diff options
Diffstat (limited to 'src/streaming/stream-compression')
-rw-r--r-- | src/streaming/stream-compression/brotli.c | 142 | ||||
-rw-r--r-- | src/streaming/stream-compression/brotli.h | 15 | ||||
-rw-r--r-- | src/streaming/stream-compression/compression.c | 703 | ||||
-rw-r--r-- | src/streaming/stream-compression/compression.h | 183 | ||||
-rw-r--r-- | src/streaming/stream-compression/gzip.c | 164 | ||||
-rw-r--r-- | src/streaming/stream-compression/gzip.h | 15 | ||||
-rw-r--r-- | src/streaming/stream-compression/lz4.c | 143 | ||||
-rw-r--r-- | src/streaming/stream-compression/lz4.h | 19 | ||||
-rw-r--r-- | src/streaming/stream-compression/zstd.c | 163 | ||||
-rw-r--r-- | src/streaming/stream-compression/zstd.h | 19 |
10 files changed, 1566 insertions, 0 deletions
diff --git a/src/streaming/stream-compression/brotli.c b/src/streaming/stream-compression/brotli.c new file mode 100644 index 000000000..c2c09cdc5 --- /dev/null +++ b/src/streaming/stream-compression/brotli.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "brotli.h" + +#ifdef ENABLE_BROTLI +#include <brotli/encode.h> +#include <brotli/decode.h> + +void rrdpush_compressor_init_brotli(struct compressor_state *state) { + if (!state->initialized) { + state->initialized = true; + state->stream = BrotliEncoderCreateInstance(NULL, NULL, NULL); + + if (state->level < BROTLI_MIN_QUALITY) { + state->level = BROTLI_MIN_QUALITY; + } else if (state->level > BROTLI_MAX_QUALITY) { + state->level = BROTLI_MAX_QUALITY; + } + + BrotliEncoderSetParameter(state->stream, BROTLI_PARAM_QUALITY, state->level); + } +} + +void rrdpush_compressor_destroy_brotli(struct compressor_state *state) { + if (state->stream) { + BrotliEncoderDestroyInstance(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_compress_brotli(struct compressor_state *state, const char *data, size_t size, const char **out) { + if (unlikely(!state || !size || !out)) + return 0; + + simple_ring_buffer_make_room(&state->output, MAX(BrotliEncoderMaxCompressedSize(size), COMPRESSION_MAX_CHUNK)); + + size_t available_out = state->output.size; + + size_t available_in = size; + const uint8_t *next_in = (const uint8_t *)data; + uint8_t *next_out = (uint8_t *)state->output.data; + + if (!BrotliEncoderCompressStream(state->stream, BROTLI_OPERATION_FLUSH, &available_in, &next_in, &available_out, &next_out, NULL)) { + netdata_log_error("STREAM: Brotli compression failed."); + return 0; + } + + if(available_in != 0) { + netdata_log_error("STREAM: BrotliEncoderCompressStream() did not use all the input buffer, %zu bytes out of %zu remain", + available_in, size); + return 0; + } + + size_t compressed_size = state->output.size - available_out; + if(available_out == 0) { + netdata_log_error("STREAM: BrotliEncoderCompressStream() needs a bigger output buffer than the one we provided " + "(output buffer %zu bytes, compressed payload %zu bytes)", + state->output.size, size); + return 0; + } + + if(compressed_size == 0) { + netdata_log_error("STREAM: BrotliEncoderCompressStream() did not produce any output from the input provided " + "(input buffer %zu bytes)", + size); + return 0; + } + + state->sender_locked.total_compressions++; + state->sender_locked.total_uncompressed += size - available_in; + state->sender_locked.total_compressed += compressed_size; + + *out = state->output.data; + return compressed_size; +} + +void rrdpush_decompressor_init_brotli(struct decompressor_state *state) { + if (!state->initialized) { + state->initialized = true; + state->stream = BrotliDecoderCreateInstance(NULL, NULL, NULL); + + simple_ring_buffer_make_room(&state->output, COMPRESSION_MAX_CHUNK); + } +} + +void rrdpush_decompressor_destroy_brotli(struct decompressor_state *state) { + if (state->stream) { + BrotliDecoderDestroyInstance(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_decompress_brotli(struct decompressor_state *state, const char *compressed_data, size_t compressed_size) { + if (unlikely(!state || !compressed_data || !compressed_size)) + return 0; + + // The state.output ring buffer is always EMPTY at this point, + // meaning that (state->output.read_pos == state->output.write_pos) + // However, THEY ARE NOT ZERO. + + size_t available_out = state->output.size; + size_t available_in = compressed_size; + const uint8_t *next_in = (const uint8_t *)compressed_data; + uint8_t *next_out = (uint8_t *)state->output.data; + + if (BrotliDecoderDecompressStream(state->stream, &available_in, &next_in, &available_out, &next_out, NULL) == BROTLI_DECODER_RESULT_ERROR) { + netdata_log_error("STREAM: Brotli decompression failed."); + return 0; + } + + if(available_in != 0) { + netdata_log_error("STREAM: BrotliDecoderDecompressStream() did not use all the input buffer, %zu bytes out of %zu remain", + available_in, compressed_size); + return 0; + } + + size_t decompressed_size = state->output.size - available_out; + if(available_out == 0) { + netdata_log_error("STREAM: BrotliDecoderDecompressStream() needs a bigger output buffer than the one we provided " + "(output buffer %zu bytes, compressed payload %zu bytes)", + state->output.size, compressed_size); + return 0; + } + + if(decompressed_size == 0) { + netdata_log_error("STREAM: BrotliDecoderDecompressStream() did not produce any output from the input provided " + "(input buffer %zu bytes)", + compressed_size); + return 0; + } + + state->output.read_pos = 0; + state->output.write_pos = decompressed_size; + + state->total_compressed += compressed_size - available_in; + state->total_uncompressed += decompressed_size; + state->total_compressions++; + + return decompressed_size; +} + +#endif // ENABLE_BROTLI diff --git a/src/streaming/stream-compression/brotli.h b/src/streaming/stream-compression/brotli.h new file mode 100644 index 000000000..4955e5a82 --- /dev/null +++ b/src/streaming/stream-compression/brotli.