae2d162fa + +# query parent connection +journalctl MESSAGE_ID=6e2e3839067648968b646045dbf28d66 + +# query alert transitions +journalctl MESSAGE_ID=9ce0cb58ab8b44df82c4bf1ad9ee22de + +# query alert notifications +journalctl MESSAGE_ID=6db0018e83e34320ae2a659d78019fb7 +``` diff --git a/libnetdata/log/journal.c b/libnetdata/log/journal.c new file mode 100644 index 00000000..21978cf5 --- /dev/null +++ b/libnetdata/log/journal.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "journal.h" + +bool is_path_unix_socket(const char *path) { + if(!path || !*path) + return false; + + struct stat statbuf; + + // Check if the path is valid + if (!path || !*path) + return false; + + // Use stat to check if the file exists and is a socket + if (stat(path, &statbuf) == -1) + // The file does not exist or cannot be accessed + return false; + + // Check if the file is a socket + if (S_ISSOCK(statbuf.st_mode)) + return true; + + return false; +} + +bool is_stderr_connected_to_journal(void) { + const char *journal_stream = getenv("JOURNAL_STREAM"); + if (!journal_stream) + return false; // JOURNAL_STREAM is not set + + struct stat stderr_stat; + if (fstat(STDERR_FILENO, &stderr_stat) < 0) + return false; // Error in getting stderr info + + // Parse device and inode from JOURNAL_STREAM + char *endptr; + long journal_dev = strtol(journal_stream, &endptr, 10); + if (*endptr != ':') + return false; // Format error in JOURNAL_STREAM + + long journal_ino = strtol(endptr + 1, NULL, 10); + + return (stderr_stat.st_dev == (dev_t)journal_dev) && (stderr_stat.st_ino == (ino_t)journal_ino); +} + +int journal_direct_fd(const char *path) { + if(!path || !*path) + path = JOURNAL_DIRECT_SOCKET; + + if(!is_path_unix_socket(path)) + return -1; + + int fd = socket(AF_UNIX, SOCK_DGRAM, 0); + if (fd < 0) return -1; + + struct sockaddr_un addr; + memset(&addr, 0, sizeof(struct sockaddr_un)); + addr.sun_family = AF_UNIX; + strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1); + + // Connect the socket (optional, but can simplify send operations) + if (connect(fd, (struct sockaddr *)&addr, sizeof(addr)) < 0) { + close(fd); + return -1; + } + + return fd; +} + +static inline bool journal_send_with_memfd(int fd, const char *msg, size_t msg_len) { +#if defined(__NR_memfd_create) && defined(MFD_ALLOW_SEALING) && defined(F_ADD_SEALS) && defined(F_SEAL_SHRINK) && defined(F_SEAL_GROW) && defined(F_SEAL_WRITE) + // Create a memory file descriptor + int memfd = (int)syscall(__NR_memfd_create, "journald", MFD_ALLOW_SEALING); + if (memfd < 0) return false; + + // Write data to the memfd + if (write(memfd, msg, msg_len) != (ssize_t)msg_len) { + close(memfd); + return false; + } + + // Seal the memfd to make it immutable + if (fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_WRITE) < 0) { + close(memfd); + return false; + } + + struct iovec iov = {0}; + struct msghdr msghdr = {0}; + struct cmsghdr *cmsghdr; + char cmsgbuf[CMSG_SPACE(sizeof(int))]; + + msghdr.msg_iov = &iov; + msghdr.msg_iovlen = 1; + msghdr.msg_control = cmsgbuf; + msghdr.msg_controllen = sizeof(cmsgbuf); + + cmsghdr = CMSG_FIRSTHDR(&msghdr); + cmsghdr->cmsg_level = SOL_SOCKET; + cmsghdr->cmsg_type = SCM_RIGHTS; + cmsghdr->cmsg_len = CMSG_LEN(sizeof(int)); + memcpy(CMSG_DATA(cmsghdr), &memfd, sizeof(int)); + + ssize_t r = sendmsg(fd, &msghdr, 0); + + close(memfd); + return r >= 0; +#else + return false; +#endif +} + +bool journal_direct_send(int fd, const char *msg, size_t msg_len) { + // Send the datagram + if (send(fd, msg, msg_len, 0) < 0) { + if(errno != EMSGSIZE) + return false; + + // datagram is too large, fallback to memfd + if(!journal_send_with_memfd(fd, msg, msg_len)) + return false; + } + + return true; +} + +void journal_construct_path(char *dst, size_t dst_len, const char *host_prefix, const char *namespace_str) { + if(!host_prefix) + host_prefix = ""; + + if(namespace_str) + snprintfz(dst, dst_len, "%s/run/systemd/journal.%s/socket", + host_prefix, namespace_str); + else + snprintfz(dst, dst_len, "%s" JOURNAL_DIRECT_SOCKET, + host_prefix); +} diff --git a/libnetdata/log/journal.h b/libnetdata/log/journal.h new file mode 100644 index 00000000..df8ece18 --- /dev/null +++ b/libnetdata/log/journal.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_LOG_JOURNAL_H +#define NETDATA_LOG_JOURNAL_H + +#define JOURNAL_DIRECT_SOCKET "/run/systemd/journal/socket" + +void journal_construct_path(char *dst, size_t dst_len, const char *host_prefix, const char *namespace_str); + +int journal_direct_fd(const char *path); +bool journal_direct_send(int fd, const char *msg, size_t msg_len); + +bool is_path_unix_socket(const char *path); +bool is_stderr_connected_to_journal(void); + +#endif //NETDATA_LOG_JOURNAL_H diff --git a/libnetdata/log/log.c b/libnetdata/log/log.c index 02bb776c..c805716c 100644 --- a/libnetdata/log/log.c +++ b/libnetdata/log/log.c @@ -1,1038 +1,2305 @@ // SPDX-License-Identifier: GPL-3.0-or-later -#include <daemon/main.h> +#define SD_JOURNAL_SUPPRESS_LOCATION + #include "../libnetdata.h" +#include <daemon/main.h> + +#ifdef __FreeBSD__ +#include <sys/endian.h> +#endif + +#ifdef __APPLE__ +#include <machine/endian.h> +#endif #ifdef HAVE_BACKTRACE #include <execinfo.h> #endif -int web_server_is_multithreaded = 1; +#ifdef HAVE_SYSTEMD +#include <systemd/sd-journal.h> +#endif + +#include <syslog.h> const char *program_name = ""; + uint64_t debug_flags = 0; -int access_log_syslog = 0; -int error_log_syslog = 0; -int collector_log_syslog = 0; -int output_log_syslog = 0; // debug log -int health_log_syslog = 0; +#ifdef ENABLE_ACLK +int aclklog_enabled = 0; +#endif + +// ---------------------------------------------------------------------------- + +struct nd_log_source; +static bool nd_log_limit_reached(struct nd_log_source *source); -int stdaccess_fd = -1; -FILE *stdaccess = NULL; +// ---------------------------------------------------------------------------- +// logging method + +typedef enum __attribute__((__packed__)) { + NDLM_DISABLED = 0, + NDLM_DEVNULL, + NDLM_DEFAULT, + NDLM_JOURNAL, + NDLM_SYSLOG, + NDLM_STDOUT, + NDLM_STDERR, + NDLM_FILE, +} ND_LOG_METHOD; + +static struct { + ND_LOG_METHOD method; + const char *name; +} nd_log_methods[] = { + { .method = NDLM_DISABLED, .name = "none" }, + { .method = NDLM_DEVNULL, .name = "/dev/null" }, + { .method = NDLM_DEFAULT, .name = "default" }, + { .method = NDLM_JOURNAL, .name = "journal" }, + { .method = NDLM_SYSLOG, .name = "syslog" }, + { .method = NDLM_STDOUT, .name = "stdout" }, + { .method = NDLM_STDERR, .name = "stderr" }, + { .method = NDLM_FILE, .name = "file" }, +}; + +static ND_LOG_METHOD nd_log_method2id(const char *method) { + if(!method || !*method) + return NDLM_DEFAULT; + + size_t entries = sizeof(nd_log_methods) / sizeof(nd_log_methods[0]); + for(size_t i = 0; i < entries ;i++) { + if(strcmp(nd_log_methods[i].name, method) == 0) + return nd_log_methods[i].method; + } -int stdhealth_fd = -1; -FILE *stdhealth = NULL; + return NDLM_FILE; +} -int stdcollector_fd = -1; -FILE *stderror = NULL; +static const char *nd_log_id2method(ND_LOG_METHOD method) { + size_t entries = sizeof(nd_log_methods) / sizeof(nd_log_methods[0]); + for(size_t i = 0; i < entries ;i++) { + if(method == nd_log_methods[i].method) + return nd_log_methods[i].name; + } -const char *stdaccess_filename = NULL; -const char *stderr_filename = NULL; -const char *stdout_filename = NULL; -const char *facility_log = NULL; -const char *stdhealth_filename = NULL; -const char *stdcollector_filename = NULL; + return "unknown"; +} -netdata_log_level_t global_log_severity_level = NETDATA_LOG_LEVEL_INFO; +#define IS_VALID_LOG_METHOD_FOR_EXTERNAL_PLUGINS(ndlo) ((ndlo) == NDLM_JOURNAL || (ndlo) == NDLM_SYSLOG || (ndlo) == NDLM_STDERR) -#ifdef ENABLE_ACLK -const char *aclklog_filename = NULL; -int aclklog_fd = -1; -FILE *aclklog = NULL; -int aclklog_syslog = 1; -int aclklog_enabled = 0; +const char *nd_log_method_for_external_plugins(const char *s) { + if(s && *s) { + ND_LOG_METHOD method = nd_log_method2id(s); + if(IS_VALID_LOG_METHOD_FOR_EXTERNAL_PLUGINS(method)) + return nd_log_id2method(method); + } + + return nd_log_id2method(NDLM_STDERR); +} + +// ---------------------------------------------------------------------------- +// workaround strerror_r() + +#if defined(STRERROR_R_CHAR_P) +// GLIBC version of strerror_r +static const char *strerror_result(const char *a, const char *b) { (void)b; return a; } +#elif defined(HAVE_STRERROR_R) +// POSIX version of strerror_r +static const char *strerror_result(int a, const char *b) { (void)a; return b; } +#elif defined(HAVE_C__GENERIC) + +// what a trick! +// http://stackoverflow.com/questions/479207/function-overloading-in-c +static const char *strerror_result_int(int a, const char *b) { (void)a; return b; } +static const char *strerror_result_string(const char *a, const char *b) { (void)b; return a; } + +#define strerror_result(a, b) _Generic((a), \ + int: strerror_result_int, \ + char *: strerror_result_string \ + )(a, b) + +#else +#error "cannot detect the format of function strerror_r()" #endif +static const char *errno2str(int errnum, char *buf, size_t size) { + return strerror_result(strerror_r(errnum, buf, size), buf); +} + // ---------------------------------------------------------------------------- -// Log facility(https://tools.ietf.org/html/rfc5424) +// facilities // -// The facilities accepted in the Netdata are in according with the following -// header files for their respective operating system: -// sys/syslog.h (Linux ) +// sys/syslog.h (Linux) // sys/sys/syslog.h (FreeBSD) // bsd/sys/syslog.h (darwin-xnu) -#define LOG_AUTH_KEY "auth" -#define LOG_AUTHPRIV_KEY "authpriv" -#ifdef __FreeBSD__ -# define LOG_CONSOLE_KEY "console" -#endif -#define LOG_CRON_KEY "cron" -#define LOG_DAEMON_KEY "daemon" -#define LOG_FTP_KEY "ftp" -#ifdef __APPLE__ -# define LOG_INSTALL_KEY "install" -#endif -#define LOG_KERN_KEY "kern" -#define LOG_LPR_KEY "lpr" -#define LOG_MAIL_KEY "mail" -//#define LOG_INTERNAL_MARK_KEY "mark" -#ifdef __APPLE__ -# define LOG_NETINFO_KEY "netinfo" -# define LOG_RAS_KEY "ras" -# define LOG_REMOTEAUTH_KEY "remoteauth" -#endif -#define LOG_NEWS_KEY "news" -#ifdef __FreeBSD__ -# define LOG_NTP_KEY "ntp" -#endif -#define LOG_SECURITY_KEY "security" -#define LOG_SYSLOG_KEY "syslog" -#define LOG_USER_KEY "user" -#define LOG_UUCP_KEY "uucp" -#ifdef __APPLE__ -# define LOG_LAUNCHD_KEY "launchd" -#endif -#define LOG_LOCAL0_KEY "local0" -#define LOG_LOCAL1_KEY "local1" -#define LOG_LOCAL2_KEY "local2" -#define LOG_LOCAL3_KEY "local3" -#define LOG_LOCAL4_KEY "local4" -#define LOG_LOCAL5_KEY "local5" -#define LOG_LOCAL6_KEY "local6" -#define LOG_LOCAL7_KEY "local7" - -static int log_facility_id(const char *facility_name) -{ - static int - hash_auth = 0, - hash_authpriv = 0, -#ifdef __FreeBSD__ - hash_console = 0, -#endif - hash_cron = 0, - hash_daemon = 0, - hash_ftp = 0, -#ifdef __APPLE__ - hash_install = 0, -#endif - hash_kern = 0, - hash_lpr = 0, - hash_mail = 0, -// hash_mark = 0, -#ifdef __APPLE__ - hash_netinfo = 0, - hash_ras = 0, - hash_remoteauth = 0, -#endif - hash_news = 0, -#ifdef __FreeBSD__ - hash_ntp = 0, -#endif - hash_security = 0, - hash_syslog = 0, - hash_user = 0, - hash_uucp = 0, -#ifdef __APPLE__ - hash_launchd = 0, -#endif - hash_local0 = 0, - hash_local1 = 0, - hash_local2 = 0, - hash_local3 = 0, - hash_local4 = 0, - hash_local5 = 0, - hash_local6 = 0, - hash_local7 = 0; - - if(unlikely(!hash_auth)) - { - hash_auth = simple_hash(LOG_AUTH_KEY); - hash_authpriv = simple_hash(LOG_AUTHPRIV_KEY); -#ifdef __FreeBSD__ - hash_console = simple_hash(LOG_CONSOLE_KEY); -#endif - hash_cron = simple_hash(LOG_CRON_KEY); - hash_daemon = simple_hash(LOG_DAEMON_KEY); - hash_ftp = simple_hash(LOG_FTP_KEY); -#ifdef __APPLE__ - hash_install = simple_hash(LOG_INSTALL_KEY); -#endif - hash_kern = simple_hash(LOG_KERN_KEY); - hash_lpr = simple_hash(LOG_LPR_KEY); - hash_mail = simple_hash(LOG_MAIL_KEY); -// hash_mark = simple_uhash(); -#ifdef __APPLE__ - hash_netinfo = simple_hash(LOG_NETINFO_KEY); - hash_ras = simple_hash(LOG_RAS_KEY); - hash_remoteauth = simple_hash(LOG_REMOTEAUTH_KEY); -#endif - hash_news = simple_hash(LOG_NEWS_KEY); +static struct { + int facility; + const char *name; +} nd_log_facilities[] = { + { LOG_AUTH, "auth" }, + { LOG_AUTHPRIV, "authpriv" }, + { LOG_CRON, "cron" }, + { LOG_DAEMON, "daemon" }, + { LOG_FTP, "ftp" }, + { LOG_KERN, "kern" }, + { LOG_LPR, "lpr" }, + { LOG_MAIL, "mail" }, + { LOG_NEWS, "news" }, + { LOG_SYSLOG, "syslog" }, + { LOG_USER, "user" }, + { LOG_UUCP, "uucp" }, + { LOG_LOCAL0, "local0" }, + { LOG_LOCAL1, "local1" }, + { LOG_LOCAL2, "local2" }, + { LOG_LOCAL3, "local3" }, + { LOG_LOCAL4, "local4" }, + { LOG_LOCAL5, "local5" }, + { LOG_LOCAL6, "local6" }, + { LOG_LOCAL7, "local7" }, + #ifdef __FreeBSD__ - hash_ntp = simple_hash(LOG_NTP_KEY); + { LOG_CONSOLE, "console" }, + { LOG_NTP, "ntp" }, + + // FreeBSD does not consider 'security' as deprecated. + { LOG_SECURITY, "security" }, +#else + // For all other O/S 'security' is mapped to 'auth'. + { LOG_AUTH, "security" }, #endif - hash_security = simple_hash(LOG_SECURITY_KEY); - hash_syslog = simple_hash(LOG_SYSLOG_KEY); - hash_user = simple_hash(LOG_USER_KEY); - hash_uucp = simple_hash(LOG_UUCP_KEY); + #ifdef __APPLE__ - hash_launchd = simple_hash(LOG_LAUNCHD_KEY); + { LOG_INSTALL, "install" }, + { LOG_NETINFO, "netinfo" }, + { LOG_RAS, "ras" }, + { LOG_REMOTEAUTH, "remoteauth" }, + { LOG_LAUNCHD, "launchd" }, + #endif - hash_local0 = simple_hash(LOG_LOCAL0_KEY); - hash_local1 = simple_hash(LOG_LOCAL1_KEY); - hash_local2 = simple_hash(LOG_LOCAL2_KEY); - hash_local3 = simple_hash(LOG_LOCAL3_KEY); - hash_local4 = simple_hash(LOG_LOCAL4_KEY); - hash_local5 = simple_hash(LOG_LOCAL5_KEY); - hash_local6 = simple_hash(LOG_LOCAL6_KEY); - hash_local7 = simple_hash(LOG_LOCAL7_KEY); +}; + +static int nd_log_facility2id(const char *facility) { + size_t entries = sizeof(nd_log_facilities) / sizeof(nd_log_facilities[0]); + for(size_t i = 0; i < entries ;i++) { + if(strcmp(nd_log_facilities[i].name, facility) == 0) + return nd_log_facilities[i].facility; } - int hash = simple_hash(facility_name); - if ( hash == hash_auth ) - { - return LOG_AUTH; + return LOG_DAEMON; +} + +static const char *nd_log_id2facility(int facility) { + size_t entries = sizeof(nd_log_facilities) / sizeof(nd_log_facilities[0]); + for(size_t i = 0; i < entries ;i++) { + if(nd_log_facilities[i].facility == facility) + return nd_log_facilities[i].name; } - else if ( hash == hash_authpriv ) - { - return LOG_AUTHPRIV; + + return "daemon"; +} + +// ---------------------------------------------------------------------------- +// priorities + +static struct { + ND_LOG_FIELD_PRIORITY priority; + const char *name; +} nd_log_priorities[] = { + { .priority = NDLP_EMERG, .name = "emergency" }, + { .priority = NDLP_EMERG, .name = "emerg" }, + { .priority = NDLP_ALERT, .name = "alert" }, + { .priority = NDLP_CRIT, .name = "critical" }, + { .priority = NDLP_CRIT, .name = "crit" }, + { .priority = NDLP_ERR, .name = "error" }, + { .priority = NDLP_ERR, .name = "err" }, + { .priority = NDLP_WARNING, .name = "warning" }, + { .priority = NDLP_WARNING, .name = "warn" }, + { .priority = NDLP_NOTICE, .name = "notice" }, + { .priority = NDLP_INFO, .name = NDLP_INFO_STR }, + { .priority = NDLP_DEBUG, .name = "debug" }, +}; + +int nd_log_priority2id(const char *priority) { + size_t entries = sizeof(nd_log_priorities) / sizeof(nd_log_priorities[0]); + for(size_t i = 0; i < entries ;i++) { + if(strcmp(nd_log_priorities[i].name, priority) == 0) + return nd_log_priorities[i].priority; } -#ifdef __FreeBSD__ - else if ( hash == hash_console ) - { - return LOG_CONSOLE; + + return NDLP_INFO; +} + +const char *nd_log_id2priority(ND_LOG_FIELD_PRIORITY priority) { + size_t entries = sizeof(nd_log_priorities) / sizeof(nd_log_priorities[0]); + for(size_t i = 0; i < entries ;i++) { + if(priority == nd_log_priorities[i].priority) + return nd_log_priorities[i].name; } -#endif - else if ( hash == hash_cron ) - { - return LOG_CRON; + + return NDLP_INFO_STR; +} + +// ---------------------------------------------------------------------------- +// log sources + +const char *nd_log_sources[] = { + [NDLS_UNSET] = "UNSET", + [NDLS_ACCESS] = "access", + [NDLS_ACLK] = "aclk", + [NDLS_COLLECTORS] = "collector", + [NDLS_DAEMON] = "daemon", + [NDLS_HEALTH] = "health", + [NDLS_DEBUG] = "debug", +}; + +size_t nd_log_source2id(const char *source, ND_LOG_SOURCES def) { + size_t entries = sizeof(nd_log_sources) / sizeof(nd_log_sources[0]); + for(size_t i = 0; i < entries ;i++) { + if(strcmp(nd_log_sources[i], source) == 0) + return i; } - else if ( hash == hash_daemon ) - { - return LOG_DAEMON; + + return def; +} + + +static const char *nd_log_id2source(ND_LOG_SOURCES source) { + size_t entries = sizeof(nd_log_sources) / sizeof(nd_log_sources[0]); + if(source < entries) + return nd_log_sources[source]; + + return nd_log_sources[NDLS_COLLECTORS]; +} + +// ---------------------------------------------------------------------------- +// log output formats + +typedef enum __attribute__((__packed__)) { + NDLF_JOURNAL, + NDLF_LOGFMT, + NDLF_JSON, +} ND_LOG_FORMAT; + +static struct { + ND_LOG_FORMAT format; + const char *name; +} nd_log_formats[] = { + { .format = NDLF_JOURNAL, .name = "journal" }, + { .format = NDLF_LOGFMT, .name = "logfmt" }, + { .format = NDLF_JSON, .name = "json" }, +}; + +static ND_LOG_FORMAT nd_log_format2id(const char *format) { + if(!format || !*format) + return NDLF_LOGFMT; + + size_t entries = sizeof(nd_log_formats) / sizeof(nd_log_formats[0]); + for(size_t i = 0; i < entries ;i++) { + if(strcmp(nd_log_formats[i].name, format) == 0) + return nd_log_formats[i].format; } - else if ( hash == hash_ftp ) - { - return LOG_FTP; + + return NDLF_LOGFMT; +} + +static const char *nd_log_id2format(ND_LOG_FORMAT format) { + size_t entries = sizeof(nd_log_formats) / sizeof(nd_log_formats[0]); + for(size_t i = 0; i < entries ;i++) { + if(format == nd_log_formats[i].format) + return nd_log_formats[i].name; } -#ifdef __APPLE__ - else if ( hash == hash_install ) - { - return LOG_INSTALL; + + return "logfmt"; +} + +// ---------------------------------------------------------------------------- +// format dates + +void log_date(char *buffer, size_t len, time_t now) { + if(unlikely(!buffer || !len)) + return; + + time_t t = now; + struct tm *tmp, tmbuf; + + tmp = localtime_r(&t, &tmbuf); + + if (unlikely(!tmp)) { + buffer[0] = '\0'; + return; } -#endif - else if ( hash == hash_kern ) - { - return LOG_KERN; + + if (unlikely(strftime(buffer, len, "%Y-%m-%d %H:%M:%S", tmp) == 0)) + buffer[0] = '\0'; + + buffer[len - 1] = '\0'; +} + +// ---------------------------------------------------------------------------- + +struct nd_log_limit { + usec_t started_monotonic_ut; + uint32_t counter; + uint32_t prevented; + + uint32_t throttle_period; + uint32_t logs_per_period; + uint32_t logs_per_period_backup; +}; + +#define ND_LOG_LIMITS_DEFAULT (struct nd_log_limit){ .logs_per_period = ND_LOG_DEFAULT_THROTTLE_LOGS, .logs_per_period_backup = ND_LOG_DEFAULT_THROTTLE_LOGS, .throttle_period = ND_LOG_DEFAULT_THROTTLE_PERIOD, } +#define ND_LOG_LIMITS_UNLIMITED (struct nd_log_limit){ .logs_per_period = 0, .logs_per_period_backup = 0, .throttle_period = 0, } + +struct nd_log_source { + SPINLOCK spinlock; + ND_LOG_METHOD method; + ND_LOG_FORMAT format; + const char *filename; + int fd; + FILE *fp; + + ND_LOG_FIELD_PRIORITY min_priority; + const char *pending_msg; + struct nd_log_limit limits; +}; + +static __thread ND_LOG_SOURCES overwrite_thread_source = 0; + +void nd_log_set_thread_source(ND_LOG_SOURCES source) { + overwrite_thread_source = source; +} + +static struct { + uuid_t invocation_id; + + ND_LOG_SOURCES overwrite_process_source; + + struct nd_log_source sources[_NDLS_MAX]; + + struct { + bool initialized; + } journal; + + struct { + bool initialized; + int fd; + char filename[FILENAME_MAX + 1]; + } journal_direct; + + struct { + bool initialized; + int facility; + } syslog; + + struct { + SPINLOCK spinlock; + bool initialized; + } std_output; + + struct { + SPINLOCK spinlock; + bool initialized; + } std_error; + +} nd_log = { + .overwrite_process_source = 0, + .journal = { + .initialized = false, + }, + .journal_direct = { + .initialized = false, + .fd = -1, + }, + .syslog = { + .initialized = false, + .facility = LOG_DAEMON, + }, + .std_output = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .initialized = false, + }, + .std_error = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .initialized = false, + }, + .sources = { + [NDLS_UNSET] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DISABLED, + .format = NDLF_JOURNAL, + .filename = NULL, + .fd = -1, + .fp = NULL, + .min_priority = NDLP_EMERG, + .limits = ND_LOG_LIMITS_UNLIMITED, + }, + [NDLS_ACCESS] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DEFAULT, + .format = NDLF_LOGFMT, + .filename = LOG_DIR "/access.log", + .fd = -1, + .fp = NULL, + .min_priority = NDLP_DEBUG, + .limits = ND_LOG_LIMITS_UNLIMITED, + }, + [NDLS_ACLK] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_FILE, + .format = NDLF_LOGFMT, + .filename = LOG_DIR "/aclk.log", + .fd = -1, + .fp = NULL, + .min_priority = NDLP_DEBUG, + .limits = ND_LOG_LIMITS_UNLIMITED, + }, + [NDLS_COLLECTORS] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DEFAULT, + .format = NDLF_LOGFMT, + .filename = LOG_DIR "/collectors.log", + .fd = STDERR_FILENO, + .fp = NULL, + .min_priority = NDLP_INFO, + .limits = ND_LOG_LIMITS_DEFAULT, + }, + [NDLS_DEBUG] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DISABLED, + .format = NDLF_LOGFMT, + .filename = LOG_DIR "/debug.log", + .fd = STDOUT_FILENO, + .fp = NULL, + .min_priority = NDLP_DEBUG, + .limits = ND_LOG_LIMITS_UNLIMITED, + }, + [NDLS_DAEMON] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DEFAULT, + .filename = LOG_DIR "/daemon.log", + .format = NDLF_LOGFMT, + .fd = -1, + .fp = NULL, + .min_priority = NDLP_INFO, + .limits = ND_LOG_LIMITS_DEFAULT, + }, + [NDLS_HEALTH] = { + .spinlock = NETDATA_SPINLOCK_INITIALIZER, + .method = NDLM_DEFAULT, + .format = NDLF_LOGFMT, + .filename = LOG_DIR "/health.log", + .fd = -1, + .fp = NULL, + .min_priority = NDLP_DEBUG, + .limits = ND_LOG_LIMITS_UNLIMITED, + }, + }, +}; + +__attribute__((constructor)) void initialize_invocation_id(void) { + // check for a NETDATA_INVOCATION_ID + if(uuid_parse_flexi(getenv("NETDATA_INVOCATION_ID"), nd_log.invocation_id) != 0) { + // not found, check for systemd set INVOCATION_ID + if(uuid_parse_flexi(getenv("INVOCATION_ID"), nd_log.invocation_id) != 0) { + // not found, generate a new one + uuid_generate_random(nd_log.invocation_id); + } + } + + char uuid[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(nd_log.invocation_id, uuid); + setenv("NETDATA_INVOCATION_ID", uuid, 1); +} + +int nd_log_health_fd(void) { + if(nd_log.sources[NDLS_HEALTH].method == NDLM_FILE && nd_log.sources[NDLS_HEALTH].fd != -1) + return nd_log.sources[NDLS_HEALTH].fd; + + return STDERR_FILENO; +} + +void nd_log_set_user_settings(ND_LOG_SOURCES source, const char *setting) { + char buf[FILENAME_MAX + 100]; + if(setting && *setting) + strncpyz(buf, setting, sizeof(buf) - 1); + else + buf[0] = '\0'; + + struct nd_log_source *ls = &nd_log.sources[source]; + char *output = strrchr(buf, '@'); + + if(!output) + // all of it is the output + output = buf; + else { + // we found an '@', the next char is the output + *output = '\0'; + output++; + + // parse the other params + char *remaining = buf; + while(remaining) { + char *value = strsep_skip_consecutive_separators(&remaining, ","); + if (!value || !*value) continue; + + char *name = strsep_skip_consecutive_separators(&value, "="); + if (!name || !*name) continue; + + if(strcmp(name, "logfmt") == 0) + ls->format = NDLF_LOGFMT; + else if(strcmp(name, "json") == 0) + ls->format = NDLF_JSON; + else if(strcmp(name, "journal") == 0) + ls->format = NDLF_JOURNAL; + else if(strcmp(name, "level") == 0 && value && *value) + ls->min_priority = nd_log_priority2id(value); + else if(strcmp(name, "protection") == 0 && value && *value) { + if(strcmp(value, "off") == 0 || strcmp(value, "none") == 0) { + ls->limits = ND_LOG_LIMITS_UNLIMITED; + ls->limits.counter = 0; + ls->limits.prevented = 0; + } + else { + ls->limits = ND_LOG_LIMITS_DEFAULT; + + char *slash = strchr(value, '/'); + if(slash) { + *slash = '\0'; + slash++; + ls->limits.logs_per_period = ls->limits.logs_per_period_backup = str2u(value); + ls->limits.throttle_period = str2u(slash); + } + else { + ls->limits.logs_per_period = ls->limits.logs_per_period_backup = str2u(value); + ls->limits.throttle_period = ND_LOG_DEFAULT_THROTTLE_PERIOD; + } + } + } + else + nd_log(NDLS_DAEMON, NDLP_ERR, "Error while parsing configuration of log source '%s'. " + "In config '%s', '%s' is not understood.", + nd_log_id2source(source), setting, name); + } } - else if ( hash == hash_lpr ) - { - return LOG_LPR; + + if(!output || !*output || strcmp(output, "none") == 0 || strcmp(output, "off") == 0) { + ls->method = NDLM_DISABLED; + ls->filename = "/dev/null"; } - else if ( hash == hash_mail ) - { - return LOG_MAIL; + else if(strcmp(output, "journal") == 0) { + ls->method = NDLM_JOURNAL; + ls->filename = NULL; } - /* - else if ( hash == hash_mark ) - { - //this is internal for all OS - return INTERNAL_MARK; + else if(strcmp(output, "syslog") == 0) { + ls->method = NDLM_SYSLOG; + ls->filename = NULL; } - */ -#ifdef __APPLE__ - else if ( hash == hash_netinfo ) - { - return LOG_NETINFO; + else if(strcmp(output, "/dev/null") == 0) { + ls->method = NDLM_DEVNULL; + ls->filename = "/dev/null"; } - else if ( hash == hash_ras ) - { - return LOG_RAS; + else if(strcmp(output, "system") == 0) { + if(ls->fd == STDERR_FILENO) { + ls->method = NDLM_STDERR; + ls->filename = NULL; + ls->fd = STDERR_FILENO; + } + else { + ls->method = NDLM_STDOUT; + ls->filename = NULL; + ls->fd = STDOUT_FILENO; + } } - else if ( hash == hash_remoteauth ) - { - return LOG_REMOTEAUTH; + else if(strcmp(output, "stderr") == 0) { + ls->method = NDLM_STDERR; + ls->filename = NULL; + ls->fd = STDERR_FILENO; } -#endif - else if ( hash == hash_news ) - { - return LOG_NEWS; + else if(strcmp(output, "stdout") == 0) { + ls->method = NDLM_STDOUT; + ls->filename = NULL; + ls->fd = STDOUT_FILENO; } -#ifdef __FreeBSD__ - else if ( hash == hash_ntp ) - { - return LOG_NTP; + else { + ls->method = NDLM_FILE; + ls->filename = strdupz(output); } + +#if defined(NETDATA_INTERNAL_CHECKS) || defined(NETDATA_DEV_MODE) + ls->min_priority = NDLP_DEBUG; #endif - else if ( hash == hash_security ) - { - //FreeBSD is the unique that does not consider - //this facility deprecated. We are keeping - //it for other OS while they are kept in their headers. -#ifdef __FreeBSD__ - return LOG_SECURITY; -#else - return LOG_AUTH; -#endif - } - else if ( hash == hash_syslog ) - { - return LOG_SYSLOG; + + if(source == NDLS_COLLECTORS) { + // set the method for the collector processes we will spawn + + ND_LOG_METHOD method; + ND_LOG_FORMAT format = ls->format; + ND_LOG_FIELD_PRIORITY priority = ls->min_priority; + + if(ls->method == NDLM_SYSLOG || ls->method == NDLM_JOURNAL) + method = ls->method; + else + method = NDLM_STDERR; + + setenv("NETDATA_LOG_METHOD", nd_log_id2method(method), 1); + setenv("NETDATA_LOG_FORMAT", nd_log_id2format(format), 1); + setenv("NETDATA_LOG_LEVEL", nd_log_id2priority(priority), 1); } - else if ( hash == hash_user ) - { - return LOG_USER; +} + +void nd_log_set_priority_level(const char *setting) { + if(!setting || !*setting) + setting = "info"; + + ND_LOG_FIELD_PRIORITY priority = nd_log_priority2id(setting); + +#if defined(NETDATA_INTERNAL_CHECKS) || defined(NETDATA_DEV_MODE) + priority = NDLP_DEBUG; +#endif + + for (size_t i = 0; i < _NDLS_MAX; i++) { + if (i != NDLS_DEBUG) + nd_log.sources[i].min_priority = priority; } - else if ( hash == hash_uucp ) - { - return LOG_UUCP; + + // the right one + setenv("NETDATA_LOG_LEVEL", nd_log_id2priority(priority), 1); +} + +void nd_log_set_facility(const char *facility) { + if(!facility || !