From f99c4526d94d3e04124c5c48ab4a3da6ca53a458 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Wed, 31 Mar 2021 14:58:11 +0200 Subject: Adding upstream version 1.30.0. Signed-off-by: Daniel Baumann --- collectors/QUICKSTART.md | 4 +- collectors/all.h | 9 +- collectors/apps.plugin/apps_groups.conf | 8 +- collectors/apps.plugin/apps_plugin.c | 22 +- collectors/cgroups.plugin/sys_fs_cgroup.c | 97 +- collectors/cups.plugin/cups_plugin.c | 14 +- collectors/ebpf.plugin/Makefile.am | 18 +- collectors/ebpf.plugin/README.md | 51 +- collectors/ebpf.plugin/ebpf.c | 1122 +++----------------- collectors/ebpf.plugin/ebpf.conf | 45 - collectors/ebpf.plugin/ebpf.d.conf | 36 + collectors/ebpf.plugin/ebpf.d/cachestat.conf | 14 + .../ebpf.plugin/ebpf.d/ebpf_kernel_reject_list.txt | 1 + collectors/ebpf.plugin/ebpf.d/network.conf | 30 + collectors/ebpf.plugin/ebpf.d/process.conf | 14 + collectors/ebpf.plugin/ebpf.d/sync.conf | 23 + collectors/ebpf.plugin/ebpf.h | 38 +- collectors/ebpf.plugin/ebpf_apps.c | 32 +- collectors/ebpf.plugin/ebpf_apps.h | 15 +- collectors/ebpf.plugin/ebpf_cachestat.c | 655 ++++++++++++ collectors/ebpf.plugin/ebpf_cachestat.h | 64 ++ collectors/ebpf.plugin/ebpf_kernel_reject_list.txt | 1 - collectors/ebpf.plugin/ebpf_process.c | 68 +- collectors/ebpf.plugin/ebpf_process.h | 4 +- collectors/ebpf.plugin/ebpf_socket.c | 1029 +++++++++++++++++- collectors/ebpf.plugin/ebpf_socket.h | 29 +- collectors/ebpf.plugin/ebpf_sync.c | 389 +++++++ collectors/ebpf.plugin/ebpf_sync.h | 54 + collectors/freeipmi.plugin/README.md | 4 +- collectors/freeipmi.plugin/freeipmi_plugin.c | 37 +- collectors/nfacct.plugin/plugin_nfacct.c | 57 +- collectors/proc.plugin/proc_diskstats.c | 64 +- collectors/proc.plugin/proc_net_dev.c | 430 ++++++-- collectors/proc.plugin/proc_self_mountinfo.c | 17 +- collectors/proc.plugin/proc_self_mountinfo.h | 7 +- collectors/python.d.plugin/README.md | 7 +- collectors/python.d.plugin/adaptec_raid/README.md | 4 +- .../adaptec_raid/adaptec_raid.chart.py | 10 +- collectors/python.d.plugin/alarms/README.md | 4 +- collectors/python.d.plugin/alarms/alarms.chart.py | 43 +- collectors/python.d.plugin/alarms/alarms.conf | 4 + collectors/python.d.plugin/anomalies/README.md | 3 +- collectors/python.d.plugin/chrony/README.md | 4 +- .../python.d.plugin/example/example.chart.py | 7 +- collectors/python.d.plugin/example/example.conf | 25 +- collectors/python.d.plugin/hpssa/README.md | 7 +- collectors/python.d.plugin/megacli/README.md | 3 +- collectors/python.d.plugin/samba/README.md | 4 +- .../python.d.plugin/smartd_log/smartd_log.chart.py | 9 + collectors/statsd.plugin/Makefile.am | 1 + collectors/statsd.plugin/README.md | 38 +- collectors/statsd.plugin/k6.conf | 104 ++ collectors/statsd.plugin/statsd.c | 6 +- collectors/tc.plugin/plugin_tc.c | 16 +- collectors/xenstat.plugin/xenstat_plugin.c | 20 +- 55 files changed, 3401 insertions(+), 1420 deletions(-) delete mode 100644 collectors/ebpf.plugin/ebpf.conf create mode 100644 collectors/ebpf.plugin/ebpf.d.conf create mode 100644 collectors/ebpf.plugin/ebpf.d/cachestat.conf create mode 100644 collectors/ebpf.plugin/ebpf.d/ebpf_kernel_reject_list.txt create mode 100644 collectors/ebpf.plugin/ebpf.d/network.conf create mode 100644 collectors/ebpf.plugin/ebpf.d/process.conf create mode 100644 collectors/ebpf.plugin/ebpf.d/sync.conf create mode 100644 collectors/ebpf.plugin/ebpf_cachestat.c create mode 100644 collectors/ebpf.plugin/ebpf_cachestat.h delete mode 100644 collectors/ebpf.plugin/ebpf_kernel_reject_list.txt create mode 100644 collectors/ebpf.plugin/ebpf_sync.c create mode 100644 collectors/ebpf.plugin/ebpf_sync.h create mode 100644 collectors/statsd.plugin/k6.conf (limited to 'collectors') diff --git a/collectors/QUICKSTART.md b/collectors/QUICKSTART.md index a691ffc4c..809ec18af 100644 --- a/collectors/QUICKSTART.md +++ b/collectors/QUICKSTART.md @@ -104,8 +104,8 @@ parameters as a reference, to configure the collector. Most collectors are enabled and will auto-detect their app/service without manual configuration. However, you need to restart Netdata to trigger the auto-detection process. -To restart Netdata on most systems, use `service netdata restart`. For other systems, see the [other restart -methods](/docs/getting-started.md#start-stop-and-restart-netdata). +To restart Netdata on most systems, use `sudo systemctl restart netdata`, or the [appropriate +method](/docs/configure/start-stop-restart.md) for your system. Open Netdata's dashboard in your browser, or refresh the page if you already have it open. You should now see a new entry in the menu and new interactive charts! diff --git a/collectors/all.h b/collectors/all.h index 153fce931..295261b56 100644 --- a/collectors/all.h +++ b/collectors/all.h @@ -105,10 +105,11 @@ #define NETDATA_CHART_PRIO_DISK_OPS 2001 #define NETDATA_CHART_PRIO_DISK_QOPS 2002 #define NETDATA_CHART_PRIO_DISK_BACKLOG 2003 -#define NETDATA_CHART_PRIO_DISK_UTIL 2004 -#define NETDATA_CHART_PRIO_DISK_AWAIT 2005 -#define NETDATA_CHART_PRIO_DISK_AVGSZ 2006 -#define NETDATA_CHART_PRIO_DISK_SVCTM 2007 +#define NETDATA_CHART_PRIO_DISK_BUSY 2004 +#define NETDATA_CHART_PRIO_DISK_UTIL 2005 +#define NETDATA_CHART_PRIO_DISK_AWAIT 2006 +#define NETDATA_CHART_PRIO_DISK_AVGSZ 2007 +#define NETDATA_CHART_PRIO_DISK_SVCTM 2008 #define NETDATA_CHART_PRIO_DISK_MOPS 2021 #define NETDATA_CHART_PRIO_DISK_IOTIME 2022 #define NETDATA_CHART_PRIO_BCACHE_CACHE_ALLOC 2120 diff --git a/collectors/apps.plugin/apps_groups.conf b/collectors/apps.plugin/apps_groups.conf index 7242ed30d..cffd26c95 100644 --- a/collectors/apps.plugin/apps_groups.conf +++ b/collectors/apps.plugin/apps_groups.conf @@ -119,13 +119,13 @@ columndb: clickhouse-server* # ----------------------------------------------------------------------------- # email servers -email: dovecot imapd pop3d amavis* master zmstat* zmmailboxdmgr qmgr oqmgr saslauthd opendkim clamd freshclam tlsmgr postfwd2 postscreen postfix smtp* lmtp* sendmail +email: dovecot imapd pop3d amavis* zmstat* zmmailboxdmgr saslauthd opendkim postfwd2 smtp* lmtp* sendmail postfix master pickup qmgr showq tlsmgr postscreen oqmgr # ----------------------------------------------------------------------------- # network, routing, VPN ppp: ppp* -vpn: openvpn pptp* cjdroute gvpe tincd +vpn: openvpn pptp* cjdroute gvpe tincd wireguard wifi: hostapd wpa_supplicant NetworkManager routing: ospfd* ospf6d* bgpd bfdd fabricd isisd eigrpd sharpd staticd ripd ripngd pimd pbrd nhrpd ldpd zebra vrrpd vtysh bird* modem: ModemManager @@ -232,12 +232,12 @@ backup: rsync lsyncd bacula* borg rclone # ----------------------------------------------------------------------------- # cron -cron: cron* atd anacron systemd-cron* +cron: cron* atd anacron systemd-cron* incrond # ----------------------------------------------------------------------------- # UPS -ups: upsmon upsd */nut/* +ups: upsmon upsd */nut/* apcupsd # ----------------------------------------------------------------------------- # media players, servers, clients diff --git a/collectors/apps.plugin/apps_plugin.c b/collectors/apps.plugin/apps_plugin.c index 7cbbb075c..4d4626e6b 100644 --- a/collectors/apps.plugin/apps_plugin.c +++ b/collectors/apps.plugin/apps_plugin.c @@ -491,7 +491,7 @@ typedef enum fd_filetype { } FD_FILETYPE; struct file_descriptor { - avl avl; + avl_t avl; #ifdef NETDATA_INTERNAL_CHECKS uint32_t magic; @@ -514,7 +514,7 @@ static int // read users and groups from files struct user_or_group_id { - avl avl; + avl_t avl; union { uid_t uid; @@ -639,7 +639,7 @@ int read_user_or_group_ids(struct user_or_group_ids *ids, struct timespec *last_ struct user_or_group_id *existing_user_id = NULL; if(likely(ids->root)) - existing_user_id = (struct user_or_group_id *)avl_search(&ids->index, (avl *) user_or_group_id); + existing_user_id = (struct user_or_group_id *)avl_search(&ids->index, (avl_t *) user_or_group_id); if(unlikely(existing_user_id)) { freez(existing_user_id->name); @@ -648,7 +648,7 @@ int read_user_or_group_ids(struct user_or_group_ids *ids, struct timespec *last_ freez(user_or_group_id); } else { - if(unlikely(avl_insert(&ids->index, (avl *) user_or_group_id) != (void *) user_or_group_id)) { + if(unlikely(avl_insert(&ids->index, (avl_t *) user_or_group_id) != (void *) user_or_group_id)) { error("INTERNAL ERROR: duplicate indexing of id during realloc"); }; @@ -664,7 +664,7 @@ int read_user_or_group_ids(struct user_or_group_ids *ids, struct timespec *last_ while(user_or_group_id) { if(unlikely(!user_or_group_id->updated)) { - if(unlikely((struct user_or_group_id *)avl_remove(&ids->index, (avl *) user_or_group_id) != user_or_group_id)) + if(unlikely((struct user_or_group_id *)avl_remove(&ids->index, (avl_t *) user_or_group_id) != user_or_group_id)) error("INTERNAL ERROR: removal of unused id from index, removed a different id"); if(prev_user_id) @@ -716,7 +716,7 @@ static struct target *get_users_target(uid_t uid) { int ret = read_user_or_group_ids(&all_user_ids, &last_passwd_modification_time); if(likely(!ret && all_user_ids.index.root)) - user_or_group_id = (struct user_or_group_id *)avl_search(&all_user_ids.index, (avl *) &user_id_to_find); + user_or_group_id = (struct user_or_group_id *)avl_search(&all_user_ids.index, (avl_t *) &user_id_to_find); } if(user_or_group_id && user_or_group_id->name && *user_or_group_id->name) { @@ -764,7 +764,7 @@ struct target *get_groups_target(gid_t gid) int ret = read_user_or_group_ids(&all_group_ids, &last_group_modification_time); if(likely(!ret && all_group_ids.index.root)) - group_id = (struct user_or_group_id *)avl_search(&all_group_ids.index, (avl *) &group_id_to_find); + group_id = (struct user_or_group_id *)avl_search(&all_group_ids.index, (avl_t *) &group_id_to_find); } if(group_id && group_id->name && *group_id->name) { @@ -1690,7 +1690,7 @@ int file_descriptor_compare(void* a, void* b) { return strcmp(((struct file_descriptor *)a)->name, ((struct file_descriptor *)b)->name); } -// int file_descriptor_iterator(avl *a) { if(a) {}; return 0; } +// int file_descriptor_iterator(avl_t *a) { if(a) {}; return 0; } avl_tree_type all_files_index = { NULL, @@ -1707,11 +1707,11 @@ static struct file_descriptor *file_descriptor_find(const char *name, uint32_t h tmp.magic = 0x0BADCAFE; #endif /* NETDATA_INTERNAL_CHECKS */ - return (struct file_descriptor *)avl_search(&all_files_index, (avl *) &tmp); + return (struct file_descriptor *)avl_search(&all_files_index, (avl_t *) &tmp); } -#define file_descriptor_add(fd) avl_insert(&all_files_index, (avl *)(fd)) -#define file_descriptor_remove(fd) avl_remove(&all_files_index, (avl *)(fd)) +#define file_descriptor_add(fd) avl_insert(&all_files_index, (avl_t *)(fd)) +#define file_descriptor_remove(fd) avl_remove(&all_files_index, (avl_t *)(fd)) // ---------------------------------------------------------------------------- diff --git a/collectors/cgroups.plugin/sys_fs_cgroup.c b/collectors/cgroups.plugin/sys_fs_cgroup.c index df1f5f21a..ceffffe92 100644 --- a/collectors/cgroups.plugin/sys_fs_cgroup.c +++ b/collectors/cgroups.plugin/sys_fs_cgroup.c @@ -31,7 +31,7 @@ static int cgroup_enable_pressure_memory_full = CONFIG_BOOLEAN_AUTO; static int cgroup_enable_systemd_services = CONFIG_BOOLEAN_YES; static int cgroup_enable_systemd_services_detailed_memory = CONFIG_BOOLEAN_NO; -static int cgroup_used_memory_without_cache = CONFIG_BOOLEAN_YES; +static int cgroup_used_memory = CONFIG_BOOLEAN_YES; static int cgroup_use_unified_cgroups = CONFIG_BOOLEAN_NO; static int cgroup_unified_exist = CONFIG_BOOLEAN_AUTO; @@ -226,7 +226,7 @@ void read_cgroup_plugin_configuration() { cgroup_enable_cpuacct_stat = config_get_boolean_ondemand("plugin:cgroups", "enable cpuacct stat (total CPU)", cgroup_enable_cpuacct_stat); cgroup_enable_cpuacct_usage = config_get_boolean_ondemand("plugin:cgroups", "enable cpuacct usage (per core CPU)", cgroup_enable_cpuacct_usage); - cgroup_enable_memory = config_get_boolean_ondemand("plugin:cgroups", "enable memory (used mem including cache)", cgroup_enable_memory); + cgroup_enable_memory = config_get_boolean_ondemand("plugin:cgroups", "enable memory", cgroup_enable_memory); cgroup_enable_detailed_memory = config_get_boolean_ondemand("plugin:cgroups", "enable detailed memory", cgroup_enable_detailed_memory); cgroup_enable_memory_failcnt = config_get_boolean_ondemand("plugin:cgroups", "enable memory limits fail count", cgroup_enable_memory_failcnt); cgroup_enable_swap = config_get_boolean_ondemand("plugin:cgroups", "enable swap memory", cgroup_enable_swap); @@ -250,7 +250,7 @@ void read_cgroup_plugin_configuration() { cgroup_enable_systemd_services = config_get_boolean("plugin:cgroups", "enable systemd services", cgroup_enable_systemd_services); cgroup_enable_systemd_services_detailed_memory = config_get_boolean("plugin:cgroups", "enable systemd services detailed memory", cgroup_enable_systemd_services_detailed_memory); - cgroup_used_memory_without_cache = config_get_boolean("plugin:cgroups", "report used memory without cache", cgroup_used_memory_without_cache); + cgroup_used_memory = config_get_boolean("plugin:cgroups", "report used memory", cgroup_used_memory); char filename[FILENAME_MAX + 1], *s; struct mountinfo *mi, *root = mountinfo_read(0); @@ -327,7 +327,7 @@ void read_cgroup_plugin_configuration() { cgroup_enable_blkio_queued_ops = CONFIG_BOOLEAN_NO; cgroup_search_in_devices = 0; cgroup_enable_systemd_services_detailed_memory = CONFIG_BOOLEAN_NO; - cgroup_used_memory_without_cache = CONFIG_BOOLEAN_NO; //unified cgroups use different values + cgroup_used_memory = CONFIG_BOOLEAN_NO; //unified cgroups use different values //TODO: can there be more than 1 cgroup2 mount point? mi = mountinfo_find_by_filesystem_super_option(root, "cgroup2", "rw"); //there is no cgroup2 specific super option - for now use 'rw' option @@ -541,7 +541,11 @@ struct memory { /* unsigned long long total_inactive_anon; unsigned long long total_active_anon; +*/ + unsigned long long total_inactive_file; + +/* unsigned long long total_active_file; unsigned long long total_unevictable; */ @@ -628,6 +632,7 @@ struct cgroup { RRDSET *st_cpu_limit; RRDSET *st_cpu_per_core; RRDSET *st_mem; + RRDSET *st_mem_utilization; RRDSET *st_writeback; RRDSET *st_mem_activity; RRDSET *st_pgfaults; @@ -1069,6 +1074,7 @@ static inline void cgroup_read_memory(struct memory *mem, char parent_cg_is_unif arl_expect(mem->arl_base, "total_pgpgout", &mem->total_pgpgout); arl_expect(mem->arl_base, "total_pgfault", &mem->total_pgfault); arl_expect(mem->arl_base, "total_pgmajfault", &mem->total_pgmajfault); + arl_expect(mem->arl_base, "total_inactive_file", &mem->total_inactive_file); } else { mem->arl_base = arl_create("cgroup/memory", NULL, 60); @@ -1082,6 +1088,7 @@ static inline void cgroup_read_memory(struct memory *mem, char parent_cg_is_unif mem->arl_dirty = arl_expect(mem->arl_base, "file_dirty", &mem->total_dirty); arl_expect(mem->arl_base, "pgfault", &mem->total_pgfault); arl_expect(mem->arl_base, "pgmajfault", &mem->total_pgmajfault); + arl_expect(mem->arl_base, "inactive_file", &mem->total_inactive_file); } } @@ -1105,9 +1112,9 @@ static inline void cgroup_read_memory(struct memory *mem, char parent_cg_is_unif if(unlikely(mem->enabled_detailed == CONFIG_BOOLEAN_AUTO)) { if(( (!parent_cg_is_unified) && ( mem->total_cache || mem->total_dirty || mem->total_rss || mem->total_rss_huge || mem->total_mapped_file || mem->total_writeback - || mem->total_swap || mem->total_pgpgin || mem->total_pgpgout || mem->total_pgfault || mem->total_pgmajfault)) + || mem->total_swap || mem->total_pgpgin || mem->total_pgpgout || mem->total_pgfault || mem->total_pgmajfault || mem->total_inactive_file)) || (parent_cg_is_unified && ( mem->anon || mem->total_dirty || mem->kernel_stack || mem->slab || mem->sock || mem->total_writeback - || mem->anon_thp || mem->total_pgfault || mem->total_pgmajfault)) + || mem->anon_thp || mem->total_pgfault || mem->total_pgmajfault || mem->total_inactive_file)) || netdata_zero_metrics_enabled == CONFIG_BOOLEAN_YES) mem->enabled_detailed = CONFIG_BOOLEAN_YES; else @@ -1125,6 +1132,11 @@ memory_next: mem->enabled_usage_in_bytes = CONFIG_BOOLEAN_YES; } + if (likely(mem->updated_usage_in_bytes && mem->updated_detailed)) { + mem->usage_in_bytes = + (mem->usage_in_bytes > mem->total_inactive_file) ? (mem->usage_in_bytes - mem->total_inactive_file) : 0; + } + // read msw_usage_in_bytes if(likely(mem->filename_msw_usage_in_bytes)) { mem->updated_msw_usage_in_bytes = !read_single_number_file(mem->filename_msw_usage_in_bytes, &mem->msw_usage_in_bytes); @@ -1515,6 +1527,7 @@ static inline void cgroup_free(struct cgroup *cg) { if(cg->st_pgfaults) rrdset_is_obsolete(cg->st_pgfaults); if(cg->st_mem_usage) rrdset_is_obsolete(cg->st_mem_usage); if(cg->st_mem_usage_limit) rrdset_is_obsolete(cg->st_mem_usage_limit); + if(cg->st_mem_utilization) rrdset_is_obsolete(cg->st_mem_utilization); if(cg->st_mem_failcnt) rrdset_is_obsolete(cg->st_mem_failcnt); if(cg->st_io) rrdset_is_obsolete(cg->st_io); if(cg->st_serviced_ops) rrdset_is_obsolete(cg->st_serviced_ops); @@ -1751,7 +1764,7 @@ static inline void update_filenames() debug(D_CGROUP, "cpuacct.usage_percpu file for cgroup '%s': '%s' does not exist.", cg->id, filename); } - if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory_without_cache) && !cg->memory.filename_detailed && (cgroup_used_memory_without_cache || cgroup_enable_systemd_services_detailed_memory || !(cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE)))) { + if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !(cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE)))) { snprintfz(filename, FILENAME_MAX, "%s%s/memory.stat", cgroup_memory_base, cg->id); if(likely(stat(filename, &buf) != -1)) { cg->memory.filename_detailed = strdupz(filename); @@ -1898,7 +1911,7 @@ static inline void update_filenames() else debug(D_CGROUP, "cpu.stat file for unified cgroup '%s': '%s' does not exist.", cg->id, filename); } - if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory_without_cache) && !cg->memory.filename_detailed && (cgroup_used_memory_without_cache || cgroup_enable_systemd_services_detailed_memory || !(cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE)))) { + if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !(cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE)))) { snprintfz(filename, FILENAME_MAX, "%s%s/memory.stat", cgroup_unified_base, cg->id); if(likely(stat(filename, &buf) != -1)) { cg->memory.filename_detailed = strdupz(filename); @@ -2187,8 +2200,7 @@ void update_systemd_services_charts( , NULL , "mem" , "services.mem_usage" - , (cgroup_used_memory_without_cache) ? "Systemd Services Used Memory without Cache" - : "Systemd Services Used Memory" + , "Systemd Services Used Memory" , "MiB" , PLUGIN_CGROUPS_NAME , PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME @@ -2705,7 +2717,7 @@ void update_systemd_services_charts( if(unlikely(!cg->rd_mem_usage)) cg->rd_mem_usage = rrddim_add(st_mem_usage, cg->chart_id, cg->chart_title, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_set_by_pointer(st_mem_usage, cg->rd_mem_usage, cg->memory.usage_in_bytes - ((cgroup_used_memory_without_cache)?cg->memory.total_cache:0)); + rrddim_set_by_pointer(st_mem_usage, cg->rd_mem_usage, cg->memory.usage_in_bytes); } if(likely(do_mem_detailed && cg->memory.updated_detailed)) { @@ -2936,15 +2948,15 @@ static inline void update_cpu_limits(char **filename, unsigned long long *value, // parse the cpuset string and calculate the number of cpus the cgroup is allowed to use while(*s) { unsigned long long n = cpuset_str2ull(&s); + ncpus++; if(*s == ',') { s++; - ncpus++; continue; } if(*s == '-') { s++; unsigned long long m = cpuset_str2ull(&s); - ncpus += m - n + 1; // calculate the number of cpus in the region + ncpus += m - n; // calculate the number of cpus in the region } s++; } @@ -3275,7 +3287,7 @@ void update_cgroup_charts(int update_every) { , "MiB" , PLUGIN_CGROUPS_NAME , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 210 + , cgroup_containers_chart_priority + 220 , update_every , RRDSET_TYPE_STACKED ); @@ -3421,7 +3433,7 @@ void update_cgroup_charts(int update_every) { if(likely(cg->memory.updated_usage_in_bytes && cg->memory.enabled_usage_in_bytes == CONFIG_BOOLEAN_YES)) { if(unlikely(!cg->st_mem_usage)) { - snprintfz(title, CHART_TITLE_MAX, "Used Memory %s", (cgroup_used_memory_without_cache && cg->memory.updated_detailed)?"without Cache ":""); + snprintfz(title, CHART_TITLE_MAX, "Used Memory"); cg->st_mem_usage = rrdset_create_localhost( cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) @@ -3433,7 +3445,7 @@ void update_cgroup_charts(int update_every) { , "MiB" , PLUGIN_CGROUPS_NAME , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 200 + , cgroup_containers_chart_priority + 210 , update_every , RRDSET_TYPE_STACKED ); @@ -3446,9 +3458,13 @@ void update_cgroup_charts(int update_every) { else rrdset_next(cg->st_mem_usage); - rrddim_set(cg->st_mem_usage, "ram", cg->memory.usage_in_bytes - ((cgroup_used_memory_without_cache)?cg->memory.total_cache:0)); + rrddim_set(cg->st_mem_usage, "ram", cg->memory.usage_in_bytes); if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - rrddim_set(cg->st_mem_usage, "swap", (cg->memory.msw_usage_in_bytes > cg->memory.usage_in_bytes)?cg->memory.msw_usage_in_bytes - cg->memory.usage_in_bytes:0); + rrddim_set( + cg->st_mem_usage, + "swap", + (cg->memory.msw_usage_in_bytes > cg->memory.usage_in_bytes) ? + cg->memory.msw_usage_in_bytes - cg->memory.usage_in_bytes : 0); } else { rrddim_set(cg->st_mem_usage, "swap", cg->memory.msw_usage_in_bytes); } @@ -3484,7 +3500,7 @@ void update_cgroup_charts(int update_every) { memory_limit = cg->memory_limit; if(unlikely(!cg->st_mem_usage_limit)) { - snprintfz(title, CHART_TITLE_MAX, "Used RAM without Cache within the limits"); + snprintfz(title, CHART_TITLE_MAX, "Used RAM within the limits"); cg->st_mem_usage_limit = rrdset_create_localhost( cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) @@ -3496,7 +3512,7 @@ void update_cgroup_charts(int update_every) { , "MiB" , PLUGIN_CGROUPS_NAME , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 199 + , cgroup_containers_chart_priority + 200 , update_every , RRDSET_TYPE_STACKED ); @@ -3511,9 +3527,41 @@ void update_cgroup_charts(int update_every) { rrdset_isnot_obsolete(cg->st_mem_usage_limit); - rrddim_set(cg->st_mem_usage_limit, "available", memory_limit - (cg->memory.usage_in_bytes - ((cgroup_used_memory_without_cache)?cg->memory.total_cache:0))); - rrddim_set(cg->st_mem_usage_limit, "used", cg->memory.usage_in_bytes - ((cgroup_used_memory_without_cache)?cg->memory.total_cache:0)); + rrddim_set(cg->st_mem_usage_limit, "available", memory_limit - cg->memory.usage_in_bytes); + rrddim_set(cg->st_mem_usage_limit, "used", cg->memory.usage_in_bytes); rrdset_done(cg->st_mem_usage_limit); + + if (unlikely(!cg->st_mem_utilization)) { + snprintfz(title, CHART_TITLE_MAX, "Memory Utilization"); + + cg->st_mem_utilization = rrdset_create_localhost( + cgroup_chart_type(type, cg->chart_id, RRD_ID_LENGTH_MAX) + , "mem_utilization" + , NULL + , "mem" + , "cgroup.mem_utilization" + , title + , "percentage" + , PLUGIN_CGROUPS_NAME + , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME + , cgroup_containers_chart_priority + 199 + , update_every + , RRDSET_TYPE_AREA + ); + + rrdset_update_labels(cg->st_mem_utilization, cg->chart_labels); + + rrddim_add(cg->st_mem_utilization, "utilization", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } else + rrdset_next(cg->st_mem_utilization); + + if (memory_limit) { + rrdset_isnot_obsolete(cg->st_mem_utilization); + + rrddim_set( + cg->st_mem_utilization, "utilization", cg->memory.usage_in_bytes * 100 / memory_limit); + rrdset_done(cg->st_mem_utilization); + } } } else { @@ -3521,6 +3569,11 @@ void update_cgroup_charts(int update_every) { rrdset_is_obsolete(cg->st_mem_usage_limit); cg->st_mem_usage_limit = NULL; } + + if(unlikely(cg->st_mem_utilization)) { + rrdset_is_obsolete(cg->st_mem_utilization); + cg->st_mem_utilization = NULL; + } } update_memory_limits(&cg->filename_memoryswap_limit, &cg->chart_var_memoryswap_limit, &cg->memoryswap_limit, "memory_and_swap_limit", cg); diff --git a/collectors/cups.plugin/cups_plugin.c b/collectors/cups.plugin/cups_plugin.c index dc8643755..a80930e4d 100644 --- a/collectors/cups.plugin/cups_plugin.c +++ b/collectors/cups.plugin/cups_plugin.c @@ -7,6 +7,7 @@ */ #include "../../libnetdata/libnetdata.h" +#include #include // callback required by fatal() @@ -45,10 +46,6 @@ static int debug = 0; static int netdata_update_every = 1; static int netdata_priority = 100004; - -#ifdef HAVE_CUPS -#include - http_t *http; // connection to the cups daemon /* @@ -468,12 +465,3 @@ int main(int argc, char **argv) { httpClose(http); info("CUPS process exiting"); } - -#else // !HAVE_CUPS - -int main(int argc, char **argv) -{ - fatal("cups.plugin is not compiled."); -} - -#endif // !HAVE_CUPS diff --git a/collectors/ebpf.plugin/Makefile.am b/collectors/ebpf.plugin/Makefile.am index 1327d47a6..4fb2056fd 100644 --- a/collectors/ebpf.plugin/Makefile.am +++ b/collectors/ebpf.plugin/Makefile.am @@ -10,6 +10,12 @@ CLEANFILES = \ include $(top_srcdir)/build/subst.inc SUFFIXES = .in +userebpfconfigdir=$(configdir)/ebpf.d + +# Explicitly install directories to avoid permission issues due to umask +install-exec-local: + $(INSTALL) -d $(DESTDIR)$(userebpfconfigdir) + dist_plugins_SCRIPTS = \ reset_netdata_trace.sh \ $(NULL) @@ -19,7 +25,15 @@ dist_noinst_DATA = \ README.md \ $(NULL) +ebpfconfigdir=$(libconfigdir)/ebpf.d dist_libconfig_DATA = \ - ebpf.conf \ - ebpf_kernel_reject_list.txt \ + ebpf.d.conf \ + $(NULL) + +dist_ebpfconfig_DATA = \ + ebpf.d/ebpf_kernel_reject_list.txt \ + ebpf.d/cachestat.conf \ + ebpf.d/network.conf \ + ebpf.d/process.conf \ + ebpf.d/sync.conf \ $(NULL) diff --git a/collectors/ebpf.plugin/README.md b/collectors/ebpf.plugin/README.md index 5ea3b4951..405eab875 100644 --- a/collectors/ebpf.plugin/README.md +++ b/collectors/ebpf.plugin/README.md @@ -148,6 +148,7 @@ accepts the following values: ​ - `return`: In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates new charts for the return of these functions, such as errors. Monitoring function returns can help in debugging software, such as failing to close file descriptors or creating zombie processes. +- `update every`: Number of seconds used for eBPF to send data for Netdata. #### Integration with `apps.plugin` @@ -186,16 +187,45 @@ If you want to _disable_ the integration with `apps.plugin` along with the above apps = yes ``` -### `[ebpf programs]` +#### `[ebpf programs]` The eBPF collector enables and runs the following eBPF programs by default: +- `cachestat`: Netdata's eBPF data collector creates charts about the memory page cache. When the integration with + [`apps.plugin`](/collectors/apps.plugin/README.md) is enabled, this collector creates charts for the whole host _and_ + for each application. - `process`: This eBPF program creates charts that show information about process creation, VFS IO, and files removed. When in `return` mode, it also creates charts showing errors when these operations are executed. - `network viewer`: This eBPF program creates charts with information about `TCP` and `UDP` functions, including the bandwidth consumed by each. +- `sync`: Montitor calls for syscalls sync(2), fsync(2), fdatasync(2), syncfs(2), msync(2), and sync_file_range(2). -### `[network connections]` +## Thread configuration + +You can configure each thread of the eBPF data collector by editing either the `cachestat.conf`, `process.conf`, +or `network.conf` files. Use [`edit-config`](/docs/configure/nodes.md) from your Netdata config directory: + +```bash +cd /etc/netdata/ # Replace with your Netdata configuration directory, if not /etc/netdata/ +./edit-config ebpf.d/process.conf +``` + +### Configuration files + +The following configuration files are available: + +- `cachestat.conf`: Configuration for the `cachestat` thread. +- `process.conf`: Configuration for the `process` thread. +- `network.conf`: Configuration for the `network viewer` thread. This config file overwrites the global options and + also lets you specify which network the eBPF collector monitors. +- `sync.conf`: Configuration for the `sync` thread. + +### Network configuration + +The network configuration has specific options to configure which network(s) the eBPF collector monitors. These options +are divided in the following sections: + +#### `[network connections]` You can configure the information shown on `outbound` and `inbound` charts with the settings in this section. @@ -232,7 +262,7 @@ The dimensions for the traffic charts are created using the destination IPs of t changed setting `resolve hostname ips = yes` and restarting Netdata, after this Netdata will create dimensions using the `hostnames` every time that is possible to resolve IPs to their hostnames. -### `[service name]` +#### `[service name]` Netdata uses the list of services in `/etc/services` to plot network connection charts. If this file does not contain the name for a particular service you use in your infrastructure, you will need to add it to the `[service name]` section. @@ -245,6 +275,21 @@ service in network connection charts, and thus see the name of the service inste 19999 = Netdata ``` +### Sync configuration + +The sync configuration has specific options to disable monitoring for syscalls, as default option all syscalls are +monitored. + +```conf +[syscalls] + sync = yes + msync = yes + fsync = yes + fdatasync = yes + syncfs = yes + sync_file_range = yes +``` + ## Troubleshooting If the eBPF collector does not work, you can troubleshoot it by running the `ebpf.plugin` command and investigating its diff --git a/collectors/ebpf.plugin/ebpf.c b/collectors/ebpf.plugin/ebpf.c index 26bcfcf17..26dacfd3e 100644 --- a/collectors/ebpf.plugin/ebpf.c +++ b/collectors/ebpf.plugin/ebpf.c @@ -52,8 +52,6 @@ void netdata_cleanup_and_exit(int ret) *****************************************************************/ char *ebpf_plugin_dir = PLUGINS_DIR; -char *ebpf_user_config_dir = CONFIG_DIR; -char *ebpf_stock_config_dir = LIBCONFIG_DIR; static char *ebpf_configured_log_dir = LOG_DIR; char *ebpf_algorithms[] = {"absolute", "incremental"}; @@ -79,13 +77,19 @@ pthread_cond_t collect_data_cond_var; ebpf_module_t ebpf_modules[] = { { .thread_name = "process", .config_name = "process", .enabled = 0, .start_routine = ebpf_process_thread, .update_time = 1, .global_charts = 1, .apps_charts = 1, .mode = MODE_ENTRY, - .optional = 0 }, + .optional = 0, .apps_routine = ebpf_process_create_apps_charts }, { .thread_name = "socket", .config_name = "socket", .enabled = 0, .start_routine = ebpf_socket_thread, .update_time = 1, .global_charts = 1, .apps_charts = 1, .mode = MODE_ENTRY, - .optional = 0 }, + .optional = 0, .apps_routine = ebpf_socket_create_apps_charts }, + { .thread_name = "cachestat", .config_name = "cachestat", .enabled = 0, .start_routine = ebpf_cachestat_thread, + .update_time = 1, .global_charts = 1, .apps_charts = 1, .mode = MODE_ENTRY, + .optional = 0, .apps_routine = ebpf_cachestat_create_apps_charts }, + { .thread_name = "sync", .config_name = "sync", .enabled = 0, .start_routine = ebpf_sync_thread, + .update_time = 1, .global_charts = 1, .apps_charts = 1, .mode = MODE_ENTRY, + .optional = 0, .apps_routine = NULL }, { .thread_name = NULL, .enabled = 0, .start_routine = NULL, .update_time = 1, .global_charts = 0, .apps_charts = 1, .mode = MODE_ENTRY, - .optional = 0 }, + .optional = 0, .apps_routine = NULL }, }; // Link with apps.plugin @@ -100,58 +104,6 @@ ebpf_network_viewer_options_t network_viewer_opt; * *****************************************************************/ -/** - * Cleanup publish syscall - * - * @param nps list of structures to clean - */ -void ebpf_cleanup_publish_syscall(netdata_publish_syscall_t *nps) -{ - while (nps) { - freez(nps->algorithm); - nps = nps->next; - } -} - -/** - * Clean port Structure - * - * Clean the allocated list. - * - * @param clean the list that will be cleaned - */ -void clean_port_structure(ebpf_network_viewer_port_list_t **clean) -{ - ebpf_network_viewer_port_list_t *move = *clean; - while (move) { - ebpf_network_viewer_port_list_t *next = move->next; - freez(move->value); - freez(move); - - move = next; - } - *clean = NULL; -} - -/** - * Clean IP structure - * - * Clean the allocated list. - * - * @param clean the list that will be cleaned - */ -static void clean_ip_structure(ebpf_network_viewer_ip_list_t **clean) -{ - ebpf_network_viewer_ip_list_t *move = *clean; - while (move) { - ebpf_network_viewer_ip_list_t *next = move->next; - freez(move); - - move = next; - } - *clean = NULL; -} - /** * Clean Loaded Events * @@ -318,6 +270,25 @@ void write_err_chart(char *name, char *family, netdata_publish_syscall_t *move, write_end_chart(); } +/** + * Write charts + * + * Write the current information to publish the charts. + * + * @param family chart family + * @param chart chart id + * @param dim dimension name + * @param v1 value. + */ +void ebpf_one_dimension_write_charts(char *family, char *chart, char *dim, long long v1) +{ + write_begin_chart(family, chart); + + write_chart_dimension(dim, v1); + + write_end_chart(); +} + /** * Call the necessary functions to create a chart. * @@ -343,23 +314,26 @@ void write_io_chart(char *chart, char *family, char *dwrite, long long vwrite, c /** * Write chart cmd on standard output * - * @param type the chart type - * @param id the chart id - * @param title the chart title - * @param units the units label - * @param family the group name used to attach the chart on dashaboard - * @param charttype the chart type - * @param order the chart order + * @param type chart type + * @param id chart id + * @param title chart title + * @param units units label + * @param family group name used to attach the chart on dashaboard + * @param charttype chart type + * @param context chart context + * @param order chart order */ -void ebpf_write_chart_cmd(char *type, char *id, char *title, char *units, char *family, char *charttype, int order) +void ebpf_write_chart_cmd(char *type, char *id, char *title, char *units, char *family, + char *charttype, char *context, int order) { - printf("CHART %s.%s '' '%s' '%s' '%s' '' %s %d %d\n", + printf("CHART %s.%s '' '%s' '%s' '%s' '%s' '%s' %d %d\n", type, id, title, units, - family, - charttype, + (family)?family:"", + (context)?context:"", + (charttype)?charttype:"", order, update_every); } @@ -398,26 +372,31 @@ void ebpf_create_global_dimension(void *ptr, int end) /** * Call write_chart_cmd to create the charts * - * @param type the chart type - * @param id the chart id - * @param units the axis label - * @param family the group name used to attach the chart on dashaboard - * @param order the order number of the specified chart - * @param ncd a pointer to a function called to create dimensions - * @param move a pointer for a structure that has the dimensions - * @param end number of dimensions for the chart created + * @param type chart type + * @param id chart id + * @param title chart title + * @param units axis label + * @param family group name used to attach the chart on dashaboard + * @param context chart context + * @param charttype chart type + * @param order order number of the specified chart + * @param ncd a pointer to a function called to create dimensions + * @param move a pointer for a structure that has the dimensions + * @param end number of dimensions for the chart created */ void ebpf_create_chart(char *type, char *id, char *title, char *units, char *family, + char *context, + char *charttype, int order, void (*ncd)(void *, int), void *move, int end) { - ebpf_write_chart_cmd(type, id, title, units, family, "line", order); + ebpf_write_chart_cmd(type, id, title, units, family, charttype, context, order); ncd(move, end); } @@ -429,15 +408,16 @@ void ebpf_create_chart(char *type, * @param title the value displayed on vertical axis. * @param units the value displayed on vertical axis. * @param family Submenu that the chart will be attached on dashboard. + * @param charttype chart type * @param order the chart order * @param algorithm the algorithm used by dimension * @param root structure used to create the dimensions. */ -void ebpf_create_charts_on_apps(char *id, char *title, char *units, char *family, int order, +void ebpf_create_charts_on_apps(char *id, char *title, char *units, char *family, char *charttype, int order, char *algorithm, struct target *root) { struct target *w; - ebpf_write_chart_cmd(NETDATA_APPS_FAMILY, id, title, units, family, "stacked", order); + ebpf_write_chart_cmd(NETDATA_APPS_FAMILY, id, title, units, family, charttype, NULL, order); for (w = root; w; w = w->next) { if (unlikely(w->exposed)) @@ -580,22 +560,26 @@ void ebpf_print_help() "\n" " Available command line options:\n" "\n" - " SECONDS set the data collection frequency.\n" + " SECONDS Set the data collection frequency.\n" "\n" - " --help or -h show this help.\n" + " --help or -h Show this help.\n" "\n" - " --version or -v show software version.\n" + " --version or -v Show software version.\n" "\n" - " --global or -g disable charts per application.\n" + " --global or -g Disable charts per application.\n" "\n" - " --all or -a Enable all chart groups (global and apps), unless -g is also given.\n" + " --all or -a Enable all chart groups (global and apps), unless -g is also given.\n" "\n" - " --net or -n Enable network viewer charts.\n" + " --cachestat or -c Enable charts related to process run time.\n" "\n" - " --process or -p Enable charts related to process run time.\n" + " --net or -n Enable network viewer charts.\n" "\n" - " --return or -r Run the collector in return mode.\n" + " --process or -p Enable charts related to process run time.\n" + "\n" + " --return or -r Run the collector in return mode.\n" "\n", + " --sync or -s Enable chart related to sync run time.\n" + "\n" VERSION, (year >= 116) ? year + 1900 : 2020); } @@ -606,87 +590,6 @@ void ebpf_print_help() * *****************************************************************/ -/** - * Is ip inside the range - * - * Check if the ip is inside a IP range - * - * @param rfirst the first ip address of the range - * @param rlast the last ip address of the range - * @param cmpfirst the first ip to compare - * @param cmplast the last ip to compare - * @param family the IP family - * - * @return It returns 1 if the IP is inside the range and 0 otherwise - */ -static int is_ip_inside_range(union netdata_ip_t *rfirst, union netdata_ip_t *rlast, - union netdata_ip_t *cmpfirst, union netdata_ip_t *cmplast, int family) -{ - if (family == AF_INET) { - if (ntohl(rfirst->addr32[0]) <= ntohl(cmpfirst->addr32[0]) && - ntohl(rlast->addr32[0]) >= ntohl(cmplast->addr32[0])) - return 1; - } else { - if (memcmp(rfirst->addr8, cmpfirst->addr8, sizeof(union netdata_ip_t)) <= 0 && - memcmp(rlast->addr8, cmplast->addr8, sizeof(union netdata_ip_t)) >= 0) { - return 1; - } - - } - return 0; -} - - -/** - * Fill IP list - * - * @param out a pointer to the link list. - * @param in the structure that will be linked. - */ -static inline void fill_ip_list(ebpf_network_viewer_ip_list_t **out, ebpf_network_viewer_ip_list_t *in, char *table) -{ -#ifndef NETDATA_INTERNAL_CHECKS - UNUSED(table); -#endif - if (likely(*out)) { - ebpf_network_viewer_ip_list_t *move = *out, *store = *out; - while (move) { - if (in->ver == move->ver && is_ip_inside_range(&move->first, &move->last, &in->first, &in->last, in->ver)) { - info("The range/value (%s) is inside the range/value (%s) already inserted, it will be ignored.", - in->value, move->value); - freez(in->value); - freez(in); - return; - } - store = move; - move = move->next; - } - - store->next = in; - } else { - *out = in; - } - -#ifdef NETDATA_INTERNAL_CHECKS - char first[512], last[512]; - if (in->ver == AF_INET) { - if (inet_ntop(AF_INET, in->first.addr8, first, INET_ADDRSTRLEN) && - inet_ntop(AF_INET, in->last.addr8, last, INET_ADDRSTRLEN)) - info("Adding values %s - %s to %s IP list \"%s\" used on network viewer", - first, last, - (*out == network_viewer_opt.included_ips)?"included":"excluded", - table); - } else { - if (inet_ntop(AF_INET6, in->first.addr8, first, INET6_ADDRSTRLEN) && - inet_ntop(AF_INET6, in->last.addr8, last, INET6_ADDRSTRLEN)) - info("Adding values %s - %s to %s IP list \"%s\" used on network viewer", - first, last, - (*out == network_viewer_opt.included_ips)?"included":"excluded", - table); - } -#endif -} - /** * Read Local Ports * @@ -838,789 +741,26 @@ void fill_ebpf_data(ebpf_data_t *ef) */ static inline void how_to_load(char *ptr) { - if (!strcasecmp(ptr, "return")) + if (!strcasecmp(ptr, EBPF_CFG_LOAD_MODE_RETURN)) ebpf_set_thread_mode(MODE_RETURN); - else if (!strcasecmp(ptr, "entry")) + else if (!strcasecmp(ptr, EBPF_CFG_LOAD_MODE_DEFAULT)) ebpf_set_thread_mode(MODE_ENTRY); else error("the option %s for \"ebpf load mode\" is not a valid option.", ptr); } /** - * Fill Port list - * - * @param out a pointer to the link list. - * @param in the structure that will be linked. - */ -static inline void fill_port_list(ebpf_network_viewer_port_list_t **out, ebpf_network_viewer_port_list_t *in) -{ - if (likely(*out)) { - ebpf_network_viewer_port_list_t *move = *out, *store = *out; - uint16_t first = ntohs(in->first); - uint16_t last = ntohs(in->last); - while (move) { - uint16_t cmp_first = ntohs(move->first); - uint16_t cmp_last = ntohs(move->last); - if (cmp_first <= first && first <= cmp_last && - cmp_first <= last && last <= cmp_last ) { - info("The range/value (%u, %u) is inside the range/value (%u, %u) already inserted, it will be ignored.", - first, last, cmp_first, cmp_last); - freez(in->value); - freez(in); - return; - } else if (first <= cmp_first && cmp_first <= last && - first <= cmp_last && cmp_last <= last) { - info("The range (%u, %u) is bigger than previous range (%u, %u) already inserted, the previous will be ignored.", - first, last, cmp_first, cmp_last); - freez(move->value); - move->value = in->value; - move->first = in->first; - move->last = in->last; - freez(in); - return; - } - - store = move; - move = move->next; - } - - store->next = in; - } else { - *out = in; - } - -#ifdef NETDATA_INTERNAL_CHECKS - info("Adding values %s( %u, %u) to %s port list used on network viewer", - in->value, ntohs(in->first), ntohs(in->last), - (*out == network_viewer_opt.included_port)?"included":"excluded"); -#endif -} - -/** - * Fill port list - * - * Fill an allocated port list with the range given - * - * @param out a pointer to store the link list - * @param range the informed range for the user. - */ -static void parse_port_list(void **out, char *range) -{ - int first, last; - ebpf_network_viewer_port_list_t **list = (ebpf_network_viewer_port_list_t **)out; - - char *copied = strdupz(range); - if (*range == '*' && *(range+1) == '\0') { - first = 1; - last = 65535; - - clean_port_structure(list); - goto fillenvpl; - } - - char *end = range; - //Move while I cannot find a separator - while (*end && *end != ':' && *end != '-') end++; - - //It has a range - if (likely(*end)) { - *end++ = '\0'; - if (*end == '!') { - info("The exclusion cannot be in the second part of the range, the range %s will be ignored.", copied); - freez(copied); - return; - } - last = str2i((const char *)end); - } else { - last = 0; - } - - first = str2i((const char *)range); - if (first < NETDATA_MINIMUM_PORT_VALUE || first > NETDATA_MAXIMUM_PORT_VALUE) { - info("The first port %d of the range \"%s\" is invalid and it will be ignored!", first, copied); - freez(copied); - return; - } - - if (!last) - last = first; - - if (last < NETDATA_MINIMUM_PORT_VALUE || last > NETDATA_MAXIMUM_PORT_VALUE) { - info("The second port %d of the range \"%s\" is invalid and the whole range will be ignored!", last, copied); - freez(copied); - return; - } - - if (first > last) { - info("The specified order %s is wrong, the smallest value is always the first, it will be ignored!", copied); - freez(copied); - return; - } - - ebpf_network_viewer_port_list_t *w; -fillenvpl: - w = callocz(1, sizeof(ebpf_network_viewer_port_list_t)); - w->value = copied; - w->hash = simple_hash(copied); - w->first = (uint16_t)htons((uint16_t)first); - w->last = (uint16_t)htons((uint16_t)last); - w->cmp_first = (uint16_t)first; - w->cmp_last = (uint16_t)last; - - fill_port_list(list, w); -} - -/** - * Parse Service List - * - * @param out a pointer to store the link list - * @param service the service used to create the structure that will be linked. - */ -static void parse_service_list(void **out, char *service) -{ - ebpf_network_viewer_port_list_t **list = (ebpf_network_viewer_port_list_t **)out; - struct servent *serv = getservbyname((const char *)service, "tcp"); - if (!serv) - serv = getservbyname((const char *)service, "udp"); - - if (!serv) { - info("Cannot resolv the service '%s' with protocols TCP and UDP, it will be ignored", service); - return; - } - - ebpf_network_viewer_port_list_t *w = callocz(1, sizeof(ebpf_network_viewer_port_list_t)); - w->value = strdupz(service); - w->hash = simple_hash(service); - - w->first = w->last = (uint16_t)serv->s_port; - - fill_port_list(list, w); -} - -/** - * Netmask - * - * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) - * - * @param prefix create the netmask based in the CIDR value. - * - * @return - */ -static inline in_addr_t netmask(int prefix) { - - if (prefix == 0) - return (~((in_addr_t) - 1)); - else - return (in_addr_t)(~((1 << (32 - prefix)) - 1)); - -} - -/** - * Broadcast - * - * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) - * - * @param addr is the ip address - * @param prefix is the CIDR value. - * - * @return It returns the last address of the range - */ -static inline in_addr_t broadcast(in_addr_t addr, int prefix) -{ - return (addr | ~netmask(prefix)); -} - -/** - * Network - * - * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) - * - * @param addr is the ip address - * @param prefix is the CIDR value. - * - * @return It returns the first address of the range. - */ -static inline in_addr_t ipv4_network(in_addr_t addr, int prefix) -{ - return (addr & netmask(prefix)); -} - -/** - * IP to network long - * - * @param dst the vector to store the result - * @param ip the source ip given by our users. - * @param domain the ip domain (IPV4 or IPV6) - * @param source the original string - * - * @return it returns 0 on success and -1 otherwise. - */ -static inline int ip2nl(uint8_t *dst, char *ip, int domain, char *source) -{ - if (inet_pton(domain, ip, dst) <= 0) { - error("The address specified (%s) is invalid ", source); - return -1; - } - - return 0; -} - -/** - * Get IPV6 Last Address + * Update interval * - * @param out the address to store the last address. - * @param in the address used to do the math. - * @param prefix number of bits used to calculate the address + * Update default interval with value from user */ -static void get_ipv6_last_addr(union netdata_ip_t *out, union netdata_ip_t *in, uint64_t prefix) +static void ebpf_update_interval() { - uint64_t mask,tmp; - uint64_t ret[2]; - memcpy(ret, in->addr32, sizeof(union netdata_ip_t)); - - if (prefix == 128) { - memcpy(out->addr32, in->addr32, sizeof(union netdata_ip_t)); - return; - } else if (!prefix) { - ret[0] = ret[1] = 0xFFFFFFFFFFFFFFFF; - memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); - return; - } else if (prefix <= 64) { - ret[1] = 0xFFFFFFFFFFFFFFFFULL; - - tmp = be64toh(ret[0]); - if (prefix > 0) { - mask = 0xFFFFFFFFFFFFFFFFULL << (64 - prefix); - tmp |= ~mask; - } - ret[0] = htobe64(tmp); - } else { - mask = 0xFFFFFFFFFFFFFFFFULL << (128 - prefix); - tmp = be64toh(ret[1]); - tmp |= ~mask; - ret[1] = htobe64(tmp); - } - - memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); -} - -/** - * Calculate ipv6 first address - * - * @param out the address to store the first address. - * @param in the address used to do the math. - * @param prefix number of bits used to calculate the address - */ -static void get_ipv6_first_addr(union netdata_ip_t *out, union netdata_ip_t *in, uint64_t prefix) -{ - uint64_t mask,tmp; - uint64_t ret[2]; - - memcpy(ret, in->addr32, sizeof(union netdata_ip_t)); - - if (prefix == 128) { - memcpy(out->addr32, in->addr32, sizeof(union netdata_ip_t)); - return; - } else if (!prefix) { - ret[0] = ret[1] = 0; - memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); - return; - } else if (prefix <= 64) { - ret[1] = 0ULL; - - tmp = be64toh(ret[0]); - if (prefix > 0) { - mask = 0xFFFFFFFFFFFFFFFFULL << (64 - prefix); - tmp &= mask; - } - ret[0] = htobe64(tmp); - } else { - mask = 0xFFFFFFFFFFFFFFFFULL << (128 - prefix); - tmp = be64toh(ret[1]); - tmp &= mask; - ret[1] = htobe64(tmp); - } - - memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); -} - -/** - * Parse IP List - * - * Parse IP list and link it. - * - * @param out a pointer to store the link list - * @param ip the value given as parameter - */ -static void parse_ip_list(void **out, char *ip) -{ - ebpf_network_viewer_ip_list_t **list = (ebpf_network_viewer_ip_list_t **)out; - - char *ipdup = strdupz(ip); - union netdata_ip_t first = { }; - union netdata_ip_t last = { }; - char *is_ipv6; - if (*ip == '*' && *(ip+1) == '\0') { - memset(first.addr8, 0, sizeof(first.addr8)); - memset(last.addr8, 0xFF, sizeof(last.addr8)); - - is_ipv6 = ip; - - clean_ip_structure(list); - goto storethisip; - } - - char *end = ip; - // Move while I cannot find a separator - while (*end && *end != '/' && *end != '-') end++; - - // We will use only the classic IPV6 for while, but we could consider the base 85 in a near future - // https://tools.ietf.org/html/rfc1924 - is_ipv6 = strchr(ip, ':'); - - int select; - if (*end && !is_ipv6) { // IPV4 range - select = (*end == '/') ? 