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "compression.h" + +#ifndef NETDATA_STREAMING_COMPRESSION_BROTLI_H +#define NETDATA_STREAMING_COMPRESSION_BROTLI_H + +void rrdpush_compressor_init_brotli(struct compressor_state *state); +void rrdpush_compressor_destroy_brotli(struct compressor_state *state); +size_t rrdpush_compress_brotli(struct compressor_state *state, const char *data, size_t size, const char **out); +size_t rrdpush_decompress_brotli(struct decompressor_state *state, const char *compressed_data, size_t compressed_size); +void rrdpush_decompressor_init_brotli(struct decompressor_state *state); +void rrdpush_decompressor_destroy_brotli(struct decompressor_state *state); + +#endif //NETDATA_STREAMING_COMPRESSION_BROTLI_H diff --git a/src/streaming/stream-compression/compression.c b/src/streaming/stream-compression/compression.c new file mode 100644 index 000000000..3c9930656 --- /dev/null +++ b/src/streaming/stream-compression/compression.c @@ -0,0 +1,703 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "compression.h" + +#include "gzip.h" + +#ifdef ENABLE_LZ4 +#include "lz4.h" +#endif + +#ifdef ENABLE_ZSTD +#include "zstd.h" +#endif + +#ifdef ENABLE_BROTLI +#include "brotli.h" +#endif + +int rrdpush_compression_levels[COMPRESSION_ALGORITHM_MAX] = { + [COMPRESSION_ALGORITHM_NONE] = 0, + [COMPRESSION_ALGORITHM_ZSTD] = 3, // 1 (faster) - 22 (smaller) + [COMPRESSION_ALGORITHM_LZ4] = 1, // 1 (smaller) - 9 (faster) + [COMPRESSION_ALGORITHM_BROTLI] = 3, // 0 (faster) - 11 (smaller) + [COMPRESSION_ALGORITHM_GZIP] = 1, // 1 (faster) - 9 (smaller) +}; + +void rrdpush_parse_compression_order(struct receiver_state *rpt, const char *order) { + // empty all slots + for(size_t i = 0; i < COMPRESSION_ALGORITHM_MAX ;i++) + rpt->config.compression_priorities[i] = STREAM_CAP_NONE; + + char *s = strdupz(order); + + char *words[COMPRESSION_ALGORITHM_MAX + 100] = { NULL }; + size_t num_words = quoted_strings_splitter_whitespace(s, words, COMPRESSION_ALGORITHM_MAX + 100); + size_t slot = 0; + STREAM_CAPABILITIES added = STREAM_CAP_NONE; + for(size_t i = 0; i < num_words && slot < COMPRESSION_ALGORITHM_MAX ;i++) { + if((STREAM_CAP_ZSTD_AVAILABLE) && strcasecmp(words[i], "zstd") == 0 && !(added & STREAM_CAP_ZSTD)) { + rpt->config.compression_priorities[slot++] = STREAM_CAP_ZSTD; + added |= STREAM_CAP_ZSTD; + } + else if((STREAM_CAP_LZ4_AVAILABLE) && strcasecmp(words[i], "lz4") == 0 && !(added & STREAM_CAP_LZ4)) { + rpt->config.compression_priorities[slot++] = STREAM_CAP_LZ4; + added |= STREAM_CAP_LZ4; + } + else if((STREAM_CAP_BROTLI_AVAILABLE) && strcasecmp(words[i], "brotli") == 0 && !(added & STREAM_CAP_BROTLI)) { + rpt->config.compression_priorities[slot++] = STREAM_CAP_BROTLI; + added |= STREAM_CAP_BROTLI; + } + else if(strcasecmp(words[i], "gzip") == 0 && !(added & STREAM_CAP_GZIP)) { + rpt->config.compression_priorities[slot++] = STREAM_CAP_GZIP; + added |= STREAM_CAP_GZIP; + } + } + + freez(s); + + // make sure all participate + if((STREAM_CAP_ZSTD_AVAILABLE) && slot < COMPRESSION_ALGORITHM_MAX && !(added & STREAM_CAP_ZSTD)) + rpt->config.compression_priorities[slot++] = STREAM_CAP_ZSTD; + if((STREAM_CAP_LZ4_AVAILABLE) && slot < COMPRESSION_ALGORITHM_MAX && !(added & STREAM_CAP_LZ4)) + rpt->config.compression_priorities[slot++] = STREAM_CAP_LZ4; + if((STREAM_CAP_BROTLI_AVAILABLE) && slot < COMPRESSION_ALGORITHM_MAX && !(added & STREAM_CAP_BROTLI)) + rpt->config.compression_priorities[slot++] = STREAM_CAP_BROTLI; + if(slot < COMPRESSION_ALGORITHM_MAX && !(added & STREAM_CAP_GZIP)) + rpt->config.compression_priorities[slot++] = STREAM_CAP_GZIP; +} + +void rrdpush_select_receiver_compression_algorithm(struct receiver_state *rpt) { + if (!rpt->config.rrdpush_compression) + rpt->capabilities &= ~STREAM_CAP_COMPRESSIONS_AVAILABLE; + + // select the right compression before sending our capabilities to the child + if(stream_has_more_than_one_capability_of(rpt->capabilities, STREAM_CAP_COMPRESSIONS_AVAILABLE)) { + STREAM_CAPABILITIES compressions = rpt->capabilities & STREAM_CAP_COMPRESSIONS_AVAILABLE; + for(int i = 0; i < COMPRESSION_ALGORITHM_MAX; i++) { + STREAM_CAPABILITIES c = rpt->config.compression_priorities[i]; + + if(!(c & STREAM_CAP_COMPRESSIONS_AVAILABLE)) + continue; + + if(compressions & c) { + STREAM_CAPABILITIES exclude = compressions; + exclude &= ~c; + + rpt->capabilities &= ~exclude; + break; + } + } + } +} + +bool rrdpush_compression_initialize(struct sender_state *s) { + rrdpush_compressor_destroy(&s->compressor); + + // IMPORTANT + // KEEP THE SAME ORDER IN DECOMPRESSION + + if(stream_has_capability(s, STREAM_CAP_ZSTD)) + s->compressor.algorithm = COMPRESSION_ALGORITHM_ZSTD; + else if(stream_has_capability(s, STREAM_CAP_LZ4)) + s->compressor.algorithm = COMPRESSION_ALGORITHM_LZ4; + else if(stream_has_capability(s, STREAM_CAP_BROTLI)) + s->compressor.algorithm = COMPRESSION_ALGORITHM_BROTLI; + else if(stream_has_capability(s, STREAM_CAP_GZIP)) + s->compressor.algorithm = COMPRESSION_ALGORITHM_GZIP; + else + s->compressor.algorithm = COMPRESSION_ALGORITHM_NONE; + + if(s->compressor.algorithm != COMPRESSION_ALGORITHM_NONE) { + s->compressor.level = rrdpush_compression_levels[s->compressor.algorithm]; + rrdpush_compressor_init(&s->compressor); + return true; + } + + return false; +} + +bool rrdpush_decompression_initialize(struct receiver_state *rpt) { + rrdpush_decompressor_destroy(&rpt->decompressor); + + // IMPORTANT + // KEEP THE SAME ORDER IN COMPRESSION + + if(stream_has_capability(rpt, STREAM_CAP_ZSTD)) + rpt->decompressor.algorithm = COMPRESSION_ALGORITHM_ZSTD; + else if(stream_has_capability(rpt, STREAM_CAP_LZ4)) + rpt->decompressor.algorithm = COMPRESSION_ALGORITHM_LZ4; + else if(stream_has_capability(rpt, STREAM_CAP_BROTLI)) + rpt->decompressor.algorithm = COMPRESSION_ALGORITHM_BROTLI; + else if(stream_has_capability(rpt, STREAM_CAP_GZIP)) + rpt->decompressor.algorithm = COMPRESSION_ALGORITHM_GZIP; + else + rpt->decompressor.algorithm = COMPRESSION_ALGORITHM_NONE; + + if(rpt->decompressor.algorithm != COMPRESSION_ALGORITHM_NONE) { + rrdpush_decompressor_init(&rpt->decompressor); + return true; + } + + return false; +} + +/* +* In case of stream compression buffer overflow +* Inform the user through the error log file and +* deactivate compression by downgrading the stream protocol. +*/ +void rrdpush_compression_deactivate(struct sender_state *s) { + switch(s->compressor.algorithm) { + case COMPRESSION_ALGORITHM_MAX: + case COMPRESSION_ALGORITHM_NONE: + netdata_log_error("STREAM_COMPRESSION: compression error on 'host:%s' without any compression enabled. Ignoring error.", + rrdhost_hostname(s->host)); + break; + + case COMPRESSION_ALGORITHM_GZIP: + netdata_log_error("STREAM_COMPRESSION: GZIP compression error on 'host:%s'. Disabling GZIP for this node.", + rrdhost_hostname(s->host)); + s->disabled_capabilities |= STREAM_CAP_GZIP; + break; + + case COMPRESSION_ALGORITHM_LZ4: + netdata_log_error("STREAM_COMPRESSION: LZ4 compression error on 'host:%s'. Disabling ZSTD for this