*facility) + facility = "daemon"; + + nd_log.syslog.facility = nd_log_facility2id(facility); + setenv("NETDATA_SYSLOG_FACILITY", nd_log_id2facility(nd_log.syslog.facility), 1); +} + +void nd_log_set_flood_protection(size_t logs, time_t period) { + nd_log.sources[NDLS_DAEMON].limits.logs_per_period = + nd_log.sources[NDLS_DAEMON].limits.logs_per_period_backup; + nd_log.sources[NDLS_COLLECTORS].limits.logs_per_period = + nd_log.sources[NDLS_COLLECTORS].limits.logs_per_period_backup = logs; + + nd_log.sources[NDLS_DAEMON].limits.throttle_period = + nd_log.sources[NDLS_COLLECTORS].limits.throttle_period = period; + + char buf[100]; + snprintfz(buf, sizeof(buf), "%" PRIu64, (uint64_t )period); + setenv("NETDATA_ERRORS_THROTTLE_PERIOD", buf, 1); + snprintfz(buf, sizeof(buf), "%" PRIu64, (uint64_t )logs); + setenv("NETDATA_ERRORS_PER_PERIOD", buf, 1); +} + +static bool nd_log_journal_systemd_init(void) { +#ifdef HAVE_SYSTEMD + nd_log.journal.initialized = true; +#else + nd_log.journal.initialized = false; +#endif + + return nd_log.journal.initialized; +} + +static void nd_log_journal_direct_set_env(void) { + if(nd_log.sources[NDLS_COLLECTORS].method == NDLM_JOURNAL) + setenv("NETDATA_SYSTEMD_JOURNAL_PATH", nd_log.journal_direct.filename, 1); +} + +static bool nd_log_journal_direct_init(const char *path) { + if(nd_log.journal_direct.initialized) { + nd_log_journal_direct_set_env(); + return true; } - else if ( hash == hash_local0 ) - { - return LOG_LOCAL0; + + int fd; + char filename[FILENAME_MAX + 1]; + if(!is_path_unix_socket(path)) { + + journal_construct_path(filename, sizeof(filename), netdata_configured_host_prefix, "netdata"); + if (!is_path_unix_socket(filename) || (fd = journal_direct_fd(filename)) == -1) { + + journal_construct_path(filename, sizeof(filename), netdata_configured_host_prefix, NULL); + if (!is_path_unix_socket(filename) || (fd = journal_direct_fd(filename)) == -1) { + + journal_construct_path(filename, sizeof(filename), NULL, "netdata"); + if (!is_path_unix_socket(filename) || (fd = journal_direct_fd(filename)) == -1) { + + journal_construct_path(filename, sizeof(filename), NULL, NULL); + if (!is_path_unix_socket(filename) || (fd = journal_direct_fd(filename)) == -1) + return false; + } + } + } } - else if ( hash == hash_local1 ) - { - return LOG_LOCAL1; + else { + snprintfz(filename, sizeof(filename), "%s", path); + fd = journal_direct_fd(filename); } - else if ( hash == hash_local2 ) - { - return LOG_LOCAL2; + + if(fd < 0) + return false; + + nd_log.journal_direct.fd = fd; + nd_log.journal_direct.initialized = true; + + strncpyz(nd_log.journal_direct.filename, filename, sizeof(nd_log.journal_direct.filename) - 1); + nd_log_journal_direct_set_env(); + + return true; +} + +static void nd_log_syslog_init() { + if(nd_log.syslog.initialized) + return; + + openlog(program_name, LOG_PID, nd_log.syslog.facility); + nd_log.syslog.initialized = true; +} + +void nd_log_initialize_for_external_plugins(const char *name) { + // if we don't run under Netdata, log to stderr, + // otherwise, use the logging method Netdata wants us to use. + setenv("NETDATA_LOG_METHOD", "stderr", 0); + setenv("NETDATA_LOG_FORMAT", "logfmt", 0); + + nd_log.overwrite_process_source = NDLS_COLLECTORS; + program_name = name; + + for(size_t i = 0; i < _NDLS_MAX ;i++) { + nd_log.sources[i].method = STDERR_FILENO; + nd_log.sources[i].fd = -1; + nd_log.sources[i].fp = NULL; } - else if ( hash == hash_local3 ) - { - return LOG_LOCAL3; + + nd_log_set_priority_level(getenv("NETDATA_LOG_LEVEL")); + nd_log_set_facility(getenv("NETDATA_SYSLOG_FACILITY")); + + time_t period = 1200; + size_t logs = 200; + const char *s = getenv("NETDATA_ERRORS_THROTTLE_PERIOD"); + if(s && *s >= '0' && *s <= '9') { + period = str2l(s); + if(period < 0) period = 0; } - else if ( hash == hash_local4 ) - { - return LOG_LOCAL4; + + s = getenv("NETDATA_ERRORS_PER_PERIOD"); + if(s && *s >= '0' && *s <= '9') + logs = str2u(s); + + nd_log_set_flood_protection(logs, period); + + if(!netdata_configured_host_prefix) { + s = getenv("NETDATA_HOST_PREFIX"); + if(s && *s) + netdata_configured_host_prefix = (char *)s; } - else if ( hash == hash_local5 ) - { - return LOG_LOCAL5; + + ND_LOG_METHOD method = nd_log_method2id(getenv("NETDATA_LOG_METHOD")); + ND_LOG_FORMAT format = nd_log_format2id(getenv("NETDATA_LOG_FORMAT")); + + if(!IS_VALID_LOG_METHOD_FOR_EXTERNAL_PLUGINS(method)) { + if(is_stderr_connected_to_journal()) { + nd_log(NDLS_COLLECTORS, NDLP_WARNING, "NETDATA_LOG_METHOD is not set. Using journal."); + method = NDLM_JOURNAL; + } + else { + nd_log(NDLS_COLLECTORS, NDLP_WARNING, "NETDATA_LOG_METHOD is not set. Using stderr."); + method = NDLM_STDERR; + } } - else if ( hash == hash_local6 ) - { - return LOG_LOCAL6; + + switch(method) { + case NDLM_JOURNAL: + if(!nd_log_journal_direct_init(getenv("NETDATA_SYSTEMD_JOURNAL_PATH")) || + !nd_log_journal_direct_init(NULL) || !nd_log_journal_systemd_init()) { + nd_log(NDLS_COLLECTORS, NDLP_WARNING, "Failed to initialize journal. Using stderr."); + method = NDLM_STDERR; + } + break; + + case NDLM_SYSLOG: + nd_log_syslog_init(); + break; + + default: + method = NDLM_STDERR; + break; } - else if ( hash == hash_local7 ) - { - return LOG_LOCAL7; + + for(size_t i = 0; i < _NDLS_MAX ;i++) { + nd_log.sources[i].method = method; + nd_log.sources[i].format = format; + nd_log.sources[i].fd = -1; + nd_log.sources[i].fp = NULL; } -#ifdef __APPLE__ - else if ( hash == hash_launchd ) - { - return LOG_LAUNCHD; + +// nd_log(NDLS_COLLECTORS, NDLP_NOTICE, "FINAL_LOG_METHOD: %s", nd_log_id2method(method)); +} + +static bool nd_log_replace_existing_fd(struct nd_log_source *e, int new_fd) { + if(new_fd == -1 || e->fd == -1 || + (e->fd == STDOUT_FILENO && nd_log.std_output.initialized) || + (e->fd == STDERR_FILENO && nd_log.std_error.initialized)) + return false; + + if(new_fd != e->fd) { + int t = dup2(new_fd, e->fd); + + bool ret = true; + if (t == -1) { + netdata_log_error("Cannot dup2() new fd %d to old fd %d for '%s'", new_fd, e->fd, e->filename); + ret = false; + } + else + close(new_fd); + + if(e->fd == STDOUT_FILENO) + nd_log.std_output.initialized = true; + else if(e->fd == STDERR_FILENO) + nd_log.std_error.initialized = true; + + return ret; } -#endif - return LOG_DAEMON; + return false; } -//we do not need to use this now, but I already created this function to be -//used case necessary. -/* -char *log_facility_name(int code) -{ - char *defvalue = { "daemon" }; - switch(code) - { - case LOG_AUTH: - { - return "auth"; - } - case LOG_AUTHPRIV: - { - return "authpriv"; - } -#ifdef __FreeBSD__ - case LOG_CONSOLE: - { - return "console"; - } -#endif - case LOG_CRON: - { - return "cron"; - } - case LOG_DAEMON: - { - return defvalue; - } - case LOG_FTP: - { - return "ftp"; - } -#ifdef __APPLE__ - case LOG_INSTALL: - { - return "install"; - } -#endif - case LOG_KERN: - { - return "kern"; - } - case LOG_LPR: - { - return "lpr"; - } - case LOG_MAIL: - { - return "mail"; - } -#ifdef __APPLE__ - case LOG_NETINFO: - { - return "netinfo" ; - } - case LOG_RAS: - { - return "ras"; +static void nd_log_open(struct nd_log_source *e, ND_LOG_SOURCES source) { + if(e->method == NDLM_DEFAULT) + nd_log_set_user_settings(source, e->filename); + + if((e->method == NDLM_FILE && !e->filename) || + (e->method == NDLM_DEVNULL && e->fd == -1)) + e->method = NDLM_DISABLED; + + if(e->fp) + fflush(e->fp); + + switch(e->method) { + case NDLM_SYSLOG: + nd_log_syslog_init(); + break; + + case NDLM_JOURNAL: + nd_log_journal_direct_init(NULL); + nd_log_journal_systemd_init(); + break; + + case NDLM_STDOUT: + e->fp = stdout; + e->fd = STDOUT_FILENO; + break; + + case NDLM_DISABLED: + break; + + case NDLM_DEFAULT: + case NDLM_STDERR: + e->method = NDLM_STDERR; + e->fp = stderr; + e->fd = STDERR_FILENO; + break; + + case NDLM_DEVNULL: + case NDLM_FILE: { + int fd = open(e->filename, O_WRONLY | O_APPEND | O_CREAT, 0664); + if(fd == -1) { + if(e->fd != STDOUT_FILENO && e->fd != STDERR_FILENO) { + e->fd = STDERR_FILENO; + e->method = NDLM_STDERR; + netdata_log_error("Cannot open log file '%s'. Falling back to stderr.", e->filename); + } + else + netdata_log_error("Cannot open log file '%s'. Leaving fd %d as-is.", e->filename, e->fd); } - case LOG_REMOTEAUTH: - { - return "remoteauth"; + else { + if (!nd_log_replace_existing_fd(e, fd)) { + if(e->fd == STDOUT_FILENO || e->fd == STDERR_FILENO) { + if(e->fd == STDOUT_FILENO) + e->method = NDLM_STDOUT; + else if(e->fd == STDERR_FILENO) + e->method = NDLM_STDERR; + + // we have dup2() fd, so we can close the one we opened + if(fd != STDOUT_FILENO && fd != STDERR_FILENO) + close(fd); + } + else + e->fd = fd; + } } -#endif - case LOG_NEWS: - { - return "news"; - } -#ifdef __FreeBSD__ - case LOG_NTP: - { - return "ntp" ; - } - case LOG_SECURITY: - { - return "security"; - } -#endif - case LOG_SYSLOG: - { - return "syslog"; - } - case LOG_USER: - { - return "user"; - } - case LOG_UUCP: - { - return "uucp"; - } - case LOG_LOCAL0: - { - return "local0"; - } - case LOG_LOCAL1: - { - return "local1"; - } - case LOG_LOCAL2: - { - return "local2"; - } - case LOG_LOCAL3: - { - return "local3"; - } - case LOG_LOCAL4: - { - return "local4" ; - } - case LOG_LOCAL5: - { - return "local5"; - } - case LOG_LOCAL6: - { - return "local6"; - } - case LOG_LOCAL7: - { - return "local7" ; + + // at this point we have e->fd set properly + + if(e->fd == STDOUT_FILENO) + e->fp = stdout; + else if(e->fd == STDERR_FILENO) + e->fp = stderr; + + if(!e->fp) { + e->fp = fdopen(e->fd, "a"); + if (!e->fp) { + netdata_log_error("Cannot fdopen() fd %d ('%s')", e->fd, e->filename); + + if(e->fd != STDOUT_FILENO && e->fd != STDERR_FILENO) + close(e->fd); + + e->fp = stderr; + e->fd = STDERR_FILENO; + } } -#ifdef __APPLE__ - case LOG_LAUNCHD: - { - return "launchd"; + else { + if (setvbuf(e->fp, NULL, _IOLBF, 0) != 0) + netdata_log_error("Cannot set line buffering on fd %d ('%s')", e->fd, e->filename); } -#endif + } + break; } - - return defvalue; } -*/ - -// ---------------------------------------------------------------------------- -void syslog_init() { - static int i = 0; +static void nd_log_stdin_init(int fd, const char *filename) { + int f = open(filename, O_WRONLY | O_APPEND | O_CREAT, 0664); + if(f == -1) + return; - if(!i) { - openlog(program_name, LOG_PID,log_facility_id(facility_log)); - i = 1; + if(f != fd) { + dup2(f, fd); + close(f); } } -void log_date(char *buffer, size_t len, time_t now) { - if(unlikely(!buffer || !len)) - return; +void nd_log_initialize(void) { + nd_log_stdin_init(STDIN_FILENO, "/dev/null"); - time_t t = now; - struct tm *tmp, tmbuf; + for(size_t i = 0 ; i < _NDLS_MAX ; i++) + nd_log_open(&nd_log.sources[i], i); +} - tmp = localtime_r(&t, &tmbuf); +void nd_log_reopen_log_files(void) { + netdata_log_info("Reopening all log files."); - if (tmp == NULL) { - buffer[0] = '\0'; + nd_log.std_output.initialized = false; + nd_log.std_error.initialized = false; + nd_log_initialize(); + + netdata_log_info("Log files re-opened."); +} + +void chown_open_file(int fd, uid_t uid, gid_t gid) { + if(fd == -1) return; + + struct stat buf; + + if(fstat(fd, &buf) == -1) { + netdata_log_error("Cannot fstat() fd %d", fd); return; } - if (unlikely(strftime(buffer, len, "%Y-%m-%d %H:%M:%S", tmp) == 0)) - buffer[0] = '\0'; - - buffer[len - 1] = '\0'; + if((buf.st_uid != uid || buf.st_gid != gid) && S_ISREG(buf.st_mode)) { + if(fchown(fd, uid, gid) == -1) + netdata_log_error("Cannot fchown() fd %d.", fd); + } } -static netdata_mutex_t log_mutex = NETDATA_MUTEX_INITIALIZER; -static inline void log_lock() { - netdata_mutex_lock(&log_mutex); -} -static inline void log_unlock() { - netdata_mutex_unlock(&log_mutex); +void nd_log_chown_log_files(uid_t uid, gid_t gid) { + for(size_t i = 0 ; i < _NDLS_MAX ; i++) { + if(nd_log.sources[i].fd != -1 && nd_log.sources[i].fd != STDIN_FILENO) + chown_open_file(nd_log.sources[i].fd, uid, gid); + } } -static FILE *open_log_file(int fd, FILE *fp, const char *filename, int *enabled_syslog, int is_stdaccess, int *fd_ptr) { - int f, devnull = 0; +// ---------------------------------------------------------------------------- +// annotators +struct log_field; +static void errno_annotator(BUFFER *wb, const char *key, struct log_field *lf); +static void priority_annotator(BUFFER *wb, const char *key, struct log_field *lf); +static void timestamp_usec_annotator(BUFFER *wb, const char *key, struct log_field *lf); + +// ---------------------------------------------------------------------------- - if(!filename || !*filename || !strcmp(filename, "none") || !strcmp(filename, "/dev/null")) { - filename = "/dev/null"; - devnull = 1; +typedef void (*annotator_t)(BUFFER *wb, const char *key, struct log_field *lf); + +struct log_field { + const char *journal; + const char *logfmt; + annotator_t logfmt_annotator; + struct log_stack_entry entry; +}; + +#define THREAD_LOG_STACK_MAX 50 + +static __thread struct log_stack_entry *thread_log_stack_base[THREAD_LOG_STACK_MAX]; +static __thread size_t thread_log_stack_next = 0; + +static __thread struct log_field thread_log_fields[_NDF_MAX] = { + // THE ORDER DEFINES THE ORDER FIELDS WILL APPEAR IN logfmt + + [NDF_STOP] = { // processing will not stop on this - so it is ok to be first + .journal = NULL, + .logfmt = NULL, + .logfmt_annotator = NULL, + }, + [NDF_TIMESTAMP_REALTIME_USEC] = { + .journal = NULL, + .logfmt = "time", + .logfmt_annotator = timestamp_usec_annotator, + }, + [NDF_SYSLOG_IDENTIFIER] = { + .journal = "SYSLOG_IDENTIFIER", // standard journald field + .logfmt = "comm", + }, + [NDF_LOG_SOURCE] = { + .journal = "ND_LOG_SOURCE", + .logfmt = "source", + }, + [NDF_PRIORITY] = { + .journal = "PRIORITY", // standard journald field + .logfmt = "level", + .logfmt_annotator = priority_annotator, + }, + [NDF_ERRNO] = { + .journal = "ERRNO", // standard journald field + .logfmt = "errno", + .logfmt_annotator = errno_annotator, + }, + [NDF_INVOCATION_ID] = { + .journal = "INVOCATION_ID", // standard journald field + .logfmt = NULL, + }, + [NDF_LINE] = { + .journal = "CODE_LINE", // standard journald field + .logfmt = NULL, + }, + [NDF_FILE] = { + .journal = "CODE_FILE", // standard journald field + .logfmt = NULL, + }, + [NDF_FUNC] = { + .journal = "CODE_FUNC", // standard journald field + .logfmt = NULL, + }, + [NDF_TID] = { + .journal = "TID", // standard journald field + .logfmt = "tid", + }, + [NDF_THREAD_TAG] = { + .journal = "THREAD_TAG", + .logfmt = "thread", + }, + [NDF_MESSAGE_ID] = { + .journal = "MESSAGE_ID", + .logfmt = "msg_id", + }, + [NDF_MODULE] = { + .journal = "ND_MODULE", + .logfmt = "module", + }, + [NDF_NIDL_NODE] = { + .journal = "ND_NIDL_NODE", + .logfmt = "node", + }, + [NDF_NIDL_INSTANCE] = { + .journal = "ND_NIDL_INSTANCE", + .logfmt = "instance", + }, + [NDF_NIDL_CONTEXT] = { + .journal = "ND_NIDL_CONTEXT", + .logfmt = "context", + }, + [NDF_NIDL_DIMENSION] = { + .journal = "ND_NIDL_DIMENSION", + .logfmt = "dimension", + }, + [NDF_SRC_TRANSPORT] = { + .journal = "ND_SRC_TRANSPORT", + .logfmt = "src_transport", + }, + [NDF_SRC_IP] = { + .journal = "ND_SRC_IP", + .logfmt = "src_ip", + }, + [NDF_SRC_PORT] = { + .journal = "ND_SRC_PORT", + .logfmt = "src_port", + }, + [NDF_SRC_CAPABILITIES] = { + .journal = "ND_SRC_CAPABILITIES", + .logfmt = "src_capabilities", + }, + [NDF_DST_TRANSPORT] = { + .journal = "ND_DST_TRANSPORT", + .logfmt = "dst_transport", + }, + [NDF_DST_IP] = { + .journal = "ND_DST_IP", + .logfmt = "dst_ip", + }, + [NDF_DST_PORT] = { + .journal = "ND_DST_PORT", + .logfmt = "dst_port", + }, + [NDF_DST_CAPABILITIES] = { + .journal = "ND_DST_CAPABILITIES", + .logfmt = "dst_capabilities", + }, + [NDF_REQUEST_METHOD] = { + .journal = "ND_REQUEST_METHOD", + .logfmt = "req_method", + }, + [NDF_RESPONSE_CODE] = { + .journal = "ND_RESPONSE_CODE", + .logfmt = "code", + }, + [NDF_CONNECTION_ID] = { + .journal = "ND_CONNECTION_ID", + .logfmt = "conn", + }, + [NDF_TRANSACTION_ID] = { + .journal = "ND_TRANSACTION_ID", + .logfmt = "transaction", + }, + [NDF_RESPONSE_SENT_BYTES] = { + .journal = "ND_RESPONSE_SENT_BYTES", + .logfmt = "sent_bytes", + }, + [NDF_RESPONSE_SIZE_BYTES] = { + .journal = "ND_RESPONSE_SIZE_BYTES", + .logfmt = "size_bytes", + }, + [NDF_RESPONSE_PREPARATION_TIME_USEC] = { + .journal = "ND_RESPONSE_PREP_TIME_USEC", + .logfmt = "prep_ut", + }, + [NDF_RESPONSE_SENT_TIME_USEC] = { + .journal = "ND_RESPONSE_SENT_TIME_USEC", + .logfmt = "sent_ut", + }, + [NDF_RESPONSE_TOTAL_TIME_USEC] = { + .journal = "ND_RESPONSE_TOTAL_TIME_USEC", + .logfmt = "total_ut", + }, + [NDF_ALERT_ID] = { + .journal = "ND_ALERT_ID", + .logfmt = "alert_id", + }, + [NDF_ALERT_UNIQUE_ID] = { + .journal = "ND_ALERT_UNIQUE_ID", + .logfmt = "alert_unique_id", + }, + [NDF_ALERT_TRANSITION_ID] = { + .journal = "ND_ALERT_TRANSITION_ID", + .logfmt = "alert_transition_id", + }, + [NDF_ALERT_EVENT_ID] = { + .journal = "ND_ALERT_EVENT_ID", + .logfmt = "alert_event_id", + }, + [NDF_ALERT_CONFIG_HASH] = { + .journal = "ND_ALERT_CONFIG", + .logfmt = "alert_config", + }, + [NDF_ALERT_NAME] = { + .journal = "ND_ALERT_NAME", + .logfmt = "alert", + }, + [NDF_ALERT_CLASS] = { + .journal = "ND_ALERT_CLASS", + .logfmt = "alert_class", + }, + [NDF_ALERT_COMPONENT] = { + .journal = "ND_ALERT_COMPONENT", + .logfmt = "alert_component", + }, + [NDF_ALERT_TYPE] = { + .journal = "ND_ALERT_TYPE", + .logfmt = "alert_type", + }, + [NDF_ALERT_EXEC] = { + .journal = "ND_ALERT_EXEC", + .logfmt = "alert_exec", + }, + [NDF_ALERT_RECIPIENT] = { + .journal = "ND_ALERT_RECIPIENT", + .logfmt = "alert_recipient", + }, + [NDF_ALERT_VALUE] = { + .journal = "ND_ALERT_VALUE", + .logfmt = "alert_value", + }, + [NDF_ALERT_VALUE_OLD] = { + .journal = "ND_ALERT_VALUE_OLD", + .logfmt = "alert_value_old", + }, + [NDF_ALERT_STATUS] = { + .journal = "ND_ALERT_STATUS", + .logfmt = "alert_status", + }, + [NDF_ALERT_STATUS_OLD] = { + .journal = "ND_ALERT_STATUS_OLD", + .logfmt = "alert_value_old", + }, + [NDF_ALERT_UNITS] = { + .journal = "ND_ALERT_UNITS", + .logfmt = "alert_units", + }, + [NDF_ALERT_SUMMARY] = { + .journal = "ND_ALERT_SUMMARY", + .logfmt = "alert_summary", + }, + [NDF_ALERT_INFO] = { + .journal = "ND_ALERT_INFO", + .logfmt = "alert_info", + }, + [NDF_ALERT_DURATION] = { + .journal = "ND_ALERT_DURATION", + .logfmt = "alert_duration", + }, + [NDF_ALERT_NOTIFICATION_REALTIME_USEC] = { + .journal = "ND_ALERT_NOTIFICATION_TIMESTAMP_USEC", + .logfmt = "alert_notification_timestamp", + .logfmt_annotator = timestamp_usec_annotator, + }, + + // put new items here + // leave the request URL and the message last + + [NDF_REQUEST] = { + .journal = "ND_REQUEST", + .logfmt = "request", + }, + [NDF_MESSAGE] = { + .journal = "MESSAGE", + .logfmt = "msg", + }, +}; + +#define THREAD_FIELDS_MAX (sizeof(thread_log_fields) / sizeof(thread_log_fields[0])) + +ND_LOG_FIELD_ID nd_log_field_id_by_name(const char *field, size_t len) { + for(size_t i = 0; i < THREAD_FIELDS_MAX ;i++) { + if(thread_log_fields[i].journal && strlen(thread_log_fields[i].journal) == len && strncmp(field, thread_log_fields[i].journal, len) == 0) + return i; } - if(!strcmp(filename, "syslog")) { - filename = "/dev/null"; - devnull = 1; + return NDF_STOP; +} - syslog_init(); - if(enabled_syslog) *enabled_syslog = 1; - } - else if(enabled_syslog) *enabled_syslog = 0; +void log_stack_pop(void *ptr) { + if(!ptr) return; - // don't do anything if the user is willing - // to have the standard one - if(!strcmp(filename, "system")) { - if(fd != -1 && !is_stdaccess) { - if(fd_ptr) *fd_ptr = fd; - return fp; - } + struct log_stack_entry *lgs = *(struct log_stack_entry (*)[])ptr; - filename = "stderr"; + if(unlikely(!thread_log_stack_next || lgs != thread_log_stack_base[thread_log_stack_next - 1])) { + fatal("You cannot pop in the middle of the stack, or an item not in the stack"); + return; } - if(!strcmp(filename, "stdout")) - f = STDOUT_FILENO; + thread_log_stack_next--; +} - else if(!strcmp(filename, "stderr")) - f = STDERR_FILENO; +void log_stack_push(struct log_stack_entry *lgs) { + if(!lgs || thread_log_stack_next >= THREAD_LOG_STACK_MAX) return; + thread_log_stack_base[thread_log_stack_next++] = lgs; +} - else { - f = open(filename, O_WRONLY | O_APPEND | O_CREAT, 0664); - if(f == -1) { - netdata_log_error("Cannot open file '%s'. Leaving %d to its default.", filename, fd); - if(fd_ptr) *fd_ptr = fd; - return fp; +// ---------------------------------------------------------------------------- +// json formatter + +static void nd_logger_json(BUFFER *wb, struct log_field *fields, size_t fields_max) { + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + buffer_json_initialize(wb, "\"", "\"", 0, true, BUFFER_JSON_OPTIONS_MINIFY); + CLEAN_BUFFER *tmp = NULL; + + for (size_t i = 0; i < fields_max; i++) { + if (!fields[i].entry.set || !fields[i].logfmt) + continue; + + const char *key = fields[i].logfmt; + + const char *s = NULL; + switch(fields[i].entry.type) { + case NDFT_TXT: + s = fields[i].entry.txt; + break; + case NDFT_STR: + s = string2str(fields[i].entry.str); + break; + case NDFT_BFR: + s = buffer_tostring(fields[i].entry.bfr); + break; + case NDFT_U64: + buffer_json_member_add_uint64(wb, key, fields[i].entry.u64); + break; + case NDFT_I64: + buffer_json_member_add_int64(wb, key, fields[i].entry.i64); + break; + case NDFT_DBL: + buffer_json_member_add_double(wb, key, fields[i].entry.dbl); + break; + case NDFT_UUID:{ + char u[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(*fields[i].entry.uuid, u); + buffer_json_member_add_string(wb, key, u); + } + break; + case NDFT_CALLBACK: { + if(!tmp) + tmp = buffer_create(1024, NULL); + else + buffer_flush(tmp); + if(fields[i].entry.cb.formatter(tmp, fields[i].entry.cb.formatter_data)) + s = buffer_tostring(tmp); + else + s = NULL; + } + break; + default: + s = "UNHANDLED"; + break; } + + if(s && *s) + buffer_json_member_add_string(wb, key, s); } - // if there is a level-2 file pointer - // flush it before switching the level-1 fds - if(fp) - fflush(fp); + buffer_json_finalize(wb); +} - if(devnull && is_stdaccess) { - fd = -1; - fp = NULL; +// ---------------------------------------------------------------------------- +// logfmt formatter + + +static int64_t log_field_to_int64(struct log_field *lf) { + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + CLEAN_BUFFER *tmp = NULL; + const char *s = NULL; + + switch(lf->entry.type) { + case NDFT_UUID: + case NDFT_UNSET: + return 0; + + case NDFT_TXT: + s = lf->entry.txt; + break; + + case NDFT_STR: + s = string2str(lf->entry.str); + break; + + case NDFT_BFR: + s = buffer_tostring(lf->entry.bfr); + break; + + case NDFT_CALLBACK: + if(!tmp) + tmp = buffer_create(0, NULL); + else + buffer_flush(tmp); + + if(lf->entry.cb.formatter(tmp, lf->entry.cb.formatter_data)) + s = buffer_tostring(tmp); + else + s = NULL; + break; + + case NDFT_U64: + return lf->entry.u64; + + case NDFT_I64: + return lf->entry.i64; + + case NDFT_DBL: + return lf->entry.dbl; } - if(fd != f && fd != -1) { - // it automatically closes - int t = dup2(f, fd); - if (t == -1) { - netdata_log_error("Cannot dup2() new fd %d to old fd %d for '%s'", f, fd, filename); - close(f); - if(fd_ptr) *fd_ptr = fd; - return fp; - } - // netdata_log_info("dup2() new fd %d to old fd %d for '%s'", f, fd, filename); - close(f); - } - else fd = f; + if(s && *s) + return str2ll(s, NULL); - if(!fp) { - fp = fdopen(fd, "a"); - if (!fp) - netdata_log_error("Cannot fdopen() fd %d ('%s')", fd, filename); - else { - if (setvbuf(fp, NULL, _IOLBF, 0) != 0) - netdata_log_error("Cannot set line buffering on fd %d ('%s')", fd, filename); - } + return 0; +} + +static uint64_t log_field_to_uint64(struct log_field *lf) { + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + CLEAN_BUFFER *tmp = NULL; + const char *s = NULL; + + switch(lf->entry.type) { + case NDFT_UUID: + case NDFT_UNSET: + return 0; + + case NDFT_TXT: + s = lf->entry.txt; + break; + + case NDFT_STR: + s = string2str(lf->entry.str); + break; + + case NDFT_BFR: + s = buffer_tostring(lf->entry.bfr); + break; + + case NDFT_CALLBACK: + if(!tmp) + tmp = buffer_create(0, NULL); + else + buffer_flush(tmp); + + if(lf->entry.cb.formatter(tmp, lf->entry.cb.formatter_data)) + s = buffer_tostring(tmp); + else + s = NULL; + break; + + case NDFT_U64: + return lf->entry.u64; + + case NDFT_I64: + return lf->entry.i64; + + case NDFT_DBL: + return lf->entry.dbl; } - if(fd_ptr) *fd_ptr = fd; - return fp; + if(s && *s) + return str2uint64_t(s, NULL); + + return 0; } -void reopen_all_log_files() { - if(stdout_filename) - open_log_file(STDOUT_FILENO, stdout, stdout_filename, &output_log_syslog, 0, NULL); +static void timestamp_usec_annotator(BUFFER *wb, const char *key, struct log_field *lf) { + usec_t ut = log_field_to_uint64(lf); - if(stdcollector_filename) - open_log_file(STDERR_FILENO, stderr, stdcollector_filename, &collector_log_syslog, 0, NULL); + if(!ut) + return; - if(stderr_filename) { - // Netdata starts using stderr and if it has success to open file it redirects - FILE *fp = open_log_file(stdcollector_fd, stderror, stderr_filename, - &error_log_syslog, 1, &stdcollector_fd); - if (fp) - stderror = fp; - } + char datetime[RFC3339_MAX_LENGTH]; + rfc3339_datetime_ut(datetime, sizeof(datetime), ut, 3, false); -#ifdef ENABLE_ACLK - if (aclklog_enabled) - aclklog = open_log_file(aclklog_fd, aclklog, aclklog_filename, NULL, 0, &aclklog_fd); -#endif + if(buffer_strlen(wb)) + buffer_fast_strcat(wb, " ", 1); - if(stdaccess_filename) - stdaccess = open_log_file(stdaccess_fd, stdaccess, stdaccess_filename, &access_log_syslog, 1, &stdaccess_fd); + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_json_strcat(wb, datetime); +} + +static void errno_annotator(BUFFER *wb, const char *key, struct log_field *lf) { + int64_t errnum = log_field_to_int64(lf); + + if(errnum == 0) + return; - if(stdhealth_filename) - stdhealth = open_log_file(stdhealth_fd, stdhealth, stdhealth_filename, &health_log_syslog, 1, &stdhealth_fd); + char buf[1024]; + const char *s = errno2str(errnum, buf, sizeof(buf)); + + if(buffer_strlen(wb)) + buffer_fast_strcat(wb, " ", 1); + + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=\"", 2); + buffer_print_int64(wb, errnum); + buffer_fast_strcat(wb, ", ", 2); + buffer_json_strcat(wb, s); + buffer_fast_strcat(wb, "\"", 1); } -void open_all_log_files() { - // disable stdin - open_log_file(STDIN_FILENO, stdin, "/dev/null", NULL, 0, NULL); +static void priority_annotator(BUFFER *wb, const char *key, struct log_field *lf) { + uint64_t pri = log_field_to_uint64(lf); - open_log_file(STDOUT_FILENO, stdout, stdout_filename, &output_log_syslog, 0, NULL); - open_log_file(STDERR_FILENO, stderr, stdcollector_filename, &collector_log_syslog, 0, NULL); + if(buffer_strlen(wb)) + buffer_fast_strcat(wb, " ", 1); - // Netdata starts using stderr and if it has success to open file it redirects - FILE *fp = open_log_file(stdcollector_fd, NULL, stderr_filename, &error_log_syslog, 1, &stdcollector_fd); - if (fp) - stderror = fp; + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_strcat(wb, nd_log_id2priority(pri)); +} -#ifdef ENABLE_ACLK - if(aclklog_enabled) - aclklog = open_log_file(aclklog_fd, aclklog, aclklog_filename, NULL, 0, &aclklog_fd); -#endif +static bool needs_quotes_for_logfmt(const char *s) { + static bool safe_for_logfmt[256] = { + [' '] = true, ['!'] = true, ['"'] = false, ['#'] = true, ['$'] = true, ['%'] = true, ['&'] = true, + ['\''] = true, ['('] = true, [')'] = true, ['*'] = true, ['+'] = true, [','] = true, ['-'] = true, + ['.'] = true, ['/'] = true, ['0'] = true, ['1'] = true, ['2'] = true, ['3'] = true, ['4'] = true, + ['5'] = true, ['6'] = true, ['7'] = true, ['8'] = true, ['9'] = true, [':'] = true, [';'] = true, + ['<'] = true, ['='] = true, ['>'] = true, ['?'] = true, ['@'] = true, ['A'] = true, ['B'] = true, + ['C'] = true, ['D'] = true, ['E'] = true, ['F'] = true, ['G'] = true, ['H'] = true, ['I'] = true, + ['J'] = true, ['K'] = true, ['L'] = true, ['M'] = true, ['N'] = true, ['O'] = true, ['P'] = true, + ['Q'] = true, ['R'] = true, ['S'] = true, ['T'] = true, ['U'] = true, ['V'] = true, ['W'] = true, + ['X'] = true, ['Y'] = true, ['Z'] = true, ['['] = true, ['\\'] = false, [']'] = true, ['^'] = true, + ['_'] = true, ['`'] = true, ['a'] = true, ['b'] = true, ['c'] = true, ['d'] = true, ['e'] = true, + ['f'] = true, ['g'] = true, ['h'] = true, ['i'] = true, ['j'] = true, ['k'] = true, ['l'] = true, + ['m'] = true, ['n'] = true, ['o'] = true, ['p'] = true, ['q'] = true, ['r'] = true, ['s'] = true, + ['t'] = true, ['u'] = true, ['v'] = true, ['w'] = true, ['x'] = true, ['y'] = true, ['z'] = true, + ['{'] = true, ['|'] = true, ['}'] = true, ['~'] = true, [0x7f] = true, + }; + + if(!