0 : 1; - *end++ = '\0'; - if (*end == '!') { - info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); - goto cleanipdup; - } - - if (!select) { // CIDR - select = ip2nl(first.addr8, ip, AF_INET, ipdup); - if (select) - goto cleanipdup; - - select = (int) str2i(end); - if (select < NETDATA_MINIMUM_IPV4_CIDR || select > NETDATA_MAXIMUM_IPV4_CIDR) { - info("The specified CIDR %s is not valid, the IP %s will be ignored.", end, ip); - goto cleanipdup; - } - - last.addr32[0] = htonl(broadcast(ntohl(first.addr32[0]), select)); - // This was added to remove - // https://app.codacy.com/manual/netdata/netdata/pullRequest?prid=5810941&bid=19021977 - UNUSED(last.addr32[0]); - - uint32_t ipv4_test = htonl(ipv4_network(ntohl(first.addr32[0]), select)); - if (first.addr32[0] != ipv4_test) { - first.addr32[0] = ipv4_test; - struct in_addr ipv4_convert; - ipv4_convert.s_addr = ipv4_test; - char ipv4_msg[INET_ADDRSTRLEN]; - if(inet_ntop(AF_INET, &ipv4_convert, ipv4_msg, INET_ADDRSTRLEN)) - info("The network value of CIDR %s was updated for %s .", ipdup, ipv4_msg); - } - } else { // Range - select = ip2nl(first.addr8, ip, AF_INET, ipdup); - if (select) - goto cleanipdup; - - select = ip2nl(last.addr8, end, AF_INET, ipdup); - if (select) - goto cleanipdup; - } - - if (htonl(first.addr32[0]) > htonl(last.addr32[0])) { - info("The specified range %s is invalid, the second address is smallest than the first, it will be ignored.", - ipdup); - goto cleanipdup; - } - } else if (is_ipv6) { // IPV6 - if (!*end) { // Unique - select = ip2nl(first.addr8, ip, AF_INET6, ipdup); - if (select) - goto cleanipdup; - - memcpy(last.addr8, first.addr8, sizeof(first.addr8)); - } else if (*end == '-') { - *end++ = 0x00; - if (*end == '!') { - info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); - goto cleanipdup; - } - - select = ip2nl(first.addr8, ip, AF_INET6, ipdup); - if (select) - goto cleanipdup; - - select = ip2nl(last.addr8, end, AF_INET6, ipdup); - if (select) - goto cleanipdup; - } else { // CIDR - *end++ = 0x00; - if (*end == '!') { - info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); - goto cleanipdup; - } - - select = str2i(end); - if (select < 0 || select > 128) { - info("The CIDR %s is not valid, the address %s will be ignored.", end, ip); - goto cleanipdup; - } - - uint64_t prefix = (uint64_t)select; - select = ip2nl(first.addr8, ip, AF_INET6, ipdup); - if (select) - goto cleanipdup; - - get_ipv6_last_addr(&last, &first, prefix); - - union netdata_ip_t ipv6_test; - get_ipv6_first_addr(&ipv6_test, &first, prefix); - - if (memcmp(first.addr8, ipv6_test.addr8, sizeof(union netdata_ip_t)) != 0) { - memcpy(first.addr8, ipv6_test.addr8, sizeof(union netdata_ip_t)); - - struct in6_addr ipv6_convert; - memcpy(ipv6_convert.s6_addr, ipv6_test.addr8, sizeof(union netdata_ip_t)); - - char ipv6_msg[INET6_ADDRSTRLEN]; - if(inet_ntop(AF_INET6, &ipv6_convert, ipv6_msg, INET6_ADDRSTRLEN)) - info("The network value of CIDR %s was updated for %s .", ipdup, ipv6_msg); - } - } - - if ((be64toh(*(uint64_t *)&first.addr32[2]) > be64toh(*(uint64_t *)&last.addr32[2]) && - !memcmp(first.addr32, last.addr32, 2*sizeof(uint32_t))) || - (be64toh(*(uint64_t *)&first.addr32) > be64toh(*(uint64_t *)&last.addr32)) ) { - info("The specified range %s is invalid, the second address is smallest than the first, it will be ignored.", - ipdup); - goto cleanipdup; - } - } else { // Unique ip - select = ip2nl(first.addr8, ip, AF_INET, ipdup); - if (select) - goto cleanipdup; - - memcpy(last.addr8, first.addr8, sizeof(first.addr8)); - } - - ebpf_network_viewer_ip_list_t *store; - -storethisip: - store = callocz(1, sizeof(ebpf_network_viewer_ip_list_t)); - store->value = ipdup; - store->hash = simple_hash(ipdup); - store->ver = (uint8_t)(!is_ipv6)?AF_INET:AF_INET6; - memcpy(store->first.addr8, first.addr8, sizeof(first.addr8)); - memcpy(store->last.addr8, last.addr8, sizeof(last.addr8)); - - fill_ip_list(list, store, "socket"); - return; - -cleanipdup: - freez(ipdup); -} - -/** - * Parse IP Range - * - * Parse the IP ranges given and create Network Viewer IP Structure - * - * @param ptr is a pointer with the text to parse. - */ -static void parse_ips(char *ptr) -{ - // No value - if (unlikely(!ptr)) - return; - - while (likely(ptr)) { - // Move forward until next valid character - while (isspace(*ptr)) ptr++; - - // No valid value found - if (unlikely(!*ptr)) - return; - - // Find space that ends the list - char *end = strchr(ptr, ' '); - if (end) { - *end++ = '\0'; - } - - int neg = 0; - if (*ptr == '!') { - neg++; - ptr++; - } - - if (isascii(*ptr)) { // Parse port - parse_ip_list((!neg)?(void **)&network_viewer_opt.included_ips:(void **)&network_viewer_opt.excluded_ips, - ptr); - } - - ptr = end; - } -} - - -/** - * Parse Port Range - * - * Parse the port ranges given and create Network Viewer Port Structure - * - * @param ptr is a pointer with the text to parse. - */ -static void parse_ports(char *ptr) -{ - // No value - if (unlikely(!ptr)) - return; - - while (likely(ptr)) { - // Move forward until next valid character - while (isspace(*ptr)) ptr++; - - // No valid value found - if (unlikely(!*ptr)) - return; - - // Find space that ends the list - char *end = strchr(ptr, ' '); - if (end) { - *end++ = '\0'; - } - - int neg = 0; - if (*ptr == '!') { - neg++; - ptr++; - } - - if (isdigit(*ptr)) { // Parse port - parse_port_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, - ptr); - } else if (isalpha(*ptr)) { // Parse service - parse_service_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, - ptr); - } else if (*ptr == '*') { // All - parse_port_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, - ptr); - } - - ptr = end; - } -} - -/** - * Link hostname - * - * @param out is the output link list - * @param in the hostname to add to list. - */ -static void link_hostname(ebpf_network_viewer_hostname_list_t **out, ebpf_network_viewer_hostname_list_t *in) -{ - if (likely(*out)) { - ebpf_network_viewer_hostname_list_t *move = *out; - for (; move->next ; move = move->next ) { - if (move->hash == in->hash && !strcmp(move->value, in->value)) { - info("The hostname %s was already inserted, it will be ignored.", in->value); - freez(in->value); - simple_pattern_free(in->value_pattern); - freez(in); - return; - } - } - - move->next = in; - } else { - *out = in; - } -#ifdef NETDATA_INTERNAL_CHECKS - info("Adding value %s to %s hostname list used on network viewer", - in->value, - (*out == network_viewer_opt.included_hostnames)?"included":"excluded"); -#endif -} - -/** - * Link Hostnames - * - * Parse the list of hostnames to create the link list. - * This is not associated with the IP, because simple patterns like *example* cannot be resolved to IP. - * - * @param out is the output link list - * @param parse is a pointer with the text to parser. - */ -static void link_hostnames(char *parse) -{ - // No value - if (unlikely(!parse)) - return; - - while (likely(parse)) { - // Find the first valid value - while (isspace(*parse)) parse++; - - // No valid value found - if (unlikely(!*parse)) - return; - - // Find space that ends the list - char *end = strchr(parse, ' '); - if (end) { - *end++ = '\0'; - } - - int neg = 0; - if (*parse == '!') { - neg++; - parse++; - } - - ebpf_network_viewer_hostname_list_t *hostname = callocz(1 , sizeof(ebpf_network_viewer_hostname_list_t)); - hostname->value = strdupz(parse); - hostname->hash = simple_hash(parse); - hostname->value_pattern = simple_pattern_create(parse, NULL, SIMPLE_PATTERN_EXACT); - - link_hostname((!neg)?&network_viewer_opt.included_hostnames:&network_viewer_opt.excluded_hostnames, - hostname); - - parse = end; - } -} - -/** - * Read max dimension. - * - * Netdata plot two dimensions per connection, so it is necessary to adjust the values. - */ -static void read_max_dimension() -{ - int maxdim ; - maxdim = (int) appconfig_get_number(&collector_config, - EBPF_NETWORK_VIEWER_SECTION, - "maximum dimensions", - NETDATA_NV_CAP_VALUE); - if (maxdim < 0) { - error("'maximum dimensions = %d' must be a positive number, Netdata will change for default value %ld.", - maxdim, NETDATA_NV_CAP_VALUE); - maxdim = NETDATA_NV_CAP_VALUE; - } - - maxdim /= 2; - if (!maxdim) { - info("The number of dimensions is too small (%u), we are setting it to minimum 2", network_viewer_opt.max_dim); - network_viewer_opt.max_dim = 1; - } - - network_viewer_opt.max_dim = (uint32_t)maxdim; -} - -/** - * Parse network viewer section - */ -static void parse_network_viewer_section() -{ - read_max_dimension(); - - network_viewer_opt.hostname_resolution_enabled = appconfig_get_boolean(&collector_config, - EBPF_NETWORK_VIEWER_SECTION, - "resolve hostnames", - CONFIG_BOOLEAN_NO); - - network_viewer_opt.service_resolution_enabled = appconfig_get_boolean(&collector_config, - EBPF_NETWORK_VIEWER_SECTION, - "resolve service names", - CONFIG_BOOLEAN_NO); - - char *value = appconfig_get(&collector_config, EBPF_NETWORK_VIEWER_SECTION, - "ports", NULL); - parse_ports(value); - - if (network_viewer_opt.hostname_resolution_enabled) { - value = appconfig_get(&collector_config, EBPF_NETWORK_VIEWER_SECTION, "hostnames", NULL); - link_hostnames(value); - } else { - info("Name resolution is disabled, collector will not parser \"hostnames\" list."); - } - - value = appconfig_get(&collector_config, EBPF_NETWORK_VIEWER_SECTION, - "ips", "!127.0.0.1/8 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16 fc00::/7 !::1/128"); - parse_ips(value); -} - -/** - * Link dimension name - * - * Link user specified names inside a link list. - * - * @param port the port number associated to the dimension name. - * @param hash the calculated hash for the dimension name. - * @param name the dimension name. - */ -static void link_dimension_name(char *port, uint32_t hash, char *value) -{ - int test = str2i(port); - if (test < NETDATA_MINIMUM_PORT_VALUE || test > NETDATA_MAXIMUM_PORT_VALUE){ - error("The dimension given (%s = %s) has an invalid value and it will be ignored.", port, value); - return; - } - - ebpf_network_viewer_dim_name_t *w; - w = callocz(1, sizeof(ebpf_network_viewer_dim_name_t)); - - w->name = strdupz(value); - w->hash = hash; - - w->port = (uint16_t) htons(test); - - ebpf_network_viewer_dim_name_t *names = network_viewer_opt.names; - if (unlikely(!names)) { - network_viewer_opt.names = w; - } else { - for (; names->next; names = names->next) { - if (names->port == w->port) { - info("Dupplicated definition for a service, the name %s will be ignored. ", names->name); - freez(names->name); - names->name = w->name; - names->hash = w->hash; - freez(w); - return; - } - } - names->next = w; - } - -#ifdef NETDATA_INTERNAL_CHECKS - info("Adding values %s( %u) to dimension name list used on network viewer", w->name, htons(w->port)); -#endif -} - -/** - * Parse service Name section. - * - * This function gets the values that will be used to overwrite dimensions. - */ -static void parse_service_name_section() -{ - struct section *co = appconfig_get_section(&collector_config, EBPF_SERVICE_NAME_SECTION); - if (co) { - struct config_option *cv; - for (cv = co->values; cv ; cv = cv->next) { - link_dimension_name(cv->name, cv->hash, cv->value); - } - } - - // Always associated the default port to Netdata - ebpf_network_viewer_dim_name_t *names = network_viewer_opt.names; - if (names) { - uint16_t default_port = htons(19999); - while (names) { - if (names->port == default_port) - return; - - names = names->next; - } + int i; + int value = (int) appconfig_get_number(&collector_config, EBPF_GLOBAL_SECTION, EBPF_CFG_UPDATE_EVERY, 1); + for (i = 0; ebpf_modules[i].thread_name; i++) { + ebpf_modules[i].update_time = value; } - - char *port_string = getenv("NETDATA_LISTEN_PORT"); - if (port_string) - link_dimension_name(port_string, simple_hash(port_string), "Netdata"); } /** @@ -1633,18 +773,22 @@ static void read_collector_values(int *disable_apps) // Read global section char *value; if (appconfig_exists(&collector_config, EBPF_GLOBAL_SECTION, "load")) // Backward compatibility - value = appconfig_get(&collector_config, EBPF_GLOBAL_SECTION, "load", "entry"); + value = appconfig_get(&collector_config, EBPF_GLOBAL_SECTION, "load", + EBPF_CFG_LOAD_MODE_DEFAULT); else - value = appconfig_get(&collector_config, EBPF_GLOBAL_SECTION, "ebpf load mode", "entry"); + value = appconfig_get(&collector_config, EBPF_GLOBAL_SECTION, EBPF_CFG_LOAD_MODE, + EBPF_CFG_LOAD_MODE_DEFAULT); how_to_load(value); + ebpf_update_interval(); + // This is kept to keep compatibility uint32_t enabled = appconfig_get_boolean(&collector_config, EBPF_GLOBAL_SECTION, "disable apps", CONFIG_BOOLEAN_NO); if (!enabled) { // Apps is a positive sentence, so we need to invert the values to disable apps. - enabled = appconfig_get_boolean(&collector_config, EBPF_GLOBAL_SECTION, "apps", + enabled = appconfig_get_boolean(&collector_config, EBPF_GLOBAL_SECTION, EBPF_CFG_APPLICATION, CONFIG_BOOLEAN_YES); enabled = (enabled == CONFIG_BOOLEAN_NO)?CONFIG_BOOLEAN_YES:CONFIG_BOOLEAN_NO; } @@ -1652,7 +796,7 @@ static void read_collector_values(int *disable_apps) // Read ebpf programs section enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, - ebpf_modules[0].config_name, CONFIG_BOOLEAN_YES); + ebpf_modules[EBPF_MODULE_PROCESS_IDX].config_name, CONFIG_BOOLEAN_YES); int started = 0; if (enabled) { ebpf_enable_chart(EBPF_MODULE_PROCESS_IDX, *disable_apps); @@ -1663,14 +807,16 @@ static void read_collector_values(int *disable_apps) enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, "network viewer", CONFIG_BOOLEAN_NO); if (!enabled) - enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, ebpf_modules[1].config_name, + enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, + ebpf_modules[EBPF_MODULE_SOCKET_IDX].config_name, CONFIG_BOOLEAN_NO); if (enabled) { ebpf_enable_chart(EBPF_MODULE_SOCKET_IDX, *disable_apps); // Read network viewer section if network viewer is enabled - parse_network_viewer_section(); - parse_service_name_section(); + // This is kept here to keep backward compatibility + parse_network_viewer_section(&collector_config); + parse_service_name_section(&collector_config); started++; } @@ -1680,13 +826,30 @@ static void read_collector_values(int *disable_apps) if (!enabled) enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, "network connections", CONFIG_BOOLEAN_NO); - ebpf_modules[1].optional = enabled; + ebpf_modules[EBPF_MODULE_SOCKET_IDX].optional = enabled; + + enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, "cachestat", + CONFIG_BOOLEAN_NO); + + if (enabled) { + ebpf_enable_chart(EBPF_MODULE_CACHESTAT_IDX, *disable_apps); + started++; + } + + enabled = appconfig_get_boolean(&collector_config, EBPF_PROGRAMS_SECTION, "sync", + CONFIG_BOOLEAN_YES); + + if (enabled) { + ebpf_enable_chart(EBPF_MODULE_SYNC_IDX, *disable_apps); + started++; + } if (!started){ ebpf_enable_all_charts(*disable_apps); // Read network viewer section - parse_network_viewer_section(); - parse_service_name_section(); + // This is kept here to keep backward compatibility + parse_network_viewer_section(&collector_config); + parse_service_name_section(&collector_config); } } @@ -1702,10 +865,13 @@ static int load_collector_config(char *path, int *disable_apps) { char lpath[4096]; - snprintf(lpath, 4095, "%s/%s", path, "ebpf.conf"); - - if (!appconfig_load(&collector_config, lpath, 0, NULL)) - return -1; + snprintf(lpath, 4095, "%s/%s", path, NETDATA_EBPF_CONFIG_FILE); + if (!appconfig_load(&collector_config, lpath, 0, NULL)) { + snprintf(lpath, 4095, "%s/%s", path, NETDATA_EBPF_OLD_CONFIG_FILE); + if (!appconfig_load(&collector_config, lpath, 0, NULL)) { + return -1; + } + } read_collector_values(disable_apps); @@ -1756,13 +922,15 @@ static void parse_args(int argc, char **argv) int freq = 0; int option_index = 0; static struct option long_options[] = { - {"help", no_argument, 0, 'h' }, - {"version", no_argument, 0, 'v' }, - {"global", no_argument, 0, 'g' }, - {"all", no_argument, 0, 'a' }, - {"net", no_argument, 0, 'n' }, - {"process", no_argument, 0, 'p' }, - {"return", no_argument, 0, 'r' }, + {"help", no_argument, 0, 'h' }, + {"version", no_argument, 0, 'v' }, + {"global", no_argument, 0, 'g' }, + {"all", no_argument, 0, 'a' }, + {"cachestat", no_argument, 0, 'c' }, + {"net", no_argument, 0, 'n' }, + {"process", no_argument, 0, 'p' }, + {"return", no_argument, 0, 'r' }, + {"sync", no_argument, 0, 's' }, {0, 0, 0, 0} }; @@ -1777,7 +945,7 @@ static void parse_args(int argc, char **argv) } while (1) { - int c = getopt_long(argc, argv, "hvganpr", long_options, &option_index); + int c = getopt_long(argc, argv, "hvgcanprs", long_options, &option_index); if (c == -1) break; @@ -1803,6 +971,15 @@ static void parse_args(int argc, char **argv) ebpf_enable_all_charts(disable_apps); #ifdef NETDATA_INTERNAL_CHECKS info("EBPF running with all chart groups, because it was started with the option \"--all\" or \"-a\"."); +#endif + break; + } + case 'c': { + enabled = 1; + ebpf_enable_chart(EBPF_MODULE_CACHESTAT_IDX, disable_apps); +#ifdef NETDATA_INTERNAL_CHECKS + info( + "EBPF enabling \"CACHESTAT\" charts, because it was started with the option \"--cachestat\" or \"-c\"."); #endif break; } @@ -1827,6 +1004,14 @@ static void parse_args(int argc, char **argv) ebpf_set_thread_mode(MODE_RETURN); #ifdef NETDATA_INTERNAL_CHECKS info("EBPF running in \"return\" mode, because it was started with the option \"--return\" or \"-r\"."); +#endif + break; + } + case 's': { + enabled = 1; + ebpf_enable_chart(EBPF_MODULE_SYNC_IDX, disable_apps); +#ifdef NETDATA_INTERNAL_CHECKS + info("EBPF enabling \"sync\" chart, because it was started with the option \"--sync\" or \"-s\"."); #endif break; } @@ -1948,9 +1133,16 @@ int main(int argc, char **argv) read_local_ports("/proc/net/udp6", IPPROTO_UDP); struct netdata_static_thread ebpf_threads[] = { - {"EBPF PROCESS", NULL, NULL, 1, NULL, NULL, ebpf_modules[0].start_routine}, - {"EBPF SOCKET" , NULL, NULL, 1, NULL, NULL, ebpf_modules[1].start_routine}, - {NULL , NULL, NULL, 0, NULL, NULL, NULL} + {"EBPF PROCESS", NULL, NULL, 1, + NULL, NULL, ebpf_modules[EBPF_MODULE_PROCESS_IDX].start_routine}, + {"EBPF SOCKET" , NULL, NULL, 1, + NULL, NULL, ebpf_modules[EBPF_MODULE_SOCKET_IDX].start_routine}, + {"EBPF CACHESTAT" , NULL, NULL, 1, + NULL, NULL, ebpf_modules[EBPF_MODULE_CACHESTAT_IDX].start_routine}, + {"EBPF SYNC" , NULL, NULL, 1, + NULL, NULL, ebpf_modules[EBPF_MODULE_SYNC_IDX].start_routine}, + {NULL , NULL, NULL, 0, + NULL, NULL, NULL} }; //clean_loaded_events(); diff --git a/collectors/ebpf.plugin/ebpf.conf b/collectors/ebpf.plugin/ebpf.conf deleted file mode 100644 index 3a5b77395..000000000 --- a/collectors/ebpf.plugin/ebpf.conf +++ /dev/null @@ -1,45 +0,0 @@ -# -# Global options -# -# The `ebpf load mode` option accepts the following values : -# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. -# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates -# new charts for the return of these functions, such as errors. -# -# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. -# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to -# 'no'. -# -[global] - ebpf load mode = entry - apps = yes - -# -# eBPF Programs -# -# The eBPF collector enables and runs the following eBPF programs by default: -# -# `process` : This eBPF program creates charts that show information about process creation, VFS IO, and -# files removed. -# `socket` : This eBPF program creates charts with information about `TCP` and `UDP` functions, including the -# bandwidth consumed by each. -[ebpf programs] - process = yes - socket = yes - network connections = no - -# -# Network Connection -# -# This is a feature with status WIP(Work in Progress) -# -[network connections] - maximum dimensions = 50 - resolve hostnames = no - resolve service names = no - ports = * - ips = !127.0.0.1/8 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16 fc00::/7 !::1/128 - hostnames = * - -[service name] - 19999 = Netdata diff --git a/collectors/ebpf.plugin/ebpf.d.conf b/collectors/ebpf.plugin/ebpf.d.conf new file mode 100644 index 000000000..7191d7416 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d.conf @@ -0,0 +1,36 @@ +# +# Global options +# +# The `ebpf load mode` option accepts the following values : +# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. +# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates +# new charts for the return of these functions, such as errors. +# +# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. +# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to +# 'no'. +# +# The `update every` option defines the number of seconds used to read data from kernel and send to netdata +[global] + ebpf load mode = entry + apps = yes + update every = 1 + +# +# eBPF Programs +# +# The eBPF collector enables and runs the following eBPF programs by default: +# +# `cachestat`: Make charts for kernel functions related to page cache. +# `process` : This eBPF program creates charts that show information about process creation, VFS IO, and +# files removed. +# `socket` : This eBPF program creates charts with information about `TCP` and `UDP` functions, including the +# bandwidth consumed by each. +# `sync` : Montitor calls for syscall sync(2). +[ebpf programs] + cachestat = no + process = yes + socket = yes + sync = yes + network connections = no + diff --git a/collectors/ebpf.plugin/ebpf.d/cachestat.conf b/collectors/ebpf.plugin/ebpf.d/cachestat.conf new file mode 100644 index 000000000..78277cf56 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d/cachestat.conf @@ -0,0 +1,14 @@ +# The `ebpf load mode` option accepts the following values : +# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. +# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates +# new charts for the return of these functions, such as errors. +# +# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. +# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to +# 'no'. +# +# +[global] + ebpf load mode = entry + apps = yes + update every = 2 diff --git a/collectors/ebpf.plugin/ebpf.d/ebpf_kernel_reject_list.txt b/collectors/ebpf.plugin/ebpf.d/ebpf_kernel_reject_list.txt new file mode 100644 index 000000000..539bf357f --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d/ebpf_kernel_reject_list.txt @@ -0,0 +1 @@ +Ubuntu 4.18.0 diff --git a/collectors/ebpf.plugin/ebpf.d/network.conf b/collectors/ebpf.plugin/ebpf.d/network.conf new file mode 100644 index 000000000..b033bc39c --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d/network.conf @@ -0,0 +1,30 @@ +# The `ebpf load mode` option accepts the following values : +# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. +# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates +# new charts for the return of these functions, such as errors. +# +# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. +# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to +# 'no'. +# +# +[global] + ebpf load mode = entry + apps = yes + update every = 1 + +# +# Network Connection +# +# This is a feature with status WIP(Work in Progress) +# +[network connections] + maximum dimensions = 50 + resolve hostnames = no + resolve service names = no + ports = * + ips = !127.0.0.1/8 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16 fc00::/7 !::1/128 + hostnames = * + +[service name] + 19999 = Netdata diff --git a/collectors/ebpf.plugin/ebpf.d/process.conf b/collectors/ebpf.plugin/ebpf.d/process.conf new file mode 100644 index 000000000..7806dc844 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d/process.conf @@ -0,0 +1,14 @@ +# The `ebpf load mode` option accepts the following values : +# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. +# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates +# new charts for the return of these functions, such as errors. +# +# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. +# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to +# 'no'. +# +# +[global] + ebpf load mode = entry + apps = yes + update every = 1 diff --git a/collectors/ebpf.plugin/ebpf.d/sync.conf b/collectors/ebpf.plugin/ebpf.d/sync.conf new file mode 100644 index 000000000..de28f3394 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf.d/sync.conf @@ -0,0 +1,23 @@ +# The `ebpf load mode` option accepts the following values : +# `entry` : The eBPF collector only monitors calls for the functions, and does not show charts related to errors. +# `return : In the `return` mode, the eBPF collector monitors the same kernel functions as `entry`, but also creates +# new charts for the return of these functions, such as errors. +# +# The eBPF collector also creates charts for each running application through an integration with the `apps plugin`. +# If you want to disable the integration with `apps.plugin` along with the above charts, change the setting `apps` to +# 'no'. +# +# +[global] + ebpf load mode = entry + apps = yes + update every = 2 + +# List of monitored syscalls +[syscalls] + sync = yes + msync = yes + fsync = yes + fdatasync = yes + syncfs = yes + sync_file_range = yes diff --git a/collectors/ebpf.plugin/ebpf.h b/collectors/ebpf.plugin/ebpf.h index 35013c2b2..6796dcdad 100644 --- a/collectors/ebpf.plugin/ebpf.h +++ b/collectors/ebpf.plugin/ebpf.h @@ -31,6 +31,9 @@ #include "ebpf_apps.h" +#define NETDATA_EBPF_OLD_CONFIG_FILE "ebpf.conf" +#define NETDATA_EBPF_CONFIG_FILE "ebpf.d.conf" + typedef struct netdata_syscall_stat { unsigned long bytes; // total number of bytes uint64_t call; // total number of calls @@ -70,8 +73,12 @@ typedef struct netdata_error_report { } netdata_error_report_t; extern ebpf_module_t ebpf_modules[]; -#define EBPF_MODULE_PROCESS_IDX 0 -#define EBPF_MODULE_SOCKET_IDX 1 +enum ebpf_module_indexes { + EBPF_MODULE_PROCESS_IDX, + EBPF_MODULE_SOCKET_IDX, + EBPF_MODULE_CACHESTAT_IDX, + EBPF_MODULE_SYNC_IDX +}; // Copied from musl header #ifndef offsetof @@ -84,6 +91,9 @@ extern ebpf_module_t ebpf_modules[]; // Chart defintions #define NETDATA_EBPF_FAMILY "ebpf" +#define NETDATA_EBPF_CHART_TYPE_LINE "line" +#define NETDATA_EBPF_CHART_TYPE_STACKED "stacked" +#define NETDATA_EBPF_MEMORY_GROUP "mem" // Log file #define NETDATA_DEVELOPER_LOG_FILE "developer.log" @@ -133,6 +143,7 @@ extern void ebpf_write_chart_cmd(char *type, char *units, char *family, char *charttype, + char *context, int order); extern void ebpf_write_global_dimension(char *name, char *id, char *algorithm); @@ -144,6 +155,8 @@ extern void ebpf_create_chart(char *type, char *title, char *units, char *family, + char *context, + char *charttype, int order, void (*ncd)(void *, int), void *move, @@ -166,6 +179,7 @@ extern void ebpf_create_charts_on_apps(char *name, char *title, char *units, char *family, + char *charttype, int order, char *algorithm, struct target *root); @@ -174,11 +188,9 @@ extern void write_end_chart(); extern void ebpf_cleanup_publish_syscall(netdata_publish_syscall_t *nps); -#define EBPF_GLOBAL_SECTION "global" #define EBPF_PROGRAMS_SECTION "ebpf programs" -#define EBPF_NETWORK_VIEWER_SECTION "network connections" -#define EBPF_SERVICE_NAME_SECTION "service name" +#define EBPF_COMMON_DIMENSION_PERCENTAGE "%" #define EBPF_COMMON_DIMENSION_CALL "calls/s" #define EBPF_COMMON_DIMENSION_BITS "kilobits/s" #define EBPF_COMMON_DIMENSION_BYTES "bytes/s" @@ -186,22 +198,24 @@ extern void ebpf_cleanup_publish_syscall(netdata_publish_syscall_t *nps); #define EBPF_COMMON_DIMENSION_PACKETS "packets" // Common variables -extern char *ebpf_user_config_dir; -extern char *ebpf_stock_config_dir; extern int debug_enabled; extern struct pid_stat *root_of_pids; extern char *ebpf_algorithms[]; - -// Socket functions and variables -// Common functions -extern void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root); -extern collected_number get_value_from_structure(char *basis, size_t offset); +extern struct config collector_config; extern struct pid_stat *root_of_pids; extern ebpf_process_stat_t *global_process_stat; extern size_t all_pids_count; extern int update_every; extern uint32_t finalized_threads; +// Socket functions and variables +// Common functions +extern void ebpf_process_create_apps_charts(struct ebpf_module *em, void *ptr); +extern void ebpf_socket_create_apps_charts(struct ebpf_module *em, void *ptr); +extern void ebpf_cachestat_create_apps_charts(struct ebpf_module *em, void *root); +extern void ebpf_one_dimension_write_charts(char *family, char *chart, char *dim, long long v1); +extern collected_number get_value_from_structure(char *basis, size_t offset); + #define EBPF_MAX_SYNCHRONIZATION_TIME 300 #endif /* NETDATA_COLLECTOR_EBPF_H */ diff --git a/collectors/ebpf.plugin/ebpf_apps.c b/collectors/ebpf.plugin/ebpf_apps.c index 844ce23b8..1be7b9260 100644 --- a/collectors/ebpf.plugin/ebpf_apps.c +++ b/collectors/ebpf.plugin/ebpf_apps.c @@ -909,6 +909,26 @@ static inline void del_pid_entry(pid_t pid) all_pids_count--; } +/** + * Cleanup variable from other threads + * + * @param pid current pid. + */ +void cleanup_variables_from_other_threads(uint32_t pid) +{ + // Clean socket structures + if (socket_bandwidth_curr) { + freez(socket_bandwidth_curr[pid]); + socket_bandwidth_curr[pid] = NULL; + } + + // Clean cachestat strcture + if (cachestat_pid) { + freez(cachestat_pid[pid]); + cachestat_pid[pid] = NULL; + } +} + /** * Remove PIDs when they are not running more. */ @@ -932,11 +952,7 @@ void cleanup_exited_pids() freez(current_apps_data[r]); current_apps_data[r] = NULL; - // Clean socket structures - if (socket_bandwidth_curr) { - freez(socket_bandwidth_curr[r]); - socket_bandwidth_curr[r] = NULL; - } + cleanup_variables_from_other_threads(r); } else { if (unlikely(p->keep)) p->keeploops++; @@ -1054,11 +1070,7 @@ void collect_data_for_all_processes(int tbl_pid_stats_fd) freez(current_apps_data[key]); current_apps_data[key] = NULL; - // Clean socket structures - if (socket_bandwidth_curr) { - freez(socket_bandwidth_curr[key]); - socket_bandwidth_curr[key] = NULL; - } + cleanup_variables_from_other_threads(key); pids = pids->next; continue; diff --git a/collectors/ebpf.plugin/ebpf_apps.h b/collectors/ebpf.plugin/ebpf_apps.h index f8cb7ac72..eb54754c6 100644 --- a/collectors/ebpf.plugin/ebpf_apps.h +++ b/collectors/ebpf.plugin/ebpf_apps.h @@ -11,12 +11,15 @@ #include "libnetdata/ebpf/ebpf.h" #define NETDATA_APPS_FAMILY "apps" -#define NETDATA_APPS_FILE_GROUP "ebpf file" -#define NETDATA_APPS_VFS_GROUP "ebpf vfs" -#define NETDATA_APPS_PROCESS_GROUP "ebpf process" -#define NETDATA_APPS_NET_GROUP "ebpf net" +#define NETDATA_APPS_FILE_GROUP "file (eBPF)" +#define NETDATA_APPS_VFS_GROUP "vfs (eBPF)" +#define NETDATA_APPS_PROCESS_GROUP "process (eBPF)" +#define NETDATA_APPS_NET_GROUP "net (eBPF)" +#define NETDATA_APPS_CACHESTAT_GROUP "page cache (eBPF)" #include "ebpf_process.h" +#include "ebpf_cachestat.h" +#include "ebpf_sync.h" #define MAX_COMPARE_NAME 100 #define MAX_NAME 100 @@ -105,6 +108,9 @@ struct target { uid_t uid; gid_t gid; + // Page cache statistic per process + netdata_publish_cachestat_t cachestat; + /* These variables are not necessary for eBPF collector kernel_uint_t minflt; kernel_uint_t cminflt; @@ -426,5 +432,6 @@ extern void collect_data_for_all_processes(int tbl_pid_stats_fd); extern ebpf_process_stat_t **global_process_stats; extern ebpf_process_publish_apps_t **current_apps_data; +extern netdata_publish_cachestat_t **cachestat_pid; #endif /* NETDATA_EBPF_APPS_H */ diff --git a/collectors/ebpf.plugin/ebpf_cachestat.c b/collectors/ebpf.plugin/ebpf_cachestat.c new file mode 100644 index 000000000..6516d4da2 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf_cachestat.c @@ -0,0 +1,655 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "ebpf.h" +#include "ebpf_cachestat.h" + +static ebpf_data_t cachestat_data; +netdata_publish_cachestat_t **cachestat_pid; + +static struct bpf_link **probe_links = NULL; +static struct bpf_object *objects = NULL; + +static char *cachestat_counter_dimension_name[NETDATA_CACHESTAT_END] = { "ratio", "dirty", "hit", + "miss" }; +static netdata_syscall_stat_t cachestat_counter_aggregated_data[NETDATA_CACHESTAT_END]; +static netdata_publish_syscall_t cachestat_counter_publish_aggregated[NETDATA_CACHESTAT_END]; + +netdata_cachestat_pid_t *cachestat_vector = NULL; + +static netdata_idx_t *cachestat_hash_values = NULL; + +static int read_thread_closed = 1; + +struct netdata_static_thread cachestat_threads = {"CACHESTAT KERNEL", + NULL, NULL, 1, NULL, + NULL, NULL}; + +static int *map_fd = NULL; + +struct config cachestat_config = { .first_section = NULL, + .last_section = NULL, + .mutex = NETDATA_MUTEX_INITIALIZER, + .index = { .avl_tree = { .root = NULL, .compar = appconfig_section_compare }, + .rwlock = AVL_LOCK_INITIALIZER } }; + +/***************************************************************** + * + * FUNCTIONS TO CLOSE THE THREAD + * + *****************************************************************/ + +/** + * Clean PID structures + * + * Clean the allocated structures. + */ +static void clean_pid_structures() { + struct pid_stat *pids = root_of_pids; + while (pids) { + freez(cachestat_pid[pids->pid]); + + pids = pids->next; + } +} + +/** + * Clean up the main thread. + * + * @param ptr thread data. + */ +static void ebpf_cachestat_cleanup(void *ptr) +{ + ebpf_module_t *em = (ebpf_module_t *)ptr; + if (!em->enabled) + return; + + heartbeat_t hb; + heartbeat_init(&hb); + uint32_t tick = 2*USEC_PER_MS; + while (!read_thread_closed) { + usec_t dt = heartbeat_next(&hb, tick); + UNUSED(dt); + } + + clean_pid_structures(); + freez(cachestat_pid); + + ebpf_cleanup_publish_syscall(cachestat_counter_publish_aggregated); + + freez(cachestat_vector); + freez(cachestat_hash_values); + + struct bpf_program *prog; + size_t i = 0 ; + bpf_object__for_each_program(prog, objects) { + bpf_link__destroy(probe_links[i]); + i++; + } + bpf_object__close(objects); +} + +/***************************************************************** + * + * COMMON FUNCTIONS + * + *****************************************************************/ + +/** + * Update publish + * + * Update publish values before to write dimension. + * + * @param out strcuture that will receive data. + * @param mpa calls for mark_page_accessed during the last second. + * @param mbd calls for mark_buffer_dirty during the last second. + * @param apcl calls for add_to_page_cache_lru during the last second. + * @param apd calls for account_page_dirtied during the last second. + */ +void cachestat_update_publish(netdata_publish_cachestat_t *out, uint64_t mpa, uint64_t mbd, + uint64_t apcl, uint64_t apd) +{ + // Adapted algorithm from https://github.com/iovisor/bcc/blob/master/tools/cachestat.py#L126-L138 + calculated_number total = (calculated_number) (((long long)mpa) - ((long long)mbd)); + if (total < 0) + total = 0; + + calculated_number misses = (calculated_number) ( ((long long) apcl) - ((long long) apd) ); + if (misses < 0) + misses = 0; + + // If hits are < 0, then its possible misses are overestimate due to possibly page cache read ahead adding + // more pages than needed. In this case just assume misses as total and reset hits. + calculated_number hits = total - misses; + if (hits < 0 ) { + misses = total; + hits = 0; + } + + calculated_number ratio = (total > 0) ? hits/total : 0; + + out->ratio = (long long )(ratio*100); + out->hit = (long long)hits; + out->miss = (long long)misses; +} + +/** + * Save previous values + * + * Save values used this time. + * + * @param publish + */ +static void save_previous_values(netdata_publish_cachestat_t *publish) { + publish->prev.mark_page_accessed = cachestat_hash_values[NETDATA_KEY_CALLS_MARK_PAGE_ACCESSED]; + publish->prev.account_page_dirtied = cachestat_hash_values[NETDATA_KEY_CALLS_ACCOUNT_PAGE_DIRTIED]; + publish->prev.add_to_page_cache_lru = cachestat_hash_values[NETDATA_KEY_CALLS_ADD_TO_PAGE_CACHE_LRU]; + publish->prev.mark_buffer_dirty = cachestat_hash_values[NETDATA_KEY_CALLS_MARK_BUFFER_DIRTY]; +} + +/** + * Calculate statistics + * + * @param publish the structure where we will store the data. + */ +static void calculate_stats(netdata_publish_cachestat_t *publish) { + if (!publish->prev.mark_page_accessed) { + save_previous_values(publish); + return; + } + + uint64_t mpa = cachestat_hash_values[NETDATA_KEY_CALLS_MARK_PAGE_ACCESSED] - publish->prev.mark_page_accessed; + uint64_t mbd = cachestat_hash_values[NETDATA_KEY_CALLS_MARK_BUFFER_DIRTY] - publish->prev.mark_buffer_dirty; + uint64_t apcl = cachestat_hash_values[NETDATA_KEY_CALLS_ADD_TO_PAGE_CACHE_LRU] - publish->prev.add_to_page_cache_lru; + uint64_t apd = cachestat_hash_values[NETDATA_KEY_CALLS_ACCOUNT_PAGE_DIRTIED] - publish->prev.account_page_dirtied; + + save_previous_values(publish); + + // We are changing the original algorithm to have a smooth ratio. + cachestat_update_publish(publish, mpa, mbd, apcl, apd); +} + + +/***************************************************************** + * + * APPS + * + *****************************************************************/ + +/** + * Apps Accumulator + * + * Sum all values read from kernel and store in the first address. + * + * @param out the vector with read values. + */ +static void cachestat_apps_accumulator(netdata_cachestat_pid_t *out) +{ + int i, end = (running_on_kernel >= NETDATA_KERNEL_V4_15) ? ebpf_nprocs : 1; + netdata_cachestat_pid_t *total = &out[0]; + for (i = 1; i < end; i++) { + netdata_cachestat_pid_t *w = &out[i]; + total->account_page_dirtied += w->account_page_dirtied; + total->add_to_page_cache_lru += w->add_to_page_cache_lru; + total->mark_buffer_dirty += w->mark_buffer_dirty; + total->mark_page_accessed += w->mark_page_accessed; + } +} + +/** + * Save Pid values + * + * Save the current values inside the structure + * + * @param out vector used to plot charts + * @param publish vector with values read from hash tables. + */ +static inline void cachestat_save_pid_values(netdata_publish_cachestat_t *out, netdata_cachestat_pid_t *publish) +{ + if (!out->current.mark_page_accessed) { + memcpy(&out->current, &publish[0], sizeof(netdata_cachestat_pid_t)); + return; + } + + memcpy(&out->prev, &out->current, sizeof(netdata_cachestat_pid_t)); + memcpy(&out->current, &publish[0], sizeof(netdata_cachestat_pid_t)); +} + +/** + * Fill PID + * + * Fill PID structures + * + * @param current_pid pid that we are collecting data + * @param out values read from hash tables; + */ +static void cachestat_fill_pid(uint32_t current_pid, netdata_cachestat_pid_t *publish) +{ + netdata_publish_cachestat_t *curr = cachestat_pid[current_pid]; + if (!curr) { + curr = callocz(1, sizeof(netdata_publish_cachestat_t)); + cachestat_pid[current_pid] = curr; + + cachestat_save_pid_values(curr, publish); + return; + } + + cachestat_save_pid_values(curr, publish); +} + +/** + * Read APPS table + * + * Read the apps table and store data inside the structure. + */ +static void read_apps_table() +{ + netdata_cachestat_pid_t *cv = cachestat_vector; + uint32_t key; + struct pid_stat *pids = root_of_pids; + int fd = map_fd[NETDATA_CACHESTAT_PID_STATS]; + size_t length = sizeof(netdata_cachestat_pid_t)*ebpf_nprocs; + while (pids) { + key = pids->pid; + + if (bpf_map_lookup_elem(fd, &key, cv)) { + pids = pids->next; + continue; + } + + cachestat_apps_accumulator(cv); + + cachestat_fill_pid(key, cv); + + // We are cleaning to avoid passing data read from one process to other. + memset(cv, 0, length); + + pids = pids->next; + } +} + +/** + * Create apps charts + * + * Call ebpf_create_chart to create the charts on apps submenu. + * + * @param em a pointer to the structure with the default values. + */ +void ebpf_cachestat_create_apps_charts(struct ebpf_module *em, void *ptr) +{ + UNUSED(em); + struct target *root = ptr; + ebpf_create_charts_on_apps(NETDATA_CACHESTAT_HIT_RATIO_CHART, + "The ratio is calculated dividing the Hit pages per total cache accesses without counting dirties.", + EBPF_COMMON_DIMENSION_PERCENTAGE, + NETDATA_APPS_CACHESTAT_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, + 20090, + ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], + root); + + ebpf_create_charts_on_apps(NETDATA_CACHESTAT_DIRTY_CHART, + "Number of pages marked as dirty. When a page is called dirty, this means that the data stored inside the page needs to be written to devices.", + EBPF_CACHESTAT_DIMENSION_PAGE, + NETDATA_APPS_CACHESTAT_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, + 20091, + ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], + root); + + ebpf_create_charts_on_apps(NETDATA_CACHESTAT_HIT_CHART, + "Number of cache access without counting dirty pages and page additions.", + EBPF_CACHESTAT_DIMENSION_HITS, + NETDATA_APPS_CACHESTAT_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, + 20092, + ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], + root); + + ebpf_create_charts_on_apps(NETDATA_CACHESTAT_MISSES_CHART, + "Page caches added without counting dirty pages", + EBPF_CACHESTAT_DIMENSION_MISSES, + NETDATA_APPS_CACHESTAT_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, + 20093, + ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], + root); +} + +/***************************************************************** + * + * MAIN LOOP + * + *****************************************************************/ + +/** + * Read global counter + * + * Read the table with number of calls for all functions + */ +static void read_global_table() +{ + uint32_t idx; + netdata_idx_t *val = cachestat_hash_values; + netdata_idx_t stored; + int fd = map_fd[NETDATA_CACHESTAT_GLOBAL_STATS]; + + for (idx = NETDATA_KEY_CALLS_ADD_TO_PAGE_CACHE_LRU; idx < NETDATA_CACHESTAT_END; idx++) { + if (!bpf_map_lookup_elem(fd, &idx, &stored)) { + val[idx] = stored; + } + } +} + +/** + * Socket read hash + * + * This is the thread callback. + * This thread is necessary, because we cannot freeze the whole plugin to read the data on very busy socket. + * + * @param ptr It is a NULL value for this thread. + * + * @return It always returns NULL. + */ +void *ebpf_cachestat_read_hash(void *ptr) +{ + read_thread_closed = 0; + + heartbeat_t hb; + heartbeat_init(&hb); + + ebpf_module_t *em = (ebpf_module_t *)ptr; + + usec_t step = NETDATA_LATENCY_CACHESTAT_SLEEP_MS * em->update_time; + int apps = em->apps_charts; + while (!close_ebpf_plugin) { + usec_t dt = heartbeat_next(&hb, step); + (void)dt; + + read_global_table(); + + if (apps) + read_apps_table(); + } + read_thread_closed = 1; + + return NULL; +} + +/** + * Send global + * + * Send global charts to Netdata + */ +static void cachestat_send_global(netdata_publish_cachestat_t *publish) +{ + calculate_stats(publish); + + netdata_publish_syscall_t *ptr = cachestat_counter_publish_aggregated; + // The algorithm sets this value to zero sometimes, we are not written them to have a smooth chart + if (publish->ratio) { + ebpf_one_dimension_write_charts( + NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_HIT_RATIO_CHART, ptr[NETDATA_CACHESTAT_IDX_RATIO].dimension, + publish->ratio); + } + + ebpf_one_dimension_write_charts( + NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_DIRTY_CHART, ptr[NETDATA_CACHESTAT_IDX_DIRTY].dimension, + cachestat_hash_values[NETDATA_KEY_CALLS_MARK_BUFFER_DIRTY]); + + ebpf_one_dimension_write_charts( + NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_HIT_CHART, ptr[NETDATA_CACHESTAT_IDX_HIT].dimension, publish->hit); + + ebpf_one_dimension_write_charts( + NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_MISSES_CHART, ptr[NETDATA_CACHESTAT_IDX_MISS].dimension, + publish->miss); +} + +/** + * Cachestat sum PIDs + * + * Sum values for all PIDs associated to a group + * + * @param publish output structure. + * @param root structure with listed IPs + */ +void ebpf_cachestat_sum_pids(netdata_publish_cachestat_t *publish, struct pid_on_target *root) +{ + memcpy(&publish->prev, &publish->current,sizeof(publish->current)); + memset(&publish->current, 0, sizeof(publish->current)); + + netdata_cachestat_pid_t *dst = &publish->current; + while (root) { + int32_t pid = root->pid; + netdata_publish_cachestat_t *w = cachestat_pid[pid]; + if (w) { + netdata_cachestat_pid_t *src = &w->current; + dst->account_page_dirtied += src->account_page_dirtied; + dst->add_to_page_cache_lru += src->add_to_page_cache_lru; + dst->mark_buffer_dirty += src->mark_buffer_dirty; + dst->mark_page_accessed += src->mark_page_accessed; + } + + root = root->next; + } +} + +/** + * Send data to Netdata calling auxiliar functions. + * + * @param root the target list. +*/ +void ebpf_cache_send_apps_data(struct target *root) +{ + struct target *w; + collected_number value; + + write_begin_chart(NETDATA_APPS_FAMILY, NETDATA_CACHESTAT_HIT_RATIO_CHART); + for (w = root; w; w = w->next) { + if (unlikely(w->exposed && w->processes)) { + ebpf_cachestat_sum_pids(&w->cachestat, w->root_pid); + netdata_cachestat_pid_t *current = &w->cachestat.current; + netdata_cachestat_pid_t *prev = &w->cachestat.prev; + + uint64_t mpa = current->mark_page_accessed - prev->mark_page_accessed; + uint64_t mbd = current->mark_buffer_dirty - prev->mark_buffer_dirty; + w->cachestat.dirty = current->mark_buffer_dirty; + uint64_t apcl = current->add_to_page_cache_lru - prev->add_to_page_cache_lru; + uint64_t apd = current->account_page_dirtied - prev->account_page_dirtied; + + cachestat_update_publish(&w->cachestat, mpa, mbd, apcl, apd); + value = (collected_number) w->cachestat.ratio; + // Here we are using different approach to have a chart more smooth + write_chart_dimension(w->name, value); + } + } + write_end_chart(); + + write_begin_chart(NETDATA_APPS_FAMILY, NETDATA_CACHESTAT_DIRTY_CHART); + for (w = root; w; w = w->next) { + if (unlikely(w->exposed && w->processes)) { + value = (collected_number) w->cachestat.dirty; + write_chart_dimension(w->name, value); + } + } + write_end_chart(); + + write_begin_chart(NETDATA_APPS_FAMILY, NETDATA_CACHESTAT_HIT_CHART); + for (w = root; w; w = w->next) { + if (unlikely(w->exposed && w->processes)) { + value = (collected_number) w->cachestat.hit; + write_chart_dimension(w->name, value); + } + } + write_end_chart(); + + write_begin_chart(NETDATA_APPS_FAMILY, NETDATA_CACHESTAT_MISSES_CHART); + for (w = root; w; w = w->next) { + if (unlikely(w->exposed && w->processes)) { + value = (collected_number) w->cachestat.miss; + write_chart_dimension(w->name, value); + } + } + write_end_chart(); +} + +/** +* Main loop for this collector. +*/ +static void cachestat_collector(ebpf_module_t *em) +{ + cachestat_threads.thread = mallocz(sizeof(netdata_thread_t)); + cachestat_threads.start_routine = ebpf_cachestat_read_hash; + + map_fd = cachestat_data.map_fd; + + netdata_thread_create(cachestat_threads.thread, cachestat_threads.name, NETDATA_THREAD_OPTION_JOINABLE, + ebpf_cachestat_read_hash, em); + + netdata_publish_cachestat_t publish; + memset(&publish, 0, sizeof(publish)); + int