node.", + rrdhost_hostname(s->host)); + s->disabled_capabilities |= STREAM_CAP_LZ4; + break; + + case COMPRESSION_ALGORITHM_ZSTD: + netdata_log_error("STREAM_COMPRESSION: ZSTD compression error on 'host:%s'. Disabling ZSTD for this node.", + rrdhost_hostname(s->host)); + s->disabled_capabilities |= STREAM_CAP_ZSTD; + break; + + case COMPRESSION_ALGORITHM_BROTLI: + netdata_log_error("STREAM_COMPRESSION: BROTLI compression error on 'host:%s'. Disabling BROTLI for this node.", + rrdhost_hostname(s->host)); + s->disabled_capabilities |= STREAM_CAP_BROTLI; + break; + } +} + +// ---------------------------------------------------------------------------- +// compressor public API + +void rrdpush_compressor_init(struct compressor_state *state) { + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + rrdpush_compressor_init_zstd(state); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + rrdpush_compressor_init_lz4(state); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + rrdpush_compressor_init_brotli(state); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + rrdpush_compressor_init_gzip(state); + break; + } + + simple_ring_buffer_reset(&state->input); + simple_ring_buffer_reset(&state->output); +} + +void rrdpush_compressor_destroy(struct compressor_state *state) { + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + rrdpush_compressor_destroy_zstd(state); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + rrdpush_compressor_destroy_lz4(state); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + rrdpush_compressor_destroy_brotli(state); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + rrdpush_compressor_destroy_gzip(state); + break; + } + + state->initialized = false; + + simple_ring_buffer_destroy(&state->input); + simple_ring_buffer_destroy(&state->output); +} + +size_t rrdpush_compress(struct compressor_state *state, const char *data, size_t size, const char **out) { + size_t ret = 0; + + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + ret = rrdpush_compress_zstd(state, data, size, out); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + ret = rrdpush_compress_lz4(state, data, size, out); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + ret = rrdpush_compress_brotli(state, data, size, out); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + ret = rrdpush_compress_gzip(state, data, size, out); + break; + } + + if(unlikely(ret >= COMPRESSION_MAX_CHUNK)) { + netdata_log_error("RRDPUSH_COMPRESS: compressed data is %zu bytes, which is >= than the max chunk size %d", + ret, COMPRESSION_MAX_CHUNK); + return 0; + } + + return ret; +} + +// ---------------------------------------------------------------------------- +// decompressor public API + +void rrdpush_decompressor_destroy(struct decompressor_state *state) { + if(unlikely(!state->initialized)) + return; + + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + rrdpush_decompressor_destroy_zstd(state); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + rrdpush_decompressor_destroy_lz4(state); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + rrdpush_decompressor_destroy_brotli(state); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + rrdpush_decompressor_destroy_gzip(state); + break; + } + + simple_ring_buffer_destroy(&state->output); + + state->initialized = false; +} + +void rrdpush_decompressor_init(struct decompressor_state *state) { + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + rrdpush_decompressor_init_zstd(state); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + rrdpush_decompressor_init_lz4(state); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + rrdpush_decompressor_init_brotli(state); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + rrdpush_decompressor_init_gzip(state); + break; + } + + state->signature_size = RRDPUSH_COMPRESSION_SIGNATURE_SIZE; + simple_ring_buffer_reset(&state->output); +} + +size_t rrdpush_decompress(struct decompressor_state *state, const char *compressed_data, size_t compressed_size) { + if (unlikely(state->output.read_pos != state->output.write_pos)) + fatal("RRDPUSH_DECOMPRESS: asked to decompress new data, while there are unread data in the decompression buffer!"); + + size_t ret = 0; + + switch(state->algorithm) { +#ifdef ENABLE_ZSTD + case COMPRESSION_ALGORITHM_ZSTD: + ret = rrdpush_decompress_zstd(state, compressed_data, compressed_size); + break; +#endif + +#ifdef ENABLE_LZ4 + case COMPRESSION_ALGORITHM_LZ4: + ret = rrdpush_decompress_lz4(state, compressed_data, compressed_size); + break; +#endif + +#ifdef ENABLE_BROTLI + case COMPRESSION_ALGORITHM_BROTLI: + ret = rrdpush_decompress_brotli(state, compressed_data, compressed_size); + break; +#endif + + default: + case COMPRESSION_ALGORITHM_GZIP: + ret = rrdpush_decompress_gzip(state, compressed_data, compressed_size); + break; + } + + // for backwards compatibility we cannot check for COMPRESSION_MAX_MSG_SIZE, + // because old children may send this big payloads. + if(unlikely(ret > COMPRESSION_MAX_CHUNK)) { + netdata_log_error("RRDPUSH_DECOMPRESS: decompressed data is %zu bytes, which is bigger than the max msg size %d", + ret, COMPRESSION_MAX_CHUNK); + return 0; + } + + return ret; +} + +// ---------------------------------------------------------------------------- +// unit test + +void unittest_generate_random_name(char *dst, size_t size) { + if(size < 7) + size = 7; + + size_t len = 5 + os_random32() % (size - 6); + + for(size_t i = 0; i < len ; i++) { + if(os_random8() % 2 == 0) + dst[i] = 'A' + os_random8() % 26; + else + dst[i] = 'a' + os_random8() % 26; + } + + dst[len] = '\0'; +} + +void unittest_generate_message(BUFFER *wb, time_t now_s, size_t counter) { + bool with_slots = true; + NUMBER_ENCODING integer_encoding = NUMBER_ENCODING_BASE64; + NUMBER_ENCODING doubles_encoding = NUMBER_ENCODING_BASE64; + time_t update_every = 1; + time_t point_end_time_s = now_s; + time_t wall_clock_time_s = now_s; + size_t chart_slot = counter + 1; + size_t dimensions = 2 + os_random8() % 5; + char chart[RRD_ID_LENGTH_MAX + 1] = "name"; + unittest_generate_random_name(chart, 5 + os_random8() % 30); + + buffer_fast_strcat(wb, PLUGINSD_KEYWORD_BEGIN_V2, sizeof(PLUGINSD_KEYWORD_BEGIN_V2) - 1); + + if(with_slots) { + buffer_fast_strcat(wb, " "PLUGINSD_KEYWORD_SLOT":", sizeof(PLUGINSD_KEYWORD_SLOT) - 1 + 2); + buffer_print_uint64_encoded(wb, integer_encoding, chart_slot); + } + + buffer_fast_strcat(wb, " '", 2); + buffer_strcat(wb, chart); + buffer_fast_strcat(wb, "' ", 