*s) + return true; + + while(*s) { + if(*s == '=' || isspace(*s) || !safe_for_logfmt[(uint8_t)*s]) + return true; + + s++; + } + + return false; +} + +static void string_to_logfmt(BUFFER *wb, const char *s) { + bool spaces = needs_quotes_for_logfmt(s); - stdaccess = open_log_file(stdaccess_fd, stdaccess, stdaccess_filename, &access_log_syslog, 1, &stdaccess_fd); + if(spaces) + buffer_fast_strcat(wb, "\"", 1); - stdhealth = open_log_file(stdhealth_fd, stdhealth, stdhealth_filename, &health_log_syslog, 1, &stdhealth_fd); + buffer_json_strcat(wb, s); + + if(spaces) + buffer_fast_strcat(wb, "\"", 1); } -// ---------------------------------------------------------------------------- -// error log throttling +static void nd_logger_logfmt(BUFFER *wb, struct log_field *fields, size_t fields_max) { + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + CLEAN_BUFFER *tmp = NULL; -time_t error_log_throttle_period = 1200; -unsigned long error_log_errors_per_period = 200; -unsigned long error_log_errors_per_period_backup = 0; + for (size_t i = 0; i < fields_max; i++) { + if (!fields[i].entry.set || !fields[i].logfmt) + continue; -int error_log_limit(int reset) { - static time_t start = 0; - static unsigned long counter = 0, prevented = 0; + const char *key = fields[i].logfmt; - FILE *fp = stderror ? stderror : stderr; + if(fields[i].logfmt_annotator) + fields[i].logfmt_annotator(wb, key, &fields[i]); + else { + if(buffer_strlen(wb)) + buffer_fast_strcat(wb, " ", 1); + + switch(fields[i].entry.type) { + case NDFT_TXT: + if(*fields[i].entry.txt) { + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + string_to_logfmt(wb, fields[i].entry.txt); + } + break; + case NDFT_STR: + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + string_to_logfmt(wb, string2str(fields[i].entry.str)); + break; + case NDFT_BFR: + if(buffer_strlen(fields[i].entry.bfr)) { + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + string_to_logfmt(wb, buffer_tostring(fields[i].entry.bfr)); + } + break; + case NDFT_U64: + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_print_uint64(wb, fields[i].entry.u64); + break; + case NDFT_I64: + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_print_int64(wb, fields[i].entry.i64); + break; + case NDFT_DBL: + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_print_netdata_double(wb, fields[i].entry.dbl); + break; + case NDFT_UUID: { + char u[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(*fields[i].entry.uuid, u); + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + buffer_fast_strcat(wb, u, sizeof(u) - 1); + } + break; + case NDFT_CALLBACK: { + if(!tmp) + tmp = buffer_create(1024, NULL); + else + buffer_flush(tmp); + if(fields[i].entry.cb.formatter(tmp, fields[i].entry.cb.formatter_data)) { + buffer_strcat(wb, key); + buffer_fast_strcat(wb, "=", 1); + string_to_logfmt(wb, buffer_tostring(tmp)); + } + } + break; + default: + buffer_strcat(wb, "UNHANDLED"); + break; + } + } + } +} - // fprintf(fp, "FLOOD: counter=%lu, allowed=%lu, backup=%lu, period=%llu\n", counter, error_log_errors_per_period, error_log_errors_per_period_backup, (unsigned long long)error_log_throttle_period); +// ---------------------------------------------------------------------------- +// journal logger - // do not throttle if the period is 0 - if(error_log_throttle_period == 0) - return 0; +bool nd_log_journal_socket_available(void) { + if(netdata_configured_host_prefix && *netdata_configured_host_prefix) { + char filename[FILENAME_MAX + 1]; - // prevent all logs if the errors per period is 0 - if(error_log_errors_per_period == 0) -#ifdef NETDATA_INTERNAL_CHECKS - return 0; -#else - return 1; -#endif + snprintfz(filename, sizeof(filename), "%s%s", + netdata_configured_host_prefix, "/run/systemd/journal/socket"); - time_t now = now_monotonic_sec(); - if(!start) start = now; - - if(reset) { - if(prevented) { - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf( - fp, - "%s: %s LOG FLOOD PROTECTION reset for process '%s' " - "(prevented %lu logs in the last %"PRId64" seconds).\n", - date, - program_name, - program_name, - prevented, - (int64_t)(now - start)); + if(is_path_unix_socket(filename)) + return true; + } + + return is_path_unix_socket("/run/systemd/journal/socket"); +} + +static bool nd_logger_journal_libsystemd(struct log_field *fields, size_t fields_max) { +#ifdef HAVE_SYSTEMD + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + struct iovec iov[fields_max]; + int iov_count = 0; + + memset(iov, 0, sizeof(iov)); + + CLEAN_BUFFER *tmp = NULL; + + for (size_t i = 0; i < fields_max; i++) { + if (!fields[i].entry.set || !fields[i].journal) + continue; + + const char *key = fields[i].journal; + char *value = NULL; + switch (fields[i].entry.type) { + case NDFT_TXT: + if(*fields[i].entry.txt) + asprintf(&value, "%s=%s", key, fields[i].entry.txt); + break; + case NDFT_STR: + asprintf(&value, "%s=%s", key, string2str(fields[i].entry.str)); + break; + case NDFT_BFR: + if(buffer_strlen(fields[i].entry.bfr)) + asprintf(&value, "%s=%s", key, buffer_tostring(fields[i].entry.bfr)); + break; + case NDFT_U64: + asprintf(&value, "%s=%" PRIu64, key, fields[i].entry.u64); + break; + case NDFT_I64: + asprintf(&value, "%s=%" PRId64, key, fields[i].entry.i64); + break; + case NDFT_DBL: + asprintf(&value, "%s=%f", key, fields[i].entry.dbl); + break; + case NDFT_UUID: { + char u[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(*fields[i].entry.uuid, u); + asprintf(&value, "%s=%s", key, u); + } + break; + case NDFT_CALLBACK: { + if(!tmp) + tmp = buffer_create(1024, NULL); + else + buffer_flush(tmp); + if(fields[i].entry.cb.formatter(tmp, fields[i].entry.cb.formatter_data)) + asprintf(&value, "%s=%s", key, buffer_tostring(tmp)); + } + break; + default: + asprintf(&value, "%s=%s", key, "UNHANDLED"); + break; } - start = now; - counter = 0; - prevented = 0; - } - - // detect if we log too much - counter++; - - if(now - start > error_log_throttle_period) { - if(prevented) { - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf( - fp, - "%s: %s LOG FLOOD PROTECTION resuming logging from process '%s' " - "(prevented %lu logs in the last %"PRId64" seconds).\n", - date, - program_name, - program_name, - prevented, - (int64_t)error_log_throttle_period); + if (value) { + iov[iov_count].iov_base = value; + iov[iov_count].iov_len = strlen(value); + iov_count++; } + } - // restart the period accounting - start = now; - counter = 1; - prevented = 0; + int r = sd_journal_sendv(iov, iov_count); - // log this error - return 0; - } - - if(counter > error_log_errors_per_period) { - if(!prevented) { - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf( - fp, - "%s: %s LOG FLOOD PROTECTION too many logs (%lu logs in %"PRId64" seconds, threshold is set to %lu logs " - "in %"PRId64" seconds). Preventing more logs from process '%s' for %"PRId64" seconds.\n", - date, - program_name, - counter, - (int64_t)(now - start), - error_log_errors_per_period, - (int64_t)error_log_throttle_period, - program_name, - (int64_t)(start + error_log_throttle_period - now)); + // Clean up allocated memory + for (int i = 0; i < iov_count; i++) { + if (iov[i].iov_base != NULL) { + free(iov[i].iov_base); } + } - prevented++; - - // prevent logging this error -#ifdef NETDATA_INTERNAL_CHECKS - return 0; + return r == 0; #else - return 1; + return false; #endif - } - - return 0; } -void error_log_limit_reset(void) { - log_lock(); +static bool nd_logger_journal_direct(struct log_field *fields, size_t fields_max) { + if(!nd_log.journal_direct.initialized) + return false; + + // --- FIELD_PARSER_VERSIONS --- + // + // IMPORTANT: + // THERE ARE 6 VERSIONS OF THIS CODE + // + // 1. journal (direct socket API), + // 2. journal (libsystemd API), + // 3. logfmt, + // 4. json, + // 5. convert to uint64 + // 6. convert to int64 + // + // UPDATE ALL OF THEM FOR NEW FEATURES OR FIXES + + CLEAN_BUFFER *wb = buffer_create(4096, NULL); + CLEAN_BUFFER *tmp = NULL; + + for (size_t i = 0; i < fields_max; i++) { + if (!fields[i].entry.set || !fields[i].journal) + continue; + + const char *key = fields[i].journal; + + const char *s = NULL; + switch(fields[i].entry.type) { + case NDFT_TXT: + s = fields[i].entry.txt; + break; + case NDFT_STR: + s = string2str(fields[i].entry.str); + break; + case NDFT_BFR: + s = buffer_tostring(fields[i].entry.bfr); + break; + case NDFT_U64: + buffer_strcat(wb, key); + buffer_putc(wb, '='); + buffer_print_uint64(wb, fields[i].entry.u64); + buffer_putc(wb, '\n'); + break; + case NDFT_I64: + buffer_strcat(wb, key); + buffer_putc(wb, '='); + buffer_print_int64(wb, fields[i].entry.i64); + buffer_putc(wb, '\n'); + break; + case NDFT_DBL: + buffer_strcat(wb, key); + buffer_putc(wb, '='); + buffer_print_netdata_double(wb, fields[i].entry.dbl); + buffer_putc(wb, '\n'); + break; + case NDFT_UUID:{ + char u[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(*fields[i].entry.uuid, u); + buffer_strcat(wb, key); + buffer_putc(wb, '='); + buffer_fast_strcat(wb, u, sizeof(u) - 1); + buffer_putc(wb, '\n'); + } + break; + case NDFT_CALLBACK: { + if(!tmp) + tmp = buffer_create(1024, NULL); + else + buffer_flush(tmp); + if(fields[i].entry.cb.formatter(tmp, fields[i].entry.cb.formatter_data)) + s = buffer_tostring(tmp); + else + s = NULL; + } + break; + default: + s = "UNHANDLED"; + break; + } - error_log_errors_per_period = error_log_errors_per_period_backup; - error_log_limit(1); + if(s && *s) { + buffer_strcat(wb, key); + if(!strchr(s, '\n')) { + buffer_putc(wb, '='); + buffer_strcat(wb, s); + buffer_putc(wb, '\n'); + } + else { + buffer_putc(wb, '\n'); + size_t size = strlen(s); + uint64_t le_size = htole64(size); + buffer_memcat(wb, &le_size, sizeof(le_size)); + buffer_memcat(wb, s, size); + buffer_putc(wb, '\n'); + } + } + } - log_unlock(); + return journal_direct_send(nd_log.journal_direct.fd, buffer_tostring(wb), buffer_strlen(wb)); } -void error_log_limit_unlimited(void) { - log_lock(); +// ---------------------------------------------------------------------------- +// syslog logger - uses logfmt - error_log_errors_per_period = error_log_errors_per_period_backup; - error_log_limit(1); +static bool nd_logger_syslog(int priority, ND_LOG_FORMAT format, struct log_field *fields, size_t fields_max) { + CLEAN_BUFFER *wb = buffer_create(1024, NULL); - error_log_errors_per_period = ((error_log_errors_per_period_backup * 10) < 10000) ? 10000 : (error_log_errors_per_period_backup * 10); + nd_logger_logfmt(wb, fields, fields_max); + syslog(priority, "%s", buffer_tostring(wb)); - log_unlock(); + return true; } // ---------------------------------------------------------------------------- -// debug log - -void debug_int( const char *file, const char *function, const unsigned long line, const char *fmt, ... ) { - va_list args; +// file logger - uses logfmt - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); +static bool nd_logger_file(FILE *fp, ND_LOG_FORMAT format, struct log_field *fields, size_t fields_max) { + BUFFER *wb = buffer_create(1024, NULL); - va_start( args, fmt ); - printf("%s: %s DEBUG : %s : (%04lu@%-20.20s:%-15.15s): ", date, program_name, netdata_thread_tag(), line, file, function); - vprintf(fmt, args); - va_end( args ); - putchar('\n'); + if(format == NDLF_JSON) + nd_logger_json(wb, fields, fields_max); + else + nd_logger_logfmt(wb, fields, fields_max); - if(output_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_ERR, fmt, args ); - va_end( args ); - } + int r = fprintf(fp, "%s\n", buffer_tostring(wb)); + fflush(fp); - fflush(stdout); + buffer_free(wb); + return r > 0; } // ---------------------------------------------------------------------------- -// info log +// logger router + +static ND_LOG_METHOD nd_logger_select_output(ND_LOG_SOURCES source, FILE **fpp, SPINLOCK **spinlock) { + *spinlock = NULL; + ND_LOG_METHOD output = nd_log.sources[source].method; + + switch(output) { + case NDLM_JOURNAL: + if(unlikely(!nd_log.journal_direct.initialized && !nd_log.journal.initialized)) { + output = NDLM_FILE; + *fpp = stderr; + *spinlock = &nd_log.std_error.spinlock; + } + else { + *fpp = NULL; + *spinlock = NULL; + } + break; -void info_int( int is_collector, const char *file __maybe_unused, const char *function __maybe_unused, const unsigned long line __maybe_unused, const char *fmt, ... ) -{ -#if !defined(NETDATA_INTERNAL_CHECKS) && !defined(NETDATA_DEV_MODE) - if (NETDATA_LOG_LEVEL_INFO > global_log_severity_level) - return; -#endif + case NDLM_SYSLOG: + if(unlikely(!nd_log.syslog.initialized)) { + output = NDLM_FILE; + *spinlock = &nd_log.std_error.spinlock; + *fpp = stderr; + } + else { + *spinlock = NULL; + *fpp = NULL; + } + break; - va_list args; - FILE *fp = (is_collector || !stderror) ? stderr : stderror; + case NDLM_FILE: + if(!nd_log.sources[source].fp) { + *fpp = stderr; + *spinlock = &nd_log.std_error.spinlock; + } + else { + *fpp = nd_log.sources[source].fp; + *spinlock = &nd_log.sources[source].spinlock; + } + break; - log_lock(); + case NDLM_STDOUT: + output = NDLM_FILE; + *fpp = stdout; + *spinlock = &nd_log.std_output.spinlock; + break; - // prevent logging too much - if (error_log_limit(0)) { - log_unlock(); - return; + default: + case NDLM_DEFAULT: + case NDLM_STDERR: + output = NDLM_FILE; + *fpp = stderr; + *spinlock = &nd_log.std_error.spinlock; + break; + + case NDLM_DISABLED: + case NDLM_DEVNULL: + output = NDLM_DISABLED; + *fpp = NULL; + *spinlock = NULL; + break; } - if(collector_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_INFO, fmt, args ); - va_end( args ); + return output; +} + +// ---------------------------------------------------------------------------- +// high level logger + +static void nd_logger_log_fields(SPINLOCK *spinlock, FILE *fp, bool limit, ND_LOG_FIELD_PRIORITY priority, + ND_LOG_METHOD output, struct nd_log_source *source, + struct log_field *fields, size_t fields_max) { + if(spinlock) + spinlock_lock(spinlock); + + // check the limits + if(limit && nd_log_limit_reached(source)) + goto cleanup; + + if(output == NDLM_JOURNAL) { + if(!nd_logger_journal_direct(fields, fields_max) && !nd_logger_journal_libsystemd(fields, fields_max)) { + // we can't log to journal, let's log to stderr + if(spinlock) + spinlock_unlock(spinlock); + + output = NDLM_FILE; + spinlock = &nd_log.std_error.spinlock; + fp = stderr; + + if(spinlock) + spinlock_lock(spinlock); + } } - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); + if(output == NDLM_SYSLOG) + nd_logger_syslog(priority, source->format, fields, fields_max); - va_start( args, fmt ); -#ifdef NETDATA_INTERNAL_CHECKS - fprintf(fp, "%s: %s INFO : %s : (%04lu@%-20.20s:%-15.15s): ", - date, program_name, netdata_thread_tag(), line, file, function); -#else - fprintf(fp, "%s: %s INFO : %s : ", date, program_name, netdata_thread_tag()); -#endif - vfprintf(fp, fmt, args ); - va_end( args ); + if(output == NDLM_FILE) + nd_logger_file(fp, source->format, fields, fields_max); - fputc('\n', fp); - log_unlock(); +cleanup: + if(spinlock) + spinlock_unlock(spinlock); } -// ---------------------------------------------------------------------------- -// error log +static void nd_logger_unset_all_thread_fields(void) { + size_t fields_max = THREAD_FIELDS_MAX; + for(size_t i = 0; i < fields_max ; i++) + thread_log_fields[i].entry.set = false; +} -#if defined(STRERROR_R_CHAR_P) -// GLIBC version of strerror_r -static const char *strerror_result(const char *a, const char *b) { (void)b; return a; } -#elif defined(HAVE_STRERROR_R) -// POSIX version of strerror_r -static const char *strerror_result(int a, const char *b) { (void)a; return b; } -#elif defined(HAVE_C__GENERIC) +static void nd_logger_merge_log_stack_to_thread_fields(void) { + for(size_t c = 0; c < thread_log_stack_next ;c++) { + struct log_stack_entry *lgs = thread_log_stack_base[c]; -// what a trick! -// http://stackoverflow.com/questions/479207/function-overloading-in-c -static const char *strerror_result_int(int a, const char *b) { (void)a; return b; } -static const char *strerror_result_string(const char *a, const char *b) { (void)b; return a; } + for(size_t i = 0; lgs[i].id != NDF_STOP ; i++) { + if(lgs[i].id >= _NDF_MAX || !lgs[i].set) + continue; -#define strerror_result(a, b) _Generic((a), \ - int: strerror_result_int, \ - char *: strerror_result_string \ - )(a, b) + struct log_stack_entry *e = &lgs[i]; + ND_LOG_STACK_FIELD_TYPE type = lgs[i].type; -#else -#error "cannot detect the format of function strerror_r()" -#endif + // do not add empty / unset fields + if((type == NDFT_TXT && (!e->txt || !*e->txt)) || + (type == NDFT_BFR && (!e->bfr || !buffer_strlen(e->bfr))) || + (type == NDFT_STR && !e->str) || + (type == NDFT_UUID && !e->uuid) || + (type == NDFT_CALLBACK && !e->cb.formatter) || + type == NDFT_UNSET) + continue; -void error_limit_int(ERROR_LIMIT *erl, const char *prefix, const char *file __maybe_unused, const char *function __maybe_unused, const unsigned long line __maybe_unused, const char *fmt, ... ) { - FILE *fp = stderror ? stderror : stderr; + thread_log_fields[lgs[i].id].entry = *e; + } + } +} - if(erl->sleep_ut) - sleep_usec(erl->sleep_ut); +static void nd_logger(const char *file, const char *function, const unsigned long line, + ND_LOG_SOURCES source, ND_LOG_FIELD_PRIORITY priority, bool limit, int saved_errno, + const char *fmt, va_list ap) { - // save a copy of errno - just in case this function generates a new error - int __errno = errno; + SPINLOCK *spinlock; + FILE *fp; + ND_LOG_METHOD output = nd_logger_select_output(source, &fp, &spinlock); + if(output != NDLM_FILE && output != NDLM_JOURNAL && output != NDLM_SYSLOG) + return; - va_list args; + // mark all fields as unset + nd_logger_unset_all_thread_fields(); - log_lock(); + // flatten the log stack into the fields + nd_logger_merge_log_stack_to_thread_fields(); - erl->count++; - time_t now = now_boottime_sec(); - if(now - erl->last_logged < erl->log_every) { - log_unlock(); - return; + // set the common fields that are automatically set by the logging subsystem + + if(likely(!thread_log_fields[NDF_INVOCATION_ID].entry.set)) + thread_log_fields[NDF_INVOCATION_ID].entry = ND_LOG_FIELD_UUID(NDF_INVOCATION_ID, &nd_log.invocation_id); + + if(likely(!thread_log_fields[NDF_LOG_SOURCE].entry.set)) + thread_log_fields[NDF_LOG_SOURCE].entry = ND_LOG_FIELD_TXT(NDF_LOG_SOURCE, nd_log_id2source(source)); + else { + ND_LOG_SOURCES src = source; + + if(thread_log_fields[NDF_LOG_SOURCE].entry.type == NDFT_TXT) + src = nd_log_source2id(thread_log_fields[NDF_LOG_SOURCE].entry.txt, source); + else if(thread_log_fields[NDF_LOG_SOURCE].entry.type == NDFT_U64) + src = thread_log_fields[NDF_LOG_SOURCE].entry.u64; + + if(src != source && src >= 0 && src < _NDLS_MAX) { + source = src; + output = nd_logger_select_output(source, &fp, &spinlock); + if(output != NDLM_FILE && output != NDLM_JOURNAL && output != NDLM_SYSLOG) + return; + } } - // prevent logging too much - if (error_log_limit(0)) { - log_unlock(); - return; + if(likely(!thread_log_fields[NDF_SYSLOG_IDENTIFIER].entry.set)) + thread_log_fields[NDF_SYSLOG_IDENTIFIER].entry = ND_LOG_FIELD_TXT(NDF_SYSLOG_IDENTIFIER, program_name); + + if(likely(!thread_log_fields[NDF_LINE].entry.set)) { + thread_log_fields[NDF_LINE].entry = ND_LOG_FIELD_U64(NDF_LINE, line); + thread_log_fields[NDF_FILE].entry = ND_LOG_FIELD_TXT(NDF_FILE, file); + thread_log_fields[NDF_FUNC].entry = ND_LOG_FIELD_TXT(NDF_FUNC, function); } - if(collector_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_ERR, fmt, args ); - va_end( args ); + if(likely(!thread_log_fields[NDF_PRIORITY].entry.set)) { + thread_log_fields[NDF_PRIORITY].entry = ND_LOG_FIELD_U64(NDF_PRIORITY, priority); } - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); + if(likely(!thread_log_fields[NDF_TID].entry.set)) + thread_log_fields[NDF_TID].entry = ND_LOG_FIELD_U64(NDF_TID, gettid()); - va_start( args, fmt ); -#ifdef NETDATA_INTERNAL_CHECKS - fprintf(fp, "%s: %s %-5.5s : %s : (%04lu@%-20.20s:%-15.15s): ", - date, program_name, prefix, netdata_thread_tag(), line, file, function); -#else - fprintf(fp, "%s: %s %-5.5s : %s : ", date, program_name, prefix, netdata_thread_tag()); -#endif - vfprintf(fp, fmt, args ); - va_end( args ); + char os_threadname[NETDATA_THREAD_NAME_MAX + 1]; + if(likely(!thread_log_fields[NDF_THREAD_TAG].entry.set)) { + const char *thread_tag = netdata_thread_tag(); + if(!netdata_thread_tag_exists()) { + if (!netdata_thread_tag_exists()) { + os_thread_get_current_name_np(os_threadname); + if ('\0' != os_threadname[0]) + /* If it is not an empty string replace "MAIN" thread_tag */ + thread_tag = os_threadname; + } + } + thread_log_fields[NDF_THREAD_TAG].entry = ND_LOG_FIELD_TXT(NDF_THREAD_TAG, thread_tag); - if(erl->count > 1) - fprintf(fp, " (similar messages repeated %zu times in the last %llu secs)", - erl->count, (unsigned long long)(erl->last_logged ? now - erl->last_logged : 0)); + // TODO: fix the ND_MODULE in logging by setting proper module name in threads +// if(!thread_log_fields[NDF_MODULE].entry.set) +// thread_log_fields[NDF_MODULE].entry = ND_LOG_FIELD_CB(NDF_MODULE, thread_tag_to_module, (void *)thread_tag); + } - if(erl->sleep_ut) - fprintf(fp, " (sleeping for %"PRIu64" microseconds every time this happens)", erl->sleep_ut); + if(likely(!thread_log_fields[NDF_TIMESTAMP_REALTIME_USEC].entry.set)) + thread_log_fields[NDF_TIMESTAMP_REALTIME_USEC].entry = ND_LOG_FIELD_U64(NDF_TIMESTAMP_REALTIME_USEC, now_realtime_usec()); - if(__errno) { - char buf[1024]; - fprintf(fp, - " (errno %d, %s)\n", __errno, strerror_result(strerror_r(__errno, buf, 1023), buf)); - errno = 0; + if(saved_errno != 0 && !thread_log_fields[NDF_ERRNO].entry.set) + thread_log_fields[NDF_ERRNO].entry = ND_LOG_FIELD_I64(NDF_ERRNO, saved_errno); + + CLEAN_BUFFER *wb = NULL; + if(fmt && !thread_log_fields[NDF_MESSAGE].entry.set) { + wb = buffer_create(1024, NULL); + buffer_vsprintf(wb, fmt, ap); + thread_log_fields[NDF_MESSAGE].entry = ND_LOG_FIELD_TXT(NDF_MESSAGE, buffer_tostring(wb)); } - else - fputc('\n', fp); - erl->last_logged = now; - erl->count = 0; + nd_logger_log_fields(spinlock, fp, limit, priority, output, &nd_log.sources[source], + thread_log_fields, THREAD_FIELDS_MAX); - log_unlock(); -} + if(nd_log.sources[source].pending_msg) { + // log a pending message -void error_int(int is_collector, const char *prefix, const char *file __maybe_unused, const char *function __maybe_unused, const unsigned long line __maybe_unused, const char *fmt, ... ) { -#if !defined(NETDATA_INTERNAL_CHECKS) && !defined(NETDATA_DEV_MODE) - if (NETDATA_LOG_LEVEL_ERROR > global_log_severity_level) - return; -#endif + nd_logger_unset_all_thread_fields(); - // save a copy of errno - just in case this function generates a new error - int __errno = errno; - FILE *fp = (is_collector || !stderror) ? stderr : stderror; + thread_log_fields[NDF_TIMESTAMP_REALTIME_USEC].entry = (struct log_stack_entry){ + .set = true, + .type = NDFT_U64, + .u64 = now_realtime_usec(), + }; - va_list args; + thread_log_fields[NDF_LOG_SOURCE].entry = (struct log_stack_entry){ + .set = true, + .type = NDFT_TXT, + .txt = nd_log_id2source(source), + }; - log_lock(); + thread_log_fields[NDF_SYSLOG_IDENTIFIER].entry = (struct log_stack_entry){ + .set = true, + .type = NDFT_TXT, + .txt = program_name, + }; - // prevent logging too much - if (error_log_limit(0)) { - log_unlock(); - return; - } + thread_log_fields[NDF_MESSAGE].entry = (struct log_stack_entry){ + .set = true, + .type = NDFT_TXT, + .txt = nd_log.sources[source].pending_msg, + }; + + nd_logger_log_fields(spinlock, fp, false, priority, output, + &nd_log.sources[source], + thread_log_fields, THREAD_FIELDS_MAX); - if(collector_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_ERR, fmt, args ); - va_end( args ); + freez((void *)nd_log.sources[source].pending_msg); + nd_log.sources[source].pending_msg = NULL; } - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); + errno = 0; +} - va_start( args, fmt ); -#ifdef NETDATA_INTERNAL_CHECKS - fprintf(fp, "%s: %s %-5.5s : %s : (%04lu@%-20.20s:%-15.15s): ", - date, program_name, prefix, netdata_thread_tag(), line, file, function); -#else - fprintf(fp, "%s: %s %-5.5s : %s : ", date, program_name, prefix, netdata_thread_tag()); -#endif - vfprintf(fp, fmt, args ); - va_end( args ); +static ND_LOG_SOURCES nd_log_validate_source(ND_LOG_SOURCES source) { + if(source >= _NDLS_MAX) + source = NDLS_DAEMON; - if(__errno) { - char buf[1024]; - fprintf(fp, - " (errno %d, %s)\n", __errno, strerror_result(strerror_r(__errno, buf, 1023), buf)); - errno = 0; - } - else - fputc('\n', fp); + if(overwrite_thread_source) + source = overwrite_thread_source; - log_unlock(); -} + if(nd_log.overwrite_process_source) + source = nd_log.overwrite_process_source; -#ifdef NETDATA_INTERNAL_CHECKS -static void crash_netdata(void) { - // make Netdata core dump - abort(); + return source; } -#endif -#ifdef HAVE_BACKTRACE -#define BT_BUF_SIZE 100 -static void print_call_stack(void) { - FILE *fp = (!stderror) ? stderr : stderror; +// ---------------------------------------------------------------------------- +// public API for loggers - int nptrs; - void *buffer[BT_BUF_SIZE]; +void netdata_logger(ND_LOG_SOURCES source, ND_LOG_FIELD_PRIORITY priority, const char *file, const char *function, unsigned long line, const char *fmt, ... ) { + int saved_errno = errno; + source = nd_log_validate_source(source); - nptrs = backtrace(buffer, BT_BUF_SIZE); - if(nptrs) - backtrace_symbols_fd(buffer, nptrs, fileno(fp)); + if (source != NDLS_DEBUG && priority > nd_log.sources[source].min_priority) + return; + + va_list args; + va_start(args, fmt); + nd_logger(file, function, line, source, priority, + source == NDLS_DAEMON || source == NDLS_COLLECTORS, + saved_errno, fmt, args); + va_end(args); } -#endif -void fatal_int( const char *file, const char *function, const unsigned long line, const char *fmt, ... ) { - FILE *fp = stderror ? stderror : stderr; +void netdata_logger_with_limit(ERROR_LIMIT *erl, ND_LOG_SOURCES source, ND_LOG_FIELD_PRIORITY priority, const char *file __maybe_unused, const char *function __maybe_unused, const unsigned long line __maybe_unused, const char *fmt, ... ) { + int saved_errno = errno; + source = nd_log_validate_source(source); - // save a copy of errno - just in case this function generates a new error - int __errno = errno; - va_list args; - const char *thread_tag; - char os_threadname[NETDATA_THREAD_NAME_MAX + 1]; + if (source != NDLS_DEBUG && priority > nd_log.sources[source].min_priority) + return; - if(collector_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_CRIT, fmt, args ); - va_end( args ); - } + if(erl->sleep_ut) + sleep_usec(erl->sleep_ut); - thread_tag = netdata_thread_tag(); - if (!netdata_thread_tag_exists()) { - os_thread_get_current_name_np(os_threadname); - if ('\0' != os_threadname[0]) { /* If it is not an empty string replace "MAIN" thread_tag */ - thread_tag = os_threadname; - } + spinlock_lock(&erl->spinlock); + + erl->count++; + time_t now = now_boottime_sec(); + if(now - erl->last_logged < erl->log_every) { + spinlock_unlock(&erl->spinlock); + return; } - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); + spinlock_unlock(&erl->spinlock); - log_lock(); + va_list args; + va_start(args, fmt); + nd_logger(file, function, line, source, priority, + source == NDLS_DAEMON || source == NDLS_COLLECTORS, + saved_errno, fmt, args); + va_end(args); + erl->last_logged = now; + erl->count = 0; +} - va_start( args, fmt ); -#ifdef