apps = em->apps_charts; + while (!close_ebpf_plugin) { + pthread_mutex_lock(&collect_data_mutex); + pthread_cond_wait(&collect_data_cond_var, &collect_data_mutex); + + pthread_mutex_lock(&lock); + + cachestat_send_global(&publish); + + if (apps) + ebpf_cache_send_apps_data(apps_groups_root_target); + + pthread_mutex_unlock(&lock); + pthread_mutex_unlock(&collect_data_mutex); + } +} + +/***************************************************************** + * + * INITIALIZE THREAD + * + *****************************************************************/ + +/** + * Create global charts + * + * Call ebpf_create_chart to create the charts for the collector. + */ +static void ebpf_create_memory_charts() +{ + ebpf_create_chart(NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_HIT_RATIO_CHART, + "Hit is calculating using total cache added without dirties per total added because of red misses.", + EBPF_CACHESTAT_DIMENSION_HITS, NETDATA_CACHESTAT_SUBMENU, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, + 21100, + ebpf_create_global_dimension, + cachestat_counter_publish_aggregated, 1); + + ebpf_create_chart(NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_DIRTY_CHART, + "Number of dirty pages added to the page cache.", + EBPF_CACHESTAT_DIMENSION_PAGE, NETDATA_CACHESTAT_SUBMENU, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, + 21101, + ebpf_create_global_dimension, + &cachestat_counter_publish_aggregated[NETDATA_CACHESTAT_IDX_DIRTY], 1); + + ebpf_create_chart(NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_HIT_CHART, + "Hits are function calls that Netdata counts.", + EBPF_CACHESTAT_DIMENSION_HITS, NETDATA_CACHESTAT_SUBMENU, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, + 21102, + ebpf_create_global_dimension, + &cachestat_counter_publish_aggregated[NETDATA_CACHESTAT_IDX_HIT], 1); + + ebpf_create_chart(NETDATA_EBPF_MEMORY_GROUP, NETDATA_CACHESTAT_MISSES_CHART, + "Misses are function calls that Netdata counts.", + EBPF_CACHESTAT_DIMENSION_MISSES, NETDATA_CACHESTAT_SUBMENU, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, + 21103, + ebpf_create_global_dimension, + &cachestat_counter_publish_aggregated[NETDATA_CACHESTAT_IDX_MISS], 1); + + fflush(stdout); +} + +/** + * Allocate vectors used with this thread. + * + * We are not testing the return, because callocz does this and shutdown the software + * case it was not possible to allocate. + * + * @param length is the length for the vectors used inside the collector. + */ +static void ebpf_cachestat_allocate_global_vectors(size_t length) +{ + cachestat_pid = callocz((size_t)pid_max, sizeof(netdata_publish_cachestat_t *)); + cachestat_vector = callocz((size_t)ebpf_nprocs, sizeof(netdata_cachestat_pid_t)); + + cachestat_hash_values = callocz(length, sizeof(netdata_idx_t)); + + memset(cachestat_counter_aggregated_data, 0, length * sizeof(netdata_syscall_stat_t)); + memset(cachestat_counter_publish_aggregated, 0, length * sizeof(netdata_publish_syscall_t)); +} + +/***************************************************************** + * + * MAIN THREAD + * + *****************************************************************/ + +/** + * Cachestat thread + * + * Thread used to make cachestat thread + * + * @param ptr a pointer to `struct ebpf_module` + * + * @return It always return NULL + */ +void *ebpf_cachestat_thread(void *ptr) +{ + netdata_thread_cleanup_push(ebpf_cachestat_cleanup, ptr); + + ebpf_module_t *em = (ebpf_module_t *)ptr; + fill_ebpf_data(&cachestat_data); + + ebpf_update_module(em, &cachestat_config, NETDATA_CACHESTAT_CONFIG_FILE); + + if (!em->enabled) + goto endcachestat; + + pthread_mutex_lock(&lock); + ebpf_cachestat_allocate_global_vectors(NETDATA_CACHESTAT_END); + if (ebpf_update_kernel(&cachestat_data)) { + pthread_mutex_unlock(&lock); + goto endcachestat; + } + + probe_links = ebpf_load_program(ebpf_plugin_dir, em, kernel_string, &objects, cachestat_data.map_fd); + if (!probe_links) { + pthread_mutex_unlock(&lock); + goto endcachestat; + } + + int algorithms[NETDATA_CACHESTAT_END] = { + NETDATA_EBPF_ABSOLUTE_IDX, NETDATA_EBPF_INCREMENTAL_IDX, NETDATA_EBPF_ABSOLUTE_IDX, NETDATA_EBPF_ABSOLUTE_IDX + }; + + ebpf_global_labels(cachestat_counter_aggregated_data, cachestat_counter_publish_aggregated, + cachestat_counter_dimension_name, cachestat_counter_dimension_name, + algorithms, NETDATA_CACHESTAT_END); + + ebpf_create_memory_charts(); + + pthread_mutex_unlock(&lock); + + cachestat_collector(em); + +endcachestat: + netdata_thread_cleanup_pop(1); + return NULL; +} diff --git a/collectors/ebpf.plugin/ebpf_cachestat.h b/collectors/ebpf.plugin/ebpf_cachestat.h new file mode 100644 index 000000000..daf678975 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf_cachestat.h @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EBPF_CACHESTAT_H +#define NETDATA_EBPF_CACHESTAT_H 1 + +// charts +#define NETDATA_CACHESTAT_HIT_RATIO_CHART "cachestat_ratio" +#define NETDATA_CACHESTAT_DIRTY_CHART "cachestat_dirties" +#define NETDATA_CACHESTAT_HIT_CHART "cachestat_hits" +#define NETDATA_CACHESTAT_MISSES_CHART "cachestat_misses" + +#define NETDATA_CACHESTAT_SUBMENU "page cache (eBPF)" + +#define EBPF_CACHESTAT_DIMENSION_PAGE "pages/s" +#define EBPF_CACHESTAT_DIMENSION_HITS "hits/s" +#define EBPF_CACHESTAT_DIMENSION_MISSES "misses/s" + +#define NETDATA_LATENCY_CACHESTAT_SLEEP_MS 600000ULL + +// configuration file +#define NETDATA_CACHESTAT_CONFIG_FILE "cachestat.conf" + +// variables +enum cachestat_counters { + NETDATA_KEY_CALLS_ADD_TO_PAGE_CACHE_LRU, + NETDATA_KEY_CALLS_MARK_PAGE_ACCESSED, + NETDATA_KEY_CALLS_ACCOUNT_PAGE_DIRTIED, + NETDATA_KEY_CALLS_MARK_BUFFER_DIRTY, + + NETDATA_CACHESTAT_END +}; + +enum cachestat_indexes { + NETDATA_CACHESTAT_IDX_RATIO, + NETDATA_CACHESTAT_IDX_DIRTY, + NETDATA_CACHESTAT_IDX_HIT, + NETDATA_CACHESTAT_IDX_MISS +}; + +enum cachesta_tables { + NETDATA_CACHESTAT_GLOBAL_STATS, + NETDATA_CACHESTAT_PID_STATS +}; + +typedef struct netdata_publish_cachestat_pid { + uint64_t add_to_page_cache_lru; + uint64_t mark_page_accessed; + uint64_t account_page_dirtied; + uint64_t mark_buffer_dirty; +} netdata_cachestat_pid_t; + +typedef struct netdata_publish_cachestat { + long long ratio; + long long dirty; + long long hit; + long long miss; + + netdata_cachestat_pid_t current; + netdata_cachestat_pid_t prev; +} netdata_publish_cachestat_t; + +extern void *ebpf_cachestat_thread(void *ptr); + +#endif // NETDATA_EBPF_CACHESTAT_H diff --git a/collectors/ebpf.plugin/ebpf_kernel_reject_list.txt b/collectors/ebpf.plugin/ebpf_kernel_reject_list.txt deleted file mode 100644 index d56b216a9..000000000 --- a/collectors/ebpf.plugin/ebpf_kernel_reject_list.txt +++ /dev/null @@ -1 +0,0 @@ -Ubuntu 4.18.0-13. diff --git a/collectors/ebpf.plugin/ebpf_process.c b/collectors/ebpf.plugin/ebpf_process.c index 27e39d1a5..5fa930b2d 100644 --- a/collectors/ebpf.plugin/ebpf_process.c +++ b/collectors/ebpf.plugin/ebpf_process.c @@ -19,8 +19,8 @@ static char *process_id_names[NETDATA_KEY_PUBLISH_PROCESS_END] = { "do_sys_open" static char *status[] = { "process", "zombie" }; static netdata_idx_t *process_hash_values = NULL; -static netdata_syscall_stat_t *process_aggregated_data = NULL; -static netdata_publish_syscall_t *process_publish_aggregated = NULL; +static netdata_syscall_stat_t process_aggregated_data[NETDATA_KEY_PUBLISH_PROCESS_END]; +static netdata_publish_syscall_t process_publish_aggregated[NETDATA_KEY_PUBLISH_PROCESS_END]; static ebpf_data_t process_data; @@ -33,6 +33,12 @@ static int *map_fd = NULL; static struct bpf_object *objects = NULL; static struct bpf_link **probe_links = NULL; +struct config process_config = { .first_section = NULL, + .last_section = NULL, + .mutex = NETDATA_MUTEX_INITIALIZER, + .index = { .avl_tree = { .root = NULL, .compar = appconfig_section_compare }, + .rwlock = AVL_LOCK_INITIALIZER } }; + /***************************************************************** * * PROCESS DATA AND SEND TO NETDATA @@ -520,6 +526,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Open and close calls", EBPF_COMMON_DIMENSION_CALL, NETDATA_FILE_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21000, ebpf_create_global_dimension, process_publish_aggregated, @@ -531,6 +539,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Open fails", EBPF_COMMON_DIMENSION_CALL, NETDATA_FILE_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21001, ebpf_create_global_dimension, process_publish_aggregated, @@ -542,6 +552,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Remove files", EBPF_COMMON_DIMENSION_CALL, NETDATA_VFS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21002, ebpf_create_global_dimension, &process_publish_aggregated[NETDATA_DEL_START], @@ -552,6 +564,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Calls to IO", EBPF_COMMON_DIMENSION_CALL, NETDATA_VFS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21003, ebpf_create_global_dimension, &process_publish_aggregated[NETDATA_IN_START_BYTE], @@ -569,6 +583,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Fails to write or read", EBPF_COMMON_DIMENSION_CALL, NETDATA_VFS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21005, ebpf_create_global_dimension, &process_publish_aggregated[2], @@ -580,6 +596,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Start process", EBPF_COMMON_DIMENSION_CALL, NETDATA_PROCESS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21006, ebpf_create_global_dimension, &process_publish_aggregated[NETDATA_PROCESS_START], @@ -590,6 +608,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Exit process", EBPF_COMMON_DIMENSION_CALL, NETDATA_PROCESS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21007, ebpf_create_global_dimension, &process_publish_aggregated[NETDATA_EXIT_START], @@ -608,6 +628,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Fails to create process", EBPF_COMMON_DIMENSION_CALL, NETDATA_PROCESS_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21009, ebpf_create_global_dimension, &process_publish_aggregated[NETDATA_PROCESS_START], @@ -621,14 +643,16 @@ static void ebpf_create_global_charts(ebpf_module_t *em) * Call ebpf_create_chart to create the charts on apps submenu. * * @param em a pointer to the structure with the default values. - * @param root a pointer for the targets. + * @param ptr a pointer for the targets. */ -static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *root) +void ebpf_process_create_apps_charts(struct ebpf_module *em, void *ptr) { + struct target *root = ptr; ebpf_create_charts_on_apps(NETDATA_SYSCALL_APPS_FILE_OPEN, "Number of open files", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_FILE_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20061, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -638,6 +662,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Fails to open files", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_FILE_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20062, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -647,6 +672,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Files closed", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_FILE_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20063, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -656,6 +682,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Fails to close files", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_FILE_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20064, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -665,6 +692,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Files deleted", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20065, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -673,6 +701,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Write to disk", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20066, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], apps_groups_root_target); @@ -682,6 +711,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Fails to write", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20067, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -691,6 +721,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Read from disk", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20068, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -700,6 +731,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Fails to read", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20069, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -708,6 +740,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro ebpf_create_charts_on_apps(NETDATA_SYSCALL_APPS_VFS_WRITE_BYTES, "Bytes written on disk", EBPF_COMMON_DIMENSION_BYTES, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20070, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -715,6 +748,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro ebpf_create_charts_on_apps(NETDATA_SYSCALL_APPS_VFS_READ_BYTES, "Bytes read from disk", EBPF_COMMON_DIMENSION_BYTES, NETDATA_APPS_VFS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20071, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -723,6 +757,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Process started", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_PROCESS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20072, ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], root); @@ -731,6 +766,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Threads started", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_PROCESS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20073, ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], root); @@ -739,6 +775,7 @@ static void ebpf_process_create_apps_charts(ebpf_module_t *em, struct target *ro "Tasks closed", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_PROCESS_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20074, ebpf_algorithms[NETDATA_EBPF_ABSOLUTE_IDX], root); @@ -786,11 +823,12 @@ static void ebpf_create_apps_charts(ebpf_module_t *em, struct target *root) if (!newly_added) return; - if (ebpf_modules[EBPF_MODULE_PROCESS_IDX].apps_charts) - ebpf_process_create_apps_charts(em, root); - - if (ebpf_modules[EBPF_MODULE_SOCKET_IDX].apps_charts) - ebpf_socket_create_apps_charts(NULL, root); + int counter; + for (counter = 0; ebpf_modules[counter].thread_name; counter++) { + ebpf_module_t *current = &ebpf_modules[counter]; + if (current->enabled && current->apps_charts && current->apps_routine) + current->apps_routine(em, root); + } } /***************************************************************** @@ -904,9 +942,7 @@ static void ebpf_process_cleanup(void *ptr) UNUSED(dt); } - freez(process_aggregated_data); ebpf_cleanup_publish_syscall(process_publish_aggregated); - freez(process_publish_aggregated); freez(process_hash_values); clean_global_memory(); @@ -940,8 +976,8 @@ static void ebpf_process_cleanup(void *ptr) */ static void ebpf_process_allocate_global_vectors(size_t length) { - process_aggregated_data = callocz(length, sizeof(netdata_syscall_stat_t)); - process_publish_aggregated = callocz(length, sizeof(netdata_publish_syscall_t)); + memset(process_aggregated_data, 0, length * sizeof(netdata_syscall_stat_t)); + memset(process_publish_aggregated, 0, length * sizeof(netdata_publish_syscall_t)); process_hash_values = callocz(ebpf_nprocs, sizeof(netdata_idx_t)); global_process_stats = callocz((size_t)pid_max, sizeof(ebpf_process_stat_t *)); @@ -1018,13 +1054,15 @@ void *ebpf_process_thread(void *ptr) fill_ebpf_data(&process_data); pthread_mutex_lock(&lock); - ebpf_process_allocate_global_vectors(NETDATA_MAX_MONITOR_VECTOR); + ebpf_process_allocate_global_vectors(NETDATA_KEY_PUBLISH_PROCESS_END); if (ebpf_update_kernel(&process_data)) { pthread_mutex_unlock(&lock); goto endprocess; } + ebpf_update_module(em, &process_config, NETDATA_PROCESS_CONFIG_FILE); + set_local_pointers(); probe_links = ebpf_load_program(ebpf_plugin_dir, em, kernel_string, &objects, process_data.map_fd); if (!probe_links) { @@ -1040,7 +1078,7 @@ void *ebpf_process_thread(void *ptr) ebpf_global_labels( process_aggregated_data, process_publish_aggregated, process_dimension_names, process_id_names, - algorithms, NETDATA_MAX_MONITOR_VECTOR); + algorithms, NETDATA_KEY_PUBLISH_PROCESS_END); if (process_enabled) { ebpf_create_global_charts(em); diff --git a/collectors/ebpf.plugin/ebpf_process.h b/collectors/ebpf.plugin/ebpf_process.h index aa6ed66d6..a731227e1 100644 --- a/collectors/ebpf.plugin/ebpf_process.h +++ b/collectors/ebpf.plugin/ebpf_process.h @@ -10,7 +10,6 @@ // Internal constants #define NETDATA_GLOBAL_VECTOR 24 -#define NETDATA_MAX_MONITOR_VECTOR 9 #define NETDATA_VFS_ERRORS 3 // Map index @@ -52,6 +51,9 @@ #define NETDATA_SYSCALL_APPS_VFS_WRITE_CALLS_ERROR "vfs_write_error" #define NETDATA_SYSCALL_APPS_VFS_READ_CALLS_ERROR "vfs_read_error" +// Process configuration name +#define NETDATA_PROCESS_CONFIG_FILE "process.conf" + // Index from kernel typedef enum ebpf_process_index { NETDATA_KEY_CALLS_DO_SYS_OPEN, diff --git a/collectors/ebpf.plugin/ebpf_socket.c b/collectors/ebpf.plugin/ebpf_socket.c index 7fbc24421..a142d43b3 100644 --- a/collectors/ebpf.plugin/ebpf_socket.c +++ b/collectors/ebpf.plugin/ebpf_socket.c @@ -17,8 +17,8 @@ static char *socket_id_names[NETDATA_MAX_SOCKET_VECTOR] = { "tcp_sendmsg", "tcp_ "udp_sendmsg", "udp_recvmsg", "tcp_retransmit_skb" }; static netdata_idx_t *socket_hash_values = NULL; -static netdata_syscall_stat_t *socket_aggregated_data = NULL; -static netdata_publish_syscall_t *socket_publish_aggregated = NULL; +static netdata_syscall_stat_t socket_aggregated_data[NETDATA_MAX_SOCKET_VECTOR]; +static netdata_publish_syscall_t socket_publish_aggregated[NETDATA_MAX_SOCKET_VECTOR]; static ebpf_data_t socket_data; @@ -40,6 +40,12 @@ static int *map_fd = NULL; static struct bpf_object *objects = NULL; static struct bpf_link **probe_links = NULL; +struct config socket_config = { .first_section = NULL, + .last_section = NULL, + .mutex = NETDATA_MUTEX_INITIALIZER, + .index = { .avl_tree = { .root = NULL, .compar = appconfig_section_compare }, + .rwlock = AVL_LOCK_INITIALIZER } }; + /***************************************************************** * * PROCESS DATA AND SEND TO NETDATA @@ -279,17 +285,20 @@ static void ebpf_socket_send_data(ebpf_module_t *em) NETDATA_TCP_FUNCTION_ERROR, NETDATA_EBPF_FAMILY, socket_publish_aggregated, 2); } write_count_chart( - NETDATA_TCP_RETRANSMIT, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_RETRANSMIT_START], 1); + NETDATA_TCP_RETRANSMIT, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_IDX_TCP_RETRANSMIT], + 1); write_count_chart( - NETDATA_UDP_FUNCTION_COUNT, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_UDP_START], 2); + NETDATA_UDP_FUNCTION_COUNT, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_IDX_UDP_RECVBUF], + 2); write_io_chart( NETDATA_UDP_FUNCTION_BITS, NETDATA_EBPF_FAMILY, socket_id_names[3],(long long)common_udp.write*8/100, socket_id_names[4], (long long)common_udp.read*8/1000); if (em->mode < MODE_ENTRY) { write_err_chart( - NETDATA_UDP_FUNCTION_ERROR, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_UDP_START], 2); + NETDATA_UDP_FUNCTION_ERROR, NETDATA_EBPF_FAMILY, &socket_publish_aggregated[NETDATA_UDP_START], + 2); } } @@ -427,6 +436,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Calls to internal functions", EBPF_COMMON_DIMENSION_CALL, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21070, ebpf_create_global_dimension, socket_publish_aggregated, @@ -435,6 +446,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) ebpf_create_chart(NETDATA_EBPF_FAMILY, NETDATA_TCP_FUNCTION_BITS, "TCP bandwidth", EBPF_COMMON_DIMENSION_BITS, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21071, ebpf_create_global_dimension, socket_publish_aggregated, @@ -446,6 +459,8 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "TCP errors", EBPF_COMMON_DIMENSION_CALL, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21072, ebpf_create_global_dimension, socket_publish_aggregated, @@ -457,9 +472,11 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "Packages retransmitted", EBPF_COMMON_DIMENSION_CALL, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21073, ebpf_create_global_dimension, - &socket_publish_aggregated[NETDATA_RETRANSMIT_START], + &socket_publish_aggregated[NETDATA_IDX_TCP_RETRANSMIT], 1); ebpf_create_chart(NETDATA_EBPF_FAMILY, @@ -467,17 +484,21 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "UDP calls", EBPF_COMMON_DIMENSION_CALL, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21074, ebpf_create_global_dimension, - &socket_publish_aggregated[NETDATA_UDP_START], + &socket_publish_aggregated[NETDATA_IDX_UDP_RECVBUF], 2); ebpf_create_chart(NETDATA_EBPF_FAMILY, NETDATA_UDP_FUNCTION_BITS, "UDP bandwidth", EBPF_COMMON_DIMENSION_BITS, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21075, ebpf_create_global_dimension, - &socket_publish_aggregated[NETDATA_UDP_START], + &socket_publish_aggregated[NETDATA_IDX_UDP_RECVBUF], 2); if (em->mode < MODE_ENTRY) { @@ -486,9 +507,11 @@ static void ebpf_create_global_charts(ebpf_module_t *em) "UDP errors", EBPF_COMMON_DIMENSION_CALL, NETDATA_SOCKET_GROUP, + NULL, + NETDATA_EBPF_CHART_TYPE_LINE, 21076, ebpf_create_global_dimension, - &socket_publish_aggregated[NETDATA_UDP_START], + &socket_publish_aggregated[NETDATA_IDX_UDP_RECVBUF], 2); } } @@ -498,14 +521,17 @@ static void ebpf_create_global_charts(ebpf_module_t *em) * * Call ebpf_create_chart to create the charts on apps submenu. * - * @param em a pointer to the structure with the default values. + * @param em a pointer to the structure with the default values. + * @param ptr a pointer for targets */ -void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) +void ebpf_socket_create_apps_charts(struct ebpf_module *em, void *ptr) { UNUSED(em); + struct target *root = ptr;; ebpf_create_charts_on_apps(NETDATA_NET_APPS_BANDWIDTH_SENT, "Bytes sent", EBPF_COMMON_DIMENSION_BITS, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20080, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -513,6 +539,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) ebpf_create_charts_on_apps(NETDATA_NET_APPS_BANDWIDTH_RECV, "bytes received", EBPF_COMMON_DIMENSION_BITS, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20081, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -521,6 +548,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) "Calls for tcp_sendmsg", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20082, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -529,6 +557,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) "Calls for tcp_cleanup_rbuf", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20083, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -537,6 +566,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) "Calls for tcp_retransmit", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20084, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -545,6 +575,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) "Calls for udp_sendmsg", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20085, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -553,6 +584,7 @@ void ebpf_socket_create_apps_charts(ebpf_module_t *em, struct target *root) "Calls for udp_recvmsg", EBPF_COMMON_DIMENSION_CALL, NETDATA_APPS_NET_GROUP, + NETDATA_EBPF_CHART_TYPE_STACKED, 20086, ebpf_algorithms[NETDATA_EBPF_INCREMENTAL_IDX], root); @@ -580,7 +612,8 @@ static void ebpf_socket_create_nv_chart(char *id, char *title, char *units, title, units, family, - "stacked", + NETDATA_EBPF_CHART_TYPE_STACKED, + NULL, order); uint32_t i; @@ -616,7 +649,8 @@ static void ebpf_socket_create_nv_retransmit(char *id, char *title, char *units, title, units, family, - "stacked", + NETDATA_EBPF_CHART_TYPE_STACKED, + NULL, order); uint32_t i; @@ -1137,7 +1171,7 @@ static void store_socket_inside_avl(netdata_vector_plot_t *out, netdata_socket_t memcpy(&test.index, lindex, sizeof(netdata_socket_idx_t)); test.flags = flags; - ret = (netdata_socket_plot_t *) avl_search_lock(&out->tree, (avl *)&test); + ret = (netdata_socket_plot_t *) avl_search_lock(&out->tree, (avl_t *)&test); if (ret) { if (lvalues->ct > ret->plot.last_time) { update_socket_data(&ret->sock, lvalues); @@ -1175,7 +1209,7 @@ static void store_socket_inside_avl(netdata_vector_plot_t *out, netdata_socket_t w->flags = flags; netdata_socket_plot_t *check ; - check = (netdata_socket_plot_t *) avl_insert_lock(&out->tree, (avl *)w); + check = (netdata_socket_plot_t *) avl_insert_lock(&out->tree, (avl_t *)w); if (check != w) error("Internal error, cannot insert the AVL tree."); @@ -1427,7 +1461,7 @@ void *ebpf_socket_read_hash(void *ptr) read_thread_closed = 0; heartbeat_t hb; heartbeat_init(&hb); - usec_t step = NETDATA_SOCKET_READ_SLEEP_MS; + usec_t step = NETDATA_SOCKET_READ_SLEEP_MS * em->update_time; int fd_ipv4 = map_fd[NETDATA_SOCKET_IPV4_HASH_TABLE]; int fd_ipv6 = map_fd[NETDATA_SOCKET_IPV6_HASH_TABLE]; int network_connection = em->optional; @@ -1471,22 +1505,22 @@ static void read_hash_global_tables() } } - socket_aggregated_data[0].call = res[NETDATA_KEY_CALLS_TCP_SENDMSG]; - socket_aggregated_data[1].call = res[NETDATA_KEY_CALLS_TCP_CLEANUP_RBUF]; - socket_aggregated_data[2].call = res[NETDATA_KEY_CALLS_TCP_CLOSE]; - socket_aggregated_data[3].call = res[NETDATA_KEY_CALLS_UDP_RECVMSG]; - socket_aggregated_data[4].call = res[NETDATA_KEY_CALLS_UDP_SENDMSG]; - socket_aggregated_data[5].call = res[NETDATA_KEY_TCP_RETRANSMIT]; - - socket_aggregated_data[0].ecall = res[NETDATA_KEY_ERROR_TCP_SENDMSG]; - socket_aggregated_data[1].ecall = res[NETDATA_KEY_ERROR_TCP_CLEANUP_RBUF]; - socket_aggregated_data[3].ecall = res[NETDATA_KEY_ERROR_UDP_RECVMSG]; - socket_aggregated_data[4].ecall = res[NETDATA_KEY_ERROR_UDP_SENDMSG]; - - socket_aggregated_data[0].bytes = res[NETDATA_KEY_BYTES_TCP_SENDMSG]; - socket_aggregated_data[1].bytes = res[NETDATA_KEY_BYTES_TCP_CLEANUP_RBUF]; - socket_aggregated_data[3].bytes = res[NETDATA_KEY_BYTES_UDP_RECVMSG]; - socket_aggregated_data[4].bytes = res[NETDATA_KEY_BYTES_UDP_SENDMSG]; + socket_aggregated_data[NETDATA_IDX_TCP_SENDMSG].call = res[NETDATA_KEY_CALLS_TCP_SENDMSG]; + socket_aggregated_data[NETDATA_IDX_TCP_CLEANUP_RBUF].call = res[NETDATA_KEY_CALLS_TCP_CLEANUP_RBUF]; + socket_aggregated_data[NETDATA_IDX_TCP_CLOSE].call = res[NETDATA_KEY_CALLS_TCP_CLOSE]; + socket_aggregated_data[NETDATA_IDX_UDP_RECVBUF].call = res[NETDATA_KEY_CALLS_UDP_RECVMSG]; + socket_aggregated_data[NETDATA_IDX_UDP_SENDMSG].call = res[NETDATA_KEY_CALLS_UDP_SENDMSG]; + socket_aggregated_data[NETDATA_IDX_TCP_RETRANSMIT].call = res[NETDATA_KEY_TCP_RETRANSMIT]; + + socket_aggregated_data[NETDATA_IDX_TCP_SENDMSG].ecall = res[NETDATA_KEY_ERROR_TCP_SENDMSG]; + socket_aggregated_data[NETDATA_IDX_TCP_CLEANUP_RBUF].ecall = res[NETDATA_KEY_ERROR_TCP_CLEANUP_RBUF]; + socket_aggregated_data[NETDATA_IDX_UDP_RECVBUF].ecall = res[NETDATA_KEY_ERROR_UDP_RECVMSG]; + socket_aggregated_data[NETDATA_IDX_UDP_SENDMSG].ecall = res[NETDATA_KEY_ERROR_UDP_SENDMSG]; + + socket_aggregated_data[NETDATA_IDX_TCP_SENDMSG].bytes = res[NETDATA_KEY_BYTES_TCP_SENDMSG]; + socket_aggregated_data[NETDATA_IDX_TCP_CLEANUP_RBUF].bytes = res[NETDATA_KEY_BYTES_TCP_CLEANUP_RBUF]; + socket_aggregated_data[NETDATA_IDX_UDP_RECVBUF].bytes = res[NETDATA_KEY_BYTES_UDP_RECVMSG]; + socket_aggregated_data[NETDATA_IDX_UDP_SENDMSG].bytes = res[NETDATA_KEY_BYTES_UDP_SENDMSG]; } /** @@ -1744,6 +1778,59 @@ void clean_thread_structures() { } } +/** + * Cleanup publish syscall + * + * @param nps list of structures to clean + */ +void ebpf_cleanup_publish_syscall(netdata_publish_syscall_t *nps) +{ + while (nps) { + freez(nps->algorithm); + nps = nps->next; + } +} + +/** + * Clean port Structure + * + * Clean the allocated list. + * + * @param clean the list that will be cleaned + */ +void clean_port_structure(ebpf_network_viewer_port_list_t **clean) +{ + ebpf_network_viewer_port_list_t *move = *clean; + while (move) { + ebpf_network_viewer_port_list_t *next = move->next; + freez(move->value); + freez(move); + + move = next; + } + *clean = NULL; +} + +/** + * Clean IP structure + * + * Clean the allocated list. + * + * @param clean the list that will be cleaned + */ +static void clean_ip_structure(ebpf_network_viewer_ip_list_t **clean) +{ + ebpf_network_viewer_ip_list_t *move = *clean; + while (move) { + ebpf_network_viewer_ip_list_t *next = move->next; + freez(move->value); + freez(move); + + move = next; + } + *clean = NULL; +} + /** * Clean up the main thread. * @@ -1763,9 +1850,7 @@ static void ebpf_socket_cleanup(void *ptr) UNUSED(dt); } - freez(socket_aggregated_data); ebpf_cleanup_publish_syscall(socket_publish_aggregated); - freez(socket_publish_aggregated); freez(socket_hash_values); clean_thread_structures(); @@ -1817,8 +1902,8 @@ static void ebpf_socket_cleanup(void *ptr) */ static void ebpf_socket_allocate_global_vectors(size_t length) { - socket_aggregated_data = callocz(length, sizeof(netdata_syscall_stat_t)); - socket_publish_aggregated = callocz(length, sizeof(netdata_publish_syscall_t)); + memset(socket_aggregated_data, 0 ,length * sizeof(netdata_syscall_stat_t)); + memset(socket_publish_aggregated, 0 ,length * sizeof(netdata_publish_syscall_t)); socket_hash_values = callocz(ebpf_nprocs, sizeof(netdata_idx_t)); socket_bandwidth_curr = callocz((size_t)pid_max, sizeof(ebpf_socket_publish_apps_t *)); @@ -1856,6 +1941,874 @@ static void initialize_inbound_outbound() * *****************************************************************/ +/** + * Fill Port list + * + * @param out a pointer to the link list. + * @param in the structure that will be linked. + */ +static inline void fill_port_list(ebpf_network_viewer_port_list_t **out, ebpf_network_viewer_port_list_t *in) +{ + if (likely(*out)) { + ebpf_network_viewer_port_list_t *move = *out, *store = *out; + uint16_t first = ntohs(in->first); + uint16_t last = ntohs(in->last); + while (move) { + uint16_t cmp_first = ntohs(move->first); + uint16_t cmp_last = ntohs(move->last); + if (cmp_first <= first && first <= cmp_last && + cmp_first <= last && last <= cmp_last ) { + info("The range/value (%u, %u) is inside the range/value (%u, %u) already inserted, it will be ignored.", + first, last, cmp_first, cmp_last); + freez(in->value); + freez(in); + return; + } else if (first <= cmp_first && cmp_first <= last && + first <= cmp_last && cmp_last <= last) { + info("The range (%u, %u) is bigger than previous range (%u, %u) already inserted, the previous will be ignored.", + first, last, cmp_first, cmp_last); + freez(move->value); + move->value = in->value; + move->first = in->first; + move->last = in->last; + freez(in); + return; + } + + store = move; + move = move->next; + } + + store->next = in; + } else { + *out = in; + } + +#ifdef NETDATA_INTERNAL_CHECKS + info("Adding values %s( %u, %u) to %s port list used on network viewer", + in->value, ntohs(in->first), ntohs(in->last), + (*out == network_viewer_opt.included_port)?"included":"excluded"); +#endif +} + +/** + * Parse Service List + * + * @param out a pointer to store the link list + * @param service the service used to create the structure that will be linked. + */ +static void parse_service_list(void **out, char *service) +{ + ebpf_network_viewer_port_list_t **list = (ebpf_network_viewer_port_list_t **)out; + struct servent *serv = getservbyname((const char *)service, "tcp"); + if (!serv) + serv = getservbyname((const char *)service, "udp"); + + if (!serv) { + info("Cannot resolv the service '%s' with protocols TCP and UDP, it will be ignored", service); + return; + } + + ebpf_network_viewer_port_list_t *w = callocz(1, sizeof(ebpf_network_viewer_port_list_t)); + w->value = strdupz(service); + w->hash = simple_hash(service); + + w->first = w->last = (uint16_t)serv->s_port; + + fill_port_list(list, w); +} + +/** + * Netmask + * + * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) + * + * @param prefix create the netmask based in the CIDR value. + * + * @return + */ +static inline in_addr_t netmask(int prefix) { + + if (prefix == 0) + return (~((in_addr_t) - 1)); + else + return (in_addr_t)(~((1 << (32 - prefix)) - 1)); + +} + +/** + * Broadcast + * + * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) + * + * @param addr is the ip address + * @param prefix is the CIDR value. + * + * @return It returns the last address of the range + */ +static inline in_addr_t broadcast(in_addr_t addr, int prefix) +{ + return (addr | ~netmask(prefix)); +} + +/** + * Network + * + * Copied from iprange (https://github.com/firehol/iprange/blob/master/iprange.h) + * + * @param addr is the ip address + * @param prefix is the CIDR value. + * + * @return It returns the first address of the range. + */ +static inline in_addr_t ipv4_network(in_addr_t addr, int prefix) +{ + return (addr & netmask(prefix)); +} + +/** + * IP to network long + * + * @param dst the vector to store the result + * @param ip the source ip given by our users. + * @param domain the ip domain (IPV4 or IPV6) + * @param source the original string + * + * @return it returns 0 on success and -1 otherwise. + */ +static inline int ip2nl(uint8_t *dst, char *ip, int domain, char *source) +{ + if (inet_pton(domain, ip, dst) <= 0) { + error("The address specified (%s) is invalid ", source); + return -1; + } + + return 0; +} + +/** + * Get IPV6 Last Address + * + * @param out the address to store the last address. + * @param in the address used to do the math. + * @param prefix number of bits used to calculate the address + */ +static void get_ipv6_last_addr(union netdata_ip_t *out, union netdata_ip_t *in, uint64_t prefix) +{ + uint64_t mask,tmp; + uint64_t ret[2]; + memcpy(ret, in->addr32, sizeof(union netdata_ip_t)); + + if (prefix == 128) { + memcpy(out->addr32, in->addr32, sizeof(union netdata_ip_t)); + return; + } else if (!prefix) { + ret[0] = ret[1] = 0xFFFFFFFFFFFFFFFF; + memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); + return; + } else if (prefix <= 64) { + ret[1] = 0xFFFFFFFFFFFFFFFFULL; + + tmp = be64toh(ret[0]); + if (prefix > 0) { + mask = 0xFFFFFFFFFFFFFFFFULL << (64 - prefix); + tmp |= ~mask; + } + ret[0] = htobe64(tmp); + } else { + mask = 0xFFFFFFFFFFFFFFFFULL << (128 - prefix); + tmp = be64toh(ret[1]); + tmp |= ~mask; + ret[1] = htobe64(tmp); + } + + memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); +} + +/** + * Calculate ipv6 first address + * + * @param out the address to store the first address. + * @param in the address used to do the math. + * @param prefix number of bits used to calculate the address + */ +static void get_ipv6_first_addr(union netdata_ip_t *out, union netdata_ip_t *in, uint64_t prefix) +{ + uint64_t mask,tmp; + uint64_t ret[2]; + + memcpy(ret, in->addr32, sizeof(union netdata_ip_t)); + + if (prefix == 128) { + memcpy(out->addr32, in->addr32, sizeof(union netdata_ip_t)); + return; + } else if (!prefix) { + ret[0] = ret[1] = 0; + memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); + return; + } else if (prefix <= 64) { + ret[1] = 0ULL; + + tmp = be64toh(ret[0]); + if (prefix > 0) { + mask = 0xFFFFFFFFFFFFFFFFULL << (64 - prefix); + tmp &= mask; + } + ret[0] = htobe64(tmp); + } else { + mask = 0xFFFFFFFFFFFFFFFFULL << (128 - prefix); + tmp = be64toh(ret[1]); + tmp &= mask; + ret[1] = htobe64(tmp); + } + + memcpy(out->addr32, ret, sizeof(union netdata_ip_t)); +} + +/** + * Is ip inside the range + * + * Check if the ip is inside a IP range + * + * @param rfirst the first ip address of the range + * @param rlast the last ip address of the range + * @param cmpfirst the first ip to compare + * @param cmplast the last ip to compare + * @param family the IP family + * + * @return It returns 1 if the IP is inside the range and 0 otherwise + */ +static int is_ip_inside_range(union netdata_ip_t *rfirst, union netdata_ip_t *rlast, + union netdata_ip_t *cmpfirst, union netdata_ip_t *cmplast, int family) +{ + if (family == AF_INET) { + if (ntohl(rfirst->addr32[0]) <= ntohl(cmpfirst->addr32[0]) && + ntohl(rlast->addr32[0]) >= ntohl(cmplast->addr32[0])) + return 1; + } else { + if (memcmp(rfirst->addr8, cmpfirst->addr8, sizeof(union netdata_ip_t)) <= 0 && + memcmp(rlast->addr8, cmplast->addr8, sizeof(union netdata_ip_t)) >= 0) { + return 1; + } + + } + return 0; +} + +/** + * Fill IP list + * + * @param out a pointer to the link list. + * @param in the structure that will be linked. + */ +void fill_ip_list(ebpf_network_viewer_ip_list_t **out, ebpf_network_viewer_ip_list_t *in, char *table) +{ +#ifndef NETDATA_INTERNAL_CHECKS + UNUSED(table); +#endif + if (likely(*out)) { + ebpf_network_viewer_ip_list_t *move = *out, *store = *out; + while (move) { + if (in->ver == move->ver && is_ip_inside_range(&move->first, &move->last, &in->first, &in->last, in->ver)) { + info("The range/value (%s) is inside the range/value (%s) already inserted, it will be ignored.", + in->value, move->value); + freez(in->value); + freez(in); + return; + } + store = move; + move = move->next; + } + + store->next = in; + } else { + *out = in; + } + +#ifdef NETDATA_INTERNAL_CHECKS + char first[512], last[512]; + if (in->ver == AF_INET) { + if (inet_ntop(AF_INET, in->first.addr8, first, INET_ADDRSTRLEN) && + inet_ntop(AF_INET, in->last.addr8, last, INET_ADDRSTRLEN)) + info("Adding values %s - %s to %s IP list \"%s\" used on network viewer", + first, last, + (*out == network_viewer_opt.included_ips)?"included":"excluded", + table); + } else { + if (inet_ntop(AF_INET6, in->first.addr8, first, INET6_ADDRSTRLEN) && + inet_ntop(AF_INET6, in->last.addr8, last, INET6_ADDRSTRLEN)) + info("Adding values %s - %s to %s IP list \"%s\" used on network viewer", + first, last, + (*out == network_viewer_opt.included_ips)?"included":"excluded", + table); + } +#endif +} + +/** + * Parse IP List + * + * Parse IP list and link it. + * + * @param out a pointer to store the link list + * @param ip the value given as parameter + */ +static void parse_ip_list(void **out, char *ip) +{ + ebpf_network_viewer_ip_list_t **list = (ebpf_network_viewer_ip_list_t **)out; + + char *ipdup = strdupz(ip); + union netdata_ip_t first = { }; + union netdata_ip_t last = { }; + char *is_ipv6; + if (*ip == '*' && *(ip+1) == '\0') { + memset(first.addr8, 0, sizeof(first.addr8)); + memset(last.addr8, 0xFF, sizeof(last.addr8)); + + is_ipv6 = ip; + + clean_ip_structure(list); + goto storethisip; + } + + char *end = ip; + // Move while I cannot find a separator + while (*end && *end != '/' && *end != '-') end++; + + // We will use only the classic IPV6 for while, but we could consider the base 85 in a near future + // https://tools.ietf.org/html/rfc1924 + is_ipv6 = strchr(ip, ':'); + + int select; + if (*end && !is_ipv6) { // IPV4 range + select = (*end == '/') ? 0 : 1; + *end++ = '\0'; + if (*end == '!') { + info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); + goto cleanipdup; + } + + if (!select) { // CIDR + select = ip2nl(first.addr8, ip, AF_INET, ipdup); + if (select) + goto cleanipdup; + + select = (int) str2i(end); + if (select < NETDATA_MINIMUM_IPV4_CIDR || select > NETDATA_MAXIMUM_IPV4_CIDR) { + info("The specified CIDR %s is not valid, the IP %s will be ignored.", end, ip); + goto cleanipdup; + } + + last.addr32[0] = htonl(broadcast(ntohl(first.addr32[0]), select)); + // This was added to remove + // https://app.codacy.com/manual/netdata/netdata/pullRequest?prid=5810941&bid=19021977 + UNUSED(last.addr32[0]); + + uint32_t ipv4_test = htonl(ipv4_network(ntohl(first.addr32[0]), select)); + if (first.addr32[0] != ipv4_test) { + first.addr32[0] = ipv4_test; + struct in_addr ipv4_convert; + ipv4_convert.s_addr = ipv4_test; + char ipv4_msg[INET_ADDRSTRLEN]; + if(inet_ntop(AF_INET, &ipv4_convert, ipv4_msg, INET_ADDRSTRLEN)) + info("The network value of CIDR %s was updated for %s .", ipdup, ipv4_msg); + } + } else { // Range + select = ip2nl(first.addr8, ip, AF_INET, ipdup); + if (select) + goto cleanipdup; + + select = ip2nl(last.addr8, end, AF_INET, ipdup); + if (select) + goto cleanipdup; + } + + if (htonl(first.addr32[0]) > htonl(last.addr32[0])) { + info("The specified range %s is invalid, the second address is smallest than the first, it will be ignored.", + ipdup); + goto cleanipdup; + } + } else if (is_ipv6) { // IPV6 + if (!*end) { // Unique + select = ip2nl(first.addr8, ip, AF_INET6, ipdup); + if (select) + goto cleanipdup; + + memcpy(last.addr8, first.addr8, sizeof(first.addr8)); + } else if (*end == '-') { + *end++ = 0x00; + if (*end == '!') { + info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); + goto cleanipdup; + } + + select = ip2nl(first.addr8, ip, AF_INET6, ipdup); + if (select) + goto cleanipdup; + + select = ip2nl(last.addr8, end, AF_INET6, ipdup); + if (select) + goto cleanipdup; + } else { // CIDR + *end++ = 0x00; + if (*end == '!') { + info("The exclusion cannot be in the second part of the range %s, it will be ignored.", ipdup); + goto cleanipdup; + } + + select = str2i(end); + if (select < 0 || select > 128) { + info("The CIDR %s is not valid, the address %s will be ignored.", end, ip); + goto cleanipdup; + } + + uint64_t prefix = (uint64_t)select; + select = ip2nl(first.addr8, ip, AF_INET6, ipdup); + if (select) + goto cleanipdup; + + get_ipv6_last_addr(&last, &first, prefix); + + union netdata_ip_t ipv6_test; + get_ipv6_first_addr(&ipv6_test, &first, prefix); + + if (memcmp(first.addr8, ipv6_test.addr8, sizeof(union netdata_ip_t)) != 0) { + memcpy(first.addr8, ipv6_test.addr8, sizeof(union netdata_ip_t)); + + struct in6_addr ipv6_convert; + memcpy(ipv6_convert.s6_addr, ipv6_test.addr8, sizeof(union netdata_ip_t)); + + char ipv6_msg[INET6_ADDRSTRLEN]; + if(inet_ntop(AF_INET6, &ipv6_convert, ipv6_msg, INET6_ADDRSTRLEN)) + info("The network value of CIDR %s was updated for %s .", ipdup, ipv6_msg); + } + } + + if ((be64toh(*(uint64_t *)&first.addr32[2]) > be64toh(*(uint64_t *)&last.addr32[2]) && + !memcmp(first.addr32, last.addr32, 2*sizeof(uint32_t))) || + (be64toh(*(uint64_t *)&first.addr32) > be64toh(*(uint64_t *)&last.addr32)) ) { + info("The specified range %s is invalid, the second address is smallest than the first, it will be ignored.", + ipdup); + goto cleanipdup; + } + } else { // Unique ip + select = ip2nl(first.addr8, ip, AF_INET, ipdup); + if (select) + goto cleanipdup; + + memcpy(last.addr8, first.addr8, sizeof(first.addr8)); + } + + ebpf_network_viewer_ip_list_t *store; + + storethisip: + store = callocz(1, sizeof(ebpf_network_viewer_ip_list_t)); + store->value = ipdup; + store->hash = simple_hash(ipdup); + store->ver = (uint8_t)(!is_ipv6)?AF_INET:AF_INET6; + memcpy(store->first.addr8, first.addr8, sizeof(first.addr8)); + memcpy(store->last.addr8, last.addr8, sizeof(last.addr8)); + + fill_ip_list(list, store, "socket"); + return; + +cleanipdup: + freez(ipdup); +} + +/** + * Parse IP Range + * + * Parse the IP ranges given and create Network Viewer IP Structure + * + * @param ptr is a pointer with the text to parse. + */ +static void parse_ips(char *ptr) +{ + // No value + if (unlikely(!ptr)) + return; + + while (likely(ptr)) { + // Move forward until next valid character + while (isspace(*ptr)) ptr++; + + // No valid value found + if (unlikely(!*ptr)) + return; + + // Find space that ends the list + char *end = strchr(ptr, ' '); + if (end) { + *end++ = '\0'; + } + + int neg = 0; + if (*ptr == '!') { + neg++; + ptr++; + } + + if (isascii(*ptr)) { // Parse port + parse_ip_list((!neg)?(void **)&network_viewer_opt.included_ips:(void **)&network_viewer_opt.excluded_ips, + ptr); + } + + ptr = end; + } +} + + + +/** + * Parse port list + * + * Parse an allocated port list with the range given + * + * @param out a pointer to store the link list + * @param range the informed range for the user. + */ +static void parse_port_list(void **out, char *range) +{ + int first, last; + ebpf_network_viewer_port_list_t **list = (ebpf_network_viewer_port_list_t **)out; + + char *copied = strdupz(range); + if (*range == '*' && *(range+1) == '\0') { + first = 1; + last = 65535; + + clean_port_structure(list); + goto fillenvpl; + } + + char *end = range; + //Move while I cannot find a separator + while (*end && *end != ':' && *end != '-') end++; + + //It has a range + if (likely(*end)) { + *end++ = '\0'; + if (*end == '!') { + info("The exclusion cannot be in the second part of the range, the range %s will be ignored.", copied); + freez(copied); + return; + } + last = str2i((const char *)end); + } else { + last = 0; + } + + first = str2i((const char *)range); + if (first < NETDATA_MINIMUM_PORT_VALUE || first > NETDATA_MAXIMUM_PORT_VALUE) { + info("The first port %d of the range \"%s\" is invalid and it will be ignored!", first, copied); + freez(copied); + return; + } + + if (!last) + last = first; + + if (last < NETDATA_MINIMUM_PORT_VALUE || last > NETDATA_MAXIMUM_PORT_VALUE) { + info("The second port %d of the range \"%s\" is invalid and the whole range will be ignored!", last, copied); + freez(copied); + return; + } + + if (first > last) { + info("The specified order %s is wrong, the smallest value is always the first, it will be ignored!", copied); + freez(copied); + return; + } + + ebpf_network_viewer_port_list_t *w; +fillenvpl: + w = callocz(1, sizeof(ebpf_network_viewer_port_list_t)); + w->value = copied; + w->hash = simple_hash(copied); + w->first = (uint16_t)htons((uint16_t)first); + w->last = (uint16_t)htons((uint16_t)last); + w->cmp_first = (uint16_t)first; + w->cmp_last = (uint16_t)last; + + fill_port_list(list, w); +} + +/** + * Read max dimension. + * + * Netdata plot two dimensions per connection, so it is necessary to adjust the values. + * + * @param cfg the configuration structure + */ +static void read_max_dimension(struct config *cfg) +{ + int maxdim ; + maxdim = (int) appconfig_get_number(cfg, + EBPF_NETWORK_VIEWER_SECTION, + EBPF_MAXIMUM_DIMENSIONS, + NETDATA_NV_CAP_VALUE); + if (maxdim < 0) { + error("'maximum dimensions = %d' must be a positive number, Netdata will change for default value %ld.", + maxdim, NETDATA_NV_CAP_VALUE); + maxdim = NETDATA_NV_CAP_VALUE; + } + + maxdim /= 2; + if (!maxdim) { + info("The number of dimensions is too small (%u), we are setting it to minimum 2", network_viewer_opt.max_dim); + network_viewer_opt.max_dim = 1; + return; + } + + network_viewer_opt.max_dim = (uint32_t)maxdim; +} + +/** + * Parse Port Range + * + * Parse the port ranges given and create Network Viewer Port Structure + * + * @param ptr is a pointer with the text to parse. + */ +static void parse_ports(char *ptr) +{ + // No value + if (unlikely(!ptr)) + return; + + while (likely(ptr)) { + // Move forward until next valid character + while (isspace(*ptr)) ptr++; + + // No valid value found + if (unlikely(!*ptr)) + return; + + // Find space that ends the list + char *end = strchr(ptr, ' '); + if (end) { + *end++ = '\0'; + } + + int neg = 0; + if (*ptr == '!') { + neg++; + ptr++; + } + + if (isdigit(*ptr)) { // Parse port + parse_port_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, + ptr); + } else if (isalpha(*ptr)) { // Parse service + parse_service_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, + ptr); + } else if (*ptr == '*') { // All + parse_port_list((!neg)?(void **)&network_viewer_opt.included_port:(void **)&network_viewer_opt.excluded_port, + ptr); + } + + ptr = end; + } +} + +/** + * Link hostname + * + * @param out is the output link list + * @param in the hostname to add to list. + */ +static void link_hostname(ebpf_network_viewer_hostname_list_t **out, ebpf_network_viewer_hostname_list_t *in) +{ + if (likely(*out)) { + ebpf_network_viewer_hostname_list_t *move = *out; + for (; move->next ; move = move->next ) { + if (move->hash == in->hash && !strcmp(move->value, in->value)) { + info("The hostname %s was already inserted, it will be ignored.", in->value); + freez(in->value); + simple_pattern_free(in->value_pattern); + freez(in); + return; + } + } + + move->next = in; + } else { + *out = in; + } +#ifdef NETDATA_INTERNAL_CHECKS + info("Adding value %s to %s hostname list used on network viewer", + in->value, + (*out == network_viewer_opt.included_hostnames)?"included":"excluded"); +#endif +} + +/** + * Link Hostnames + * + * Parse the list of hostnames to create the link list. + * This is not associated with the IP, because simple patterns like *example* cannot be resolved to IP. + * + * @param out is the output link list + * @param parse is a pointer with the text to parser. + */ +static void link_hostnames(char *parse) +{ + // No value + if (unlikely(!parse)) + return; + + while (likely(parse)) { + // Find the first valid value + while (isspace(*parse)) parse++; + + // No valid value found + if (unlikely(!