2); + buffer_print_uint64_encoded(wb, integer_encoding, update_every); + buffer_fast_strcat(wb, " ", 1); + buffer_print_uint64_encoded(wb, integer_encoding, point_end_time_s); + buffer_fast_strcat(wb, " ", 1); + if(point_end_time_s == wall_clock_time_s) + buffer_fast_strcat(wb, "#", 1); + else + buffer_print_uint64_encoded(wb, integer_encoding, wall_clock_time_s); + buffer_fast_strcat(wb, "\n", 1); + + + for(size_t d = 0; d < dimensions ;d++) { + size_t dim_slot = d + 1; + char dim_id[RRD_ID_LENGTH_MAX + 1] = "dimension"; + unittest_generate_random_name(dim_id, 10 + os_random8() % 20); + int64_t last_collected_value = (os_random8() % 2 == 0) ? (int64_t)(counter + d) : (int64_t)os_random32(); + NETDATA_DOUBLE value = (os_random8() % 2 == 0) ? (NETDATA_DOUBLE)os_random64() / ((NETDATA_DOUBLE)os_random64() + 1) : (NETDATA_DOUBLE)last_collected_value; + SN_FLAGS flags = (os_random16() % 1000 == 0) ? SN_FLAG_NONE : SN_FLAG_NOT_ANOMALOUS; + + buffer_fast_strcat(wb, PLUGINSD_KEYWORD_SET_V2, sizeof(PLUGINSD_KEYWORD_SET_V2) - 1); + + if(with_slots) { + buffer_fast_strcat(wb, " "PLUGINSD_KEYWORD_SLOT":", sizeof(PLUGINSD_KEYWORD_SLOT) - 1 + 2); + buffer_print_uint64_encoded(wb, integer_encoding, dim_slot); + } + + buffer_fast_strcat(wb, " '", 2); + buffer_strcat(wb, dim_id); + buffer_fast_strcat(wb, "' ", 2); + buffer_print_int64_encoded(wb, integer_encoding, last_collected_value); + buffer_fast_strcat(wb, " ", 1); + + if((NETDATA_DOUBLE)last_collected_value == value) + buffer_fast_strcat(wb, "#", 1); + else + buffer_print_netdata_double_encoded(wb, doubles_encoding, value); + + buffer_fast_strcat(wb, " ", 1); + buffer_print_sn_flags(wb, flags, true); + buffer_fast_strcat(wb, "\n", 1); + } + + buffer_fast_strcat(wb, PLUGINSD_KEYWORD_END_V2 "\n", sizeof(PLUGINSD_KEYWORD_END_V2) - 1 + 1); +} + +int unittest_rrdpush_compression_speed(compression_algorithm_t algorithm, const char *name) { + fprintf(stderr, "\nTesting streaming compression speed with %s\n", name); + + struct compressor_state cctx = { + .initialized = false, + .algorithm = algorithm, + }; + struct decompressor_state dctx = { + .initialized = false, + .algorithm = algorithm, + }; + + rrdpush_compressor_init(&cctx); + rrdpush_decompressor_init(&dctx); + + int errors = 0; + + BUFFER *wb = buffer_create(COMPRESSION_MAX_MSG_SIZE, NULL); + time_t now_s = now_realtime_sec(); + usec_t compression_ut = 0; + usec_t decompression_ut = 0; + size_t bytes_compressed = 0; + size_t bytes_uncompressed = 0; + + usec_t compression_started_ut = now_monotonic_usec(); + usec_t decompression_started_ut = compression_started_ut; + + for(int i = 0; i < 10000 ;i++) { + compression_started_ut = now_monotonic_usec(); + decompression_ut += compression_started_ut - decompression_started_ut; + + buffer_flush(wb); + while(buffer_strlen(wb) < COMPRESSION_MAX_MSG_SIZE - 1024) + unittest_generate_message(wb, now_s, i); + + const char *txt = buffer_tostring(wb); + size_t txt_len = buffer_strlen(wb); + bytes_uncompressed += txt_len; + + const char *out; + size_t size = rrdpush_compress(&cctx, txt, txt_len, &out); + + bytes_compressed += size; + decompression_started_ut = now_monotonic_usec(); + compression_ut += decompression_started_ut - compression_started_ut; + + if(size == 0) { + fprintf(stderr, "iteration %d: compressed size %zu is zero\n", + i, size); + errors++; + goto cleanup; + } + else if(size >= COMPRESSION_MAX_CHUNK) { + fprintf(stderr, "iteration %d: compressed size %zu exceeds max allowed size\n", + i, size); + errors++; + goto cleanup; + } + else { + size_t dtxt_len = rrdpush_decompress(&dctx, out, size); + char *dtxt = (char *) &dctx.output.data[dctx.output.read_pos]; + + if(rrdpush_decompressed_bytes_in_buffer(&dctx) != dtxt_len) { + fprintf(stderr, "iteration %d: decompressed size %zu does not rrdpush_decompressed_bytes_in_buffer() %zu\n", + i, dtxt_len, rrdpush_decompressed_bytes_in_buffer(&dctx) + ); + errors++; + goto cleanup; + } + + if(!dtxt_len) { + fprintf(stderr, "iteration %d: decompressed size is zero\n", i); + errors++; + goto cleanup; + } + else if(dtxt_len != txt_len) { + fprintf(stderr, "iteration %d: decompressed size %zu does not match original size %zu\n", + i, dtxt_len, txt_len + ); + errors++; + goto cleanup; + } + else { + if(memcmp(txt, dtxt, txt_len) != 0) { + fprintf(stderr, "iteration %d: decompressed data '%s' do not match original data length %zu\n", + i, dtxt, txt_len); + errors++; + goto cleanup; + } + } + } + + // here we are supposed to copy the data and advance the position + dctx.output.read_pos += rrdpush_decompressed_bytes_in_buffer(&dctx); + } + +cleanup: + rrdpush_compressor_destroy(&cctx); + rrdpush_decompressor_destroy(&dctx); + + if(errors) + fprintf(stderr, "Compression with %s: FAILED (%d errors)\n", name, errors); + else + fprintf(stderr, "Compression with %s: OK " + "(compression %zu usec, decompression %zu usec, bytes raw %zu, compressed %zu, savings ratio %0.2f%%)\n", + name, compression_ut, decompression_ut, + bytes_uncompressed, bytes_compressed, + 100.0 - (double)bytes_compressed * 100.0 / (double)bytes_uncompressed); + + return errors; +} + +int unittest_rrdpush_compression(compression_algorithm_t algorithm, const char *name) { + fprintf(stderr, "\nTesting streaming compression with %s\n", name); + + struct compressor_state cctx = { + .initialized = false, + .algorithm = algorithm, + }; + struct decompressor_state dctx = { + .initialized = false, + .algorithm = algorithm, + }; + + char txt[COMPRESSION_MAX_MSG_SIZE]; + + rrdpush_compressor_init(&cctx); + rrdpush_decompressor_init(&dctx); + + int errors = 0; + + memset(txt, '=', COMPRESSION_MAX_MSG_SIZE); + + for(int i = 0; i < COMPRESSION_MAX_MSG_SIZE ;i++) { + txt[i] = 'A' + (i % 26); + size_t txt_len = i + 1; + + const char *out; + size_t size = rrdpush_compress(&cctx, txt, txt_len, &out); + + if(size == 0) { + fprintf(stderr, "iteration %d: compressed size %zu is zero\n", + i, size); + errors++; + goto cleanup; + } + else if(size >= COMPRESSION_MAX_CHUNK) { + fprintf(stderr, "iteration %d: compressed size %zu exceeds max allowed size\n", + i, size); + errors++; + goto cleanup; + } + else { + size_t dtxt_len = rrdpush_decompress(&dctx, out, size); + char *dtxt = (char *) &dctx.output.data[dctx.output.read_pos]; + + if(rrdpush_decompressed_bytes_in_buffer(&dctx) != dtxt_len) { + fprintf(stderr, "iteration %d: decompressed size %zu does not rrdpush_decompressed_bytes_in_buffer() %zu\n", + i, dtxt_len, rrdpush_decompressed_bytes_in_buffer(&dctx) + ); + errors++; + goto