NETDATA_INTERNAL_CHECKS - fprintf(fp, - "%s: %s FATAL : %s : (%04lu@%-20.20s:%-15.15s): ", date, program_name, thread_tag, line, file, function); -#else - fprintf(fp, "%s: %s FATAL : %s : ", date, program_name, thread_tag); -#endif - vfprintf(fp, fmt, args ); - va_end( args ); +void netdata_logger_fatal( const char *file, const char *function, const unsigned long line, const char *fmt, ... ) { + int saved_errno = errno; + ND_LOG_SOURCES source = NDLS_DAEMON; + source = nd_log_validate_source(source); - perror(" # "); - fputc('\n', fp); + va_list args; + va_start(args, fmt); + nd_logger(file, function, line, source, NDLP_ALERT, true, saved_errno, fmt, args); + va_end(args); - log_unlock(); + char date[LOG_DATE_LENGTH]; + log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); char action_data[70+1]; - snprintfz(action_data, 70, "%04lu@%-10.10s:%-15.15s/%d", line, file, function, __errno); + snprintfz(action_data, 70, "%04lu@%-10.10s:%-15.15s/%d", line, file, function, saved_errno); char action_result[60+1]; + char os_threadname[NETDATA_THREAD_NAME_MAX + 1]; + const char *thread_tag = netdata_thread_tag(); + if(!netdata_thread_tag_exists()) { + if (!netdata_thread_tag_exists()) { + os_thread_get_current_name_np(os_threadname); + if ('\0' != os_threadname[0]) + /* If it is not an empty string replace "MAIN" thread_tag */ + thread_tag = os_threadname; + } + } + if(!thread_tag) + thread_tag = "UNKNOWN"; + const char *tag_to_send = thread_tag; // anonymize thread names @@ -1045,129 +2312,120 @@ void fatal_int( const char *file, const char *function, const unsigned long line send_statistics("FATAL", action_result, action_data); #ifdef HAVE_BACKTRACE - print_call_stack(); + int fd = nd_log.sources[NDLS_DAEMON].fd; + if(fd == -1) + fd = STDERR_FILENO; + + int nptrs; + void *buffer[10000]; + + nptrs = backtrace(buffer, sizeof(buffer)); + if(nptrs) + backtrace_symbols_fd(buffer, nptrs, fd); #endif #ifdef NETDATA_INTERNAL_CHECKS - crash_netdata(); + abort(); #endif netdata_cleanup_and_exit(1); } // ---------------------------------------------------------------------------- -// access log - -void netdata_log_access( const char *fmt, ... ) { - va_list args; - - if(access_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_INFO, fmt, args ); - va_end( args ); - } - - if(stdaccess) { - static netdata_mutex_t access_mutex = NETDATA_MUTEX_INITIALIZER; - - if(web_server_is_multithreaded) - netdata_mutex_lock(&access_mutex); +// log limits - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf(stdaccess, "%s: ", date); +void nd_log_limits_reset(void) { + usec_t now_ut = now_monotonic_usec(); - va_start( args, fmt ); - vfprintf( stdaccess, fmt, args ); - va_end( args ); - fputc('\n', stdaccess); + spinlock_lock(&nd_log.std_output.spinlock); + spinlock_lock(&nd_log.std_error.spinlock); - if(web_server_is_multithreaded) - netdata_mutex_unlock(&access_mutex); + for(size_t i = 0; i < _NDLS_MAX ;i++) { + spinlock_lock(&nd_log.sources[i].spinlock); + nd_log.sources[i].limits.prevented = 0; + nd_log.sources[i].limits.counter = 0; + nd_log.sources[i].limits.started_monotonic_ut = now_ut; + nd_log.sources[i].limits.logs_per_period = nd_log.sources[i].limits.logs_per_period_backup; + spinlock_unlock(&nd_log.sources[i].spinlock); } -} - -// ---------------------------------------------------------------------------- -// health log -void netdata_log_health( const char *fmt, ... ) { - va_list args; + spinlock_unlock(&nd_log.std_output.spinlock); + spinlock_unlock(&nd_log.std_error.spinlock); +} - if(health_log_syslog) { - va_start( args, fmt ); - vsyslog(LOG_INFO, fmt, args ); - va_end( args ); +void nd_log_limits_unlimited(void) { + nd_log_limits_reset(); + for(size_t i = 0; i < _NDLS_MAX ;i++) { + nd_log.sources[i].limits.logs_per_period = 0; } +} - if(stdhealth) { - static netdata_mutex_t health_mutex = NETDATA_MUTEX_INITIALIZER; +static bool nd_log_limit_reached(struct nd_log_source *source) { + if(source->limits.throttle_period == 0 || source->limits.logs_per_period == 0) + return false; - if(web_server_is_multithreaded) - netdata_mutex_lock(&health_mutex); + usec_t now_ut = now_monotonic_usec(); + if(!source->limits.started_monotonic_ut) + source->limits.started_monotonic_ut = now_ut; - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf(stdhealth, "%s: ", date); + source->limits.counter++; - va_start( args, fmt ); - vfprintf( stdhealth, fmt, args ); - va_end( args ); - fputc('\n', stdhealth); + if(now_ut - source->limits.started_monotonic_ut > (usec_t)source->limits.throttle_period) { + if(source->limits.prevented) { + BUFFER *wb = buffer_create(1024, NULL); + buffer_sprintf(wb, + "LOG FLOOD PROTECTION: resuming logging " + "(prevented %"PRIu32" logs in the last %"PRIu32" seconds).", + source->limits.prevented, + source->limits.throttle_period); - if(web_server_is_multithreaded) - netdata_mutex_unlock(&health_mutex); - } -} + if(source->pending_msg) + freez((void *)source->pending_msg); -#ifdef ENABLE_ACLK -void log_aclk_message_bin( const char *data, const size_t data_len, int tx, const char *mqtt_topic, const char *message_name) { - if (aclklog) { - static netdata_mutex_t aclklog_mutex = NETDATA_MUTEX_INITIALIZER; - netdata_mutex_lock(&aclklog_mutex); + source->pending_msg = strdupz(buffer_tostring(wb)); - char date[LOG_DATE_LENGTH]; - log_date(date, LOG_DATE_LENGTH, now_realtime_sec()); - fprintf(aclklog, "%s: %s Msg:\"%s\", MQTT-topic:\"%s\": ", date, tx ? "OUTGOING" : "INCOMING", message_name, mqtt_topic); - - fwrite(data, data_len, 1, aclklog); + buffer_free(wb); + } - fputc('\n', aclklog); + // restart the period accounting + source->limits.started_monotonic_ut = now_ut; + source->limits.counter = 1; + source->limits.prevented = 0; - netdata_mutex_unlock(&aclklog_mutex); + // log this error + return false; } -} -#endif -void log_set_global_severity_level(netdata_log_level_t value) -{ - global_log_severity_level = value; -} + if(source->limits.counter > source->limits.logs_per_period) { + if(!source->limits.prevented) { + BUFFER *wb = buffer_create(1024, NULL); + buffer_sprintf(wb, + "LOG FLOOD PROTECTION: too many logs (%"PRIu32" logs in %"PRId64" seconds, threshold is set to %"PRIu32" logs " + "in %"PRIu32" seconds). Preventing more logs from process '%s' for %"PRId64" seconds.", + source->limits.counter, + (int64_t)((now_ut - source->limits.started_monotonic_ut) / USEC_PER_SEC), + source->limits.logs_per_period, + source->limits.throttle_period, + program_name, + (int64_t)((source->limits.started_monotonic_ut + (source->limits.throttle_period * USEC_PER_SEC) - now_ut)) / USEC_PER_SEC); + + if(source->pending_msg) + freez((void *)source->pending_msg); + + source->pending_msg = strdupz(buffer_tostring(wb)); + + buffer_free(wb); + } -netdata_log_level_t log_severity_string_to_severity_level(char *level) -{ - if (!strcmp(level, NETDATA_LOG_LEVEL_INFO_STR)) - return NETDATA_LOG_LEVEL_INFO; - if (!strcmp(level, NETDATA_LOG_LEVEL_ERROR_STR) || !strcmp(level, NETDATA_LOG_LEVEL_ERROR_SHORT_STR)) - return NETDATA_LOG_LEVEL_ERROR; + source->limits.prevented++; - return NETDATA_LOG_LEVEL_INFO; -} - -char *log_severity_level_to_severity_string(netdata_log_level_t level) -{ - switch (level) { - case NETDATA_LOG_LEVEL_ERROR: - return NETDATA_LOG_LEVEL_ERROR_STR; - case NETDATA_LOG_LEVEL_INFO: - default: - return NETDATA_LOG_LEVEL_INFO_STR; + // prevent logging this error +#ifdef NETDATA_INTERNAL_CHECKS + return false; +#else + return true; +#endif } -} -void log_set_global_severity_for_external_plugins() { - char *s = getenv("NETDATA_LOG_SEVERITY_LEVEL"); - if (!s) - return; - netdata_log_level_t level = log_severity_string_to_severity_level(s); - log_set_global_severity_level(level); + return false; } diff --git a/libnetdata/log/log.h b/libnetdata/log/log.h index cf0865cf..ad634693 100644 --- a/libnetdata/log/log.h +++ b/libnetdata/log/log.h @@ -9,6 +9,184 @@ extern "C" { #include "../libnetdata.h" +#define ND_LOG_DEFAULT_THROTTLE_LOGS 1000 +#define ND_LOG_DEFAULT_THROTTLE_PERIOD 60 + +typedef enum __attribute__((__packed__)) { + NDLS_UNSET = 0, // internal use only + NDLS_ACCESS, // access.log + NDLS_ACLK, // aclk.log + NDLS_COLLECTORS, // collectors.log + NDLS_DAEMON, // error.log + NDLS_HEALTH, // health.log + NDLS_DEBUG, // debug.log + + // terminator + _NDLS_MAX, +} ND_LOG_SOURCES; + +typedef enum __attribute__((__packed__)) { + NDLP_EMERG = LOG_EMERG, + NDLP_ALERT = LOG_ALERT, + NDLP_CRIT = LOG_CRIT, + NDLP_ERR = LOG_ERR, + NDLP_WARNING = LOG_WARNING, + NDLP_NOTICE = LOG_NOTICE, + NDLP_INFO = LOG_INFO, + NDLP_DEBUG = LOG_DEBUG, +} ND_LOG_FIELD_PRIORITY; + +typedef enum __attribute__((__packed__)) { + // KEEP THESE IN THE SAME ORDER AS in thread_log_fields (log.c) + // so that it easy to audit for missing fields + + NDF_STOP = 0, + NDF_TIMESTAMP_REALTIME_USEC, // the timestamp of the log message - added automatically + NDF_SYSLOG_IDENTIFIER, // the syslog identifier of the application - added automatically + NDF_LOG_SOURCE, // DAEMON, COLLECTORS, HEALTH, ACCESS, ACLK - set at the log call + NDF_PRIORITY, // the syslog priority (severity) - set at the log call + NDF_ERRNO, // the ERRNO at the time of the log call - added automatically + NDF_INVOCATION_ID, // the INVOCATION_ID of Netdata - added automatically + NDF_LINE, // the source code file line number - added automatically + NDF_FILE, // the source code filename - added automatically + NDF_FUNC, // the source code function - added automatically + NDF_TID, // the thread ID of the thread logging - added automatically + NDF_THREAD_TAG, // the thread tag of the thread logging - added automatically + NDF_MESSAGE_ID, // for specific events + NDF_MODULE, // for internal plugin module, all other get the NDF_THREAD_TAG + + NDF_NIDL_NODE, // the node / rrdhost currently being worked + NDF_NIDL_INSTANCE, // the instance / rrdset currently being worked + NDF_NIDL_CONTEXT, // the context of the instance currently being worked + NDF_NIDL_DIMENSION, // the dimension / rrddim currently being worked + + // web server, aclk and stream receiver + NDF_SRC_TRANSPORT, // the transport we received the request, one of: http, https, pluginsd + + // web server and stream receiver + NDF_SRC_IP, // the streaming / web server source IP + NDF_SRC_PORT, // the streaming / web server source Port + NDF_SRC_CAPABILITIES, // the stream receiver capabilities + + // stream sender (established links) + NDF_DST_TRANSPORT, // the transport we send the request, one of: http, https + NDF_DST_IP, // the destination streaming IP + NDF_DST_PORT, // the destination streaming Port + NDF_DST_CAPABILITIES, // the destination streaming capabilities + + // web server, aclk and stream receiver + NDF_REQUEST_METHOD, // for http like requests, the http request method + NDF_RESPONSE_CODE, // for http like requests, the http response code, otherwise a status string + + // web server (all), aclk (queries) + NDF_CONNECTION_ID, // the web server connection ID + NDF_TRANSACTION_ID, // the web server and API transaction ID + NDF_RESPONSE_SENT_BYTES, // for http like requests, the response bytes + NDF_RESPONSE_SIZE_BYTES, // for http like requests, the uncompressed response size + NDF_RESPONSE_PREPARATION_TIME_USEC, // for http like requests, the preparation time + NDF_RESPONSE_SENT_TIME_USEC, // for http like requests, the time to send the response back + NDF_RESPONSE_TOTAL_TIME_USEC, // for http like requests, the total time to complete the response + + // health alerts + NDF_ALERT_ID, + NDF_ALERT_UNIQUE_ID, + NDF_ALERT_EVENT_ID, + NDF_ALERT_TRANSITION_ID, + NDF_ALERT_CONFIG_HASH, + NDF_ALERT_NAME, + NDF_ALERT_CLASS, + NDF_ALERT_COMPONENT, + NDF_ALERT_TYPE, + NDF_ALERT_EXEC, + NDF_ALERT_RECIPIENT, + NDF_ALERT_DURATION, + NDF_ALERT_VALUE, + NDF_ALERT_VALUE_OLD, + NDF_ALERT_STATUS, + NDF_ALERT_STATUS_OLD, + NDF_ALERT_SOURCE, + NDF_ALERT_UNITS, + NDF_ALERT_SUMMARY, + NDF_ALERT_INFO, + NDF_ALERT_NOTIFICATION_REALTIME_USEC, + // NDF_ALERT_FLAGS, + + // put new items here + // leave the request URL and the message last + + NDF_REQUEST, // the request we are currently working on + NDF_MESSAGE, // the log message, if any + + // terminator + _NDF_MAX, +} ND_LOG_FIELD_ID; + +typedef enum __attribute__((__packed__)) { + NDFT_UNSET = 0, + NDFT_TXT, + NDFT_STR, + NDFT_BFR, + NDFT_U64, + NDFT_I64, + NDFT_DBL, + NDFT_UUID, + NDFT_CALLBACK, +} ND_LOG_STACK_FIELD_TYPE; + +void nd_log_set_user_settings(ND_LOG_SOURCES source, const char *setting); +void nd_log_set_facility(const char *facility); +void nd_log_set_priority_level(const char *setting); +void nd_log_initialize(void); +void nd_log_reopen_log_files(void); +void chown_open_file(int fd, uid_t uid, gid_t gid); +void nd_log_chown_log_files(uid_t uid, gid_t gid); +void nd_log_set_flood_protection(size_t logs, time_t period); +void nd_log_initialize_for_external_plugins(const char *name); +void nd_log_set_thread_source(ND_LOG_SOURCES source); +bool nd_log_journal_socket_available(void); +ND_LOG_FIELD_ID nd_log_field_id_by_name(const char *field, size_t len); +int nd_log_priority2id(const char *priority); +const char *nd_log_id2priority(ND_LOG_FIELD_PRIORITY priority); +const char *nd_log_method_for_external_plugins(const char *s); + +int nd_log_health_fd(void); +typedef bool (*log_formatter_callback_t)(BUFFER *wb, void *data); + +struct log_stack_entry { + ND_LOG_FIELD_ID id; + ND_LOG_STACK_FIELD_TYPE type; + bool set; + union { + const char *txt; + struct netdata_string *str; + BUFFER *bfr; + uint64_t u64; + int64_t i64; + double dbl; + const uuid_t *uuid; + struct { + log_formatter_callback_t formatter; + void *formatter_data; + } cb; + }; +}; + +#define ND_LOG_STACK _cleanup_(log_stack_pop) struct log_stack_entry +#define ND_LOG_STACK_PUSH(lgs) log_stack_push(lgs) + +#define ND_LOG_FIELD_TXT(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_TXT, .txt = (value), .set = true, } +#define ND_LOG_FIELD_STR(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_STR, .str = (value), .set = true, } +#define ND_LOG_FIELD_BFR(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_BFR, .bfr = (value), .set = true, } +#define ND_LOG_FIELD_U64(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_U64, .u64 = (value), .set = true, } +#define ND_LOG_FIELD_I64(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_I64, .i64 = (value), .set = true, } +#define ND_LOG_FIELD_DBL(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_DBL, .dbl = (value), .set = true, } +#define ND_LOG_FIELD_CB(field, func, data) (struct log_stack_entry){ .id = (field), .type = NDFT_CALLBACK, .cb = { .formatter = (func), .formatter_data = (data) }, .set = true, } +#define ND_LOG_FIELD_UUID(field, value) (struct log_stack_entry){ .id = (field), .type = NDFT_UUID, .uuid = (value), .set = true, } +#define ND_LOG_FIELD_END() (struct log_stack_entry){ .id = NDF_STOP, .type = NDFT_UNSET, .set = false, } + +void log_stack_pop(void *ptr); +void log_stack_push(struct log_stack_entry *lgs); + #define D_WEB_BUFFER 0x0000000000000001 #define D_WEB_CLIENT 0x0000000000000002 #define D_LISTENER 0x0000000000000004 @@ -46,114 +224,75 @@ extern "C" { #define D_REPLICATION 0x0000002000000000 #define D_SYSTEM 0x8000000000000000 -extern int web_server_is_multithreaded; - extern uint64_t debug_flags; extern const char *program_name; -extern int stdaccess_fd; -extern FILE *stdaccess; +#ifdef ENABLE_ACLK +extern int aclklog_enabled; +#endif -extern int stdhealth_fd; -extern FILE *stdhealth; +#define LOG_DATE_LENGTH 26 +void log_date(char *buffer, size_t len, time_t now); -extern int stdcollector_fd; -extern FILE *stderror; +static inline void debug_dummy(void) {} -extern const char *stdaccess_filename; -extern const char *stderr_filename; -extern const char *stdout_filename; -extern const char *stdhealth_filename; -extern const char *stdcollector_filename; -extern const char *facility_log; +void nd_log_limits_reset(void); +void nd_log_limits_unlimited(void); -#ifdef ENABLE_ACLK -extern const char *aclklog_filename; -extern int aclklog_fd; -extern FILE *aclklog; -extern int aclklog_enabled; +#define NDLP_INFO_STR "info" + +#ifdef NETDATA_INTERNAL_CHECKS +#define netdata_log_debug(type, args...) do { if(unlikely(debug_flags & type)) netdata_logger(NDLS_DEBUG, NDLP_DEBUG, __FILE__, __FUNCTION__, __LINE__, ##args); } while(0) +#define internal_error(condition, args...) do { if(unlikely(condition)) netdata_logger(NDLS_DAEMON, NDLP_DEBUG, __FILE__, __FUNCTION__, __LINE__, ##args); } while(0) +#define internal_fatal(condition, args...) do { if(unlikely(condition)) netdata_logger_fatal(__FILE__, __FUNCTION__, __LINE__, ##args); } while(0) +#else +#define netdata_log_debug(type, args...) debug_dummy() +#define internal_error(args...) debug_dummy() +#define internal_fatal(args...) debug_dummy() #endif -extern int access_log_syslog; -extern int error_log_syslog; -extern int output_log_syslog; -extern int health_log_syslog; +#define fatal(args...) netdata_logger_fatal(__FILE__, __FUNCTION__, __LINE__, ##args) +#define fatal_assert(expr) ((expr) ? (void)(0) : netdata_logger_fatal(__FILE__, __FUNCTION__, __LINE__, "Assertion `%s' failed", #expr)) -extern time_t error_log_throttle_period; -extern unsigned long error_log_errors_per_period, error_log_errors_per_period_backup; -int error_log_limit(int reset); +// ---------------------------------------------------------------------------- +// normal logging -void open_all_log_files(); -void reopen_all_log_files(); +void netdata_logger(ND_LOG_SOURCES source, ND_LOG_FIELD_PRIORITY priority, const char *file, const char *function, unsigned long line, const char *fmt, ... ) PRINTFLIKE(6, 7); +#define nd_log(NDLS, NDLP, args...) netdata_logger(NDLS, NDLP, __FILE__, __FUNCTION__, __LINE__, ##args) +#define nd_log_daemon(NDLP, args...) netdata_logger(NDLS_DAEMON, NDLP, __FILE__, __FUNCTION__, __LINE__, ##args) +#define nd_log_collector(NDLP, args...) netdata_logger(NDLS_COLLECTORS, NDLP, __FILE__, __FUNCTION__, __LINE__, ##args) -#define LOG_DATE_LENGTH 26 -void log_date(char *buffer, size_t len, time_t now); +#define netdata_log_info(args...) netdata_logger(NDLS_DAEMON, NDLP_INFO, __FILE__, __FUNCTION__, __LINE__, ##args) +#define netdata_log_error(args...) netdata_logger(NDLS_DAEMON, NDLP_ERR, __FILE__, __FUNCTION__, __LINE__, ##args) +#define collector_info(args...) netdata_logger(NDLS_COLLECTORS, NDLP_INFO, __FILE__, __FUNCTION__, __LINE__, ##args) +#define collector_error(args...) netdata_logger(NDLS_COLLECTORS, NDLP_ERR, __FILE__, __FUNCTION__, __LINE__, ##args) -static inline void debug_dummy(void) {} +#define log_aclk_message_bin(__data, __data_len, __tx, __mqtt_topic, __message_name) \ + nd_log(NDLS_ACLK, NDLP_INFO, \ + "direction:%s message:'%s' topic:'%s' json:'%.*s'", \ + (__tx) ? "OUTGOING" : "INCOMING", __message_name, __mqtt_topic, (int)(__data_len), __data) -void error_log_limit_reset(void); -void error_log_limit_unlimited(void); +// ---------------------------------------------------------------------------- +// logging with limits typedef struct error_with_limit { + SPINLOCK spinlock; time_t log_every; size_t count; time_t last_logged; usec_t sleep_ut; } ERROR_LIMIT; -typedef enum netdata_log_level { - NETDATA_LOG_LEVEL_ERROR, - NETDATA_LOG_LEVEL_INFO, - - NETDATA_LOG_LEVEL_END -} netdata_log_level_t; +#define nd_log_limit_static_global_var(var, log_every_secs, sleep_usecs) static ERROR_LIMIT var = { .last_logged = 0, .count = 0, .log_every = (log_every_secs), .sleep_ut = (sleep_usecs) } +#define nd_log_limit_static_thread_var(var, log_every_secs, sleep_usecs) static __thread ERROR_LIMIT var = { .last_logged = 0, .count = 0, .log_every = (log_every_secs), .sleep_ut = (sleep_usecs) } +void netdata_logger_with_limit(ERROR_LIMIT *erl, ND_LOG_SOURCES source, ND_LOG_FIELD_PRIORITY priority, const char *file, const char *function, unsigned long line, const char *fmt, ... ) PRINTFLIKE(7, 8);; +#define nd_log_limit(erl, NDLS, NDLP, args...) netdata_logger_with_limit(erl, NDLS, NDLP, __FILE__, __FUNCTION__, __LINE__, ##args) -#define NETDATA_LOG_LEVEL_INFO_STR "info" -#define NETDATA_LOG_LEVEL_ERROR_STR "error" -#define NETDATA_LOG_LEVEL_ERROR_SHORT_STR "err" - -extern netdata_log_level_t global_log_severity_level; -netdata_log_level_t log_severity_string_to_severity_level(char *level); -char *log_severity_level_to_severity_string(netdata_log_level_t level); -void log_set_global_severity_level(netdata_log_level_t value); -void log_set_global_severity_for_external_plugins(); - -#define error_limit_static_global_var(var, log_every_secs, sleep_usecs) static ERROR_LIMIT var = { .last_logged = 0, .count = 0, .log_every = (log_every_secs), .sleep_ut = (sleep_usecs) } -#define error_limit_static_thread_var(var, log_every_secs, sleep_usecs) static __thread ERROR_LIMIT var = { .last_logged = 0, .count = 0, .log_every = (log_every_secs), .sleep_ut = (sleep_usecs) } - -#ifdef NETDATA_INTERNAL_CHECKS -#define netdata_log_debug(type, args...) do { if(unlikely(debug_flags & type)) debug_int(__FILE__, __FUNCTION__, __LINE__, ##args); } while(0) -#define internal_error(condition, args...) do { if(unlikely(condition)) error_int(0, "IERR", __FILE__, __FUNCTION__, __LINE__, ##args); } while(0) -#define internal_fatal(condition, args...) do { if(unlikely(condition)) fatal_int(__FILE__, __FUNCTION__, __LINE__, ##args); } while(0) -#else -#define netdata_log_debug(type, args...) debug_dummy() -#define internal_error(args...) debug_dummy() -#define internal_fatal(args...) debug_dummy() -#endif - -#define netdata_log_info(args...) info_int(0, __FILE__, __FUNCTION__, __LINE__, ##args) -#define collector_info(args...) info_int(1, __FILE__, __FUNCTION__, __LINE__, ##args) -#define infoerr(args...) error_int(0, "INFO", __FILE__, __FUNCTION__, __LINE__, ##args) -#define netdata_log_error(args...) error_int(0, "ERROR", __FILE__, __FUNCTION__, __LINE__, ##args) -#define collector_infoerr(args...) error_int(1, "INFO", __FILE__, __FUNCTION__, __LINE__, ##args) -#define collector_error(args...) error_int(1, "ERROR", __FILE__, __FUNCTION__, __LINE__, ##args) -#define error_limit(erl, args...) error_limit_int(erl, "ERROR", __FILE__, __FUNCTION__, __LINE__, ##args) -#define fatal(args...) fatal_int(__FILE__, __FUNCTION__, __LINE__, ##args) -#define fatal_assert(expr) ((expr) ? (void)(0) : fatal_int(__FILE__, __FUNCTION__, __LINE__, "Assertion `%s' failed", #expr)) +// ---------------------------------------------------------------------------- void send_statistics(const char *action, const char *action_result, const char *action_data); -void debug_int( const char *file, const char *function, const unsigned long line, const char *fmt, ... ) PRINTFLIKE(4, 5); -void info_int( int is_collector, const char *file, const char *function, const unsigned long line, const char *fmt, ... ) PRINTFLIKE(5, 6); -void error_int( int is_collector, const char *prefix, const char *file, const char *function, const unsigned long line, const char *fmt, ... ) PRINTFLIKE(6, 7); -void error_limit_int(ERROR_LIMIT *erl, const char *prefix, const char *file __maybe_unused, const char *function __maybe_unused, unsigned long line __maybe_unused, const char *fmt, ... ) PRINTFLIKE(6, 7);; -void fatal_int( const char *file, const char *function, const unsigned long line, const char *fmt, ... ) NORETURN PRINTFLIKE(4, 5); -void netdata_log_access( const char *fmt, ... ) PRINTFLIKE(1, 2); -void netdata_log_health( const char *fmt, ... ) PRINTFLIKE(1, 2); - -#ifdef ENABLE_ACLK -void log_aclk_message_bin( const char *data, const size_t data_len, int tx, const char *mqtt_topic, const char *message_name); -#endif +void netdata_logger_fatal( const char *file, const char *function, unsigned long line, const char *fmt, ... ) NORETURN PRINTFLIKE(4, 5); # ifdef __cplusplus } diff --git a/libnetdata/log/systemd-cat-native.c b/libnetdata/log/systemd-cat-native.c new file mode 100644 index 00000000..de6211cc --- /dev/null +++ b/libnetdata/log/systemd-cat-native.c @@ -0,0 +1,820 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "systemd-cat-native.h" +#include "../required_dummies.h" + +#ifdef __FreeBSD__ +#include <sys/endian.h> +#endif + +#ifdef __APPLE__ +#include <machine/endian.h> +#endif + +static void log_message_to_stderr(BUFFER *msg) { + CLEAN_BUFFER *tmp = buffer_create(0, NULL); + + for(size_t i = 0; i < msg->len ;i++) { + if(isprint(msg->buffer[i])) + buffer_putc(tmp, msg->buffer[i]); + else { + buffer_putc(tmp, '['); + buffer_print_uint64_hex(tmp, msg->buffer[i]); + buffer_putc(tmp, ']'); + } + } + + fprintf(stderr, "SENDING: %s\n", buffer_tostring(tmp)); +} + +static inline buffered_reader_ret_t get_next_line(struct buffered_reader *reader, BUFFER *line, int timeout_ms) { + while(true) { + if(unlikely(!buffered_reader_next_line(reader, line))) { + buffered_reader_ret_t ret = buffered_reader_read_timeout(reader, STDIN_FILENO, timeout_ms, false); + if(unlikely(ret != BUFFERED_READER_READ_OK)) + return ret; + + continue; + } + else { + // make sure the buffer is NULL terminated + line->buffer[line->len] = '\0'; + + // remove the trailing newlines + while(line->len && line->buffer[line->len - 1] == '\n') + line->buffer[--line->len] = '\0'; + + return BUFFERED_READER_READ_OK; + } + } +} + +static inline size_t copy_replacing_newlines(char *dst, size_t dst_len, const char *src, size_t src_len, const char *newline) { + if (!dst || !src) return 0; + + const char *current_src = src; + const char *src_end = src + src_len; // Pointer to the end of src + char *current_dst = dst; + size_t remaining_dst_len = dst_len; + size_t newline_len = newline && *newline ? strlen(newline) : 0; + + size_t bytes_copied = 0; // To track the number of bytes copied + + while (remaining_dst_len > 1 && current_src < src_end) { + if (newline_len > 0) { + const char *found = strstr(current_src, newline); + if (found && found < src_end) { + size_t copy_len = found - current_src; + if (copy_len >= remaining_dst_len) copy_len = remaining_dst_len - 1; + + memcpy(current_dst, current_src, copy_len); + current_dst += copy_len; + *current_dst++ = '\n'; + remaining_dst_len -= (copy_len + 1); + bytes_copied += copy_len + 1; // +1 for the newline character + current_src = found + newline_len; + continue; + } + } + + // Copy the remaining part of src to dst + size_t copy_len = src_end - current_src; + if (copy_len >= remaining_dst_len) copy_len = remaining_dst_len - 1; + + memcpy(current_dst, current_src, copy_len); + current_dst += copy_len; + remaining_dst_len -= copy_len; + bytes_copied += copy_len; + break; + } + + // Ensure the string is null-terminated + *current_dst = '\0'; + + return bytes_copied; +} + +static inline void buffer_memcat_replacing_newlines(BUFFER *wb, const char *src, size_t src_len, const char *newline) { + if(!src) return; + + const char *equal; + if(!newline || !*newline || !strstr(src, newline) || !