*parse)) + return; + + // Find space that ends the list + char *end = strchr(parse, ' '); + if (end) { + *end++ = '\0'; + } + + int neg = 0; + if (*parse == '!') { + neg++; + parse++; + } + + ebpf_network_viewer_hostname_list_t *hostname = callocz(1 , sizeof(ebpf_network_viewer_hostname_list_t)); + hostname->value = strdupz(parse); + hostname->hash = simple_hash(parse); + hostname->value_pattern = simple_pattern_create(parse, NULL, SIMPLE_PATTERN_EXACT); + + link_hostname((!neg)?&network_viewer_opt.included_hostnames:&network_viewer_opt.excluded_hostnames, + hostname); + + parse = end; + } +} + +/** + * Parse network viewer section + * + * @param cfg the configuration structure + */ +void parse_network_viewer_section(struct config *cfg) +{ + read_max_dimension(cfg); + + network_viewer_opt.hostname_resolution_enabled = appconfig_get_boolean(cfg, + EBPF_NETWORK_VIEWER_SECTION, + EBPF_CONFIG_RESOLVE_HOSTNAME, + CONFIG_BOOLEAN_NO); + + network_viewer_opt.service_resolution_enabled = appconfig_get_boolean(cfg, + EBPF_NETWORK_VIEWER_SECTION, + EBPF_CONFIG_RESOLVE_SERVICE, + CONFIG_BOOLEAN_NO); + + char *value = appconfig_get(cfg, EBPF_NETWORK_VIEWER_SECTION, EBPF_CONFIG_PORTS, NULL); + parse_ports(value); + + if (network_viewer_opt.hostname_resolution_enabled) { + value = appconfig_get(cfg, EBPF_NETWORK_VIEWER_SECTION, EBPF_CONFIG_HOSTNAMES, NULL); + link_hostnames(value); + } else { + info("Name resolution is disabled, collector will not parser \"hostnames\" list."); + } + + value = appconfig_get(cfg, EBPF_NETWORK_VIEWER_SECTION, + "ips", "!127.0.0.1/8 10.0.0.0/8 172.16.0.0/12 192.168.0.0/16 fc00::/7 !::1/128"); + parse_ips(value); +} + +/** + * Link dimension name + * + * Link user specified names inside a link list. + * + * @param port the port number associated to the dimension name. + * @param hash the calculated hash for the dimension name. + * @param name the dimension name. + */ +static void link_dimension_name(char *port, uint32_t hash, char *value) +{ + int test = str2i(port); + if (test < NETDATA_MINIMUM_PORT_VALUE || test > NETDATA_MAXIMUM_PORT_VALUE){ + error("The dimension given (%s = %s) has an invalid value and it will be ignored.", port, value); + return; + } + + ebpf_network_viewer_dim_name_t *w; + w = callocz(1, sizeof(ebpf_network_viewer_dim_name_t)); + + w->name = strdupz(value); + w->hash = hash; + + w->port = (uint16_t) htons(test); + + ebpf_network_viewer_dim_name_t *names = network_viewer_opt.names; + if (unlikely(!names)) { + network_viewer_opt.names = w; + } else { + for (; names->next; names = names->next) { + if (names->port == w->port) { + info("Dupplicated definition for a service, the name %s will be ignored. ", names->name); + freez(names->name); + names->name = w->name; + names->hash = w->hash; + freez(w); + return; + } + } + names->next = w; + } + +#ifdef NETDATA_INTERNAL_CHECKS + info("Adding values %s( %u) to dimension name list used on network viewer", w->name, htons(w->port)); +#endif +} + +/** + * Parse service Name section. + * + * This function gets the values that will be used to overwrite dimensions. + * + * @param cfg the configuration structure + */ +void parse_service_name_section(struct config *cfg) +{ + struct section *co = appconfig_get_section(cfg, EBPF_SERVICE_NAME_SECTION); + if (co) { + struct config_option *cv; + for (cv = co->values; cv ; cv = cv->next) { + link_dimension_name(cv->name, cv->hash, cv->value); + } + } + + // Always associated the default port to Netdata + ebpf_network_viewer_dim_name_t *names = network_viewer_opt.names; + if (names) { + uint16_t default_port = htons(19999); + while (names) { + if (names->port == default_port) + return; + + names = names->next; + } + } + + char *port_string = getenv("NETDATA_LISTEN_PORT"); + if (port_string) { + // if variable has an invalid value, we assume netdata is using 19999 + int default_port = str2i(port_string); + if (default_port > 0 && default_port < 65536) + link_dimension_name(port_string, simple_hash(port_string), "Netdata"); + } +} + /** * Socket thread * @@ -1875,6 +2828,10 @@ void *ebpf_socket_thread(void *ptr) ebpf_module_t *em = (ebpf_module_t *)ptr; fill_ebpf_data(&socket_data); + ebpf_update_module(em, &socket_config, NETDATA_NETWORK_CONFIG_FILE); + parse_network_viewer_section(&socket_config); + parse_service_name_section(&socket_config); + if (!em->enabled) goto endsocket; diff --git a/collectors/ebpf.plugin/ebpf_socket.h b/collectors/ebpf.plugin/ebpf_socket.h index 1316c003a..81001bab6 100644 --- a/collectors/ebpf.plugin/ebpf_socket.h +++ b/collectors/ebpf.plugin/ebpf_socket.h @@ -5,7 +5,6 @@ #include "libnetdata/avl/avl.h" // Vector indexes -#define NETDATA_MAX_SOCKET_VECTOR 6 #define NETDATA_UDP_START 3 #define NETDATA_RETRANSMIT_START 5 @@ -17,6 +16,28 @@ #define NETDATA_SOCKET_READ_SLEEP_MS 800000ULL +// config file +#define NETDATA_NETWORK_CONFIG_FILE "network.conf" +#define EBPF_NETWORK_VIEWER_SECTION "network connections" +#define EBPF_SERVICE_NAME_SECTION "service name" +#define EBPF_CONFIG_RESOLVE_HOSTNAME "resolve hostnames" +#define EBPF_CONFIG_RESOLVE_SERVICE "resolve service names" +#define EBPF_CONFIG_PORTS "ports" +#define EBPF_CONFIG_HOSTNAMES "hostnames" +#define EBPF_MAXIMUM_DIMENSIONS "maximum dimensions" + +enum ebpf_socket_publish_index { + NETDATA_IDX_TCP_SENDMSG, + NETDATA_IDX_TCP_CLEANUP_RBUF, + NETDATA_IDX_TCP_CLOSE, + NETDATA_IDX_UDP_RECVBUF, + NETDATA_IDX_UDP_SENDMSG, + NETDATA_IDX_TCP_RETRANSMIT, + + // Keep this as last and don't skip numbers as it is used as element counter + NETDATA_MAX_SOCKET_VECTOR +}; + typedef enum ebpf_socket_idx { NETDATA_KEY_CALLS_TCP_SENDMSG, NETDATA_KEY_ERROR_TCP_SENDMSG, @@ -38,6 +59,7 @@ typedef enum ebpf_socket_idx { NETDATA_KEY_TCP_RETRANSMIT, + // Keep this as last and don't skip numbers as it is used as element counter NETDATA_SOCKET_COUNTER } ebpf_socket_index_t; @@ -232,7 +254,7 @@ typedef struct netdata_socket_idx { */ typedef struct netdata_socket_plot { // Search - avl avl; + avl_t avl; netdata_socket_idx_t index; // Current data @@ -269,6 +291,9 @@ typedef struct netdata_vector_plot { extern void clean_port_structure(ebpf_network_viewer_port_list_t **clean); extern ebpf_network_viewer_port_list_t *listen_ports; extern void update_listen_table(uint16_t value, uint8_t proto); +extern void parse_network_viewer_section(struct config *cfg); +extern void fill_ip_list(ebpf_network_viewer_ip_list_t **out, ebpf_network_viewer_ip_list_t *in, char *table); +extern void parse_service_name_section(struct config *cfg); extern ebpf_socket_publish_apps_t **socket_bandwidth_curr; diff --git a/collectors/ebpf.plugin/ebpf_sync.c b/collectors/ebpf.plugin/ebpf_sync.c new file mode 100644 index 000000000..f0db1cc4a --- /dev/null +++ b/collectors/ebpf.plugin/ebpf_sync.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "ebpf.h" +#include "ebpf_sync.h" + +static ebpf_data_t sync_data; + +static char *sync_counter_dimension_name[NETDATA_SYNC_IDX_END] = { "sync", "syncfs", "msync", "fsync", "fdatasync", + "sync_file_range" }; +static netdata_syscall_stat_t sync_counter_aggregated_data[NETDATA_SYNC_IDX_END]; +static netdata_publish_syscall_t sync_counter_publish_aggregated[NETDATA_SYNC_IDX_END]; + +static int read_thread_closed = 1; + +static netdata_idx_t sync_hash_values[NETDATA_SYNC_IDX_END]; + +struct netdata_static_thread sync_threads = {"SYNC KERNEL", NULL, NULL, 1, + NULL, NULL, NULL}; + +struct config sync_config = { .first_section = NULL, + .last_section = NULL, + .mutex = NETDATA_MUTEX_INITIALIZER, + .index = { .avl_tree = { .root = NULL, .compar = appconfig_section_compare }, + .rwlock = AVL_LOCK_INITIALIZER } }; + +ebpf_sync_syscalls_t local_syscalls[] = { + {.syscall = "sync", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = "syncfs", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = "msync", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = "fsync", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = "fdatasync", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = "sync_file_range", .enabled = CONFIG_BOOLEAN_YES, .objects = NULL, .probe_links = NULL}, + {.syscall = NULL, .enabled = CONFIG_BOOLEAN_NO, .objects = NULL, .probe_links = NULL} +}; + +/***************************************************************** + * + * INITIALIZE THREAD + * + *****************************************************************/ + +/* + * Initialize Syscalls + * + * Load the eBPF programs to monitor syscalls + * + * @return 0 on success and -1 otherwise. + */ +static int ebpf_sync_initialize_syscall(ebpf_module_t *em) +{ + int i; + const char *saved_name = em->thread_name; + for (i = 0; local_syscalls[i].syscall; i++) { + ebpf_sync_syscalls_t *w = &local_syscalls[i]; + if (!w->probe_links && w->enabled) { + fill_ebpf_data(&w->kernel_info); + if (ebpf_update_kernel(&w->kernel_info)) { + em->thread_name = saved_name; + error("Cannot update the kernel for eBPF module %s", w->syscall); + return -1; + } + + em->thread_name = w->syscall; + w->probe_links = ebpf_load_program(ebpf_plugin_dir, em, kernel_string, &w->objects, w->kernel_info.map_fd); + if (!w->probe_links) { + em->thread_name = saved_name; + return -1; + } + } + } + em->thread_name = saved_name; + + memset(sync_counter_aggregated_data, 0 , NETDATA_SYNC_IDX_END * sizeof(netdata_syscall_stat_t)); + memset(sync_counter_publish_aggregated, 0 , NETDATA_SYNC_IDX_END * sizeof(netdata_publish_syscall_t)); + memset(sync_hash_values, 0 , NETDATA_SYNC_IDX_END * sizeof(netdata_idx_t)); + + return 0; +} + +/***************************************************************** + * + * DATA THREAD + * + *****************************************************************/ + +/** + * Read global table + * + * Read the table with number of calls for all functions + */ +static void read_global_table() +{ + netdata_idx_t stored; + uint32_t idx = NETDATA_SYNC_CALL; + int i; + for (i = 0; local_syscalls[i].syscall; i++) { + if (local_syscalls[i].enabled) { + int fd = local_syscalls[i].kernel_info.map_fd[NETDATA_SYNC_GLOBLAL_TABLE]; + if (!bpf_map_lookup_elem(fd, &idx, &stored)) { + sync_hash_values[i] = stored; + } + } + } +} + +/** + * Sync read hash + * + * This is the thread callback. + * + * @param ptr It is a NULL value for this thread. + * + * @return It always returns NULL. + */ +void *ebpf_sync_read_hash(void *ptr) +{ + ebpf_module_t *em = (ebpf_module_t *)ptr; + read_thread_closed = 0; + + heartbeat_t hb; + heartbeat_init(&hb); + usec_t step = NETDATA_EBPF_SYNC_SLEEP_MS * em->update_time; + + while (!close_ebpf_plugin) { + usec_t dt = heartbeat_next(&hb, step); + (void)dt; + + read_global_table(); + } + read_thread_closed = 1; + + return NULL; +} + +/** + * Create Sync charts + * + * Create charts and dimensions according user input. + * + * @param id chart id + * @param idx the first index with data. + * @param end the last index with data. + */ +static void ebpf_send_sync_chart(char *id, + int idx, + int end) +{ + write_begin_chart(NETDATA_EBPF_MEMORY_GROUP, id); + + netdata_publish_syscall_t *move = &sync_counter_publish_aggregated[idx]; + + while (move && idx <= end) { + if (local_syscalls[idx].enabled) + write_chart_dimension(move->name, sync_hash_values[idx]); + + move = move->next; + idx++; + } + + write_end_chart(); +} + +/** + * Send data + * + * Send global charts to Netdata + */ +static void sync_send_data() +{ + if (local_syscalls[NETDATA_SYNC_FSYNC_IDX].enabled || local_syscalls[NETDATA_SYNC_FDATASYNC_IDX].enabled) { + ebpf_send_sync_chart(NETDATA_EBPF_FILE_SYNC_CHART, NETDATA_SYNC_FSYNC_IDX, NETDATA_SYNC_FDATASYNC_IDX); + } + + if (local_syscalls[NETDATA_SYNC_MSYNC_IDX].enabled) + ebpf_one_dimension_write_charts(NETDATA_EBPF_MEMORY_GROUP, NETDATA_EBPF_MSYNC_CHART, + sync_counter_publish_aggregated[NETDATA_SYNC_MSYNC_IDX].dimension, + sync_hash_values[NETDATA_SYNC_MSYNC_IDX]); + + if (local_syscalls[NETDATA_SYNC_SYNC_IDX].enabled || local_syscalls[NETDATA_SYNC_SYNCFS_IDX].enabled) { + ebpf_send_sync_chart(NETDATA_EBPF_SYNC_CHART, NETDATA_SYNC_SYNC_IDX, NETDATA_SYNC_SYNCFS_IDX); + } + + if (local_syscalls[NETDATA_SYNC_SYNC_FILE_RANGE_IDX].enabled) + ebpf_one_dimension_write_charts(NETDATA_EBPF_MEMORY_GROUP, NETDATA_EBPF_FILE_SEGMENT_CHART, + sync_counter_publish_aggregated[NETDATA_SYNC_SYNC_FILE_RANGE_IDX].dimension, + sync_hash_values[NETDATA_SYNC_SYNC_FILE_RANGE_IDX]); +} + +/** +* Main loop for this collector. +*/ +static void sync_collector(ebpf_module_t *em) +{ + sync_threads.thread = mallocz(sizeof(netdata_thread_t)); + sync_threads.start_routine = ebpf_sync_read_hash; + + netdata_thread_create(sync_threads.thread, sync_threads.name, NETDATA_THREAD_OPTION_JOINABLE, + ebpf_sync_read_hash, em); + + while (!close_ebpf_plugin) { + pthread_mutex_lock(&collect_data_mutex); + pthread_cond_wait(&collect_data_cond_var, &collect_data_mutex); + + pthread_mutex_lock(&lock); + + sync_send_data(); + + pthread_mutex_unlock(&lock); + pthread_mutex_unlock(&collect_data_mutex); + } +} + + +/***************************************************************** + * + * CLEANUP THREAD + * + *****************************************************************/ + +/** + * Cleanup Objects + * + * Cleanup loaded objects when thread was initialized. + */ +void ebpf_sync_cleanup_objects() +{ + int i; + for (i = 0; local_syscalls[i].syscall; i++) { + ebpf_sync_syscalls_t *w = &local_syscalls[i]; + if (w->probe_links) { + freez(w->kernel_info.map_fd); + + struct bpf_program *prog; + size_t j = 0 ; + bpf_object__for_each_program(prog, w->objects) { + bpf_link__destroy(w->probe_links[j]); + j++; + } + bpf_object__close(w->objects); + } + } +} + +/** + * Clean up the main thread. + * + * @param ptr thread data. + */ +static void ebpf_sync_cleanup(void *ptr) +{ + ebpf_module_t *em = (ebpf_module_t *)ptr; + if (!em->enabled) + return; + + heartbeat_t hb; + heartbeat_init(&hb); + uint32_t tick = 2*USEC_PER_MS; + while (!read_thread_closed) { + usec_t dt = heartbeat_next(&hb, tick); + UNUSED(dt); + } + + ebpf_sync_cleanup_objects(); + freez(sync_threads.thread); +} + +/***************************************************************** + * + * MAIN THREAD + * + *****************************************************************/ + +/** + * Create Sync charts + * + * Create charts and dimensions according user input. + * + * @param id chart id + * @param title chart title + * @param order order number of the specified chart + * @param idx the first index with data. + * @param end the last index with data. + */ +static void ebpf_create_sync_chart(char *id, + char *title, + int order, + int idx, + int end) +{ + ebpf_write_chart_cmd(NETDATA_EBPF_MEMORY_GROUP, id, title, EBPF_COMMON_DIMENSION_CALL, + NETDATA_EBPF_SYNC_SUBMENU, NETDATA_EBPF_CHART_TYPE_LINE, NULL, order); + + netdata_publish_syscall_t *move = &sync_counter_publish_aggregated[idx]; + + while (move && idx <= end) { + if (local_syscalls[idx].enabled) + ebpf_write_global_dimension(move->name, move->dimension, move->algorithm); + + move = move->next; + idx++; + } +} + +/** + * Create global charts + * + * Call ebpf_create_chart to create the charts for the collector. + */ +static void ebpf_create_sync_charts() +{ + if (local_syscalls[NETDATA_SYNC_FSYNC_IDX].enabled || local_syscalls[NETDATA_SYNC_FDATASYNC_IDX].enabled) + ebpf_create_sync_chart(NETDATA_EBPF_FILE_SYNC_CHART, + "Monitor calls for fsync(2) and fdatasync(2).", 21300, + NETDATA_SYNC_FSYNC_IDX, NETDATA_SYNC_FDATASYNC_IDX); + + if (local_syscalls[NETDATA_SYNC_MSYNC_IDX].enabled) + ebpf_create_sync_chart(NETDATA_EBPF_MSYNC_CHART, + "Monitor calls for msync(2).", 21301, + NETDATA_SYNC_MSYNC_IDX, NETDATA_SYNC_MSYNC_IDX); + + if (local_syscalls[NETDATA_SYNC_SYNC_IDX].enabled || local_syscalls[NETDATA_SYNC_SYNCFS_IDX].enabled) + ebpf_create_sync_chart(NETDATA_EBPF_SYNC_CHART, + "Monitor calls for sync(2) and syncfs(2).", 21302, + NETDATA_SYNC_SYNC_IDX, NETDATA_SYNC_SYNCFS_IDX); + + if (local_syscalls[NETDATA_SYNC_SYNC_FILE_RANGE_IDX].enabled) + ebpf_create_sync_chart(NETDATA_EBPF_FILE_SEGMENT_CHART, + "Monitor calls for sync_file_range(2).", 21303, + NETDATA_SYNC_SYNC_FILE_RANGE_IDX, NETDATA_SYNC_SYNC_FILE_RANGE_IDX); +} + +/** + * Parse Syscalls + * + * Parse syscall options available inside ebpf.d/sync.conf + */ +static void ebpf_sync_parse_syscalls() +{ + int i; + for (i = 0; local_syscalls[i].syscall; i++) { + local_syscalls[i].enabled = appconfig_get_boolean(&sync_config, NETDATA_SYNC_CONFIG_NAME, + local_syscalls[i].syscall, CONFIG_BOOLEAN_YES); + } +} + +/** + * Sync thread + * + * Thread used to make sync thread + * + * @param ptr a pointer to `struct ebpf_module` + * + * @return It always return NULL + */ +void *ebpf_sync_thread(void *ptr) +{ + netdata_thread_cleanup_push(ebpf_sync_cleanup, ptr); + + ebpf_module_t *em = (ebpf_module_t *)ptr; + fill_ebpf_data(&sync_data); + + ebpf_update_module(em, &sync_config, NETDATA_SYNC_CONFIG_FILE); + ebpf_sync_parse_syscalls(); + + if (!em->enabled) + goto endsync; + + if (ebpf_sync_initialize_syscall(em)) { + pthread_mutex_unlock(&lock); + goto endsync; + } + + int algorithms[NETDATA_SYNC_IDX_END] = { NETDATA_EBPF_INCREMENTAL_IDX, NETDATA_EBPF_INCREMENTAL_IDX, + NETDATA_EBPF_INCREMENTAL_IDX, NETDATA_EBPF_INCREMENTAL_IDX, + NETDATA_EBPF_INCREMENTAL_IDX, NETDATA_EBPF_INCREMENTAL_IDX }; + ebpf_global_labels(sync_counter_aggregated_data, sync_counter_publish_aggregated, + sync_counter_dimension_name, sync_counter_dimension_name, + algorithms, NETDATA_SYNC_IDX_END); + + pthread_mutex_lock(&lock); + ebpf_create_sync_charts(); + pthread_mutex_unlock(&lock); + + sync_collector(em); + +endsync: + netdata_thread_cleanup_pop(1); + return NULL; +} diff --git a/collectors/ebpf.plugin/ebpf_sync.h b/collectors/ebpf.plugin/ebpf_sync.h new file mode 100644 index 000000000..458318218 --- /dev/null +++ b/collectors/ebpf.plugin/ebpf_sync.h @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_EBPF_SYNC_H +#define NETDATA_EBPF_SYNC_H 1 + +// charts +#define NETDATA_EBPF_SYNC_CHART "sync" +#define NETDATA_EBPF_MSYNC_CHART "memory_map" +#define NETDATA_EBPF_FILE_SYNC_CHART "file_sync" +#define NETDATA_EBPF_FILE_SEGMENT_CHART "file_segment" +#define NETDATA_EBPF_SYNC_SUBMENU "synchronization (eBPF)" + +#define NETDATA_EBPF_SYNC_SLEEP_MS 800000ULL + +// configuration file +#define NETDATA_SYNC_CONFIG_FILE "sync.conf" +#define NETDATA_SYNC_CONFIG_NAME "syscalls" + +enum sync_syscalls_index { + NETDATA_SYNC_SYNC_IDX, + NETDATA_SYNC_SYNCFS_IDX, + NETDATA_SYNC_MSYNC_IDX, + NETDATA_SYNC_FSYNC_IDX, + NETDATA_SYNC_FDATASYNC_IDX, + NETDATA_SYNC_SYNC_FILE_RANGE_IDX, + + NETDATA_SYNC_IDX_END +}; + +typedef struct ebpf_sync_syscalls { + char *syscall; + int enabled; + uint32_t flags; + + struct bpf_object *objects; + struct bpf_link **probe_links; + + ebpf_data_t kernel_info; +} ebpf_sync_syscalls_t; + +enum netdata_sync_charts { + NETDATA_SYNC_CALL, + + // Keep this as last and don't skip numbers as it is used as element counter + NETDATA_SYNC_END +}; + +enum netdata_sync_table { + NETDATA_SYNC_GLOBLAL_TABLE +}; + +extern void *ebpf_sync_thread(void *ptr); + +#endif /* NETDATA_EBPF_SYNC_H */ diff --git a/collectors/freeipmi.plugin/README.md b/collectors/freeipmi.plugin/README.md index 52945e3c6..02a61dd2f 100644 --- a/collectors/freeipmi.plugin/README.md +++ b/collectors/freeipmi.plugin/README.md @@ -45,7 +45,7 @@ The plugin does a speed test when it starts, to find out the duration needed by The plugin supports a few options. To see them, run: -```sh +```text # /usr/libexec/netdata/plugins.d/freeipmi.plugin -h netdata freeipmi.plugin 1.8.0-546-g72ce5d6b_rolling @@ -72,6 +72,8 @@ The plugin supports a few options. To see them, run: password PASS connect to remote IPMI host default: local IPMI processor + noauthcodecheck don't check the authentication codes returned + driver-type IPMIDRIVER Specify the driver type to use instead of doing an auto selection. The currently available outofband drivers are LAN and LAN_2_0, diff --git a/collectors/freeipmi.plugin/freeipmi_plugin.c b/collectors/freeipmi.plugin/freeipmi_plugin.c index bd3c533ca..e9702e785 100644 --- a/collectors/freeipmi.plugin/freeipmi_plugin.c +++ b/collectors/freeipmi.plugin/freeipmi_plugin.c @@ -26,8 +26,6 @@ #include #include -#ifdef HAVE_FREEIPMI - #define IPMI_PARSE_DEVICE_LAN_STR "lan" #define IPMI_PARSE_DEVICE_LAN_2_0_STR "lan_2_0" #define IPMI_PARSE_DEVICE_LAN_2_0_STR2 "lan20" @@ -1621,6 +1619,14 @@ int parse_outofband_driver_type (const char *str) return (-1); } +int host_is_local(const char *host) +{ + if (host && (!strcmp(host, "localhost") || !strcmp(host, "127.0.0.1") || !strcmp(host, "::1"))) + return (1); + + return (0); +} + int main (int argc, char **argv) { // ------------------------------------------------------------------------ @@ -1691,6 +1697,8 @@ int main (int argc, char **argv) { " password PASS connect to remote IPMI host\n" " default: local IPMI processor\n" "\n" + " noauthcodecheck don't check the authentication codes returned\n" + "\n" " driver-type IPMIDRIVER\n" " Specify the driver type to use instead of doing an auto selection. \n" " The currently available outofband drivers are LAN and LAN_2_0,\n" @@ -1765,6 +1773,23 @@ int main (int argc, char **argv) { if(debug) fprintf(stderr, "freeipmi.plugin: inband driver type set to '%d'\n", driver_type); } continue; + } else if (i < argc && strcmp("noauthcodecheck", argv[i]) == 0) { + if (!hostname || host_is_local(hostname)) { + if (debug) + fprintf( + stderr, + "freeipmi.plugin: noauthcodecheck workaround flag is ignored for inband configuration\n"); + } else if (protocol_version < 0 || protocol_version == IPMI_MONITORING_PROTOCOL_VERSION_1_5) { + workaround_flags |= IPMI_MONITORING_WORKAROUND_FLAGS_PROTOCOL_VERSION_1_5_NO_AUTH_CODE_CHECK; + if (debug) + fprintf(stderr, "freeipmi.plugin: noauthcodecheck workaround flag enabled\n"); + } else { + if (debug) + fprintf( + stderr, + "freeipmi.plugin: noauthcodecheck workaround flag is ignored for protocol version 2.0\n"); + } + continue; } else if(i < argc && strcmp("sdr-cache-dir", argv[i]) == 0) { sdr_cache_directory = argv[++i]; @@ -1861,11 +1886,3 @@ int main (int argc, char **argv) { if(now_monotonic_sec() - started_t > 14400) exit(0); } } - -#else // !HAVE_FREEIPMI - -int main(int argc, char **argv) { - fatal("freeipmi.plugin is not compiled."); -} - -#endif // !HAVE_FREEIPMI diff --git a/collectors/nfacct.plugin/plugin_nfacct.c b/collectors/nfacct.plugin/plugin_nfacct.c index 996070f1c..acdd0586d 100644 --- a/collectors/nfacct.plugin/plugin_nfacct.c +++ b/collectors/nfacct.plugin/plugin_nfacct.