cleanup; + } + + if(!dtxt_len) { + fprintf(stderr, "iteration %d: decompressed size is zero\n", i); + errors++; + goto cleanup; + } + else if(dtxt_len != txt_len) { + fprintf(stderr, "iteration %d: decompressed size %zu does not match original size %zu\n", + i, dtxt_len, txt_len + ); + errors++; + goto cleanup; + } + else { + if(memcmp(txt, dtxt, txt_len) != 0) { + txt[txt_len] = '\0'; + dtxt[txt_len + 5] = '\0'; + + fprintf(stderr, "iteration %d: decompressed data '%s' do not match original data '%s' of length %zu\n", + i, dtxt, txt, txt_len); + errors++; + goto cleanup; + } + } + } + + // fill the compressed buffer with garbage + memset((void *)out, 'x', size); + + // here we are supposed to copy the data and advance the position + dctx.output.read_pos += rrdpush_decompressed_bytes_in_buffer(&dctx); + } + +cleanup: + rrdpush_compressor_destroy(&cctx); + rrdpush_decompressor_destroy(&dctx); + + if(errors) + fprintf(stderr, "Compression with %s: FAILED (%d errors)\n", name, errors); + else + fprintf(stderr, "Compression with %s: OK\n", name); + + return errors; +} + +int unittest_rrdpush_compressions(void) { + int ret = 0; + + ret += unittest_rrdpush_compression(COMPRESSION_ALGORITHM_ZSTD, "ZSTD"); + ret += unittest_rrdpush_compression(COMPRESSION_ALGORITHM_LZ4, "LZ4"); + ret += unittest_rrdpush_compression(COMPRESSION_ALGORITHM_BROTLI, "BROTLI"); + ret += unittest_rrdpush_compression(COMPRESSION_ALGORITHM_GZIP, "GZIP"); + + ret += unittest_rrdpush_compression_speed(COMPRESSION_ALGORITHM_ZSTD, "ZSTD"); + ret += unittest_rrdpush_compression_speed(COMPRESSION_ALGORITHM_LZ4, "LZ4"); + ret += unittest_rrdpush_compression_speed(COMPRESSION_ALGORITHM_BROTLI, "BROTLI"); + ret += unittest_rrdpush_compression_speed(COMPRESSION_ALGORITHM_GZIP, "GZIP"); + + return ret; +} diff --git a/src/streaming/stream-compression/compression.h b/src/streaming/stream-compression/compression.h new file mode 100644 index 000000000..37f589b85 --- /dev/null +++ b/src/streaming/stream-compression/compression.h @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_RRDPUSH_COMPRESSION_H +#define NETDATA_RRDPUSH_COMPRESSION_H 1 + +#include "libnetdata/libnetdata.h" + +// signature MUST end with a newline + +#if COMPRESSION_MAX_MSG_SIZE >= (COMPRESSION_MAX_CHUNK - COMPRESSION_MAX_OVERHEAD) +#error "COMPRESSION_MAX_MSG_SIZE >= (COMPRESSION_MAX_CHUNK - COMPRESSION_MAX_OVERHEAD)" +#endif + +typedef uint32_t rrdpush_signature_t; +#define RRDPUSH_COMPRESSION_SIGNATURE ((rrdpush_signature_t)('z' | 0x80) | (0x80 << 8) | (0x80 << 16) | ('\n' << 24)) +#define RRDPUSH_COMPRESSION_SIGNATURE_MASK ((rrdpush_signature_t) 0xffU | (0x80U << 8) | (0x80U << 16) | (0xffU << 24)) +#define RRDPUSH_COMPRESSION_SIGNATURE_SIZE sizeof(rrdpush_signature_t) + +static inline rrdpush_signature_t rrdpush_compress_encode_signature(size_t compressed_data_size) { + rrdpush_signature_t len = ((compressed_data_size & 0x7f) | 0x80 | (((compressed_data_size & (0x7f << 7)) << 1) | 0x8000)) << 8; + return len | RRDPUSH_COMPRESSION_SIGNATURE; +} + +typedef enum { + COMPRESSION_ALGORITHM_NONE = 0, + COMPRESSION_ALGORITHM_ZSTD, + COMPRESSION_ALGORITHM_LZ4, + COMPRESSION_ALGORITHM_GZIP, + COMPRESSION_ALGORITHM_BROTLI, + + // terminator + COMPRESSION_ALGORITHM_MAX, +} compression_algorithm_t; + +extern int rrdpush_compression_levels[COMPRESSION_ALGORITHM_MAX]; + +// this defines the order the algorithms will be selected by the receiver (parent) +#define RRDPUSH_COMPRESSION_ALGORITHMS_ORDER "zstd lz4 brotli gzip" + +// ---------------------------------------------------------------------------- + +typedef struct simple_ring_buffer { + const char *data; + size_t size; + size_t read_pos; + size_t write_pos; +} SIMPLE_RING_BUFFER; + +static inline void simple_ring_buffer_reset(SIMPLE_RING_BUFFER *b) { + b->read_pos = b->write_pos = 0; +} + +static inline void simple_ring_buffer_make_room(SIMPLE_RING_BUFFER *b, size_t size) { + if(b->write_pos + size > b->size) { + if(!b->size) + b->size = COMPRESSION_MAX_CHUNK; + else + b->size *= 2; + + if(b->write_pos + size > b->size) + b->size += size; + + b->data = (const char *)reallocz((void *)b->data, b->size); + } +} + +static inline void simple_ring_buffer_append_data(SIMPLE_RING_BUFFER *b, const void *data, size_t size) { + simple_ring_buffer_make_room(b, size); + memcpy((void *)(b->data + b->write_pos), data, size); + b->write_pos += size; +} + +static inline void simple_ring_buffer_destroy(SIMPLE_RING_BUFFER *b) { + freez((void *)b->data); + b->data = NULL; + b->read_pos = b->write_pos = b->size = 0; +} + +// ---------------------------------------------------------------------------- + +struct compressor_state { + bool initialized; + compression_algorithm_t algorithm; + + SIMPLE_RING_BUFFER input; + SIMPLE_RING_BUFFER output; + + int level; + void *stream; + + struct { + size_t total_compressed; + size_t total_uncompressed; + size_t total_compressions; + } sender_locked; +}; + +void rrdpush_compressor_init(struct compressor_state *state); +void rrdpush_compressor_destroy(struct compressor_state *state); +size_t rrdpush_compress(struct compressor_state *state, const char *data, size_t size, const char **out); + +// ---------------------------------------------------------------------------- + +struct decompressor_state { + bool initialized; + compression_algorithm_t algorithm; + size_t signature_size; + + size_t total_compressed; + size_t total_uncompressed; + size_t total_compressions; + + SIMPLE_RING_BUFFER output; + + void *stream; +}; + +void rrdpush_decompressor_destroy(struct decompressor_state *state); +void rrdpush_decompressor_init(struct decompressor_state *state); +size_t rrdpush_decompress(struct decompressor_state *state, const char *compressed_data, size_t compressed_size); + +static inline size_t rrdpush_decompress_decode_signature(const char *data, size_t data_size) { + if (unlikely(!data || !data_size)) + return 0; + + if (unlikely(data_size != RRDPUSH_COMPRESSION_SIGNATURE_SIZE)) + return 0; + + rrdpush_signature_t sign = *(rrdpush_signature_t *)data; + if (unlikely((sign & RRDPUSH_COMPRESSION_SIGNATURE_MASK) != RRDPUSH_COMPRESSION_SIGNATURE)) + return 0; + + size_t length = ((sign >> 8) & 0x7f) | ((sign >> 9) & (0x7f << 7)); + return length; +} + +static inline size_t rrdpush_decompressor_start(struct decompressor_state *state, const char *header, size_t header_size) { + if(unlikely(state->output.read_pos != state->output.write_pos)) + fatal("RRDPUSH DECOMPRESS: asked to decompress new data, while there are unread data in the decompression buffer!"); + + return rrdpush_decompress_decode_signature(header, header_size); +} + +static inline size_t rrdpush_decompressed_bytes_in_buffer(struct decompressor_state *state) { + if(unlikely(state->output.read_pos > state->output.write_pos)) + fatal("RRDPUSH DECOMPRESS: invalid read/write stream positions"); + + return state->output.write_pos - state->output.read_pos; +} + +static inline size_t rrdpush_decompressor_get(struct decompressor_state *state, char *dst, size_t size) { + if (unlikely(!state || !size || !dst)) + return 0; + + size_t remaining = rrdpush_decompressed_bytes_in_buffer(state); + + if(unlikely(!remaining)) + return 0; + + size_t bytes_to_return = size; + if(bytes_to_return > remaining) + bytes_to_return = remaining; + + memcpy(dst, state->output.data + state->output.read_pos, bytes_to_return); + state->output.read_pos += bytes_to_return; + + if(unlikely(state->output.read_pos > state->output.write_pos)) + fatal("RRDPUSH DECOMPRESS: invalid read/write stream positions"); + + return bytes_to_return; +} + +// ---------------------------------------------------------------------------- + +#include "../rrdpush.h" + +bool rrdpush_compression_initialize(struct sender_state *s); +bool rrdpush_decompression_initialize(struct receiver_state *rpt); +void rrdpush_parse_compression_order(struct receiver_state *rpt, const char *order); +void rrdpush_select_receiver_compression_algorithm(struct receiver_state *rpt); +void rrdpush_compression_deactivate(struct sender_state *s); + +#endif // NETDATA_RRDPUSH_COMPRESSION_H 1 diff --git a/src/streaming/stream-compression/gzip.c b/src/streaming/stream-compression/gzip.c new file mode 100644 index 000000000..d63e9afbe --- /dev/null +++ b/src/streaming/stream-compression/gzip.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "gzip.h" +#include <zlib.h> + +void rrdpush_compressor_init_gzip(struct compressor_state *state) { + if (!state->initialized) { + state->initialized = true; + + // Initialize deflate stream + z_stream *strm = state->stream = (z_stream *) mallocz(sizeof(z_stream)); + strm->zalloc = Z_NULL; + strm->zfree = Z_NULL; + strm->opaque = Z_NULL; + + if(state->level < Z_BEST_SPEED) + state->level = Z_BEST_SPEED; + + if(state->level > Z_BEST_COMPRESSION) + state->level = Z_BEST_COMPRESSION; + + // int r = deflateInit2(strm, Z_BEST_COMPRESSION, Z_DEFLATED, 15 + 16, 8, Z_DEFAULT_STRATEGY); + int r = deflateInit2(strm, state->level, Z_DEFLATED, 15 + 16, 8, Z_DEFAULT_STRATEGY); + if (r != Z_OK) { + netdata_log_error("Failed to initialize deflate with error: %d", r); + freez(state->stream); + state->initialized = false; + return; + } + + } +} + +void rrdpush_compressor_destroy_gzip(struct compressor_state *state) { + if (state->stream) { + deflateEnd(state->stream); + freez(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_compress_gzip(struct compressor_state *state, const char *data, size_t size, const char **out) { + if (unlikely(!state || !size || !out)) + return 0; + + simple_ring_buffer_make_room(&state->output, deflateBound(state->stream, size)); + + z_stream *strm = state->stream; + strm->avail_in = (uInt)size; + strm->next_in = (Bytef *)data; + strm->avail_out = (uInt)state->output.size; + strm->next_out = (Bytef *)state->output.data; + + int ret = deflate(strm, Z_SYNC_FLUSH); + if (ret != Z_OK && ret != Z_STREAM_END) { + netdata_log_error("STREAM: deflate() failed with error %d", ret); + return 0; + } + + if(strm->avail_in != 0) { + netdata_log_error("STREAM: deflate() did not use all the input buffer, %u bytes out of %zu remain", + strm->avail_in, size); + return 0; + } + + if(strm->avail_out == 0) { + netdata_log_error("STREAM: deflate() needs a bigger output buffer than the one we provided " + "(output buffer %zu bytes, compressed payload %zu bytes)", + state->output.size, size); + return 0; + } + + size_t compressed_data_size = state->output.size - strm->avail_out; + + if(compressed_data_size == 0) { + netdata_log_error("STREAM: deflate() did not produce any output " + "(output buffer %zu bytes, compressed payload %zu bytes)", + state->output.size, size); + return 0; + } + + state->sender_locked.total_compressions++; + state->sender_locked.total_uncompressed += size; + state->sender_locked.total_compressed += compressed_data_size; + + *out = state->output.data; + return compressed_data_size; +} + +void rrdpush_decompressor_init_gzip(struct decompressor_state *state) { + if (!state->initialized) { + state->initialized = true; + + // Initialize inflate stream + z_stream *strm = state->stream = (z_stream *)mallocz(sizeof(z_stream)); + strm->zalloc = Z_NULL; + strm->zfree = Z_NULL; + strm->opaque = Z_NULL; + + int r = inflateInit2(strm, 15 + 16); + if (r != Z_OK) { + netdata_log_error("Failed to initialize inflateInit2() with error: %d", r); + freez(state->stream); + state->initialized = false; + return; + } + + simple_ring_buffer_make_room(&state->output, COMPRESSION_MAX_CHUNK); + } +} + +void rrdpush_decompressor_destroy_gzip(struct decompressor_state *state) { + if (state->stream) { + inflateEnd(state->stream); + freez(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_decompress_gzip(struct decompressor_state *state, const char *compressed_data, size_t compressed_size) { + if (unlikely(!state || !compressed_data || !compressed_size)) + return 0; + + // The state.output ring buffer is always EMPTY at this point, + // meaning that (state->output.read_pos == state->output.write_pos) + // However, THEY ARE NOT ZERO. + + z_stream *strm = state->stream; + strm->avail_in = (uInt)compressed_size; + strm->next_in = (Bytef *)compressed_data; + strm->avail_out = (uInt)state->output.size; + strm->next_out = (Bytef *)state->output.data; + + int ret = inflate(strm, Z_SYNC_FLUSH); + if (ret != Z_STREAM_END && ret != Z_OK) { + netdata_log_error("RRDPUSH DECOMPRESS: inflate() failed with error %d", ret); + return 0; + } + + if(strm->avail_in != 0) { + netdata_log_error("RRDPUSH DECOMPRESS: inflate() did not use all compressed data we provided " + "(compressed payload %zu bytes, remaining to be uncompressed %u)" + , compressed_size, strm->avail_in); + return 0; + } + + if(strm->avail_out == 0) { + netdata_log_error("RRDPUSH DECOMPRESS: inflate() needs a bigger output buffer than the one we provided " + "(compressed payload %zu bytes, output buffer size %zu bytes)" + , compressed_size, state->output.size); + return 0; + } + + size_t decompressed_size = state->output.size - strm->avail_out; + + state->output.read_pos = 0; + state->output.write_pos = decompressed_size; + + state->total_compressed += compressed_size; + state->total_uncompressed += decompressed_size; + state->total_compressions++; + + return decompressed_size; +} diff --git a/src/streaming/stream-compression/gzip.h b/src/streaming/stream-compression/gzip.h new file mode 100644 index 000000000..85f34bc6d --- /dev/null +++ b/src/streaming/stream-compression/gzip.