(equal = strchr(src, '='))) { + buffer_memcat(wb, src, src_len); + buffer_putc(wb, '\n'); + return; + } + + size_t key_len = equal - src; + buffer_memcat(wb, src, key_len); + buffer_putc(wb, '\n'); + + char *length_ptr = &wb->buffer[wb->len]; + uint64_t le_size = 0; + buffer_memcat(wb, &le_size, sizeof(le_size)); + + const char *value = ++equal; + size_t value_len = src_len - key_len - 1; + buffer_need_bytes(wb, value_len + 1); + size_t size = copy_replacing_newlines(&wb->buffer[wb->len], value_len + 1, value, value_len, newline); + wb->len += size; + buffer_putc(wb, '\n'); + + le_size = htole64(size); + memcpy(length_ptr, &le_size, sizeof(le_size)); +} + +// ---------------------------------------------------------------------------- +// log to a systemd-journal-remote + +#ifdef HAVE_CURL +#include <curl/curl.h> + +#ifndef HOST_NAME_MAX +#define HOST_NAME_MAX 256 +#endif + +char global_hostname[HOST_NAME_MAX] = ""; +char global_boot_id[UUID_COMPACT_STR_LEN] = ""; +char global_machine_id[UUID_COMPACT_STR_LEN] = ""; +char global_stream_id[UUID_COMPACT_STR_LEN] = ""; +char global_namespace[1024] = ""; +char global_systemd_invocation_id[1024] = ""; +#define BOOT_ID_PATH "/proc/sys/kernel/random/boot_id" +#define MACHINE_ID_PATH "/etc/machine-id" + +#define DEFAULT_PRIVATE_KEY "/etc/ssl/private/journal-upload.pem" +#define DEFAULT_PUBLIC_KEY "/etc/ssl/certs/journal-upload.pem" +#define DEFAULT_CA_CERT "/etc/ssl/ca/trusted.pem" + +struct upload_data { + char *data; + size_t length; +}; + +static size_t systemd_journal_remote_read_callback(void *ptr, size_t size, size_t nmemb, void *userp) { + struct upload_data *upload = (struct upload_data *)userp; + size_t buffer_size = size * nmemb; + + if (upload->length) { + size_t copy_size = upload->length < buffer_size ? upload->length : buffer_size; + memcpy(ptr, upload->data, copy_size); + upload->data += copy_size; + upload->length -= copy_size; + return copy_size; + } + + return 0; +} + +CURL* initialize_connection_to_systemd_journal_remote(const char* url, const char* private_key, const char* public_key, const char* ca_cert, struct curl_slist **headers) { + CURL *curl = curl_easy_init(); + if (!curl) { + fprintf(stderr, "Failed to initialize curl\n"); + return NULL; + } + + *headers = curl_slist_append(*headers, "Content-Type: application/vnd.fdo.journal"); + *headers = curl_slist_append(*headers, "Transfer-Encoding: chunked"); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, *headers); + curl_easy_setopt(curl, CURLOPT_URL, url); + curl_easy_setopt(curl, CURLOPT_POST, 1L); + curl_easy_setopt(curl, CURLOPT_READFUNCTION, systemd_journal_remote_read_callback); + + if (strncmp(url, "https://", 8) == 0) { + if (private_key) curl_easy_setopt(curl, CURLOPT_SSLKEY, private_key); + if (public_key) curl_easy_setopt(curl, CURLOPT_SSLCERT, public_key); + + if (strcmp(ca_cert, "all") != 0) { + curl_easy_setopt(curl, CURLOPT_CAINFO, ca_cert); + } else { + curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, 0L); + } + } + // curl_easy_setopt(curl, CURLOPT_VERBOSE, 1L); // Remove for less verbose output + + return curl; +} + +static void journal_remote_complete_event(BUFFER *msg, usec_t *monotonic_ut) { + usec_t ut = now_monotonic_usec(); + + if(monotonic_ut) + *monotonic_ut = ut; + + buffer_sprintf(msg, + "" + "__REALTIME_TIMESTAMP=%llu\n" + "__MONOTONIC_TIMESTAMP=%llu\n" + "_MACHINE_ID=%s\n" + "_BOOT_ID=%s\n" + "_HOSTNAME=%s\n" + "_TRANSPORT=stdout\n" + "_LINE_BREAK=nul\n" + "_STREAM_ID=%s\n" + "_RUNTIME_SCOPE=system\n" + "%s%s\n" + , now_realtime_usec() + , ut + , global_machine_id + , global_boot_id + , global_hostname + , global_stream_id + , global_namespace + , global_systemd_invocation_id + ); +} + +static CURLcode journal_remote_send_buffer(CURL* curl, BUFFER *msg) { + + // log_message_to_stderr(msg); + + struct upload_data upload = {0}; + + if (!curl || !buffer_strlen(msg)) + return CURLE_FAILED_INIT; + + upload.data = (char *) buffer_tostring(msg); + upload.length = buffer_strlen(msg); + + curl_easy_setopt(curl, CURLOPT_READDATA, &upload); + curl_easy_setopt(curl, CURLOPT_INFILESIZE_LARGE, (curl_off_t)upload.length); + + return curl_easy_perform(curl); +} + +typedef enum { + LOG_TO_JOURNAL_REMOTE_BAD_PARAMS = -1, + LOG_TO_JOURNAL_REMOTE_CANNOT_INITIALIZE = -2, + LOG_TO_JOURNAL_REMOTE_CANNOT_SEND = -3, + LOG_TO_JOURNAL_REMOTE_CANNOT_READ = -4, +} log_to_journal_remote_ret_t; + +static log_to_journal_remote_ret_t log_input_to_journal_remote(const char *url, const char *key, const char *cert, const char *trust, const char *newline, int timeout_ms) { + if(!url || !*url) { + fprintf(stderr, "No URL is given.\n"); + return LOG_TO_JOURNAL_REMOTE_BAD_PARAMS; + } + + if(timeout_ms < 10) + timeout_ms = 10; + + global_boot_id[0] = '\0'; + char buffer[1024]; + if(read_file(BOOT_ID_PATH, buffer, sizeof(buffer)) == 0) { + uuid_t uuid; + if(uuid_parse_flexi(buffer, uuid) == 0) + uuid_unparse_lower_compact(uuid, global_boot_id); + else + fprintf(stderr, "WARNING: cannot parse the UUID found in '%s'.\n", BOOT_ID_PATH); + } + + if(global_boot_id[0] == '\0') { + fprintf(stderr, "WARNING: cannot read '%s'. Will generate a random _BOOT_ID.\n", BOOT_ID_PATH); + uuid_t uuid; + uuid_generate_random(uuid); + uuid_unparse_lower_compact(uuid, global_boot_id); + } + + if(read_file(MACHINE_ID_PATH, buffer, sizeof(buffer)) == 0) { + uuid_t uuid; + if(uuid_parse_flexi(buffer, uuid) == 0) + uuid_unparse_lower_compact(uuid, global_machine_id); + else + fprintf(stderr, "WARNING: cannot parse the UUID found in '%s'.\n", MACHINE_ID_PATH); + } + + if(global_machine_id[0] == '\0') { + fprintf(stderr, "WARNING: cannot read '%s'. Will generate a random _MACHINE_ID.\n", MACHINE_ID_PATH); + uuid_t uuid; + uuid_generate_random(uuid); + uuid_unparse_lower_compact(uuid, global_boot_id); + } + + if(global_stream_id[0] == '\0') { + uuid_t uuid; + uuid_generate_random(uuid); + uuid_unparse_lower_compact(uuid, global_stream_id); + } + + if(global_hostname[0] == '\0') { + if(gethostname(global_hostname, sizeof(global_hostname)) != 0) { + fprintf(stderr, "WARNING: cannot get system's hostname. Will use internal default.\n"); + snprintfz(global_hostname, sizeof(global_hostname), "systemd-cat-native-unknown-hostname"); + } + } + + if(global_systemd_invocation_id[0] == '\0' && getenv("INVOCATION_ID")) + snprintfz(global_systemd_invocation_id, sizeof(global_systemd_invocation_id), "_SYSTEMD_INVOCATION_ID=%s\n", getenv("INVOCATION_ID")); + + if(!key) + key = DEFAULT_PRIVATE_KEY; + + if(!cert) + cert = DEFAULT_PUBLIC_KEY; + + if(!trust) + trust = DEFAULT_CA_CERT; + + char full_url[4096]; + snprintfz(full_url, sizeof(full_url), "%s/upload", url); + + CURL *curl; + CURLcode res = CURLE_OK; + struct curl_slist *headers = NULL; + + curl_global_init(CURL_GLOBAL_ALL); + curl = initialize_connection_to_systemd_journal_remote(full_url, key, cert, trust, &headers); + + if(!curl) + return LOG_TO_JOURNAL_REMOTE_CANNOT_INITIALIZE; + + struct buffered_reader reader; + buffered_reader_init(&reader); + CLEAN_BUFFER *line = buffer_create(sizeof(reader.read_buffer), NULL); + CLEAN_BUFFER *msg = buffer_create(sizeof(reader.read_buffer), NULL); + + size_t msg_full_events = 0; + size_t msg_partial_fields = 0; + usec_t msg_started_ut = 0; + size_t failures = 0; + size_t messages_logged = 0; + + log_to_journal_remote_ret_t ret = 0; + + while(true) { + buffered_reader_ret_t rc = get_next_line(&reader, line, timeout_ms); + if(rc == BUFFERED_READER_READ_POLL_TIMEOUT) { + if(msg_full_events && !msg_partial_fields) { + res = journal_remote_send_buffer(curl, msg); + if(res != CURLE_OK) { + fprintf(stderr, "journal_remote_send_buffer() failed: %s\n", curl_easy_strerror(res)); + failures++; + ret = LOG_TO_JOURNAL_REMOTE_CANNOT_SEND; + goto cleanup; + } + else + messages_logged++; + + msg_full_events = 0; + buffer_flush(msg); + } + } + else if(rc == BUFFERED_READER_READ_OK) { + if(!line->len) { + // an empty line - we are done for this message + if(msg_partial_fields) { + msg_partial_fields = 0; + + usec_t ut; + journal_remote_complete_event(msg, &ut); + if(!msg_full_events) + msg_started_ut = ut; + + msg_full_events++; + + if(ut - msg_started_ut >= USEC_PER_SEC / 2) { + res = journal_remote_send_buffer(curl, msg); + if(res != CURLE_OK) { + fprintf(stderr, "journal_remote_send_buffer() failed: %s\n", curl_easy_strerror(res)); + failures++; + ret = LOG_TO_JOURNAL_REMOTE_CANNOT_SEND; + goto cleanup; + } + else + messages_logged++; + + msg_full_events = 0; + buffer_flush(msg); + } + } + } + else { + buffer_memcat_replacing_newlines(msg, line->buffer, line->len, newline); + msg_partial_fields++; + } + + buffer_flush(line); + } + else { + fprintf(stderr, "cannot read input data, failed with code %d\n", rc); + ret = LOG_TO_JOURNAL_REMOTE_CANNOT_READ; + break; + } + } + + if (msg_full_events || msg_partial_fields) { + if(msg_partial_fields) { + msg_partial_fields = 0; + msg_full_events++; + journal_remote_complete_event(msg, NULL); + } + + if(msg_full_events) { + res = journal_remote_send_buffer(curl, msg); + if(res != CURLE_OK) { + fprintf(stderr, "journal_remote_send_buffer() failed: %s\n", curl_easy_strerror(res)); + failures++; + } + else + messages_logged++; + + msg_full_events = 0; + buffer_flush(msg); + } + } + +cleanup: + curl_easy_cleanup(curl); + curl_slist_free_all(headers); + curl_global_cleanup(); + + return ret; +} + +#endif + +static int help(void) { + fprintf(stderr, + "\n" + "Netdata systemd-cat-native " PACKAGE_VERSION "\n" + "\n" + "This program reads from its standard input, lines in the format:\n" + "\n" + "KEY1=VALUE1\\n\n" + "KEY2=VALUE2\\n\n" + "KEYN=VALUEN\\n\n" + "\\n\n" + "\n" + "and sends them to systemd-journal.\n" + "\n" + " - Binary journal fields are not accepted at its input\n" + " - Binary journal fields can be generated after newline processing\n" + " - Messages have to be separated by an empty line\n" + " - Keys starting with underscore are not accepted (by journald)\n" + " - Other rules imposed by systemd-journald are imposed (by journald)\n" + "\n" + "Usage:\n" + "\n" + " %s\n" + " [--newline=STRING]\n" + " [--log-as-netdata|-N]\n" + " [--namespace=NAMESPACE] [--socket=PATH]\n" +#ifdef HAVE_CURL + " [--url=URL [--key=FILENAME] [--cert=FILENAME] [--trust=FILENAME|all]]\n" +#endif + "\n" + "The program has the following modes of logging:\n" + "\n" + " * Log to a local systemd-journald or stderr\n" + "\n" + " This is the default mode. If systemd-journald is available, logs will be\n" + " sent to systemd, otherwise logs will be printed on stderr, using logfmt\n" + " formatting. Options --socket and --namespace are available to configure\n" + " the journal destination:\n" + "\n" + " --socket=PATH\n" + " The path of a systemd-journald UNIX socket.\n" + " The program will use the default systemd-journald socket when this\n" + " option is not used.\n" + "\n" + " --namespace=NAMESPACE\n" + " The name of a configured and running systemd-journald namespace.\n" + " The program will produce the socket path based on its internal\n" + " defaults, to send the messages to the systemd journal namespace.\n" + "\n" + " * Log as Netdata, enabled with --log-as-netdata or -N\n" + "\n" + " In this mode the program uses environment variables set by Netdata for\n" + " the log destination. Only log fields defined by Netdata are accepted.\n" + " If the environment variables expected by Netdata are not found, it\n" + " falls back to stderr logging in logfmt format.\n" +#ifdef HAVE_CURL + "\n" + " * Log to a systemd-journal-remote TCP socket, enabled with --url=URL\n" + "\n" + " In this mode, the program will directly sent logs to a remote systemd\n" + " journal (systemd-journal-remote expected at the destination)\n" + " This mode is available even when the local system does not support\n" + " systemd, or even it is not Linux, allowing a remote Linux systemd\n" + " journald to become the logs database of the local system.\n" + "\n" + " Unfortunately systemd-journal-remote does not accept compressed\n" + " data over the network, so the stream will be uncompressed.\n" + "\n" + " --url=URL\n" + " The destination systemd-journal-remote address and port, similarly\n" + " to what /etc/systemd/journal-upload.conf accepts.\n" + " Usually it is in the form: https://ip.address:19532\n" + " Both http and https URLs are accepted. When using https, the\n" + " following additional options are accepted:\n" + "\n" + " --key=FILENAME\n" + " The filename of the private key of the server.\n" + " The default is: " DEFAULT_PRIVATE_KEY "\n" + "\n" + " --cert=FILENAME\n" + " The filename of the public key of the server.\n" + " The default is: " DEFAULT_PUBLIC_KEY "\n" + "\n" + " --trust=FILENAME | all\n" + " The filename of the trusted CA public key.\n" + " The default is: " DEFAULT_CA_CERT "\n" + " The keyword 'all' can be used to trust all CAs.\n" + "\n" + " --namespace=NAMESPACE\n" + " Set the namespace of the messages sent.\n" + "\n" + " --keep-trying\n" + " Keep trying to send the message, if the remote journal is not there.\n" +#endif + "\n" + " NEWLINES PROCESSING\n" + " systemd-journal logs entries may have newlines in them. However the\n" + " Journal Export Format uses binary formatted data to achieve this,\n" + " making it hard for text processing.\n" + "\n" + " To overcome this limitation, this program allows single-line text\n" + " formatted values at its input, to be binary formatted multi-line Journal\n" + " Export Format at its output.\n" + "\n" + " To achieve that it allows replacing a given string to a newline.\n" + " The parameter --newline=STRING allows setting the string to be replaced\n" + " with newlines.\n" + "\n" + " For example by setting --newline='--NEWLINE--', the program will replace\n" + " all occurrences of --NEWLINE-- with the newline character, within each\n" + " VALUE of the KEY=VALUE lines. Once this this done, the program will\n" + " switch the field to the binary Journal Export Format before sending the\n" + " log event to systemd-journal.\n" + "\n", + program_name); + + return 1; +} + +// ---------------------------------------------------------------------------- +// log as Netdata + +static void lgs_reset(struct log_stack_entry *lgs) { + for(size_t i = 1; i < _NDF_MAX ;i++) { + if(lgs[i].type == NDFT_TXT && lgs[i].set && lgs[i].txt) + freez((void *)lgs[i].txt); + + lgs[i] = ND_LOG_FIELD_TXT(i, NULL); + } + + lgs[0] = ND_LOG_FIELD_TXT(NDF_MESSAGE, NULL); + lgs[_NDF_MAX] = ND_LOG_FIELD_END(); +} + +static const char *strdupz_replacing_newlines(const char *src, const char *newline) { + if(!src) src = ""; + + size_t src_len = strlen(src); + char *buffer = mallocz(src_len + 1); + copy_replacing_newlines(buffer, src_len + 1, src, src_len, newline); + return buffer; +} + +static int log_input_as_netdata(const char *newline, int timeout_ms) { + struct buffered_reader reader; + buffered_reader_init(&reader); + CLEAN_BUFFER *line = buffer_create(sizeof(reader.read_buffer), NULL); + + ND_LOG_STACK lgs[_NDF_MAX + 1] = { 0 }; + ND_LOG_STACK_PUSH(lgs); + lgs_reset(lgs); + + size_t fields_added = 0; + size_t messages_logged = 0; + ND_LOG_FIELD_PRIORITY priority = NDLP_INFO; + + while(get_next_line(&reader, line, timeout_ms) == BUFFERED_READER_READ_OK) { + if(!line->len) { + // an empty line - we are done for this message + + nd_log(NDLS_HEALTH, priority, + "added %d fields", // if the user supplied a MESSAGE, this will be ignored + fields_added); + + lgs_reset(lgs); + fields_added = 0; + messages_logged++; + } + else { + char *equal = strchr(line->buffer, '='); + if(equal) { + const char *field = line->buffer; + size_t field_len = equal - line->buffer; + ND_LOG_FIELD_ID id = nd_log_field_id_by_name(field, field_len); + if(id != NDF_STOP) { + const char *value = ++equal; + + if(lgs[id].txt) + freez((void *) lgs[id].txt); + + lgs[id].txt = strdupz_replacing_newlines(value, newline); + lgs[id].set = true; + + fields_added++; + + if(id == NDF_PRIORITY) + priority = nd_log_priority2id(value); + } + else { + struct log_stack_entry backup = lgs[NDF_MESSAGE]; + lgs[NDF_MESSAGE] = ND_LOG_FIELD_TXT(NDF_MESSAGE, NULL); + + nd_log(NDLS_COLLECTORS, NDLP_ERR, + "Field '%.*s' is not a Netdata field. Ignoring it.", + field_len, field); + + lgs[NDF_MESSAGE] = backup; + } + } + else { + struct log_stack_entry backup = lgs[NDF_MESSAGE]; + lgs[NDF_MESSAGE] = ND_LOG_FIELD_TXT(NDF_MESSAGE, NULL); + + nd_log(NDLS_COLLECTORS, NDLP_ERR, + "Line does not contain an = sign; ignoring it: %s", + line->buffer); + + lgs[NDF_MESSAGE] = backup; + } + } + + buffer_flush(line); + } + + if(fields_added) { + nd_log(NDLS_HEALTH, priority, "added %d fields", fields_added); + messages_logged++; + } + + return messages_logged ? 0 : 1; +} + +// ---------------------------------------------------------------------------- +// log to a local systemd-journald + +static bool journal_local_send_buffer(int fd, BUFFER *msg) { + // log_message_to_stderr(msg); + + bool ret = journal_direct_send(fd, msg->buffer, msg->len); + if (!ret) + fprintf(stderr, "Cannot send message to systemd journal.\n"); + + return ret; +} + +static int log_input_to_journal(const char *socket, const char *namespace, const char *newline, int timeout_ms) { + char path[FILENAME_MAX + 1]; + int fd = -1; + + if(socket) + snprintfz(path, sizeof(path), "%s", socket); + else + journal_construct_path(path, sizeof(path), NULL, namespace); + + fd = journal_direct_fd(path); + if (fd == -1) { + fprintf(stderr, "Cannot open '%s' as a UNIX socket (errno = %d)\n", + path, errno); + return 1; + } + + struct buffered_reader reader; + buffered_reader_init(&reader); + CLEAN_BUFFER *line = buffer_create(sizeof(reader.read_buffer), NULL); + CLEAN_BUFFER *msg = buffer_create(sizeof(reader.read_buffer), NULL); + + size_t messages_logged = 0; + size_t failed_messages = 0; + + while(get_next_line(&reader, line, timeout_ms) == BUFFERED_READER_READ_OK) { + if (!line->len) { + // an empty line - we are done for this message + if (msg->len) { + if(journal_local_send_buffer(fd, msg)) + messages_logged++; + else { + failed_messages++; + goto cleanup; + } + } + + buffer_flush(msg); + } + else + buffer_memcat_replacing_newlines(msg, line->buffer, line->len, newline); + + buffer_flush(line); + } + + if (msg && msg->len) { + if(journal_local_send_buffer(fd, msg)) + messages_logged++; + else + failed_messages++; + } + +cleanup: + return !failed_messages && messages_logged ? 0 : 1; +} + +int main(int argc, char *argv[]) { + clocks_init(); + nd_log_initialize_for_external_plugins(argv[0]); + + int timeout_ms = -1; // wait forever + bool log_as_netdata = false; + const char *newline = NULL; + const char *namespace = NULL; + const char *socket = getenv("NETDATA_SYSTEMD_JOURNAL_PATH"); +#ifdef HAVE_CURL + const char *url = NULL; + const char *key = NULL; + const char *cert = NULL; + const char *trust = NULL; + bool keep_trying = false; +#endif + + for(int i = 1; i < argc ;i++) { + const char *k = argv[i]; + + if(strcmp(k, "--help") == 0 || strcmp(k, "-h") == 0) + return help(); + + else if(strcmp(k, "--log-as-netdata") == 0 || strcmp(k, "-N") == 0) + log_as_netdata = true; + + else if(strncmp(k, "--namespace=", 12) == 0) + namespace = &k[12]; + + else if(strncmp(k, "--socket=", 9) == 0) + socket = &k[9]; + + else if(strncmp(k, "--newline=", 10) == 0) + newline = &k[10]; + +#ifdef HAVE_CURL + else if (strncmp(k, "--url=", 6) == 0) + url = &k[6]; + + else if (strncmp(k, "--key=", 6) == 0) + key = &k[6]; + + else if (strncmp(k, "--cert=", 7) == 0) + cert = &k[7]; + + else if (strncmp(k, "--trust=", 8) == 0) + trust = &k[8]; + + else if (strcmp(k, "--keep-trying") == 0) + keep_trying = true; +#endif + else { + fprintf(stderr, "Unknown parameter '%s'\n", k); + return 1; + } + } + +#ifdef HAVE_CURL + if(log_as_netdata && url) { + fprintf(stderr, "Cannot log to a systemd-journal-remote URL as Netdata. " + "Please either give --url or --log-as-netdata, not both.\n"); + return 1; + } + + if(socket && url) { + fprintf(stderr, "Cannot log to a systemd-journal-remote URL using a UNIX socket. " + "Please either give --url or --socket, not both.\n"); + return 1; + } + +#endif + + if(log_as_netdata && namespace) { + fprintf(stderr, "Cannot log as netdata using a namespace. " + "Please either give --log-as-netdata or --namespace, not both.\n"); + return 1; + } + + if(log_as_netdata) + return log_input_as_netdata(newline, timeout_ms); + +#ifdef HAVE_CURL + if(url) { + if(url && namespace && *namespace) + snprintfz(global_namespace, sizeof(global_namespace), "_NAMESPACE=%s\n", namespace); + + log_to_journal_remote_ret_t rc; + do { + rc = log_input_to_journal_remote(url, key, cert, trust, newline, timeout_ms); + } while(keep_trying && rc == LOG_TO_JOURNAL_REMOTE_CANNOT_SEND); + } +#endif + + return log_input_to_journal(socket, namespace, newline, timeout_ms); +} diff --git a/libnetdata/log/systemd-cat-native.h b/libnetdata/log/systemd-cat-native.h new file mode 100644 index 00000000..34e7a361 --- /dev/null +++ b/libnetdata/log/systemd-cat-native.h @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +#ifndef NETDATA_SYSTEMD_CAT_NATIVE_H +#define NETDATA_SYSTEMD_CAT_NATIVE_H + +#endif //NETDATA_SYSTEMD_CAT_NATIVE_H diff --git a/libnetdata/log/systemd-cat-native.md b/libnetdata/log/systemd-cat-native.md new file mode 100644 index 00000000..b0b15f40 --- /dev/null +++ b/libnetdata/log/systemd-cat-native.md @@ -0,0 +1,209 @@ +# systemd-cat-native + +`systemd` includes a utility called `systemd-cat`. This utility reads log lines from its standard input and sends them +to the local systemd journal. Its key limitation is that despite the fact that systemd journals support structured logs, +this command does not support sending structured logs to it. + +`systemd-cat-native` is a Netdata supplied utility to push structured logs to systemd journals. Key features: + +- reads [Journal Export Format](https://systemd.io/JOURNAL_EXPORT_FORMATS/) formatted log entries +- converts text fields into binary journal multiline log fields +- sends logs to any of these: + - local default `systemd-journald`, + - local namespace `systemd-journald`, + - remote `systemd-journal-remote` using HTTP or HTTPS, the same way `systemd-journal-upload` does. +- is the standard external logger of Netdata shell scripts + +## Simple use: + +```bash +printf "MESSAGE=hello world\nPRIORITY=6\n\n" | systemd-cat-native +``` + +The result: + + + + +Sending `PRIORITY=3` (error): + +```bash +printf "MESSAGE=hey, this is error\nPRIORITY=3\n\n" | systemd-cat-native +``` + +The result: + + +Sending multi-line log entries (in this example we replace the text `--NEWLINE--` with a newline in the log entry): + +```bash +printf "MESSAGE=hello--NEWLINE--world\nPRIORITY=6\n\n" | systemd-cat-native --newline='--NEWLINE--' +``` + +The result: + + + + +Processing the standard `\n` string can be tricky due to shell escaping. This works, but note that +we have to add a lot of backslashes to printf. + +```bash +printf "MESSAGE=hello\\\\nworld\nPRIORITY=6\n\n" | systemd-cat-native --newline='\n' +``` + +`systemd-cat-native` needs to receive it like this for newline processing to work: + +```bash +# printf "MESSAGE=hello\\\\nworld\nPRIORITY=6\n\n" +MESSAGE=hello\nworld +PRIORITY=6 + +``` + +## Best practices + +These are the rules about fields, enforced by `systemd-journald`: + +- field names can be up to **64 characters**, +- field values can be up to **48k characters**, +- the only allowed field characters are **A-Z**, **0-9** and **underscore**, +- the **first** character of fields cannot be a **digit** +- **protected** journal fields start with underscore: + * they are accepted by `systemd-journal-remote`, + * they are **NOT** accepted by a local `systemd-journald`. + +For best results, always include these fields: + +- `MESSAGE=TEXT`<br/> + The `MESSAGE` is the body of the log entry. + This field is what we usually see in our logs. + +- `PRIORITY=NUMBER`<br/> + `PRIORITY` sets the severity of the log entry.<br/> + `0=emerg, 1=alert, 2=crit, 3=err, 4=warn, 5=notice, 6=info, 7=debug` + - Emergency events (0) are usually broadcast to all terminals. + - Emergency, alert, critical, and error (0-3) are usually colored red. + - Warning (4) entries are usually colored yellow. + - Notice (5) entries are usually bold or have a brighter white color. + - Info (6) entries are the default. + - Debug (7) entries are usually grayed or dimmed. + +- `SYSLOG_IDENTIFIER=NAME`<br/> + `SYSLOG_IDENTIFIER` sets the name of application. + Use something descriptive, like: `SYSLOG_IDENTIFIER=myapp` + +You can find the most common fields at `man systemd.journal-fields`. + + +## Usage + +``` +Netdata systemd-cat-native v1.43.0-333-g5af71b875 + +This program reads from its standard input, lines in the format: + +KEY1=VALUE1\n +KEY2=VALUE2\n +KEYN=VALUEN\n +\n + +and sends them to systemd-journal. + + - Binary journal fields are not accepted at its input + - Binary journal fields can be generated after newline processing + - Messages have to be separated by an empty line + - Keys starting with underscore are not accepted (by journald) + - Other rules imposed by systemd-journald are imposed (by journald) + +Usage: + + systemd-cat-native + [--newline=STRING] + [--log-as-netdata|-N] + [--namespace=NAMESPACE] [--socket=PATH] + [--url=URL [--key=FILENAME] [--cert=FILENAME] [--trust=FILENAME|all]] + +The program has the following modes of logging: + + * Log to a local systemd-journald or stderr + + This is the default mode. If systemd-journald is available, logs will be + sent to systemd, otherwise logs will be printed on stderr, using logfmt + formatting. Options --socket and --namespace are available to configure + the journal destination: + + --socket=PATH + The path of a systemd-journald UNIX socket. + The program will use the default systemd-journald socket when this + option is not used. + + --namespace=NAMESPACE + The name of a configured and running systemd-journald namespace. + The program will produce the socket path based on its internal + defaults, to send the messages to the systemd journal namespace. + + * Log as Netdata, enabled with --log-as-netdata or -N + + In this mode the program uses environment variables set by Netdata for + the log destination. Only log fields defined by Netdata are accepted. + If the environment variables expected by Netdata are not found, it + falls back to stderr logging in logfmt format. + + * Log to a systemd-journal-remote TCP socket, enabled with --url=URL + + In this mode, the program will directly sent logs to a remote systemd + journal (systemd-journal-remote expected at the destination) + This mode is available even when the local system does not support + systemd, or even it is not Linux, allowing a remote Linux systemd + journald to become the logs database of the local system. + + Unfortunately systemd-journal-remote does not accept compressed + data over the network, so the stream will be uncompressed. + + --url=URL + The destination systemd-journal-remote address and port, similarly + to what /etc/systemd/journal-upload.conf accepts. + Usually it is in the form: https://ip.address:19532 + Both http and https URLs are accepted. When using https, the + following additional options are accepted: + + --key=FILENAME + The filename of the private key of the server. + The default is: /etc/ssl/private/journal-upload.pem + + --cert=FILENAME + The filename of the public key of the server. + The default is: /etc/ssl/certs/journal-upload.pem + + --trust=FILENAME | all + The filename of the trusted CA public key. + The default is: /etc/ssl/ca/trusted.pem + The keyword 'all' can be used to trust all CAs. + + --namespace=NAMESPACE + Set the namespace of the messages sent. + + --keep-trying + Keep trying to send the message, if the remote journal is not there. + + NEWLINES PROCESSING + systemd-journal logs entries may have newlines in them. However the + Journal Export Format uses binary formatted data to achieve this, + making it hard for text processing. + + To overcome this limitation, this program allows single-line text + formatted values at its input, to be binary formatted multi-line Journal + Export Format at its output. + + To achieve that it allows replacing a given string to a newline. + The parameter --newline=STRING allows setting the string to be replaced + with newlines. + + For example by setting --newline='--NEWLINE--', the program will replace + all occurrences of --NEWLINE-- with the newline character, within each + VALUE of the KEY=VALUE lines. Once this this done, the program will + switch the field to the binary Journal Export Format before sending the + log event to systemd-journal. + +```