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "compression.h" + +#ifndef NETDATA_STREAMING_COMPRESSION_GZIP_H +#define NETDATA_STREAMING_COMPRESSION_GZIP_H + +void rrdpush_compressor_init_gzip(struct compressor_state *state); +void rrdpush_compressor_destroy_gzip(struct compressor_state *state); +size_t rrdpush_compress_gzip(struct compressor_state *state, const char *data, size_t size, const char **out); +size_t rrdpush_decompress_gzip(struct decompressor_state *state, const char *compressed_data, size_t compressed_size); +void rrdpush_decompressor_init_gzip(struct decompressor_state *state); +void rrdpush_decompressor_destroy_gzip(struct decompressor_state *state); + +#endif //NETDATA_STREAMING_COMPRESSION_GZIP_H diff --git a/src/streaming/stream-compression/lz4.c b/src/streaming/stream-compression/lz4.c new file mode 100644 index 000000000..284192153 --- /dev/null +++ b/src/streaming/stream-compression/lz4.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "lz4.h" + +#ifdef ENABLE_LZ4 +#include "lz4.h" + +// ---------------------------------------------------------------------------- +// compress + +void rrdpush_compressor_init_lz4(struct compressor_state *state) { + if(!state->initialized) { + state->initialized = true; + state->stream = LZ4_createStream(); + + // LZ4 needs access to the last 64KB of source data + // so, we keep twice the size of each message + simple_ring_buffer_make_room(&state->input, 65536 + COMPRESSION_MAX_CHUNK * 2); + } +} + +void rrdpush_compressor_destroy_lz4(struct compressor_state *state) { + if (state->stream) { + LZ4_freeStream(state->stream); + state->stream = NULL; + } +} + +/* + * Compress the given block of data + * Compressed data will remain in the internal buffer until the next invocation + * Return the size of compressed data block as result and the pointer to internal buffer using the last argument + * or 0 in case of error + */ +size_t rrdpush_compress_lz4(struct compressor_state *state, const char *data, size_t size, const char **out) { + if(unlikely(!state || !size || !out)) + return 0; + + // we need to keep the last 64K of our previous source data + // as they were in the ring buffer + + simple_ring_buffer_make_room(&state->output, LZ4_COMPRESSBOUND(size)); + + if(state->input.write_pos + size > state->input.size) + // the input buffer cannot fit out data, restart from zero + simple_ring_buffer_reset(&state->input); + + simple_ring_buffer_append_data(&state->input, data, size); + + long int compressed_data_size = LZ4_compress_fast_continue( + state->stream, + state->input.data + state->input.read_pos, + (char *)state->output.data, + (int)(state->input.write_pos - state->input.read_pos), + (int)state->output.size, + state->level); + + if (compressed_data_size <= 0) { + netdata_log_error("STREAM: LZ4_compress_fast_continue() returned %ld " + "(source is %zu bytes, output buffer can fit %zu bytes)", + compressed_data_size, size, state->output.size); + return 0; + } + + state->input.read_pos = state->input.write_pos; + + state->sender_locked.total_compressions++; + state->sender_locked.total_uncompressed += size; + state->sender_locked.total_compressed += compressed_data_size; + + *out = state->output.data; + return compressed_data_size; +} + +// ---------------------------------------------------------------------------- +// decompress + +void rrdpush_decompressor_init_lz4(struct decompressor_state *state) { + if(!state->initialized) { + state->initialized = true; + state->stream = LZ4_createStreamDecode(); + simple_ring_buffer_make_room(&state->output, 65536 + COMPRESSION_MAX_CHUNK * 2); + } +} + +void rrdpush_decompressor_destroy_lz4(struct decompressor_state *state) { + if (state->stream) { + LZ4_freeStreamDecode(state->stream); + state->stream = NULL; + } +} + +/* + * Decompress the compressed data in the internal buffer + * Return the size of uncompressed data or 0 for error + */ +size_t rrdpush_decompress_lz4(struct decompressor_state *state, const char *compressed_data, size_t compressed_size) { + if (unlikely(!state || !compressed_data || !compressed_size)) + return 0; + + // The state.output ring buffer is always EMPTY at this point, + // meaning that (state->output.read_pos == state->output.write_pos) + // However, THEY ARE NOT ZERO. + + if (unlikely(state->output.write_pos + COMPRESSION_MAX_CHUNK > state->output.size)) + // the input buffer cannot fit out data, restart from zero + simple_ring_buffer_reset(&state->output); + + long int decompressed_size = LZ4_decompress_safe_continue( + state->stream + , compressed_data + , (char *)(state->output.data + state->output.write_pos) + , (int)compressed_size + , (int)(state->output.size - state->output.write_pos) + ); + + if (unlikely(decompressed_size < 0)) { + netdata_log_error("RRDPUSH DECOMPRESS: LZ4_decompress_safe_continue() returned negative value: %ld " + "(compressed chunk is %zu bytes)" + , decompressed_size, compressed_size); + return 0; + } + + if(unlikely(decompressed_size + state->output.write_pos > state->output.size)) + fatal("RRDPUSH DECOMPRESS: LZ4_decompress_safe_continue() overflown the stream_buffer " + "(size: %zu, pos: %zu, added: %ld, exceeding the buffer by %zu)" + , state->output.size + , state->output.write_pos + , decompressed_size + , (size_t)(state->output.write_pos + decompressed_size - state->output.size) + ); + + state->output.write_pos += decompressed_size; + + // statistics + state->total_compressed += compressed_size; + state->total_uncompressed += decompressed_size; + state->total_compressions++; + + return decompressed_size; +} + +#endif // ENABLE_LZ4 diff --git a/src/streaming/stream-compression/lz4.h b/src/streaming/stream-compression/lz4.h new file mode 100644 index 000000000..69f0fadcc --- /dev/null +++ b/src/streaming/stream-compression/lz4.