\ No newline at end of file diff --git a/libnetdata/os.c b/libnetdata/os.c index e6475a45..e4624be6 100644 --- a/libnetdata/os.c +++ b/libnetdata/os.c @@ -162,7 +162,11 @@ unsigned long read_cpuset_cpus(const char *filename, long system_cpus) { unsigned long ncpus = 0; // parse the cpuset string and calculate the number of cpus the cgroup is allowed to use - while(*s) { + while (*s) { + if (isspace(*s)) { + s++; + continue; + } unsigned long n = cpuset_str2ul(&s); ncpus++; if(*s == ',') { diff --git a/libnetdata/os.h b/libnetdata/os.h index 3cda79ed..197548b0 100644 --- a/libnetdata/os.h +++ b/libnetdata/os.h @@ -37,6 +37,7 @@ int getsysctl(const char *name, int *mib, size_t miblen, void *ptr, size_t *len) #if __APPLE__ #include <sys/sysctl.h> +#include "endian.h" #define GETSYSCTL_BY_NAME(name, var) getsysctl_by_name(name, &(var), sizeof(var)) int getsysctl_by_name(const char *name, void *ptr, size_t len); diff --git a/libnetdata/procfile/procfile.c b/libnetdata/procfile/procfile.c index 1a7e47a5..0bc731d6 100644 --- a/libnetdata/procfile/procfile.c +++ b/libnetdata/procfile/procfile.c @@ -407,9 +407,14 @@ procfile *procfile_open(const char *filename, const char *separators, uint32_t f int fd = open(filename, procfile_open_flags, 0666); if(unlikely(fd == -1)) { - if(unlikely(!(flags & PROCFILE_FLAG_NO_ERROR_ON_FILE_IO))) collector_error(PF_PREFIX ": Cannot open file '%s'", filename); - else if(unlikely(flags & PROCFILE_FLAG_ERROR_ON_ERROR_LOG)) + if (unlikely(flags & PROCFILE_FLAG_ERROR_ON_ERROR_LOG)) netdata_log_error(PF_PREFIX ": Cannot open file '%s'", filename); + else if (unlikely(!(flags & PROCFILE_FLAG_NO_ERROR_ON_FILE_IO))) { + if (errno == ENOENT) + collector_info(PF_PREFIX ": Cannot open file '%s'", filename); + else + collector_error(PF_PREFIX ": Cannot open file '%s'", filename); + } return NULL; } diff --git a/libnetdata/simple_hashtable.h b/libnetdata/simple_hashtable.h new file mode 100644 index 00000000..f6b6db90 --- /dev/null +++ b/libnetdata/simple_hashtable.h @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_SIMPLE_HASHTABLE_H +#define NETDATA_SIMPLE_HASHTABLE_H + +#ifndef XXH_INLINE_ALL +#define XXH_INLINE_ALL +#endif +#include "xxhash.h" + +typedef uint64_t SIMPLE_HASHTABLE_HASH; +#define SIMPLE_HASHTABLE_HASH_SECOND_HASH_SHIFTS 32 + +#ifndef SIMPLE_HASHTABLE_NAME +#define SIMPLE_HASHTABLE_NAME +#endif + +#ifndef SIMPLE_HASHTABLE_VALUE_TYPE +#define SIMPLE_HASHTABLE_VALUE_TYPE void +#endif + +// First layer of macro for token concatenation +#define CONCAT_INTERNAL(a, b) a ## b +// Second layer of macro, which ensures proper expansion +#define CONCAT(a, b) CONCAT_INTERNAL(a, b) + +// define names for all structures and structures +#define simple_hashtable_init_named CONCAT(simple_hashtable_init, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_destroy_named CONCAT(simple_hashtable_destroy, SIMPLE_HASHTABLE_NAME) + +#define simple_hashtable_slot_named CONCAT(simple_hashtable_slot, SIMPLE_HASHTABLE_NAME) +#define SIMPLE_HASHTABLE_SLOT_NAMED CONCAT(SIMPLE_HASHTABLE_SLOT, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_named CONCAT(simple_hashtable, SIMPLE_HASHTABLE_NAME) +#define SIMPLE_HASHTABLE_NAMED CONCAT(SIMPLE_HASHTABLE, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_resize_named CONCAT(simple_hashtable_resize, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_get_slot_named CONCAT(simple_hashtable_get_slot, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_del_slot_named CONCAT(simple_hashtable_del_slot, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_set_slot_named CONCAT(simple_hashtable_set_slot, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_first_read_only_named CONCAT(simple_hashtable_first_read_only, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_next_read_only_named CONCAT(simple_hashtable_next_read_only, SIMPLE_HASHTABLE_NAME) + +#define simple_hashtable_sorted_binary_search_named CONCAT(simple_hashtable_sorted_binary_search, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_add_value_sorted_named CONCAT(simple_hashtable_add_value_sorted, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_del_value_sorted_named CONCAT(simple_hashtable_del_value_sorted, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_replace_value_sorted_named CONCAT(simple_hashtable_replace_value_sorted, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_sorted_array_first_read_only_named CONCAT(simple_hashtable_sorted_array_first_read_only, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_sorted_array_next_read_only_named CONCAT(simple_hashtable_sorted_array_next_read_only, SIMPLE_HASHTABLE_NAME) + +typedef struct simple_hashtable_slot_named { + SIMPLE_HASHTABLE_HASH hash; + SIMPLE_HASHTABLE_VALUE_TYPE *data; +} SIMPLE_HASHTABLE_SLOT_NAMED; + +typedef struct simple_hashtable_named { + size_t resizes; + size_t searches; + size_t collisions; + size_t deletions; + size_t deleted; + size_t used; + size_t size; + SIMPLE_HASHTABLE_SLOT_NAMED *hashtable; + +#ifdef SIMPLE_HASHTABLE_SORT_FUNCTION + struct { + size_t used; + size_t size; + SIMPLE_HASHTABLE_VALUE_TYPE **array; + } sorted; +#endif +} SIMPLE_HASHTABLE_NAMED; + +#ifdef SIMPLE_HASHTABLE_SORT_FUNCTION +static inline size_t simple_hashtable_sorted_binary_search_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_VALUE_TYPE *value) { + size_t left = 0, right = ht->sorted.used; + + while (left < right) { + size_t mid = left + (right - left) / 2; + if (SIMPLE_HASHTABLE_SORT_FUNCTION(ht->sorted.array[mid], value) < 0) + left = mid + 1; + else + right = mid; + } + + return left; +} + +static inline void simple_hashtable_add_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_VALUE_TYPE *value) { + size_t index = simple_hashtable_sorted_binary_search_named(ht, value); + + // Ensure there's enough space in the sorted array + if (ht->sorted.used >= ht->sorted.size) { + size_t size = ht->sorted.size ? ht->sorted.size * 2 : 64; + SIMPLE_HASHTABLE_VALUE_TYPE **array = mallocz(size * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + if(ht->sorted.array) { + memcpy(array, ht->sorted.array, ht->sorted.size * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + freez(ht->sorted.array); + } + ht->sorted.array = array; + ht->sorted.size = size; + } + + // Use memmove to shift elements and create space for the new element + memmove(&ht->sorted.array[index + 1], &ht->sorted.array[index], (ht->sorted.used - index) * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + + ht->sorted.array[index] = value; + ht->sorted.used++; +} + +static inline void simple_hashtable_del_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_VALUE_TYPE *value) { + size_t index = simple_hashtable_sorted_binary_search_named(ht, value); + + // Check if the value exists at the found index + assert(index < ht->sorted.used && ht->sorted.array[index] == value); + + // Use memmove to shift elements and close the gap + memmove(&ht->sorted.array[index], &ht->sorted.array[index + 1], (ht->sorted.used - index - 1) * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + ht->sorted.used--; +} + +static inline void simple_hashtable_replace_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_VALUE_TYPE *old_value, SIMPLE_HASHTABLE_VALUE_TYPE *new_value) { + if(new_value == old_value) + return; + + size_t old_value_index = simple_hashtable_sorted_binary_search_named(ht, old_value); + assert(old_value_index < ht->sorted.used && ht->sorted.array[old_value_index] == old_value); + + int r = SIMPLE_HASHTABLE_SORT_FUNCTION(old_value, new_value); + if(r == 0) { + // Same value, so use the same index + ht->sorted.array[old_value_index] = new_value; + return; + } + + size_t new_value_index = simple_hashtable_sorted_binary_search_named(ht, new_value); + if(old_value_index == new_value_index) { + // Not the same value, but still at the same index + ht->sorted.array[old_value_index] = new_value; + return; + } + else if (old_value_index < new_value_index) { + // The old value is before the new value + size_t shift_start = old_value_index + 1; + size_t shift_end = new_value_index - 1; + size_t shift_size = shift_end - old_value_index; + + memmove(&ht->sorted.array[old_value_index], &ht->sorted.array[shift_start], shift_size * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + ht->sorted.array[shift_end] = new_value; + } + else { + // The old value is after the new value + size_t shift_start = new_value_index; + size_t shift_end = old_value_index; + size_t shift_size = shift_end - new_value_index; + + memmove(&ht->sorted.array[new_value_index + 1], &ht->sorted.array[shift_start], shift_size * sizeof(SIMPLE_HASHTABLE_VALUE_TYPE *)); + ht->sorted.array[new_value_index] = new_value; + } +} + +static inline SIMPLE_HASHTABLE_VALUE_TYPE **simple_hashtable_sorted_array_first_read_only_named(SIMPLE_HASHTABLE_NAMED *ht) { + if (ht->sorted.used > 0) { + return &ht->sorted.array[0]; + } + return NULL; +} + +static inline SIMPLE_HASHTABLE_VALUE_TYPE **simple_hashtable_sorted_array_next_read_only_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_VALUE_TYPE **last) { + if (!last) return NULL; + + // Calculate the current position in the sorted array + size_t currentIndex = last - ht->sorted.array; + + // Proceed to the next element if it exists + if (currentIndex + 1 < ht->sorted.used) { + return &ht->sorted.array[currentIndex + 1]; + } + + // If no more elements, return NULL + return NULL; +} + +#define SIMPLE_HASHTABLE_SORTED_FOREACH_READ_ONLY(ht, var, type, name) \ + for (type **(var) = simple_hashtable_sorted_array_first_read_only ## name(ht); \ + var; \ + (var) = simple_hashtable_sorted_array_next_read_only ## name(ht, var)) + +#define SIMPLE_HASHTABLE_SORTED_FOREACH_READ_ONLY_VALUE(var) (*(var)) + +#else +static inline void simple_hashtable_add_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht __maybe_unused, SIMPLE_HASHTABLE_VALUE_TYPE *value __maybe_unused) { ; } +static inline void simple_hashtable_del_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht __maybe_unused, SIMPLE_HASHTABLE_VALUE_TYPE *value __maybe_unused) { ; } +static inline void simple_hashtable_replace_value_sorted_named(SIMPLE_HASHTABLE_NAMED *ht __maybe_unused, SIMPLE_HASHTABLE_VALUE_TYPE *old_value __maybe_unused, SIMPLE_HASHTABLE_VALUE_TYPE *new_value __maybe_unused) { ; } +#endif + +static void simple_hashtable_init_named(SIMPLE_HASHTABLE_NAMED *ht, size_t size) { + memset(ht, 0, sizeof(*ht)); + ht->size = size; + ht->hashtable = callocz(ht->size, sizeof(*ht->hashtable)); +} + +static void simple_hashtable_destroy_named(SIMPLE_HASHTABLE_NAMED *ht) { +#ifdef SIMPLE_HASHTABLE_SORT_FUNCTION + freez(ht->sorted.array); +#endif + + freez(ht->hashtable); + memset(ht, 0, sizeof(*ht)); +} + +static inline void simple_hashtable_resize_named(SIMPLE_HASHTABLE_NAMED *ht); + +#define SHTS_DATA_UNSET ((void *)NULL) +#define SHTS_DATA_DELETED ((void *)0x01) +#define SHTS_DATA_USERNULL ((void *)0x02) +#define SHTS_IS_UNSET(sl) ((sl)->data == SHTS_DATA_UNSET) +#define SHTS_IS_DELETED(sl) ((sl)->data == SHTS_DATA_DELETED) +#define SHTS_IS_USERNULL(sl) ((sl)->data == SHTS_DATA_USERNULL) +#define SIMPLE_HASHTABLE_SLOT_DATA(sl) ((SHTS_IS_UNSET(sl) || SHTS_IS_DELETED(sl) || SHTS_IS_USERNULL(sl)) ? NULL : (sl)->data) +#define SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl) ((SHTS_IS_UNSET(sl) || SHTS_IS_DELETED(sl)) ? NULL : (sl)->data) + +// IMPORTANT +// The pointer returned by this call is valid up to the next call of this function (or the resize one) +// If you need to cache something, cache the hash, not the slot pointer. +static inline SIMPLE_HASHTABLE_SLOT_NAMED *simple_hashtable_get_slot_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_HASH hash, bool resize) { + ht->searches++; + + size_t slot; + SIMPLE_HASHTABLE_SLOT_NAMED *sl; + SIMPLE_HASHTABLE_SLOT_NAMED *deleted; + + slot = hash % ht->size; + sl = &ht->hashtable[slot]; + deleted = SHTS_IS_DELETED(sl) ? sl : NULL; + if(likely(!SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl) || sl->hash == hash)) + return (SHTS_IS_UNSET(sl) && deleted) ? deleted : sl; + + ht->collisions++; + + if(unlikely(resize && (ht->size <= (ht->used << 1) || ht->used >= ht->size))) { + simple_hashtable_resize_named(ht); + + slot = hash % ht->size; + sl = &ht->hashtable[slot]; + deleted = (!deleted && SHTS_IS_DELETED(sl)) ? sl : deleted; + if(likely(!SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl) || sl->hash == hash)) + return (SHTS_IS_UNSET(sl) && deleted) ? deleted : sl; + + ht->collisions++; + } + + slot = ((hash >> SIMPLE_HASHTABLE_HASH_SECOND_HASH_SHIFTS) + 1) % ht->size; + sl = &ht->hashtable[slot]; + deleted = (!deleted && SHTS_IS_DELETED(sl)) ? sl : deleted; + + // Linear probing until we find it + while (SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl) && sl->hash != hash) { + slot = (slot + 1) % ht->size; // Wrap around if necessary + sl = &ht->hashtable[slot]; + deleted = (!deleted && SHTS_IS_DELETED(sl)) ? sl : deleted; + ht->collisions++; + } + + return (SHTS_IS_UNSET(sl) && deleted) ? deleted : sl; +} + +static inline bool simple_hashtable_del_slot_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_SLOT_NAMED *sl) { + if(SHTS_IS_UNSET(sl) || SHTS_IS_DELETED(sl)) + return false; + + ht->deletions++; + ht->deleted++; + + simple_hashtable_del_value_sorted_named(ht, SIMPLE_HASHTABLE_SLOT_DATA(sl)); + + sl->data = SHTS_DATA_DELETED; + return true; +} + +static inline void simple_hashtable_set_slot_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_SLOT_NAMED *sl, SIMPLE_HASHTABLE_HASH hash, SIMPLE_HASHTABLE_VALUE_TYPE *data) { + if(data == NULL) + data = SHTS_DATA_USERNULL; + + if(unlikely(data == SHTS_DATA_UNSET || data == SHTS_DATA_DELETED)) { + simple_hashtable_del_slot_named(ht, sl); + return; + } + + if(likely(SHTS_IS_UNSET(sl))) { + simple_hashtable_add_value_sorted_named(ht, data); + ht->used++; + } + + else if(unlikely(SHTS_IS_DELETED(sl))) { + ht->deleted--; + } + + else + simple_hashtable_replace_value_sorted_named(ht, SIMPLE_HASHTABLE_SLOT_DATA(sl), data); + + sl->hash = hash; + sl->data = data; +} + +// IMPORTANT +// this call invalidates all SIMPLE_HASHTABLE_SLOT_NAMED pointers +static inline void simple_hashtable_resize_named(SIMPLE_HASHTABLE_NAMED *ht) { + SIMPLE_HASHTABLE_SLOT_NAMED *old = ht->hashtable; + size_t old_size = ht->size; + + ht->resizes++; + ht->size = (ht->size << 1) - ((ht->size > 16) ? 1 : 0); + ht->hashtable = callocz(ht->size, sizeof(*ht->hashtable)); + ht->used = ht->deleted = 0; + for(size_t i = 0 ; i < old_size ; i++) { + if(!SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(&old[i])) + continue; + + SIMPLE_HASHTABLE_SLOT_NAMED *slot = simple_hashtable_get_slot_named(ht, old[i].hash, false); + *slot = old[i]; + ht->used++; + } + + freez(old); +} + +// ---------------------------------------------------------------------------- +// hashtable traversal, in read-only mode +// the hashtable should not be modified while the traversal is taking place + +static inline SIMPLE_HASHTABLE_SLOT_NAMED *simple_hashtable_first_read_only_named(SIMPLE_HASHTABLE_NAMED *ht) { + for(size_t i = 0; i < ht->used ;i++) { + SIMPLE_HASHTABLE_SLOT_NAMED *sl = &ht->hashtable[i]; + if(!SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl)) + return sl; + } + + return NULL; +} + +static inline SIMPLE_HASHTABLE_SLOT_NAMED *simple_hashtable_next_read_only_named(SIMPLE_HASHTABLE_NAMED *ht, SIMPLE_HASHTABLE_SLOT_NAMED *last) { + if (!last) return NULL; + + // Calculate the current position in the array + size_t currentIndex = last - ht->hashtable; + + // Iterate over the hashtable starting from the next element + for (size_t i = currentIndex + 1; i < ht->size; i++) { + SIMPLE_HASHTABLE_SLOT_NAMED *sl = &ht->hashtable[i]; + if (!SIMPLE_HASHTABLE_SLOT_UNSET_OR_DELETED(sl)) { + return sl; + } + } + + // If no more data slots are found, return NULL + return NULL; +} + +#define SIMPLE_HASHTABLE_FOREACH_READ_ONLY(ht, var, name) \ + for(struct simple_hashtable_slot ## name *(var) = simple_hashtable_first_read_only ## name(ht); \ + var; \ + (var) = simple_hashtable_next_read_only ## name(ht, var)) + +#define SIMPLE_HASHTABLE_FOREACH_READ_ONLY_VALUE(var) SIMPLE_HASHTABLE_SLOT_DATA(var) + +// ---------------------------------------------------------------------------- +// high level implementation + +#ifdef SIMPLE_HASHTABLE_SAMPLE_IMPLEMENTATION + +#define simple_hashtable_set_named CONCAT(simple_hashtable_set, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_get_named CONCAT(simple_hashtable_get, SIMPLE_HASHTABLE_NAME) +#define simple_hashtable_del_named CONCAT(simple_hashtable_del, SIMPLE_HASHTABLE_NAME) + +static inline SIMPLE_HASHTABLE_VALUE_TYPE *simple_hashtable_set_named(SIMPLE_HASHTABLE_NAMED *ht, void *key, size_t key_len, SIMPLE_HASHTABLE_VALUE_TYPE *data) { + XXH64_hash_t hash = XXH3_64bits(key, key_len); + SIMPLE_HASHTABLE_SLOT_NAMED *sl = simple_hashtable_get_slot_named(ht, hash, true); + simple_hashtable_set_slot_named(ht, sl, hash, data); + return SIMPLE_HASHTABLE_SLOT_DATA(sl); +} + +static inline SIMPLE_HASHTABLE_VALUE_TYPE *simple_hashtable_get_named(SIMPLE_HASHTABLE_NAMED *ht, void *key, size_t key_len, SIMPLE_HASHTABLE_VALUE_TYPE *data) { + XXH64_hash_t hash = XXH3_64bits(key, key_len); + SIMPLE_HASHTABLE_SLOT_NAMED *sl = simple_hashtable_get_slot_named(ht, hash, true); + return SIMPLE_HASHTABLE_SLOT_DATA(sl); +} + +static inline bool simple_hashtable_del_named(SIMPLE_HASHTABLE_NAMED *ht, void *key, size_t key_len, SIMPLE_HASHTABLE_VALUE_TYPE *data) { + XXH64_hash_t hash = XXH3_64bits(key, key_len); + SIMPLE_HASHTABLE_SLOT_NAMED *sl = simple_hashtable_get_slot_named(ht, hash, true); + return simple_hashtable_del_slot_named(ht, sl); +} + +#endif // SIMPLE_HASHTABLE_SAMPLE_IMPLEMENTATION + +#endif //NETDATA_SIMPLE_HASHTABLE_H diff --git a/libnetdata/socket/security.c b/libnetdata/socket/security.c index 3a3a171e..4deb7662 100644 --- a/libnetdata/socket/security.c +++ b/libnetdata/socket/security.c @@ -24,7 +24,7 @@ static SOCKET_PEERS netdata_ssl_peers(NETDATA_SSL *ssl) { } static void netdata_ssl_log_error_queue(const char *call, NETDATA_SSL *ssl, unsigned long err) { - error_limit_static_thread_var(erl, 1, 0); + nd_log_limit_static_thread_var(erl, 1, 0); if(err == SSL_ERROR_NONE) err = ERR_get_error(); @@ -103,13 +103,14 @@ static void netdata_ssl_log_error_queue(const char *call, NETDATA_SSL *ssl, unsi ERR_error_string_n(err, str, 1024); str[1024] = '\0'; SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: %s() on socket local [[%s]:%d] <-> remote [[%s]:%d], returned error %lu (%s): %s", - call, peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, err, code, str); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_ERR, + "SSL: %s() on socket local [[%s]:%d] <-> remote [[%s]:%d], returned error %lu (%s): %s", + call, peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, err, code, str); } while((err = ERR_get_error())); } -bool netdata_ssl_open(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd) { +bool netdata_ssl_open_ext(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd, const unsigned char *alpn_protos, unsigned int alpn_protos_len) { errno = 0; ssl->ssl_errno = 0; @@ -138,6 +139,8 @@ bool netdata_ssl_open(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd) { ssl->state = NETDATA_SSL_STATE_FAILED; return false; } + if (alpn_protos && alpn_protos_len > 0) + SSL_set_alpn_protos(ssl->conn, alpn_protos, alpn_protos_len); } if(SSL_set_fd(ssl->conn, fd) != 1) { @@ -153,6 +156,10 @@ bool netdata_ssl_open(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd) { return true; } +bool netdata_ssl_open(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd) { + return netdata_ssl_open_ext(ssl, ctx, fd, NULL, 0); +} + void netdata_ssl_close(NETDATA_SSL *ssl) { errno = 0; ssl->ssl_errno = 0; @@ -173,7 +180,7 @@ void netdata_ssl_close(NETDATA_SSL *ssl) { } static inline bool is_handshake_complete(NETDATA_SSL *ssl, const char *op) { - error_limit_static_thread_var(erl, 1, 0); + nd_log_limit_static_thread_var(erl, 1, 0); if(unlikely(!ssl->conn)) { internal_error(true, "SSL: trying to %s on a NULL connection", op); @@ -183,22 +190,25 @@ static inline bool is_handshake_complete(NETDATA_SSL *ssl, const char *op) { switch(ssl->state) { case NETDATA_SSL_STATE_NOT_SSL: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on non-SSL connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on non-SSL connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } case NETDATA_SSL_STATE_INIT: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on an incomplete connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on an incomplete connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } case NETDATA_SSL_STATE_FAILED: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on a failed connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on a failed connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } @@ -290,7 +300,7 @@ ssize_t netdata_ssl_write(NETDATA_SSL *ssl, const void *buf, size_t num) { } static inline bool is_handshake_initialized(NETDATA_SSL *ssl, const char *op) { - error_limit_static_thread_var(erl, 1, 0); + nd_log_limit_static_thread_var(erl, 1, 0); if(unlikely(!ssl->conn)) { internal_error(true, "SSL: trying to %s on a NULL connection", op); @@ -300,8 +310,9 @@ static inline bool is_handshake_initialized(NETDATA_SSL *ssl, const char *op) { switch(ssl->state) { case NETDATA_SSL_STATE_NOT_SSL: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on non-SSL connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on non-SSL connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } @@ -311,15 +322,17 @@ static inline bool is_handshake_initialized(NETDATA_SSL *ssl, const char *op) { case NETDATA_SSL_STATE_FAILED: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on a failed connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on a failed connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } case NETDATA_SSL_STATE_COMPLETE: { SOCKET_PEERS peers = netdata_ssl_peers(ssl); - error_limit(&erl, "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on an complete connection", - peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_WARNING, + "SSL: on socket local [[%s]:%d] <-> remote [[%s]:%d], attempt to %s on an complete connection", + peers.local.ip, peers.local.port, peers.peer.ip, peers.peer.port, op); return false; } } diff --git a/libnetdata/socket/security.h b/libnetdata/socket/security.h index a4082a07..fd17b6f3 100644 --- a/libnetdata/socket/security.h +++ b/libnetdata/socket/security.h @@ -64,6 +64,7 @@ bool netdata_ssl_connect(NETDATA_SSL *ssl); bool netdata_ssl_accept(NETDATA_SSL *ssl); bool netdata_ssl_open(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd); +bool netdata_ssl_open_ext(NETDATA_SSL *ssl, SSL_CTX *ctx, int fd, const unsigned char *alpn_protos, unsigned int alpn_protos_len); void netdata_ssl_close(NETDATA_SSL *ssl); ssize_t netdata_ssl_read(NETDATA_SSL *ssl, void *buf, size_t num); diff --git a/libnetdata/socket/socket.c b/libnetdata/socket/socket.c index 67dc4c71..605e8563 100644 --- a/libnetdata/socket/socket.c +++ b/libnetdata/socket/socket.c @@ -158,7 +158,9 @@ int sock_setnonblock(int fd) { int ret = fcntl(fd, F_SETFL, flags); if(ret < 0) - netdata_log_error("Failed to set O_NONBLOCK on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set O_NONBLOCK on socket %d", + fd); return ret; } @@ -171,7 +173,9 @@ int sock_delnonblock(int fd) { int ret = fcntl(fd, F_SETFL, flags); if(ret < 0) - netdata_log_error("Failed to remove O_NONBLOCK on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to remove O_NONBLOCK on socket %d", + fd); return ret; } @@ -180,7 +184,9 @@ int sock_setreuse(int fd, int reuse) { int ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof(reuse)); if(ret == -1) - netdata_log_error("Failed to set SO_REUSEADDR on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set SO_REUSEADDR on socket %d", + fd); return ret; } @@ -191,7 +197,9 @@ int sock_setreuse_port(int fd, int reuse) { #ifdef SO_REUSEPORT ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &reuse, sizeof(reuse)); if(ret == -1 && errno != ENOPROTOOPT) - netdata_log_error("failed to set SO_REUSEPORT on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "failed to set SO_REUSEPORT on socket %d", + fd); #else ret = -1; #endif @@ -205,7 +213,9 @@ int sock_enlarge_in(int fd) { ret = setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &bs, sizeof(bs)); if(ret == -1) - netdata_log_error("Failed to set SO_RCVBUF on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set SO_RCVBUF on socket %d", + fd); return ret; } @@ -215,7 +225,9 @@ int sock_enlarge_out(int fd) { ret = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &bs, sizeof(bs)); if(ret == -1) - netdata_log_error("Failed to set SO_SNDBUF on socket %d", fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set SO_SNDBUF on socket %d", + fd); return ret; } @@ -228,16 +240,16 @@ char *strdup_client_description(int family, const char *protocol, const char *ip switch(family) { case AF_INET: - snprintfz(buffer, 100, "%s:%s:%d", protocol, ip, port); + snprintfz(buffer, sizeof(buffer) - 1, "%s:%s:%d", protocol, ip, port); break; case AF_INET6: default: - snprintfz(buffer, 100, "%s:[%s]:%d", protocol, ip, port); + snprintfz(buffer, sizeof(buffer) - 1, "%s:[%s]:%d", protocol, ip, port); break; case AF_UNIX: - snprintfz(buffer, 100, "%s:%s", protocol, ip); + snprintfz(buffer, sizeof(buffer) - 1, "%s:%s", protocol, ip); break; } @@ -250,11 +262,12 @@ char *strdup_client_description(int family, const char *protocol, const char *ip int create_listen_socket_unix(const char *path, int listen_backlog) { int sock; - netdata_log_debug(D_LISTENER, "LISTENER: UNIX creating new listening socket on path '%s'", path); - sock = socket(AF_UNIX, SOCK_STREAM, 0); if(sock < 0) { - netdata_log_error("LISTENER: UNIX socket() on path '%s' failed.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: UNIX socket() on path '%s' failed.", + path); + return -1; } @@ -268,42 +281,52 @@ int create_listen_socket_unix(const char *path, int listen_backlog) { errno = 0; if (unlink(path) == -1 && errno != ENOENT) - netdata_log_error("LISTENER: failed to remove existing (probably obsolete or left-over) file on UNIX socket path '%s'.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: failed to remove existing (probably obsolete or left-over) file on UNIX socket path '%s'.", + path); if(bind (sock, (struct sockaddr *) &name, sizeof (name)) < 0) { close(sock); - netdata_log_error("LISTENER: UNIX bind() on path '%s' failed.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: UNIX bind() on path '%s' failed.", + path); + return -1; } // we have to chmod this to 0777 so that the client will be able // to read from and write to this socket. if(chmod(path, 0777) == -1) - netdata_log_error("LISTENER: failed to chmod() socket file '%s'.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: failed to chmod() socket file '%s'.", + path); if(listen(sock, listen_backlog) < 0) { close(sock); - netdata_log_error("LISTENER: UNIX listen() on path '%s' failed.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: UNIX listen() on path '%s' failed.", + path); + return -1; } - netdata_log_debug(D_LISTENER, "LISTENER: Listening on UNIX path '%s'", path); return sock; } int create_listen_socket4(int socktype, const char *ip, uint16_t port, int listen_backlog) { int sock; - netdata_log_debug(D_LISTENER, "LISTENER: IPv4 creating new listening socket on ip '%s' port %d, socktype %d", ip, port, socktype); - sock = socket(AF_INET, socktype, 0); if(sock < 0) { - netdata_log_error("LISTENER: IPv4 socket() on ip '%s' port %d, socktype %d failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv4 socket() on ip '%s' port %d, socktype %d failed.", + ip, port, socktype); + return -1; } sock_setreuse(sock, 1); - sock_setreuse_port(sock, 1); + sock_setreuse_port(sock, 0); sock_setnonblock(sock); sock_enlarge_in(sock); @@ -314,24 +337,36 @@ int create_listen_socket4(int socktype, const char *ip, uint16_t port, int liste int ret = inet_pton(AF_INET, ip, (void *)&name.sin_addr.s_addr); if(ret != 1) { - netdata_log_error("LISTENER: Failed to convert IP '%s' to a valid IPv4 address.", ip); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Failed to convert IP '%s' to a valid IPv4 address.", + ip); + close(sock); return -1; } if(bind (sock, (struct sockaddr *) &name, sizeof (name)) < 0) { close(sock); - netdata_log_error("LISTENER: IPv4 bind() on ip '%s' port %d, socktype %d failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv4 bind() on ip '%s' port %d, socktype %d failed.", + ip, port, socktype); + return -1; } if(socktype == SOCK_STREAM && listen(sock, listen_backlog) < 0) { close(sock); - netdata_log_error("LISTENER: IPv4 listen() on ip '%s' port %d, socktype %d failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv4 listen() on ip '%s' port %d, socktype %d failed.", + ip, port, socktype); + return -1; } - netdata_log_debug(D_LISTENER, "LISTENER: Listening on IPv4 ip '%s' port %d, socktype %d", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "LISTENER: Listening on IPv4 ip '%s' port %d, socktype %d", + ip, port, socktype); + return sock; } @@ -339,22 +374,25 @@ int create_listen_socket6(int socktype, uint32_t scope_id, const char *ip, int p int sock; int ipv6only = 1; - netdata_log_debug(D_LISTENER, "LISTENER: IPv6 creating new listening socket on ip '%s' port %d, socktype %d", ip, port, socktype); - sock = socket(AF_INET6, socktype, 0); if (sock < 0) { - netdata_log_error("LISTENER: IPv6 socket() on ip '%s' port %d, socktype %d, failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv6 socket() on ip '%s' port %d, socktype %d, failed.", + ip, port, socktype); + return -1; } sock_setreuse(sock, 1); - sock_setreuse_port(sock, 1); + sock_setreuse_port(sock, 0); sock_setnonblock(sock); sock_enlarge_in(sock); /* IPv6 only */ if(setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&ipv6only, sizeof(ipv6only)) != 0) - netdata_log_error("LISTENER: Cannot set IPV6_V6ONLY on ip '%s' port %d, socktype %d.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Cannot set IPV6_V6ONLY on ip '%s' port %d, socktype %d.", + ip, port, socktype); struct sockaddr_in6 name; memset(&name, 0, sizeof(struct sockaddr_in6)); @@ -364,7 +402,10 @@ int create_listen_socket6(int socktype, uint32_t scope_id, const char *ip, int p int ret = inet_pton(AF_INET6, ip, (void *)&name.sin6_addr.s6_addr); if(ret != 1) { - netdata_log_error("LISTENER: Failed to convert IP '%s' to a valid IPv6 address.", ip); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Failed to convert IP '%s' to a valid IPv6 address.", + ip); + close(sock); return -1; } @@ -373,23 +414,35 @@ int create_listen_socket6(int socktype, uint32_t scope_id, const char *ip, int p if (bind (sock, (struct sockaddr *) &name, sizeof (name)) < 0) { close(sock); - netdata_log_error("LISTENER: IPv6 bind() on ip '%s' port %d, socktype %d failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv6 bind() on ip '%s' port %d, socktype %d failed.", + ip, port, socktype); + return -1; } if (socktype == SOCK_STREAM && listen(sock, listen_backlog) < 0) { close(sock); - netdata_log_error("LISTENER: IPv6 listen() on ip '%s' port %d, socktype %d failed.", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: IPv6 listen() on ip '%s' port %d, socktype %d failed.", + ip, port, socktype); + return -1; } - netdata_log_debug(D_LISTENER, "LISTENER: Listening on IPv6 ip '%s' port %d, socktype %d", ip, port, socktype); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "LISTENER: Listening on IPv6 ip '%s' port %d, socktype %d", + ip, port, socktype); + return sock; } static inline int listen_sockets_add(LISTEN_SOCKETS *sockets, int fd, int family, int socktype, const char *protocol, const char *ip, uint16_t port, int acl_flags) { if(sockets->opened >= MAX_LISTEN_FDS) { - netdata_log_error("LISTENER: Too many listening sockets. Failed to add listening %s socket at ip '%s' port %d, protocol %s, socktype %d", protocol, ip, port, protocol, socktype); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Too many listening sockets. Failed to add listening %s socket at ip '%s' port %d, protocol %s, socktype %d", + protocol, ip, port, protocol, socktype); + close(fd); return -1; } @@ -519,7 +572,10 @@ static inline int bind_to_this(LISTEN_SOCKETS *sockets, const char *definition, protocol_str = "unix"; int fd = create_listen_socket_unix(path, listen_backlog); if (fd == -1) { - netdata_log_error("LISTENER: Cannot create unix socket '%s'", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Cannot create unix socket '%s'", + path); + sockets->failed++; } else { acl_flags = WEB_CLIENT_ACL_DASHBOARD | WEB_CLIENT_ACL_REGISTRY | WEB_CLIENT_ACL_BADGE | WEB_CLIENT_ACL_MGMT | WEB_CLIENT_ACL_NETDATACONF | WEB_CLIENT_ACL_STREAMING | WEB_CLIENT_ACL_SSL_DEFAULT; @@ -585,7 +641,10 @@ static inline int bind_to_this(LISTEN_SOCKETS *sockets, const char *definition, if(*interface) { scope_id = if_nametoindex(interface); if(!scope_id) - netdata_log_error("LISTENER: Cannot find a network interface named '%s'. Continuing with limiting the network interface", interface); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Cannot find a network interface named '%s'. " + "Continuing with limiting the network interface", + interface); } if(!*ip || *ip == '*' || !strcmp(ip, "any") || !strcmp(ip, "all")) @@ -605,7 +664,10 @@ static inline int bind_to_this(LISTEN_SOCKETS *sockets, const char *definition, int r = getaddrinfo(ip, port, &hints, &result); if (r != 0) { - netdata_log_error("LISTENER: getaddrinfo('%s', '%s'): %s\n", ip, port, gai_strerror(r)); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: getaddrinfo('%s', '%s'): %s\n", + ip, port, gai_strerror(r)); + return -1; } @@ -622,7 +684,6 @@ static inline int bind_to_this(LISTEN_SOCKETS *sockets, const char *definition, struct sockaddr_in *sin = (struct sockaddr_in *) rp->ai_addr; inet_ntop(AF_INET, &sin->sin_addr, rip, INET_ADDRSTRLEN); rport = ntohs(sin->sin_port); - // netdata_log_info("Attempting to listen on IPv4 '%s' ('%s'), port %d ('%s'), socktype %d", rip, ip, rport, port, socktype); fd = create_listen_socket4(socktype, rip, rport, listen_backlog); break; } @@ -631,18 +692,23 @@ static inline int bind_to_this(LISTEN_SOCKETS *sockets, const char *definition, struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) rp->ai_addr; inet_ntop(AF_INET6, &sin6->sin6_addr, rip, INET6_ADDRSTRLEN); rport = ntohs(sin6->sin6_port); - // netdata_log_info("Attempting to listen on IPv6 '%s' ('%s'), port %d ('%s'), socktype %d", rip, ip, rport, port, socktype); fd = create_listen_socket6(socktype, scope_id, rip, rport, listen_backlog); break; } default: - netdata_log_debug(D_LISTENER, "LISTENER: Unknown socket family %d", family); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "LISTENER: Unknown socket family %d", + family); + break; } if (fd == -1) { - netdata_log_error("LISTENER: Cannot bind to ip '%s', port %d", rip, rport); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Cannot bind to ip '%s', port %d", + rip, rport); + sockets->failed++; } else { @@ -664,13 +730,14 @@ int listen_sockets_setup(LISTEN_SOCKETS *sockets) { long long int old_port = sockets->default_port; long long int new_port = appconfig_get_number(sockets->config, sockets->config_section, "default port", sockets->default_port); if(new_port < 1 || new_port > 65535) { - netdata_log_error("LISTENER: Invalid listen port %lld given. Defaulting to %lld.", new_port, old_port); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Invalid listen port %lld given. Defaulting to %lld.", + new_port, old_port); + sockets->default_port = (uint16_t) appconfig_set_number(sockets->config, sockets->config_section, "default port", old_port); } else sockets->default_port = (uint16_t)new_port; - netdata_log_debug(D_OPTIONS, "LISTENER: Default listen port set to %d.", sockets->default_port); - char *s = appconfig_get(sockets->config, sockets->config_section, "bind to", sockets->default_bind_to); while(*s) { char *e = s; @@ -694,7 +761,9 @@ int listen_sockets_setup(LISTEN_SOCKETS *sockets) { if(sockets->failed) { size_t i; for(i = 0; i < sockets->opened ;i++) - netdata_log_info("LISTENER: Listen socket %s opened successfully.", sockets->fds_names[i]); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "LISTENER: Listen socket %s opened successfully.", + sockets->fds_names[i]); } return (int)sockets->opened; @@ -711,13 +780,18 @@ int listen_sockets_setup(LISTEN_SOCKETS *sockets) { static inline int connect_to_unix(const char *path, struct timeval *timeout) { int fd = socket(AF_UNIX, SOCK_STREAM, 0); if(fd == -1) { - netdata_log_error("Failed to create UNIX socket() for '%s'", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to create UNIX socket() for '%s'", + path); + return -1; } if(timeout) { if(setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, (char *) timeout, sizeof(struct timeval)) < 0) - netdata_log_error("Failed to set timeout on UNIX socket '%s'", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set timeout on UNIX socket '%s'", + path); } struct sockaddr_un addr; @@ -726,12 +800,17 @@ static inline int connect_to_unix(const char *path, struct timeval *timeout) { strncpy(addr.sun_path, path, sizeof(addr.sun_path)-1); if (connect(fd, (struct sockaddr*)&addr, sizeof(addr)) == -1) { - netdata_log_error("Cannot connect to UNIX socket on path '%s'.", path); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Cannot connect to UNIX socket on path '%s'.", + path); + close(fd); return -1; } - netdata_log_debug(D_CONNECT_TO, "Connected to UNIX socket on path '%s'.", path); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "Connected to UNIX socket on path '%s'.", + path); return fd; } @@ -757,10 +836,24 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t int ai_err = getaddrinfo(host, service, &hints, &ai_head); if (ai_err != 0) { - netdata_log_error("Cannot resolve host '%s', port '%s': %s", host, service, gai_strerror(ai_err)); + + nd_log(NDLS_DAEMON, NDLP_ERR, + "Cannot resolve host '%s', port '%s': %s", + host, service, gai_strerror(ai_err)); + return -1; } + char hostBfr[NI_MAXHOST + 1]; + char servBfr[NI_MAXSERV + 1]; + + ND_LOG_STACK lgs[] = { + ND_LOG_FIELD_TXT(NDF_DST_IP, hostBfr), + ND_LOG_FIELD_TXT(NDF_DST_PORT, servBfr), + ND_LOG_FIELD_END(), + }; + ND_LOG_STACK_PUSH(lgs); + int fd = -1; for (ai = ai_head; ai != NULL && fd == -1; ai = ai->ai_next) { @@ -771,9 +864,6 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t } } - char hostBfr[NI_MAXHOST + 1]; - char servBfr[NI_MAXSERV + 1]; - getnameinfo(ai->ai_addr, ai->ai_addrlen, hostBfr, @@ -782,54 +872,21 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t sizeof(servBfr), NI_NUMERICHOST | NI_NUMERICSERV); - netdata_log_debug(D_CONNECT_TO, "Address info: host = '%s', service = '%s', ai_flags = 0x%02X, ai_family = %d (PF_INET = %d, PF_INET6 = %d), ai_socktype = %d (SOCK_STREAM = %d, SOCK_DGRAM = %d), ai_protocol = %d (IPPROTO_TCP = %d, IPPROTO_UDP = %d), ai_addrlen = %lu (sockaddr_in = %lu, sockaddr_in6 = %lu)", - hostBfr, - servBfr, - (unsigned int)ai->ai_flags, - ai->ai_family, - PF_INET, - PF_INET6, - ai->ai_socktype, - SOCK_STREAM, - SOCK_DGRAM, - ai->ai_protocol, - IPPROTO_TCP, - IPPROTO_UDP, - (unsigned long)ai->ai_addrlen, - (unsigned long)sizeof(struct sockaddr_in), - (unsigned long)sizeof(struct sockaddr_in6)); - switch (ai->ai_addr->sa_family) { case PF_INET: { struct sockaddr_in *pSadrIn = (struct sockaddr_in *)ai->ai_addr; (void)pSadrIn; - - netdata_log_debug(D_CONNECT_TO, "ai_addr = sin_family: %d (AF_INET = %d, AF_INET6 = %d), sin_addr: '%s', sin_port: '%s'", - pSadrIn->sin_family, - AF_INET, - AF_INET6, - hostBfr, - servBfr); break; } case PF_INET6: { struct sockaddr_in6 *pSadrIn6 = (struct sockaddr_in6 *) ai->ai_addr; (void)pSadrIn6; - - netdata_log_debug(D_CONNECT_TO,"ai_addr = sin6_family: %d (AF_INET = %d, AF_INET6 = %d), sin6_addr: '%s', sin6_port: '%s', sin6_flowinfo: %u, sin6_scope_id: %u", - pSadrIn6->sin6_family, - AF_INET, - AF_INET6, - hostBfr, - servBfr, - pSadrIn6->sin6_flowinfo, - pSadrIn6->sin6_scope_id); break; } default: { - netdata_log_debug(D_CONNECT_TO, "Unknown protocol family %d.", ai->ai_family); + // Unknown protocol family continue; } } @@ -838,13 +895,17 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t if(fd != -1) { if(timeout) { if(setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, (char *) timeout, sizeof(struct timeval)) < 0) - netdata_log_error("Failed to set timeout on the socket to ip '%s' port '%s'", hostBfr, servBfr); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to set timeout on the socket to ip '%s' port '%s'", + hostBfr, servBfr); } errno = 0; if(connect(fd, ai->ai_addr, ai->ai_addrlen) < 0) { if(errno == EALREADY || errno == EINPROGRESS) { - internal_error(true, "Waiting for connection to ip %s port %s to be established", hostBfr, servBfr); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "Waiting for connection to ip %s port %s to be established", + hostBfr, servBfr); // Convert 'struct timeval' to milliseconds for poll(): int timeout_milliseconds = timeout->tv_sec * 1000 + timeout->tv_usec / 1000; @@ -858,11 +919,19 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t // poll() completed normally. We can check the revents to see what happened if (fds[0].revents & POLLOUT) { // connect() completed successfully, socket is writable. - netdata_log_info("connect() to ip %s port %s completed successfully", hostBfr, servBfr); + + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "connect() to ip %s port %s completed successfully", + hostBfr, servBfr); + } else { // This means that the socket is in error. We will close it and set fd to -1 - netdata_log_error("Failed to connect to '%s', port '%s'.", hostBfr, servBfr); + + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to connect to '%s', port '%s'.", + hostBfr, servBfr); + close(fd); fd = -1; } @@ -870,27 +939,38 @@ int connect_to_this_ip46(int protocol, int socktype, const char *host, uint32_t else if (ret == 0) { // poll() timed out, the connection is not established within the specified timeout. errno = 0; - netdata_log_error("Timed out while connecting to '%s', port '%s'.", hostBfr, servBfr); + + nd_log(NDLS_DAEMON, NDLP_ERR, + "Timed out while connecting to '%s', port '%s'.", + hostBfr, servBfr); + close(fd); fd = -1; } - else { + else { // ret < 0 // poll() returned an error. - netdata_log_error("Failed to connect to '%s', port '%s'. poll() returned %d", hostBfr, servBfr, ret); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to connect to '%s', port '%s'. poll() returned %d", + hostBfr, servBfr, ret); + close(fd); fd = -1; } } else { - netdata_log_error("Failed to connect to '%s', port '%s'", hostBfr, servBfr); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to connect to '%s', port '%s'", + hostBfr, servBfr); + close(fd); fd = -1; } } - - if(fd != -1) - netdata_log_debug(D_CONNECT_TO, "Connected to '%s' on port '%s'.", hostBfr, servBfr); } + else + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to socket() to '%s', port '%s'", + hostBfr, servBfr); } freeaddrinfo(ai_head); @@ -965,17 +1045,20 @@ int connect_to_this(const char *definition, int default_port, struct timeval *ti service = e; } - netdata_log_debug(D_CONNECT_TO, "Attempting connection to host = '%s', service = '%s', interface = '%s', protocol = %d (tcp = %d, udp = %d)", host, service, interface, protocol, IPPROTO_TCP, IPPROTO_UDP); - if(!*host) { - netdata_log_error("Definition '%s' does not specify a host.", definition); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Definition '%s' does not specify a host.", + definition); + return -1; } if(*interface) { scope_id = if_nametoindex(interface); if(!scope_id) - netdata_log_error("Cannot find a network interface named '%s'. Continuing with limiting the network interface", interface); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Cannot find a network interface named '%s'. Continuing with limiting the network interface", + interface); } if(!*service) @@ -1117,7 +1200,6 @@ ssize_t recv_timeout(int sockfd, void *buf, size_t len, int flags, int timeout) } #endif - internal_error(true, "%s(): calling recv()", __FUNCTION__ ); return recv(sockfd, buf, len, flags); } @@ -1160,7 +1242,9 @@ ssize_t send_timeout(int sockfd, void *buf, size_t len, int flags, int timeout) return netdata_ssl_write(ssl, buf, len); } else { - netdata_log_error("cannot write to SSL connection - connection is not ready."); + nd_log(NDLS_DAEMON, NDLP_ERR, + "cannot write to SSL connection - connection is not ready."); + return -1; } } @@ -1224,7 +1308,6 @@ int accept4(int sock, struct sockaddr *addr, socklen_t *addrlen, int flags) { int connection_allowed(int fd, char *client_ip, char *client_host, size_t hostsize, SIMPLE_PATTERN *access_list, const char *patname, int allow_dns) { - netdata_log_debug(D_LISTENER,"checking %s... (allow_dns=%d)", patname, allow_dns); if (!access_list) return 1; if (simple_pattern_matches(access_list, client_ip)) @@ -1239,16 +1322,21 @@ int connection_allowed(int fd, char *client_ip, char *client_host, size_t hostsi if (err != 0 || (err = getnameinfo((struct sockaddr *)&sadr, addrlen, client_host, (socklen_t)hostsize, NULL, 0, NI_NAMEREQD)) != 0) { - netdata_log_error("Incoming %s on '%s' does not match a numeric pattern, and host could not be resolved (err=%s)", - patname, client_ip, gai_strerror(err)); + + nd_log(NDLS_DAEMON, NDLP_ERR, + "Incoming %s on '%s' does not match a numeric pattern, and host could not be resolved (err=%s)", + patname, client_ip, gai_strerror(err)); + if (hostsize >= 8) strcpy(client_host,"UNKNOWN"); return 0; } struct addrinfo *addr_infos = NULL; if (getaddrinfo(client_host, NULL, NULL, &addr_infos) !=0 ) { - netdata_log_error("LISTENER: cannot validate hostname '%s' from '%s' by resolving it", - client_host, client_ip); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: cannot validate hostname '%s' from '%s' by resolving it", + client_host, client_ip); + if (hostsize >= 8) strcpy(client_host,"UNKNOWN"); return 0; @@ -1266,8 +1354,6 @@ int connection_allowed(int fd, char *client_ip, char *client_host, size_t hostsi inet_ntop(AF_INET6, &((struct sockaddr_in6*)(scan->ai_addr))->sin6_addr, address, INET6_ADDRSTRLEN); break; } - netdata_log_debug(D_LISTENER, "Incoming ip %s rev-resolved onto %s, validating against forward-resolution %s", - client_ip, client_host, address); if (!strcmp(client_ip, address)) { validated = 1; break; @@ -1275,18 +1361,19 @@ int connection_allowed(int fd, char *client_ip, char *client_host, size_t hostsi scan = scan->ai_next; } if (!validated) { - netdata_log_error("LISTENER: Cannot validate '%s' as ip of '%s', not listed in DNS", client_ip, client_host); + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: Cannot validate '%s' as ip of '%s', not listed in DNS", + client_ip, client_host); + if (hostsize >= 8) strcpy(client_host,"UNKNOWN"); } if (addr_infos!=NULL) freeaddrinfo(addr_infos); } - if (!simple_pattern_matches(access_list, client_host)) { - netdata_log_debug(D_LISTENER, "Incoming connection on '%s' (%s) does not match allowed pattern for %s", - client_ip, client_host, patname); + if (!simple_pattern_matches(access_list, client_host)) return 0; - } + return 1; } @@ -1301,7 +1388,10 @@ int accept_socket(int fd, int flags, char *client_ip, size_t ipsize, char *clien if (likely(nfd >= 0)) { if (getnameinfo((struct sockaddr *)&sadr, addrlen, client_ip, (socklen_t)ipsize, client_port, (socklen_t)portsize, NI_NUMERICHOST | NI_NUMERICSERV) != 0) { - netdata_log_error("LISTENER: cannot getnameinfo() on received client connection."); + + nd_log(NDLS_DAEMON, NDLP_ERR, + "LISTENER: cannot getnameinfo() on received client connection."); + strncpyz(client_ip, "UNKNOWN", ipsize); strncpyz(client_port, "UNKNOWN", portsize); } @@ -1319,31 +1409,34 @@ int accept_socket(int fd, int flags, char *client_ip, size_t ipsize, char *clien switch (((struct sockaddr *)&sadr)->sa_family) { case AF_UNIX: - netdata_log_debug(D_LISTENER, "New UNIX domain web client from %s on socket %d.", client_ip, fd); + // netdata_log_debug(D_LISTENER, "New UNIX domain web client from %s on socket %d.", client_ip, fd); // set the port - certain versions of libc return garbage on unix sockets strncpyz(client_port, "UNIX", portsize); break; case AF_INET: - netdata_log_debug(D_LISTENER, "New IPv4 web client from %s port %s on socket %d.", client_ip, client_port, fd); + // netdata_log_debug(D_LISTENER, "New IPv4 web client from %s port %s on socket %d.", client_ip, client_port, fd); break; case AF_INET6: if (strncmp(client_ip, "::ffff:", 7) == 0) { memmove(client_ip, &client_ip[7], strlen(&client_ip[7]) + 1); - netdata_log_debug(D_LISTENER, "New IPv4 web client from %s port %s on socket %d.", client_ip, client_port, fd); + // netdata_log_debug(D_LISTENER, "New IPv4 web client from %s port %s on socket %d.", client_ip, client_port, fd); } - else - netdata_log_debug(D_LISTENER, "New IPv6 web client from %s port %s on socket %d.", client_ip, client_port, fd); + // else + // netdata_log_debug(D_LISTENER, "New IPv6 web client from %s port %s on socket %d.", client_ip, client_port, fd); break; default: - netdata_log_debug(D_LISTENER, "New UNKNOWN web client from %s port %s on socket %d.", client_ip, client_port, fd); + // netdata_log_debug(D_LISTENER, "New UNKNOWN web client from %s port %s on socket %d.", client_ip, client_port, fd); break; } if (!connection_allowed(nfd, client_ip, client_host, hostsize, access_list, "connection", allow_dns)) { errno = 0; - netdata_log_error("Permission denied for client '%s', port '%s'", client_ip, client_port); + nd_log(NDLS_DAEMON, NDLP_WARNING, + "Permission denied for client '%s', port '%s'", + client_ip, client_port); + close(nfd); nfd = -1; errno = EPERM; @@ -1351,7 +1444,9 @@ int accept_socket(int fd, int flags, char *client_ip, size_t ipsize, char *clien } #ifdef HAVE_ACCEPT4 else if (errno == ENOSYS) - netdata_log_error("netdata has been compiled with the assumption that the system has the accept4() call, but it is not here. Recompile netdata like this: ./configure --disable-accept4 ..."); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Netdata has been compiled with the assumption that the system has the accept4() call, but it is not here. " + "Recompile netdata like this: ./configure --disable-accept4 ..."); #endif return nfd; @@ -1379,19 +1474,16 @@ inline POLLINFO *poll_add_fd(POLLJOB *p , int (*snd_callback)(POLLINFO * /*pi*/, short int * /*events*/) , void *data ) { - netdata_log_debug(D_POLLFD, "POLLFD: ADD: request to add fd %d, slots = %zu, used = %zu, min = %zu, max = %zu, next free = %zd", fd, p->slots, p->used, p->min, p->max, p->first_free?(ssize_t)p->first_free->slot:(ssize_t)-1); - if(unlikely(fd < 0)) return NULL; //if(p->limit && p->used >= p->limit) { - // netdata_log_info("Max sockets limit reached (%zu sockets), dropping connection", p->used); + // nd_log(NDLS_DAEMON, NDLP_WARNING, "Max sockets limit reached (%zu sockets), dropping connection", p->used); // close(fd); // return NULL; //} if(unlikely(!p->first_free)) { size_t new_slots = p->slots + POLL_FDS_INCREASE_STEP; - netdata_log_debug(D_POLLFD, "POLLFD: ADD: increasing size (current = %zu, new = %zu, used = %zu, min = %zu, max = %zu)", p->slots, new_slots, p->used, p->min, p->max); p->fds = reallocz(p->fds, sizeof(struct pollfd) * new_slots); p->inf = reallocz(p->inf, sizeof(POLLINFO) * new_slots); @@ -1399,7 +1491,6 @@ inline POLLINFO *poll_add_fd(POLLJOB *p // reset all the newly added slots ssize_t i; for(i = new_slots - 1; i >= (ssize_t)p->slots ; i--) { - netdata_log_debug(D_POLLFD, "POLLFD: ADD: resetting new slot %zd", i); p->fds[i].fd = -1; p->fds[i].events = 0; p->fds[i].revents = 0; @@ -1430,8 +1521,6 @@ inline POLLINFO *poll_add_fd(POLLJOB *p POLLINFO *pi = p->first_free; p->first_free = p->first_free->next; - netdata_log_debug(D_POLLFD, "POLLFD: ADD: selected slot %zu, next free is %zd", pi->slot, p->first_free?(ssize_t)p->first_free->slot:(ssize_t)-1); - struct pollfd *pf = &p->fds[pi->slot]; pf->fd = fd; pf->events = POLLIN; @@ -1472,8 +1561,6 @@ inline POLLINFO *poll_add_fd(POLLJOB *p } netdata_thread_enable_cancelability(); - netdata_log_debug(D_POLLFD, "POLLFD: ADD: completed, slots = %zu, used = %zu, min = %zu, max = %zu, next free = %zd", p->slots, p->used, p->min, p->max, p->first_free?(ssize_t)p->first_free->slot:(ssize_t)-1); - return pi; } @@ -1481,7 +1568,6 @@ inline void poll_close_fd(POLLINFO *pi) { POLLJOB *p = pi->p; struct pollfd *pf = &p->fds[pi->slot]; - netdata_log_debug(D_POLLFD, "POLLFD: DEL: request to clear slot %zu (fd %d), old next free was %zd", pi->slot, pf->fd, p->first_free?(ssize_t)p->first_free->slot:(ssize_t)-1); if(unlikely(pf->fd == -1)) return; @@ -1492,7 +1578,9 @@ inline void poll_close_fd(POLLINFO *pi) { if(likely(!(pi->flags & POLLINFO_FLAG_DONT_CLOSE))) { if(close(pf->fd) == -1) - netdata_log_error("Failed to close() poll_events() socket %d", pf->fd); + nd_log(NDLS_DAEMON, NDLP_ERR, + "Failed to close() poll_events() socket %d", + pf->fd); } } @@ -1533,8 +1621,6 @@ inline void poll_close_fd(POLLINFO *pi) { } } netdata_thread_enable_cancelability(); - - netdata_log_debug(D_POLLFD, "POLLFD: DEL: completed, slots = %zu, used = %zu, min = %zu, max = %zu, next free = %zd", p->slots, p->used, p->min, p->max, p->first_free?