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "compression.h" + +#ifndef NETDATA_STREAMING_COMPRESSION_LZ4_H +#define NETDATA_STREAMING_COMPRESSION_LZ4_H + +#ifdef ENABLE_LZ4 + +void rrdpush_compressor_init_lz4(struct compressor_state *state); +void rrdpush_compressor_destroy_lz4(struct compressor_state *state); +size_t rrdpush_compress_lz4(struct compressor_state *state, const char *data, size_t size, const char **out); +size_t rrdpush_decompress_lz4(struct decompressor_state *state, const char *compressed_data, size_t compressed_size); +void rrdpush_decompressor_init_lz4(struct decompressor_state *state); +void rrdpush_decompressor_destroy_lz4(struct decompressor_state *state); + +#endif // ENABLE_LZ4 + +#endif //NETDATA_STREAMING_COMPRESSION_LZ4_H diff --git a/src/streaming/stream-compression/zstd.c b/src/streaming/stream-compression/zstd.c new file mode 100644 index 000000000..0ce27c0d3 --- /dev/null +++ b/src/streaming/stream-compression/zstd.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "zstd.h" + +#ifdef ENABLE_ZSTD +#include <zstd.h> + +void rrdpush_compressor_init_zstd(struct compressor_state *state) { + if(!state->initialized) { + state->initialized = true; + state->stream = ZSTD_createCStream(); + + if(state->level < 1) + state->level = 1; + + if(state->level > ZSTD_maxCLevel()) + state->level = ZSTD_maxCLevel(); + + size_t ret = ZSTD_initCStream(state->stream, state->level); + if(ZSTD_isError(ret)) + netdata_log_error("STREAM: ZSTD_initCStream() returned error: %s", ZSTD_getErrorName(ret)); + + // ZSTD_CCtx_setParameter(state->stream, ZSTD_c_compressionLevel, 1); + // ZSTD_CCtx_setParameter(state->stream, ZSTD_c_strategy, ZSTD_fast); + } +} + +void rrdpush_compressor_destroy_zstd(struct compressor_state *state) { + if(state->stream) { + ZSTD_freeCStream(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_compress_zstd(struct compressor_state *state, const char *data, size_t size, const char **out) { + if(unlikely(!state || !size || !out)) + return 0; + + ZSTD_inBuffer inBuffer = { + .pos = 0, + .size = size, + .src = data, + }; + + size_t wanted_size = MAX(ZSTD_compressBound(inBuffer.size - inBuffer.pos), ZSTD_CStreamOutSize()); + simple_ring_buffer_make_room(&state->output, wanted_size); + + ZSTD_outBuffer outBuffer = { + .pos = 0, + .size = state->output.size, + .dst = (void *)state->output.data, + }; + + // compress + size_t ret = ZSTD_compressStream(state->stream, &outBuffer, &inBuffer); + + // error handling + if(ZSTD_isError(ret)) { + netdata_log_error("STREAM: ZSTD_compressStream() return error: %s", ZSTD_getErrorName(ret)); + return 0; + } + + if(inBuffer.pos < inBuffer.size) { + netdata_log_error("STREAM: ZSTD_compressStream() left unprocessed input (source payload %zu bytes, consumed %zu bytes)", + inBuffer.size, inBuffer.pos); + return 0; + } + + if(outBuffer.pos == 0) { + // ZSTD needs more input to flush the output, so let's flush it manually + ret = ZSTD_flushStream(state->stream, &outBuffer); + + if(ZSTD_isError(ret)) { + netdata_log_error("STREAM: ZSTD_flushStream() return error: %s", ZSTD_getErrorName(ret)); + return 0; + } + + if(outBuffer.pos == 0) { + netdata_log_error("STREAM: ZSTD_compressStream() returned zero compressed bytes " + "(source is %zu bytes, output buffer can fit %zu bytes) " + , size, outBuffer.size); + return 0; + } + } + + state->sender_locked.total_compressions++; + state->sender_locked.total_uncompressed += size; + state->sender_locked.total_compressed += outBuffer.pos; + + // return values + *out = state->output.data; + return outBuffer.pos; +} + +void rrdpush_decompressor_init_zstd(struct decompressor_state *state) { + if(!state->initialized) { + state->initialized = true; + state->stream = ZSTD_createDStream(); + + size_t ret = ZSTD_initDStream(state->stream); + if(ZSTD_isError(ret)) + netdata_log_error("STREAM: ZSTD_initDStream() returned error: %s", ZSTD_getErrorName(ret)); + + simple_ring_buffer_make_room(&state->output, MAX(COMPRESSION_MAX_CHUNK, ZSTD_DStreamOutSize())); + } +} + +void rrdpush_decompressor_destroy_zstd(struct decompressor_state *state) { + if (state->stream) { + ZSTD_freeDStream(state->stream); + state->stream = NULL; + } +} + +size_t rrdpush_decompress_zstd(struct decompressor_state *state, const char *compressed_data, size_t compressed_size) { + if (unlikely(!state || !compressed_data || !compressed_size)) + return 0; + + // The state.output ring buffer is always EMPTY at this point, + // meaning that (state->output.read_pos == state->output.write_pos) + // However, THEY ARE NOT ZERO. + + ZSTD_inBuffer inBuffer = { + .pos = 0, + .size = compressed_size, + .src = compressed_data, + }; + + ZSTD_outBuffer outBuffer = { + .pos = 0, + .dst = (char *)state->output.data, + .size = state->output.size, + }; + + size_t ret = ZSTD_decompressStream( + state->stream + , &outBuffer + , &inBuffer); + + if(ZSTD_isError(ret)) { + netdata_log_error("STREAM: ZSTD_decompressStream() return error: %s", ZSTD_getErrorName(ret)); + return 0; + } + + if(inBuffer.pos < inBuffer.size) + fatal("RRDPUSH DECOMPRESS: ZSTD ZSTD_decompressStream() decompressed %zu bytes, " + "but %zu bytes of compressed data remain", + inBuffer.pos, inBuffer.size); + + size_t decompressed_size = outBuffer.pos; + + state->output.read_pos = 0; + state->output.write_pos = outBuffer.pos; + + // statistics + state->total_compressed += compressed_size; + state->total_uncompressed += decompressed_size; + state->total_compressions++; + + return decompressed_size; +} + +#endif // ENABLE_ZSTD diff --git a/src/streaming/stream-compression/zstd.h b/src/streaming/stream-compression/zstd.h new file mode 100644 index 000000000..bfabbf89d --- /dev/null +++ b/src/streaming/stream-compression/zstd.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "compression.h" + +#ifndef NETDATA_STREAMING_COMPRESSION_ZSTD_H +#define NETDATA_STREAMING_COMPRESSION_ZSTD_H + +#ifdef ENABLE_ZSTD + +void rrdpush_compressor_init_zstd(struct compressor_state *state); +void rrdpush_compressor_destroy_zstd(struct compressor_state *state); +size_t rrdpush_compress_zstd(struct compressor_state *state, const char *data, size_t size, const char **out); +size_t rrdpush_decompress_zstd(struct decompressor_state *state, const char *compressed_data, size_t compressed_size); +void rrdpush_decompressor_init_zstd(struct decompressor_state *state); +void rrdpush_decompressor_destroy_zstd(struct decompressor_state *state); + +#endif // ENABLE_ZSTD + +#endif //NETDATA_STREAMING_COMPRESSION_ZSTD_H |