(ssize_t)p->first_free->slot:(ssize_t)-1); } void *poll_default_add_callback(POLLINFO *pi, short int *events, void *data) { @@ -1542,14 +1628,13 @@ void *poll_default_add_callback(POLLINFO *pi, short int *events, void *data) { (void)events; (void)data; - // netdata_log_error("POLLFD: internal error: poll_default_add_callback() called"); - return NULL; } void poll_default_del_callback(POLLINFO *pi) { if(pi->data) - netdata_log_error("POLLFD: internal error: del_callback_default() called with data pointer - possible memory leak"); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: internal error: del_callback_default() called with data pointer - possible memory leak"); } int poll_default_rcv_callback(POLLINFO *pi, short int *events) { @@ -1563,12 +1648,17 @@ int poll_default_rcv_callback(POLLINFO *pi, short int *events) { if (rc < 0) { // read failed if (errno != EWOULDBLOCK && errno != EAGAIN) { - netdata_log_error("POLLFD: poll_default_rcv_callback(): recv() failed with %zd.", rc); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: poll_default_rcv_callback(): recv() failed with %zd.", + rc); + return -1; } } else if (rc) { // data received - netdata_log_info("POLLFD: internal error: poll_default_rcv_callback() is discarding %zd bytes received on socket %d", rc, pi->fd); + nd_log(NDLS_DAEMON, NDLP_WARNING, + "POLLFD: internal error: poll_default_rcv_callback() is discarding %zd bytes received on socket %d", + rc, pi->fd); } } while (rc != -1); @@ -1578,7 +1668,10 @@ int poll_default_rcv_callback(POLLINFO *pi, short int *events) { int poll_default_snd_callback(POLLINFO *pi, short int *events) { *events &= ~POLLOUT; - netdata_log_info("POLLFD: internal error: poll_default_snd_callback(): nothing to send on socket %d", pi->fd); + nd_log(NDLS_DAEMON, NDLP_WARNING, + "POLLFD: internal error: poll_default_snd_callback(): nothing to send on socket %d", + pi->fd); + return 0; } @@ -1600,17 +1693,25 @@ static void poll_events_cleanup(void *data) { } static int poll_process_error(POLLINFO *pi, struct pollfd *pf, short int revents) { - netdata_log_error("POLLFD: LISTENER: received %s %s %s on socket at slot %zu (fd %d) client '%s' port '%s' expecting %s %s %s, having %s %s %s" - , revents & POLLERR ? "POLLERR" : "" - , revents & POLLHUP ? "POLLHUP" : "" - , revents & POLLNVAL ? "POLLNVAL" : "" - , pi->slot - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , pf->events & POLLIN ? "POLLIN" : "", pf->events & POLLOUT ? "POLLOUT" : "", pf->events & POLLPRI ? "POLLPRI" : "" - , revents & POLLIN ? "POLLIN" : "", revents & POLLOUT ? "POLLOUT" : "", revents & POLLPRI ? "POLLPRI" : "" - ); + ND_LOG_STACK lgs[] = { + ND_LOG_FIELD_TXT(NDF_SRC_IP, pi->client_ip), + ND_LOG_FIELD_TXT(NDF_SRC_PORT, pi->client_port), + ND_LOG_FIELD_END(), + }; + ND_LOG_STACK_PUSH(lgs); + + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "POLLFD: LISTENER: received %s %s %s on socket at slot %zu (fd %d) client '%s' port '%s' expecting %s %s %s, having %s %s %s" + , revents & POLLERR ? "POLLERR" : "" + , revents & POLLHUP ? "POLLHUP" : "" + , revents & POLLNVAL ? "POLLNVAL" : "" + , pi->slot + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , pf->events & POLLIN ? "POLLIN" : "", pf->events & POLLOUT ? "POLLOUT" : "", pf->events & POLLPRI ? "POLLPRI" : "" + , revents & POLLIN ? "POLLIN" : "", revents & POLLOUT ? "POLLOUT" : "", revents & POLLPRI ? "POLLPRI" : "" + ); pf->events = 0; poll_close_fd(pi); @@ -1621,8 +1722,6 @@ static inline int poll_process_send(POLLJOB *p, POLLINFO *pi, struct pollfd *pf, pi->last_sent_t = now; pi->send_count++; - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: sending data to socket on slot %zu (fd %d)", pi->slot, pf->fd); - pf->events = 0; // remember the slot, in case we need to close it later @@ -1642,8 +1741,6 @@ static inline int poll_process_tcp_read(POLLJOB *p, POLLINFO *pi, struct pollfd pi->last_received_t = now; pi->recv_count++; - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: reading data from TCP client slot %zu (fd %d)", pi->slot, pf->fd); - pf->events = 0; // remember the slot, in case we need to close it later @@ -1663,8 +1760,6 @@ static inline int poll_process_udp_read(POLLINFO *pi, struct pollfd *pf, time_t pi->last_received_t = now; pi->recv_count++; - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: reading data from UDP slot %zu (fd %d)", pi->slot, pf->fd); - // TODO: access_list is not applied to UDP // but checking the access list on every UDP packet will destroy // performance, especially for statsd. @@ -1683,14 +1778,10 @@ static int poll_process_new_tcp_connection(POLLJOB *p, POLLINFO *pi, struct poll pi->last_received_t = now; pi->recv_count++; - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: accepting connections from slot %zu (fd %d)", pi->slot, pf->fd); - char client_ip[INET6_ADDRSTRLEN] = ""; char client_port[NI_MAXSERV] = ""; char client_host[NI_MAXHOST] = ""; - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: calling accept4() slot %zu (fd %d)", pi->slot, pf->fd); - int nfd = accept_socket( pf->fd,SOCK_NONBLOCK, client_ip, INET6_ADDRSTRLEN, client_port,NI_MAXSERV, client_host, NI_MAXHOST, @@ -1700,15 +1791,15 @@ static int poll_process_new_tcp_connection(POLLJOB *p, POLLINFO *pi, struct poll if (unlikely(nfd < 0)) { // accept failed - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: accept4() slot %zu (fd %d) failed.", pi->slot, pf->fd); - if(unlikely(errno == EMFILE)) { - error_limit_static_global_var(erl, 10, 1000); - error_limit(&erl, "POLLFD: LISTENER: too many open files - used by this thread %zu, max for this thread %zu", - p->used, p->limit); + nd_log_limit_static_global_var(erl, 10, 1000); + nd_log_limit(&erl, NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: too many open files - used by this thread %zu, max for this thread %zu", + p->used, p->limit); } else if(unlikely(errno != EWOULDBLOCK && errno != EAGAIN)) - netdata_log_error("POLLFD: LISTENER: accept() failed."); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: accept() failed."); } else { @@ -1755,7 +1846,8 @@ void poll_events(LISTEN_SOCKETS *sockets , size_t max_tcp_sockets ) { if(!sockets || !sockets->opened) { - netdata_log_error("POLLFD: internal error: no listening sockets are opened"); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: internal error: no listening sockets are opened"); return; } @@ -1808,7 +1900,9 @@ void poll_events(LISTEN_SOCKETS *sockets ); pi->data = data; - netdata_log_info("POLLFD: LISTENER: listening on '%s'", (sockets->fds_names[i])?sockets->fds_names[i]:"UNKNOWN"); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "POLLFD: LISTENER: listening on '%s'", + (sockets->fds_names[i])?sockets->fds_names[i]:"UNKNOWN"); } int listen_sockets_active = 1; @@ -1832,7 +1926,6 @@ void poll_events(LISTEN_SOCKETS *sockets now_usec = now_boottime_usec(); if(unlikely(timer_usec && now_usec >= next_timer_usec)) { - netdata_log_debug(D_POLLFD, "Calling timer callback after %zu usec", (size_t)(now_usec - last_timer_usec)); last_timer_usec = now_usec; p.tmr_callback(p.timer_data); now_usec = now_boottime_usec(); @@ -1849,7 +1942,11 @@ void poll_events(LISTEN_SOCKETS *sockets // enable or disable the TCP listening sockets, based on the current number of sockets used and the limit set if((listen_sockets_active && (p.limit && p.used >= p.limit)) || (!listen_sockets_active && (!p.limit || p.used < p.limit))) { listen_sockets_active = !listen_sockets_active; - netdata_log_info("%s listening sockets (used TCP sockets %zu, max allowed for this worker %zu)", (listen_sockets_active)?"ENABLING":"DISABLING", p.used, p.limit); + + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "%s listening sockets (used TCP sockets %zu, max allowed for this worker %zu)", + (listen_sockets_active)?"ENABLING":"DISABLING", p.used, p.limit); + for (i = 0; i <= p.max; i++) { if(p.inf[i].flags & POLLINFO_FLAG_SERVER_SOCKET && p.inf[i].socktype == SOCK_STREAM) { p.fds[i].events = (short int) ((listen_sockets_active) ? POLLIN : 0); @@ -1857,16 +1954,19 @@ void poll_events(LISTEN_SOCKETS *sockets } } - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: Waiting on %zu sockets for %zu ms...", p.max + 1, (size_t)timeout_ms); retval = poll(p.fds, p.max + 1, timeout_ms); time_t now = now_boottime_sec(); if(unlikely(retval == -1)) { - netdata_log_error("POLLFD: LISTENER: poll() failed while waiting on %zu sockets.", p.max + 1); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: poll() failed while waiting on %zu sockets.", + p.max + 1); + break; } else if(unlikely(!retval)) { - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: poll() timeout."); + // timeout + ; } else { POLLINFO *pi; @@ -1920,31 +2020,34 @@ void poll_events(LISTEN_SOCKETS *sockets conns[conns_max++] = i; } else - netdata_log_error("POLLFD: LISTENER: server slot %zu (fd %d) connection from %s port %s using unhandled socket type %d." - , i - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , pi->socktype - ); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: server slot %zu (fd %d) connection from %s port %s using unhandled socket type %d." + , i + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , pi->socktype + ); } else - netdata_log_error("POLLFD: LISTENER: client slot %zu (fd %d) data from %s port %s using flags %08X is neither client nor server." - , i - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , pi->flags - ); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: client slot %zu (fd %d) data from %s port %s using flags %08X is neither client nor server." + , i + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , pi->flags + ); } else - netdata_log_error("POLLFD: LISTENER: socket slot %zu (fd %d) client %s port %s unhandled event id %d." - , i - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , revents - ); + nd_log(NDLS_DAEMON, NDLP_ERR, + "POLLFD: LISTENER: socket slot %zu (fd %d) client %s port %s unhandled event id %d." + , i + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , revents + ); } // process sends @@ -1997,23 +2100,25 @@ void poll_events(LISTEN_SOCKETS *sockets if(likely(pi->flags & POLLINFO_FLAG_CLIENT_SOCKET)) { if (unlikely(pi->send_count == 0 && p.complete_request_timeout > 0 && (now - pi->connected_t) >= p.complete_request_timeout)) { - netdata_log_info("POLLFD: LISTENER: client slot %zu (fd %d) from %s port %s has not sent a complete request in %zu seconds - closing it. " - , i - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , (size_t) p.complete_request_timeout - ); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "POLLFD: LISTENER: client slot %zu (fd %d) from %s port %s has not sent a complete request in %zu seconds - closing it. " + , i + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , (size_t) p.complete_request_timeout + ); poll_close_fd(pi); } else if(unlikely(pi->recv_count && p.idle_timeout > 0 && now - ((pi->last_received_t > pi->last_sent_t) ? pi->last_received_t : pi->last_sent_t) >= p.idle_timeout )) { - netdata_log_info("POLLFD: LISTENER: client slot %zu (fd %d) from %s port %s is idle for more than %zu seconds - closing it. " - , i - , pi->fd - , pi->client_ip ? pi->client_ip : "<undefined-ip>" - , pi->client_port ? pi->client_port : "<undefined-port>" - , (size_t) p.idle_timeout - ); + nd_log(NDLS_DAEMON, NDLP_DEBUG, + "POLLFD: LISTENER: client slot %zu (fd %d) from %s port %s is idle for more than %zu seconds - closing it. " + , i + , pi->fd + , pi->client_ip ? pi->client_ip : "<undefined-ip>" + , pi->client_port ? pi->client_port : "<undefined-port>" + , (size_t) p.idle_timeout + ); poll_close_fd(pi); } } @@ -2022,5 +2127,4 @@ void poll_events(LISTEN_SOCKETS *sockets } netdata_thread_cleanup_pop(1); - netdata_log_debug(D_POLLFD, "POLLFD: LISTENER: cleanup completed"); } diff --git a/libnetdata/string/string.c b/libnetdata/string/string.c index 54b8f171..e1c8352a 100644 --- a/libnetdata/string/string.c +++ b/libnetdata/string/string.c @@ -338,10 +338,6 @@ inline const char *string2str(STRING *string) { return string->str; } -int string_strcmp(STRING *string, const char *s) { - return strcmp(string2str(string), s); -} - STRING *string_2way_merge(STRING *a, STRING *b) { static STRING *X = NULL; @@ -420,7 +416,7 @@ static char **string_unittest_generate_names(size_t entries) { char **names = mallocz(sizeof(char *) * entries); for(size_t i = 0; i < entries ;i++) { char buf[25 + 1] = ""; - snprintfz(buf, 25, "name.%zu.0123456789.%zu \t !@#$%%^&*(),./[]{}\\|~`", i, entries / 2 + i); + snprintfz(buf, sizeof(buf) - 1, "name.%zu.0123456789.%zu \t !@#$%%^&*(),./[]{}\\|~`", i, entries / 2 + i); names[i] = strdupz(buf); } return names; diff --git a/libnetdata/string/string.h b/libnetdata/string/string.h index 70840ee9..ba0e3876 100644 --- a/libnetdata/string/string.h +++ b/libnetdata/string/string.h @@ -13,7 +13,6 @@ STRING *string_dup(STRING *string); void string_freez(STRING *string); size_t string_strlen(STRING *string); const char *string2str(STRING *string) NEVERNULL; -int string_strcmp(STRING *string, const char *s); // keep common prefix/suffix and replace everything else with [x] STRING *string_2way_merge(STRING *a, STRING *b); @@ -24,6 +23,10 @@ static inline int string_cmp(STRING *s1, STRING *s2) { return (s1 == s2)?0:strcmp(string2str(s1), string2str(s2)); } +static inline int string_strcmp(STRING *string, const char *s) { + return strcmp(string2str(string), s); +} + void string_statistics(size_t *inserts, size_t *deletes, size_t *searches, size_t *entries, size_t *references, size_t *memory, size_t *duplications, size_t *releases); int string_unittest(size_t entries); diff --git a/libnetdata/threads/threads.c b/libnetdata/threads/threads.c index cc569060..c14f9a7e 100644 --- a/libnetdata/threads/threads.c +++ b/libnetdata/threads/threads.c @@ -10,7 +10,6 @@ static pthread_attr_t *netdata_threads_attr = NULL; typedef struct { void *arg; char tag[NETDATA_THREAD_NAME_MAX + 1]; - SPINLOCK detach_lock; void *(*start_routine) (void *); NETDATA_THREAD_OPTIONS options; } NETDATA_THREAD; @@ -134,8 +133,6 @@ size_t netdata_threads_init(void) { i = pthread_attr_getstacksize(netdata_threads_attr, &stacksize); if(i != 0) fatal("pthread_attr_getstacksize() failed with code %d.", i); - else - netdata_log_debug(D_OPTIONS, "initial pthread stack size is %zu bytes", stacksize); return stacksize; } @@ -152,12 +149,12 @@ void netdata_threads_init_after_fork(size_t stacksize) { if(netdata_threads_attr && stacksize > (size_t)PTHREAD_STACK_MIN) { i = pthread_attr_setstacksize(netdata_threads_attr, stacksize); if(i != 0) - netdata_log_error("pthread_attr_setstacksize() to %zu bytes, failed with code %d.", stacksize, i); + nd_log(NDLS_DAEMON, NDLP_WARNING, "pthread_attr_setstacksize() to %zu bytes, failed with code %d.", stacksize, i); else - netdata_log_info("Set threads stack size to %zu bytes", stacksize); + nd_log(NDLS_DAEMON, NDLP_DEBUG, "Set threads stack size to %zu bytes", stacksize); } else - netdata_log_error("Invalid pthread stacksize %zu", stacksize); + nd_log(NDLS_DAEMON, NDLP_WARNING, "Invalid pthread stacksize %zu", stacksize); } // ---------------------------------------------------------------------------- @@ -183,12 +180,11 @@ void rrd_collector_finished(void); static void thread_cleanup(void *ptr) { if(netdata_thread != ptr) { NETDATA_THREAD *info = (NETDATA_THREAD *)ptr; - netdata_log_error("THREADS: internal error - thread local variable does not match the one passed to this function. Expected thread '%s', passed thread '%s'", netdata_thread->tag, info->tag); + nd_log(NDLS_DAEMON, NDLP_ERR, "THREADS: internal error - thread local variable does not match the one passed to this function. Expected thread '%s', passed thread '%s'", netdata_thread->tag, info->tag); } - spinlock_lock(&netdata_thread->detach_lock); if(!(netdata_thread->options & NETDATA_THREAD_OPTION_DONT_LOG_CLEANUP)) - netdata_log_info("thread with task id %d finished", gettid()); + nd_log(NDLS_DAEMON, NDLP_DEBUG, "thread with task id %d finished", gettid()); rrd_collector_finished(); sender_thread_buffer_free(); @@ -200,32 +196,34 @@ static void thread_cleanup(void *ptr) { netdata_thread->tag[0] = '\0'; - spinlock_unlock(&netdata_thread->detach_lock); freez(netdata_thread); netdata_thread = NULL; } -static void thread_set_name_np(NETDATA_THREAD *nt) { +void netdata_thread_set_tag(const char *tag) { + if(!tag || !*tag) + return; - if (nt && nt->tag[0]) { - int ret = 0; + int ret = 0; - char threadname[NETDATA_THREAD_NAME_MAX+1]; - strncpyz(threadname, nt->tag, NETDATA_THREAD_NAME_MAX); + char threadname[NETDATA_THREAD_NAME_MAX+1]; + strncpyz(threadname, tag, NETDATA_THREAD_NAME_MAX); #if defined(__FreeBSD__) - pthread_set_name_np(pthread_self(), threadname); + pthread_set_name_np(pthread_self(), threadname); #elif defined(__APPLE__) - ret = pthread_setname_np(threadname); + ret = pthread_setname_np(threadname); #else - ret = pthread_setname_np(pthread_self(), threadname); + ret = pthread_setname_np(pthread_self(), threadname); #endif - if (ret != 0) - netdata_log_error("cannot set pthread name of %d to %s. ErrCode: %d", gettid(), threadname, ret); - else - netdata_log_info("set name of thread %d to %s", gettid(), threadname); + if (ret != 0) + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread name of %d to %s. ErrCode: %d", gettid(), threadname, ret); + else + nd_log(NDLS_DAEMON, NDLP_DEBUG, "set name of thread %d to %s", gettid(), threadname); + if(netdata_thread) { + strncpyz(netdata_thread->tag, threadname, sizeof(netdata_thread->tag) - 1); } } @@ -247,7 +245,7 @@ void uv_thread_set_name_np(uv_thread_t ut, const char* name) { thread_name_get(true); if (ret) - netdata_log_info("cannot set libuv thread name to %s. Err: %d", threadname, ret); + nd_log(NDLS_DAEMON, NDLP_NOTICE, "cannot set libuv thread name to %s. Err: %d", threadname, ret); } void os_thread_get_current_name_np(char threadname[NETDATA_THREAD_NAME_MAX + 1]) @@ -264,15 +262,23 @@ static void *netdata_thread_init(void *ptr) { netdata_thread = (NETDATA_THREAD *)ptr; if(!(netdata_thread->options & NETDATA_THREAD_OPTION_DONT_LOG_STARTUP)) - netdata_log_info("thread created with task id %d", gettid()); + nd_log(NDLS_DAEMON, NDLP_DEBUG, "thread created with task id %d", gettid()); if(pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL) != 0) - netdata_log_error("cannot set pthread cancel type to DEFERRED."); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread cancel type to DEFERRED."); if(pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL) != 0) - netdata_log_error("cannot set pthread cancel state to ENABLE."); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot set pthread cancel state to ENABLE."); - thread_set_name_np(ptr); + netdata_thread_set_tag(netdata_thread->tag); + + if (!(netdata_thread->options & NETDATA_THREAD_OPTION_JOINABLE)) { + int rc = pthread_detach(pthread_self()); + if (rc != 0) + nd_log(NDLS_DAEMON, NDLP_WARNING, + "cannot request detach of newly created %s thread. pthread_detach() failed with code %d", + netdata_thread->tag, rc); + } void *ret = NULL; pthread_cleanup_push(thread_cleanup, ptr); @@ -289,22 +295,10 @@ int netdata_thread_create(netdata_thread_t *thread, const char *tag, NETDATA_THR info->options = options; strncpyz(info->tag, tag, NETDATA_THREAD_NAME_MAX); - spinlock_init(&info->detach_lock); - spinlock_lock(&info->detach_lock); - int ret = pthread_create(thread, netdata_threads_attr, netdata_thread_init, info); if(ret != 0) - netdata_log_error("failed to create new thread for %s. pthread_create() failed with code %d", tag, ret); - - else { - if (!(options & NETDATA_THREAD_OPTION_JOINABLE)) { - int ret2 = pthread_detach(*thread); - if (ret2 != 0) - netdata_log_error("cannot request detach of newly created %s thread. pthread_detach() failed with code %d", tag, ret2); - } - } + nd_log(NDLS_DAEMON, NDLP_ERR, "failed to create new thread for %s. pthread_create() failed with code %d", tag, ret); - spinlock_unlock(&info->detach_lock); return ret; } @@ -318,9 +312,9 @@ int netdata_thread_cancel(netdata_thread_t thread) { int ret = pthread_cancel(thread); if(ret != 0) #ifdef NETDATA_INTERNAL_CHECKS - netdata_log_error("cannot cancel thread. pthread_cancel() failed with code %d at %d@%s, function %s()", ret, line, file, function); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot cancel thread. pthread_cancel() failed with code %d at %d@%s, function %s()", ret, line, file, function); #else - netdata_log_error("cannot cancel thread. pthread_cancel() failed with code %d.", ret); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot cancel thread. pthread_cancel() failed with code %d.", ret); #endif return ret; @@ -332,7 +326,7 @@ int netdata_thread_cancel(netdata_thread_t thread) { int netdata_thread_join(netdata_thread_t thread, void **retval) { int ret = pthread_join(thread, retval); if(ret != 0) - netdata_log_error("cannot join thread. pthread_join() failed with code %d.", ret); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot join thread. pthread_join() failed with code %d.", ret); return ret; } @@ -340,7 +334,7 @@ int netdata_thread_join(netdata_thread_t thread, void **retval) { int netdata_thread_detach(pthread_t thread) { int ret = pthread_detach(thread); if(ret != 0) - netdata_log_error("cannot detach thread. pthread_detach() failed with code %d.", ret); + nd_log(NDLS_DAEMON, NDLP_WARNING, "cannot detach thread. pthread_detach() failed with code %d.", ret); return ret; } diff --git a/libnetdata/threads/threads.h b/libnetdata/threads/threads.h index acb4e6ba..97c3c803 100644 --- a/libnetdata/threads/threads.h +++ b/libnetdata/threads/threads.h @@ -18,6 +18,8 @@ typedef enum { #define netdata_thread_cleanup_push(func, arg) pthread_cleanup_push(func, arg) #define netdata_thread_cleanup_pop(execute) pthread_cleanup_pop(execute) +void netdata_thread_set_tag(const char *tag); + typedef pthread_t netdata_thread_t; struct netdata_static_thread { diff --git a/libnetdata/uuid/Makefile.am b/libnetdata/uuid/Makefile.am new file mode 100644 index 00000000..161784b8 --- /dev/null +++ b/libnetdata/uuid/Makefile.am @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-3.0-or-later + +AUTOMAKE_OPTIONS = subdir-objects +MAINTAINERCLEANFILES = $(srcdir)/Makefile.in + +dist_noinst_DATA = \ + README.md \ + $(NULL) diff --git a/libnetdata/uuid/README.md b/libnetdata/uuid/README.md new file mode 100644 index 00000000..fbadfd63 --- /dev/null +++ b/libnetdata/uuid/README.md @@ -0,0 +1,13 @@ +<!-- +title: "UUID" +custom_edit_url: https://github.com/netdata/netdata/edit/master/libnetdata/uuid/README.md +sidebar_label: "UUID" +learn_topic_type: "Tasks" +learn_rel_path: "Developers/libnetdata" +--> + +# UUID + +Netdata uses libuuid for managing UUIDs. + +In this folder are a few custom helpers.
\ No newline at end of file diff --git a/libnetdata/uuid/uuid.c b/libnetdata/uuid/uuid.c new file mode 100644 index 00000000..55b66db9 --- /dev/null +++ b/libnetdata/uuid/uuid.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "../libnetdata.h" + +void uuid_unparse_lower_compact(const uuid_t uuid, char *out) { + static const char *hex_chars = "0123456789abcdef"; + for (int i = 0; i < 16; i++) { + out[i * 2] = hex_chars[(uuid[i] >> 4) & 0x0F]; + out[i * 2 + 1] = hex_chars[uuid[i] & 0x0F]; + } + out[32] = '\0'; // Null-terminate the string +} + +inline int uuid_parse_compact(const char *in, uuid_t uuid) { + if (strlen(in) != 32) + return -1; // Invalid input length + + for (int i = 0; i < 16; i++) { + int high = hex_char_to_int(in[i * 2]); + int low = hex_char_to_int(in[i * 2 + 1]); + + if (high < 0 || low < 0) + return -1; // Invalid hexadecimal character + + uuid[i] = (high << 4) | low; + } + + return 0; // Success +} + +int uuid_parse_flexi(const char *in, uuid_t uu) { + if(!in || !*in) + return -1; + + size_t hexCharCount = 0; + size_t hyphenCount = 0; + const char *s = in; + int byteIndex = 0; + uuid_t uuid; // work on a temporary place, to not corrupt the previous value of uu if we fail + + while (*s && byteIndex < 16) { + if (*s == '-') { + s++; + hyphenCount++; + + if (unlikely(hyphenCount > 4)) + // Too many hyphens + return -2; + } + + if (likely(isxdigit(*s))) { + int high = hex_char_to_int(*s++); + hexCharCount++; + + if (likely(isxdigit(*s))) { + int low = hex_char_to_int(*s++); + hexCharCount++; + + uuid[byteIndex++] = (high << 4) | low; + } + else + // Not a valid UUID (expected a pair of hex digits) + return -3; + } + else + // Not a valid UUID + return -4; + } + + if (unlikely(byteIndex < 16)) + // Not enough data to form a UUID + return -5; + + if (unlikely(hexCharCount != 32)) + // wrong number of hex digits + return -6; + + if(unlikely(hyphenCount != 0 && hyphenCount != 4)) + // wrong number of hyphens + return -7; + + // copy the final value + memcpy(uu, uuid, sizeof(uuid_t)); + + return 0; +} + + +// ---------------------------------------------------------------------------- +// unit test + +static inline void remove_hyphens(const char *uuid_with_hyphens, char *uuid_without_hyphens) { + while (*uuid_with_hyphens) { + if (*uuid_with_hyphens != '-') { + *uuid_without_hyphens++ = *uuid_with_hyphens; + } + uuid_with_hyphens++; + } + *uuid_without_hyphens = '\0'; +} + +int uuid_unittest(void) { + const int num_tests = 100000; + int failed_tests = 0; + + int i; + for (i = 0; i < num_tests; i++) { + uuid_t original_uuid, parsed_uuid; + char uuid_str_with_hyphens[UUID_STR_LEN], uuid_str_without_hyphens[UUID_COMPACT_STR_LEN]; + + // Generate a random UUID + switch(i % 2) { + case 0: + uuid_generate(original_uuid); + break; + + case 1: + uuid_generate_random(original_uuid); + break; + } + + // Unparse it with hyphens + bool lower = false; + switch(i % 3) { + case 0: + uuid_unparse_lower(original_uuid, uuid_str_with_hyphens); + lower = true; + break; + + case 1: + uuid_unparse(original_uuid, uuid_str_with_hyphens); + break; + + case 2: + uuid_unparse_upper(original_uuid, uuid_str_with_hyphens); + break; + } + + // Remove the hyphens + remove_hyphens(uuid_str_with_hyphens, uuid_str_without_hyphens); + + if(lower) { + char test[UUID_COMPACT_STR_LEN]; + uuid_unparse_lower_compact(original_uuid, test); + if(strcmp(test, uuid_str_without_hyphens) != 0) { + printf("uuid_unparse_lower_compact() failed, expected '%s', got '%s'\n", + uuid_str_without_hyphens, test); + failed_tests++; + } + } + + // Parse the UUID string with hyphens + int parse_result = uuid_parse_flexi(uuid_str_with_hyphens, parsed_uuid); + if (parse_result != 0) { + printf("uuid_parse_flexi() returned -1 (parsing error) for UUID with hyphens: %s\n", uuid_str_with_hyphens); + failed_tests++; + } else if (uuid_compare(original_uuid, parsed_uuid) != 0) { + printf("uuid_parse_flexi() parsed value mismatch for UUID with hyphens: %s\n", uuid_str_with_hyphens); + failed_tests++; + } + + // Parse the UUID string without hyphens + parse_result = uuid_parse_flexi(uuid_str_without_hyphens, parsed_uuid); + if (parse_result != 0) { + printf("uuid_parse_flexi() returned -1 (parsing error) for UUID without hyphens: %s\n", uuid_str_without_hyphens); + failed_tests++; + } + else if(uuid_compare(original_uuid, parsed_uuid) != 0) { + printf("uuid_parse_flexi() parsed value mismatch for UUID without hyphens: %s\n", uuid_str_without_hyphens); + failed_tests++; + } + + if(failed_tests) + break; + } + + printf("UUID: failed %d out of %d tests.\n", failed_tests, i); + return failed_tests; +} diff --git a/libnetdata/uuid/uuid.h b/libnetdata/uuid/uuid.h new file mode 100644 index 00000000..56764684 --- /dev/null +++ b/libnetdata/uuid/uuid.h @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_UUID_H +#define NETDATA_UUID_H + +UUID_DEFINE(streaming_from_child_msgid, 0xed,0x4c,0xdb, 0x8f, 0x1b, 0xeb, 0x4a, 0xd3, 0xb5, 0x7c, 0xb3, 0xca, 0xe2, 0xd1, 0x62, 0xfa); +UUID_DEFINE(streaming_to_parent_msgid, 0x6e, 0x2e, 0x38, 0x39, 0x06, 0x76, 0x48, 0x96, 0x8b, 0x64, 0x60, 0x45, 0xdb, 0xf2, 0x8d, 0x66); +UUID_DEFINE(health_alert_transition_msgid, 0x9c, 0xe0, 0xcb, 0x58, 0xab, 0x8b, 0x44, 0xdf, 0x82, 0xc4, 0xbf, 0x1a, 0xd9, 0xee, 0x22, 0xde); + +// this is also defined in alarm-notify.sh.in +UUID_DEFINE(health_alert_notification_msgid, 0x6d, 0xb0, 0x01, 0x8e, 0x83, 0xe3, 0x43, 0x20, 0xae, 0x2a, 0x65, 0x9d, 0x78, 0x01, 0x9f, 0xb7); + +#define UUID_COMPACT_STR_LEN 33 +void uuid_unparse_lower_compact(const uuid_t uuid, char *out); +int uuid_parse_compact(const char *in, uuid_t uuid); +int uuid_parse_flexi(const char *in, uuid_t uuid); + +static inline int uuid_memcmp(const uuid_t *uu1, const uuid_t *uu2) { + return memcmp(uu1, uu2, sizeof(uuid_t)); +} + +static inline int hex_char_to_int(char c) { + if (c >= '0' && c <= '9') return c - '0'; + if (c >= 'a' && c <= 'f') return c - 'a' + 10; + if (c >= 'A' && c <= 'F') return c - 'A' + 10; + return -1; // Invalid hexadecimal character +} + +#endif //NETDATA_UUID_H diff --git a/libnetdata/worker_utilization/worker_utilization.c b/libnetdata/worker_utilization/worker_utilization.c index ad45dbc7..f39cea8a 100644 --- a/libnetdata/worker_utilization/worker_utilization.c +++ b/libnetdata/worker_utilization/worker_utilization.c @@ -50,13 +50,16 @@ struct workers_workname { // this is what we add to Ju }; static struct workers_globals { + bool enabled; + SPINLOCK spinlock; Pvoid_t worknames_JudyHS; size_t memory; } workers_globals = { // workers globals, the base of all worknames - .spinlock = NETDATA_SPINLOCK_INITIALIZER, // a lock for the worknames index - .worknames_JudyHS = NULL, // the worknames index + .enabled = false, + .spinlock = NETDATA_SPINLOCK_INITIALIZER, // a lock for the worknames index + .worknames_JudyHS = NULL, // the worknames index }; static __thread struct worker *worker = NULL; // the current thread worker @@ -69,7 +72,14 @@ static inline usec_t worker_now_monotonic_usec(void) { #endif } +void workers_utilization_enable(void) { + workers_globals.enabled = true; +} + size_t workers_allocated_memory(void) { + if(!workers_globals.enabled) + return 0; + spinlock_lock(&workers_globals.spinlock); size_t memory = workers_globals.memory; spinlock_unlock(&workers_globals.spinlock); @@ -78,7 +88,8 @@ size_t workers_allocated_memory(void) { } void worker_register(const char *name) { - if(unlikely(worker)) return; + if(unlikely(worker || !workers_globals.enabled)) + return; worker = callocz(1, sizeof(struct worker)); worker->pid = gettid(); @@ -213,6 +224,7 @@ void worker_is_busy(size_t job_id) { void worker_set_metric(size_t job_id, NETDATA_DOUBLE value) { if(unlikely(!worker)) return; + if(unlikely(job_id >= WORKER_UTILIZATION_MAX_JOB_TYPES)) return; @@ -247,6 +259,9 @@ void workers_foreach(const char *name, void (*callback)( , NETDATA_DOUBLE *job_custom_values ) , void *data) { + if(!workers_globals.enabled) + return; + spinlock_lock(&workers_globals.spinlock); usec_t busy_time, delta; size_t i, jobs_started, jobs_running; diff --git a/libnetdata/worker_utilization/worker_utilization.h b/libnetdata/worker_utilization/worker_utilization.h index cc3f8268..e2f46c5a 100644 --- a/libnetdata/worker_utilization/worker_utilization.h +++ b/libnetdata/worker_utilization/worker_utilization.h @@ -15,6 +15,7 @@ typedef enum __attribute__((packed)) { WORKER_METRIC_INCREMENTAL_TOTAL = 4, } WORKER_METRIC_TYPE; +void workers_utilization_enable(void); size_t workers_allocated_memory(void); void worker_register(const char *name); void worker_register_job_name(size_t job_id, const char *name); |