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-3.0-or-later #include "../../libnetdata/libnetdata.h" +#include +#include +#include #define PLUGIN_NFACCT_NAME "nfacct.plugin" @@ -13,9 +16,6 @@ #define NETDATA_CHART_PRIO_NETFILTER_PACKETS 8906 #define NETDATA_CHART_PRIO_NETFILTER_BYTES 8907 -#ifdef HAVE_LIBMNL -#include - static inline size_t mnl_buffer_size() { long s = MNL_SOCKET_BUFFER_SIZE; if(s <= 0) return 8192; @@ -50,25 +50,13 @@ int health_variable_lookup(const char *variable, uint32_t hash, struct rrdcalc * // required by get_system_cpus() char *netdata_configured_host_prefix = ""; - -// Variables - +// variables static int debug = 0; - static int netdata_update_every = 1; -// ---------------------------------------------------------------------------- -// DO_NFSTAT - collect netfilter connection tracker statistics via netlink -// example: https://github.com/formorer/pkg-conntrack-tools/blob/master/src/conntrack.c - -#ifdef HAVE_LINUX_NETFILTER_NFNETLINK_CONNTRACK_H -#define DO_NFSTAT 1 - #define RRD_TYPE_NET_STAT_NETFILTER "netfilter" #define RRD_TYPE_NET_STAT_CONNTRACK "netlink" -#include - static struct { int update_every; char *buf; @@ -530,16 +518,6 @@ static void nfstat_send_metrics() { printf("END\n"); } -#endif // HAVE_LINUX_NETFILTER_NFNETLINK_CONNTRACK_H - - -// ---------------------------------------------------------------------------- -// DO_NFACCT - collect netfilter accounting statistics via netlink - -#ifdef HAVE_LIBNETFILTER_ACCT -#define DO_NFACCT 1 - -#include struct nfacct_data { char *name; @@ -760,8 +738,6 @@ static void nfacct_send_metrics() { printf("END\n"); } -#endif // HAVE_LIBNETFILTER_ACCT - static void nfacct_signal_handler(int signo) { exit((signo == SIGPIPE)?1:0); @@ -866,15 +842,13 @@ int main(int argc, char **argv) { else if(freq) error("update frequency %d seconds is too small for NFACCT. Using %d.", freq, netdata_update_every); -#ifdef DO_NFACCT - if(debug) fprintf(stderr, "nfacct.plugin: calling nfacct_init()\n"); + if (debug) + fprintf(stderr, "nfacct.plugin: calling nfacct_init()\n"); int nfacct = !nfacct_init(netdata_update_every); -#endif -#ifdef DO_NFSTAT - if(debug) fprintf(stderr, "nfacct.plugin: calling nfstat_init()\n"); + if (debug) + fprintf(stderr, "nfacct.plugin: calling nfstat_init()\n"); int nfstat = !nfstat_init(netdata_update_every); -#endif // ------------------------------------------------------------------------ // the main loop @@ -899,7 +873,6 @@ int main(int argc, char **argv) { , dt ); -#ifdef DO_NFACCT if(likely(nfacct)) { if(debug) fprintf(stderr, "nfacct.plugin: calling nfacct_collect()\n"); nfacct = !nfacct_collect(); @@ -909,9 +882,7 @@ int main(int argc, char **argv) { nfacct_send_metrics(); } } -#endif -#ifdef DO_NFSTAT if(likely(nfstat)) { if(debug) fprintf(stderr, "nfacct.plugin: calling nfstat_collect()\n"); nfstat = !nfstat_collect(); @@ -921,7 +892,6 @@ int main(int argc, char **argv) { nfstat_send_metrics(); } } -#endif fflush(stdout); @@ -931,14 +901,3 @@ int main(int argc, char **argv) { info("NFACCT process exiting"); } - -#else // !HAVE_LIBMNL - -int main(int argc, char **argv) { - (void)argc; - (void)argv; - - fatal("nfacct.plugin is not compiled."); -} - -#endif // !HAVE_LIBMNL diff --git a/collectors/proc.plugin/proc_diskstats.c b/collectors/proc.plugin/proc_diskstats.c index eee0cbe7f..b5d02f329 100644 --- a/collectors/proc.plugin/proc_diskstats.c +++ b/collectors/proc.plugin/proc_diskstats.c @@ -17,6 +17,7 @@ static struct disk { char *disk; // the name of the disk (sda, sdb, etc, after being looked up) char *device; // the device of the disk (before being looked up) + uint32_t hash; unsigned long major; unsigned long minor; int sector_size; @@ -73,6 +74,9 @@ static struct disk { RRDSET *st_backlog; RRDDIM *rd_backlog_backlog; + RRDSET *st_busy; + RRDDIM *rd_busy_busy; + RRDSET *st_util; RRDDIM *rd_util_utilization; @@ -390,7 +394,7 @@ static inline int get_disk_name_from_path(const char *path, char *result, size_t continue; } - if(major(sb.st_rdev) != major || minor(sb.st_rdev) != minor) { + if(major(sb.st_rdev) != major || minor(sb.st_rdev) != minor || strcmp(basename(filename), disk)) { //info("DEVICE-MAPPER ('%s', %lu:%lu): filename '%s' does not match %lu:%lu.", disk, major, minor, filename, (unsigned long)major(sb.st_rdev), (unsigned long)minor(sb.st_rdev)); continue; } @@ -544,13 +548,17 @@ static struct disk *get_disk(unsigned long major, unsigned long minor, char *dis struct disk *d; + uint32_t hash = simple_hash(disk); + // search for it in our RAM list. // this is sequential, but since we just walk through // and the number of disks / partitions in a system // should not be that many, it should be acceptable - for(d = disk_root; d ; d = d->next) - if(unlikely(d->major == major && d->minor == minor)) + for(d = disk_root; d ; d = d->next){ + if (unlikely( + d->major == major && d->minor == minor && d->hash == hash && !strcmp(d->device, disk))) return d; + } // not found // create a new disk structure @@ -558,6 +566,7 @@ static struct disk *get_disk(unsigned long major, unsigned long minor, char *dis d->disk = get_disk_name(major, minor, disk); d->device = strdupz(disk); + d->hash = simple_hash(d->device); d->major = major; d->minor = minor; d->type = DISK_TYPE_UNKNOWN; // Default type. Changed later if not correct. @@ -624,12 +633,12 @@ static struct disk *get_disk(unsigned long major, unsigned long minor, char *dis // check if we can find its mount point // mountinfo_find() can be called with NULL disk_mountinfo_root - struct mountinfo *mi = mountinfo_find(disk_mountinfo_root, d->major, d->minor); + struct mountinfo *mi = mountinfo_find(disk_mountinfo_root, d->major, d->minor, d->device); if(unlikely(!mi)) { // mountinfo_free_all can be called with NULL mountinfo_free_all(disk_mountinfo_root); disk_mountinfo_root = mountinfo_read(0); - mi = mountinfo_find(disk_mountinfo_root, d->major, d->minor); + mi = mountinfo_find(disk_mountinfo_root, d->major, d->minor, d->device); } if(unlikely(mi)) @@ -942,13 +951,6 @@ int do_proc_diskstats(int update_every, usec_t dt) { // I/O completion time and the backlog that may be accumulating. backlog_ms = str2ull(procfile_lineword(ff, l, 13)); // rq_ticks - - // -------------------------------------------------------------------------- - // remove slashes from disk names - char *s; - for(s = disk; *s ;s++) - if(*s == '/') *s = '_'; - // -------------------------------------------------------------------------- // get a disk structure for the disk @@ -1094,7 +1096,7 @@ int do_proc_diskstats(int update_every, usec_t dt) { rrdset_flag_set(d->st_backlog, RRDSET_FLAG_DETAIL); - d->rd_backlog_backlog = rrddim_add(d->st_backlog, "backlog", NULL, 1, 10, RRD_ALGORITHM_INCREMENTAL); + d->rd_backlog_backlog = rrddim_add(d->st_backlog, "backlog", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); } else rrdset_next(d->st_backlog); @@ -1108,6 +1110,34 @@ int do_proc_diskstats(int update_every, usec_t dt) { (busy_ms || netdata_zero_metrics_enabled == CONFIG_BOOLEAN_YES))) { d->do_util = CONFIG_BOOLEAN_YES; + if(unlikely(!d->st_busy)) { + d->st_busy = rrdset_create_localhost( + "disk_busy" + , d->device + , d->disk + , family + , "disk.busy" + , "Disk Busy Time" + , "milliseconds" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_DISKSTATS_NAME + , NETDATA_CHART_PRIO_DISK_BUSY + , update_every + , RRDSET_TYPE_AREA + ); + + rrdset_flag_set(d->st_busy, RRDSET_FLAG_DETAIL); + + d->rd_busy_busy = + rrddim_add(d->st_busy, "busy", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + else rrdset_next(d->st_busy); + + last_busy_ms = rrddim_set_by_pointer(d->st_busy, d->rd_busy_busy, busy_ms); + rrdset_done(d->st_busy); + + // -------------------------------------------------------------------- + if(unlikely(!d->st_util)) { d->st_util = rrdset_create_localhost( "disk_util" @@ -1126,11 +1156,15 @@ int do_proc_diskstats(int update_every, usec_t dt) { rrdset_flag_set(d->st_util, RRDSET_FLAG_DETAIL); - d->rd_util_utilization = rrddim_add(d->st_util, "utilization", NULL, 1, 10, RRD_ALGORITHM_INCREMENTAL); + d->rd_util_utilization = rrddim_add(d->st_util, "utilization", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); } else rrdset_next(d->st_util); - last_busy_ms = rrddim_set_by_pointer(d->st_util, d->rd_util_utilization, busy_ms); + collected_number disk_utilization = (busy_ms - last_busy_ms) / (10 * update_every); + if (disk_utilization > 100) + disk_utilization = 100; + + rrddim_set_by_pointer(d->st_util, d->rd_util_utilization, disk_utilization); rrdset_done(d->st_util); } diff --git a/collectors/proc.plugin/proc_net_dev.c b/collectors/proc.plugin/proc_net_dev.c index a7db37e61..24715f296 100644 --- a/collectors/proc.plugin/proc_net_dev.c +++ b/collectors/proc.plugin/proc_net_dev.c @@ -5,6 +5,8 @@ #define PLUGIN_PROC_MODULE_NETDEV_NAME "/proc/net/dev" #define CONFIG_SECTION_PLUGIN_PROC_NETDEV "plugin:" PLUGIN_PROC_CONFIG_NAME ":" PLUGIN_PROC_MODULE_NETDEV_NAME +#define STATE_LENGTH_MAX 32 + // As defined in https://www.kernel.org/doc/Documentation/ABI/testing/sysfs-class-net const char *operstate_names[] = { "unknown", "notpresent", "down", "lowerlayerdown", "testing", "dormant", "up" }; @@ -41,6 +43,11 @@ static struct netdev { int do_fifo; int do_compressed; int do_events; + int do_speed; + int do_duplex; + int do_operstate; + int do_carrier; + int do_mtu; const char *chart_type_net_bytes; const char *chart_type_net_packets; @@ -49,6 +56,11 @@ static struct netdev { const char *chart_type_net_events; const char *chart_type_net_drops; const char *chart_type_net_compressed; + const char *chart_type_net_speed; + const char *chart_type_net_duplex; + const char *chart_type_net_operstate; + const char *chart_type_net_carrier; + const char *chart_type_net_mtu; const char *chart_id_net_bytes; const char *chart_id_net_packets; @@ -57,6 +69,11 @@ static struct netdev { const char *chart_id_net_events; const char *chart_id_net_drops; const char *chart_id_net_compressed; + const char *chart_id_net_speed; + const char *chart_id_net_duplex; + const char *chart_id_net_operstate; + const char *chart_id_net_carrier; + const char *chart_id_net_mtu; const char *chart_family; @@ -86,6 +103,8 @@ static struct netdev { kernel_uint_t speed; kernel_uint_t duplex; kernel_uint_t operstate; + unsigned long long carrier; + unsigned long long mtu; // charts RRDSET *st_bandwidth; @@ -95,6 +114,11 @@ static struct netdev { RRDSET *st_fifo; RRDSET *st_compressed; RRDSET *st_events; + RRDSET *st_speed; + RRDSET *st_duplex; + RRDSET *st_operstate; + RRDSET *st_carrier; + RRDSET *st_mtu; // dimensions RRDDIM *rd_rbytes; @@ -115,18 +139,19 @@ static struct netdev { RRDDIM *rd_tcarrier; RRDDIM *rd_tcompressed; - usec_t speed_last_collected_usec; - usec_t duplex_last_collected_usec; - usec_t operstate_last_collected_usec; + RRDDIM *rd_speed; + RRDDIM *rd_duplex; + RRDDIM *rd_operstate; + RRDDIM *rd_carrier; + RRDDIM *rd_mtu; char *filename_speed; RRDSETVAR *chart_var_speed; char *filename_duplex; - RRDSETVAR *chart_var_duplex; - char *filename_operstate; - RRDSETVAR *chart_var_operstate; + char *filename_carrier; + char *filename_mtu; struct netdev *next; } *netdev_root = NULL, *netdev_last_used = NULL; @@ -143,6 +168,11 @@ static void netdev_charts_release(struct netdev *d) { if(d->st_fifo) rrdset_is_obsolete(d->st_fifo); if(d->st_compressed) rrdset_is_obsolete(d->st_compressed); if(d->st_events) rrdset_is_obsolete(d->st_events); + if(d->st_speed) rrdset_is_obsolete(d->st_speed); + if(d->st_duplex) rrdset_is_obsolete(d->st_duplex); + if(d->st_operstate) rrdset_is_obsolete(d->st_operstate); + if(d->st_carrier) rrdset_is_obsolete(d->st_carrier); + if(d->st_mtu) rrdset_is_obsolete(d->st_mtu); d->st_bandwidth = NULL; d->st_compressed = NULL; @@ -151,6 +181,11 @@ static void netdev_charts_release(struct netdev *d) { d->st_events = NULL; d->st_fifo = NULL; d->st_packets = NULL; + d->st_speed = NULL; + d->st_duplex = NULL; + d->st_operstate = NULL; + d->st_carrier = NULL; + d->st_mtu = NULL; d->rd_rbytes = NULL; d->rd_rpackets = NULL; @@ -170,9 +205,13 @@ static void netdev_charts_release(struct netdev *d) { d->rd_tcarrier = NULL; d->rd_tcompressed = NULL; + d->rd_speed = NULL; + d->rd_duplex = NULL; + d->rd_operstate = NULL; + d->rd_carrier = NULL; + d->rd_mtu = NULL; + d->chart_var_speed = NULL; - d->chart_var_duplex = NULL; - d->chart_var_operstate = NULL; } static void netdev_free_chart_strings(struct netdev *d) { @@ -183,6 +222,11 @@ static void netdev_free_chart_strings(struct netdev *d) { freez((void *)d->chart_type_net_events); freez((void *)d->chart_type_net_fifo); freez((void *)d->chart_type_net_packets); + freez((void *)d->chart_type_net_speed); + freez((void *)d->chart_type_net_duplex); + freez((void *)d->chart_type_net_operstate); + freez((void *)d->chart_type_net_carrier); + freez((void *)d->chart_type_net_mtu); freez((void *)d->chart_id_net_bytes); freez((void *)d->chart_id_net_compressed); @@ -191,6 +235,11 @@ static void netdev_free_chart_strings(struct netdev *d) { freez((void *)d->chart_id_net_events); freez((void *)d->chart_id_net_fifo); freez((void *)d->chart_id_net_packets); + freez((void *)d->chart_id_net_speed); + freez((void *)d->chart_id_net_duplex); + freez((void *)d->chart_id_net_operstate); + freez((void *)d->chart_id_net_carrier); + freez((void *)d->chart_id_net_mtu); freez((void *)d->chart_family); } @@ -204,6 +253,8 @@ static void netdev_free(struct netdev *d) { freez((void *)d->filename_speed); freez((void *)d->filename_duplex); freez((void *)d->filename_operstate); + freez((void *)d->filename_carrier); + freez((void *)d->filename_mtu); freez((void *)d); netdev_added--; } @@ -325,6 +376,11 @@ static inline void netdev_rename_cgroup(struct netdev *d, struct netdev_rename * d->chart_type_net_events = strdupz(buffer); d->chart_type_net_fifo = strdupz(buffer); d->chart_type_net_packets = strdupz(buffer); + d->chart_type_net_speed = strdupz(buffer); + d->chart_type_net_duplex = strdupz(buffer); + d->chart_type_net_operstate = strdupz(buffer); + d->chart_type_net_carrier = strdupz(buffer); + d->chart_type_net_mtu = strdupz(buffer); snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_%s", r->container_device); d->chart_id_net_bytes = strdupz(buffer); @@ -347,6 +403,21 @@ static inline void netdev_rename_cgroup(struct netdev *d, struct netdev_rename * snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_packets_%s", r->container_device); d->chart_id_net_packets = strdupz(buffer); + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_speed_%s", r->container_device); + d->chart_id_net_speed = strdupz(buffer); + + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_duplex_%s", r->container_device); + d->chart_id_net_duplex = strdupz(buffer); + + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_operstate_%s", r->container_device); + d->chart_id_net_operstate = strdupz(buffer); + + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_carrier_%s", r->container_device); + d->chart_id_net_carrier = strdupz(buffer); + + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net_mtu_%s", r->container_device); + d->chart_id_net_mtu = strdupz(buffer); + snprintfz(buffer, RRD_ID_LENGTH_MAX, "net %s", r->container_device); d->chart_family = strdupz(buffer); @@ -451,6 +522,11 @@ static struct netdev *get_netdev(const char *name) { d->chart_type_net_events = strdupz("net_events"); d->chart_type_net_fifo = strdupz("net_fifo"); d->chart_type_net_packets = strdupz("net_packets"); + d->chart_type_net_speed = strdupz("net_speed"); + d->chart_type_net_duplex = strdupz("net_duplex"); + d->chart_type_net_operstate = strdupz("net_operstate"); + d->chart_type_net_carrier = strdupz("net_carrier"); + d->chart_type_net_mtu = strdupz("net_mtu"); d->chart_id_net_bytes = strdupz(d->name); d->chart_id_net_compressed = strdupz(d->name); @@ -459,6 +535,11 @@ static struct netdev *get_netdev(const char *name) { d->chart_id_net_events = strdupz(d->name); d->chart_id_net_fifo = strdupz(d->name); d->chart_id_net_packets = strdupz(d->name); + d->chart_id_net_speed = strdupz(d->name); + d->chart_id_net_duplex = strdupz(d->name); + d->chart_id_net_operstate = strdupz(d->name); + d->chart_id_net_carrier = strdupz(d->name); + d->chart_id_net_mtu = strdupz(d->name); d->chart_family = strdupz(d->name); d->priority = NETDATA_CHART_PRIO_FIRST_NET_IFACE; @@ -485,14 +566,13 @@ int do_proc_net_dev(int update_every, usec_t dt) { static procfile *ff = NULL; static int enable_new_interfaces = -1; static int do_bandwidth = -1, do_packets = -1, do_errors = -1, do_drops = -1, do_fifo = -1, do_compressed = -1, - do_events = -1; + do_events = -1, do_speed = -1, do_duplex = -1, do_operstate = -1, do_carrier = -1, do_mtu = -1; static char *path_to_sys_devices_virtual_net = NULL, *path_to_sys_class_net_speed = NULL, *proc_net_dev_filename = NULL; static char *path_to_sys_class_net_duplex = NULL; static char *path_to_sys_class_net_operstate = NULL; - static long long int dt_to_refresh_speed = 0; - static long long int dt_to_refresh_duplex = 0; - static long long int dt_to_refresh_operstate = 0; + static char *path_to_sys_class_net_carrier = NULL; + static char *path_to_sys_class_net_mtu = NULL; if(unlikely(enable_new_interfaces == -1)) { char filename[FILENAME_MAX + 1]; @@ -512,6 +592,12 @@ int do_proc_net_dev(int update_every, usec_t dt) { snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/sys/class/net/%s/operstate"); path_to_sys_class_net_operstate = config_get(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "path to get net device operstate", filename); + snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/sys/class/net/%s/carrier"); + path_to_sys_class_net_carrier = config_get(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "path to get net device carrier", filename); + + snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/sys/class/net/%s/mtu"); + path_to_sys_class_net_mtu = config_get(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "path to get net device mtu", filename); + enable_new_interfaces = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "enable new interfaces detected at runtime", CONFIG_BOOLEAN_AUTO); @@ -522,19 +608,13 @@ int do_proc_net_dev(int update_every, usec_t dt) { do_fifo = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "fifo for all interfaces", CONFIG_BOOLEAN_AUTO); do_compressed = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "compressed packets for all interfaces", CONFIG_BOOLEAN_AUTO); do_events = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "frames, collisions, carrier counters for all interfaces", CONFIG_BOOLEAN_AUTO); + do_speed = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "speed for all interfaces", CONFIG_BOOLEAN_AUTO); + do_duplex = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "duplex for all interfaces", CONFIG_BOOLEAN_AUTO); + do_operstate = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "operstate for all interfaces", CONFIG_BOOLEAN_AUTO); + do_carrier = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "carrier for all interfaces", CONFIG_BOOLEAN_AUTO); + do_mtu = config_get_boolean_ondemand(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "mtu for all interfaces", CONFIG_BOOLEAN_AUTO); disabled_list = simple_pattern_create(config_get(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "disable by default interfaces matching", "lo fireqos* *-ifb"), NULL, SIMPLE_PATTERN_EXACT); - - dt_to_refresh_speed = config_get_number(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "refresh interface speed every seconds", 10) * USEC_PER_SEC; - dt_to_refresh_duplex = config_get_number(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "refresh interface duplex every seconds", 10) * USEC_PER_SEC; - dt_to_refresh_operstate = config_get_number(CONFIG_SECTION_PLUGIN_PROC_NETDEV, "refresh interface operstate every seconds", 10) * USEC_PER_SEC; - - if (dt_to_refresh_operstate < 0) - dt_to_refresh_operstate = 0; - if (dt_to_refresh_duplex < 0) - dt_to_refresh_duplex = 0; - if (dt_to_refresh_speed < 0) - dt_to_refresh_speed = 0; } if(unlikely(!ff)) { @@ -595,9 +675,16 @@ int do_proc_net_dev(int update_every, usec_t dt) { snprintfz(buffer, FILENAME_MAX, path_to_sys_class_net_duplex, d->name); d->filename_duplex = strdupz(buffer); } + snprintfz(buffer, FILENAME_MAX, path_to_sys_class_net_operstate, d->name); d->filename_operstate = strdupz(buffer); + snprintfz(buffer, FILENAME_MAX, path_to_sys_class_net_carrier, d->name); + d->filename_carrier = strdupz(buffer); + + snprintfz(buffer, FILENAME_MAX, path_to_sys_class_net_mtu, d->name); + d->filename_mtu = strdupz(buffer); + snprintfz(buffer, FILENAME_MAX, "plugin:proc:/proc/net/dev:%s", d->name); d->enabled = config_get_boolean_ondemand(buffer, "enabled", d->enabled); d->virtual = config_get_boolean(buffer, "virtual", d->virtual); @@ -612,6 +699,11 @@ int do_proc_net_dev(int update_every, usec_t dt) { d->do_fifo = config_get_boolean_ondemand(buffer, "fifo", do_fifo); d->do_compressed = config_get_boolean_ondemand(buffer, "compressed", do_compressed); d->do_events = config_get_boolean_ondemand(buffer, "events", do_events); + d->do_speed = config_get_boolean_ondemand(buffer, "speed", do_speed); + d->do_duplex = config_get_boolean_ondemand(buffer, "duplex", do_duplex); + d->do_operstate = config_get_boolean_ondemand(buffer, "operstate", do_operstate); + d->do_carrier = config_get_boolean_ondemand(buffer, "carrier", do_carrier); + d->do_mtu = config_get_boolean_ondemand(buffer, "mtu", do_mtu); } if(unlikely(!d->enabled)) @@ -659,6 +751,55 @@ int do_proc_net_dev(int update_every, usec_t dt) { d->tcarrier = str2kernel_uint_t(procfile_lineword(ff, l, 15)); } + if (d->do_duplex != CONFIG_BOOLEAN_NO && d->filename_duplex) { + char buffer[STATE_LENGTH_MAX + 1]; + + if (read_file(d->filename_duplex, buffer, STATE_LENGTH_MAX)) { + error("Cannot refresh interface %s duplex state by reading '%s'. I will stop updating it.", d->name, d->filename_duplex); + freez(d->filename_duplex); + d->filename_duplex = NULL; + } else { + // values can be unknown, half or full -- just check the first letter for speed + if (buffer[0] == 'f') + d->duplex = 2; + else if (buffer[0] == 'h') + d->duplex = 1; + else + d->duplex = 0; + } + } + + if(d->do_operstate != CONFIG_BOOLEAN_NO && d->filename_operstate) { + char buffer[STATE_LENGTH_MAX + 1], *trimmed_buffer; + + if (read_file(d->filename_operstate, buffer, STATE_LENGTH_MAX)) { + error( + "Cannot refresh %s operstate by reading '%s'. Will not update its status anymore.", + d->name, d->filename_operstate); + freez(d->filename_operstate); + d->filename_operstate = NULL; + } else { + trimmed_buffer = trim(buffer); + d->operstate = get_operstate(trimmed_buffer); + } + } + + if (d->do_carrier != CONFIG_BOOLEAN_NO && d->filename_carrier) { + if (read_single_number_file(d->filename_carrier, &d->carrier)) { + error("Cannot refresh interface %s carrier state by reading '%s'. Stop updating it.", d->name, d->filename_carrier); + freez(d->filename_carrier); + d->filename_carrier = NULL; + } + } + + if (d->do_mtu != CONFIG_BOOLEAN_NO && d->filename_mtu) { + if (read_single_number_file(d->filename_mtu, &d->mtu)) { + error("Cannot refresh mtu for interface %s by reading '%s'. Stop updating it.", d->name, d->filename_carrier); + freez(d->filename_carrier); + d->filename_carrier = NULL; + } + } + //info("PROC_NET_DEV: %s speed %zu, bytes %zu/%zu, packets %zu/%zu/%zu, errors %zu/%zu, drops %zu/%zu, fifo %zu/%zu, compressed %zu/%zu, rframe %zu, tcollisions %zu, tcarrier %zu" // , d->name, d->speed // , d->rbytes, d->tbytes @@ -715,102 +856,179 @@ int do_proc_net_dev(int update_every, usec_t dt) { // update the interface speed if(d->filename_speed) { - d->speed_last_collected_usec += dt; - - if(unlikely(d->speed_last_collected_usec >= (usec_t)dt_to_refresh_speed)) { - - if(unlikely(!d->chart_var_speed)) { - d->chart_var_speed = rrdsetvar_custom_chart_variable_create(d->st_bandwidth, "nic_speed_max"); - if(!d->chart_var_speed) { - error("Cannot create interface %s chart variable 'nic_speed_max'. Will not update its speed anymore.", d->name); - freez(d->filename_speed); - d->filename_speed = NULL; - } + if(unlikely(!d->chart_var_speed)) { + d->chart_var_speed = rrdsetvar_custom_chart_variable_create(d->st_bandwidth, "nic_speed_max"); + if(!d->chart_var_speed) { + error("Cannot create interface %s chart variable 'nic_speed_max'. Will not update its speed anymore.", d->name); + freez(d->filename_speed); + d->filename_speed = NULL; } + } - if(d->filename_speed && d->chart_var_speed) { - if(read_single_number_file(d->filename_speed, (unsigned long long *) &d->speed)) { - error("Cannot refresh interface %s speed by reading '%s'. Will not update its speed anymore.", d->name, d->filename_speed); - freez(d->filename_speed); - d->filename_speed = NULL; - } - else { - rrdsetvar_custom_chart_variable_set(d->chart_var_speed, (calculated_number) d->speed); - d->speed_last_collected_usec = 0; + if(d->filename_speed && d->chart_var_speed) { + if(read_single_number_file(d->filename_speed, (unsigned long long *) &d->speed)) { + error("Cannot refresh interface %s speed by reading '%s'. Will not update its speed anymore.", d->name, d->filename_speed); + freez(d->filename_speed); + d->filename_speed = NULL; + } + else { + rrdsetvar_custom_chart_variable_set(d->chart_var_speed, (calculated_number) d->speed * KILOBITS_IN_A_MEGABIT); + + if(d->do_speed != CONFIG_BOOLEAN_NO) { + if(unlikely(!d->st_speed)) { + d->st_speed = rrdset_create_localhost( + d->chart_type_net_speed + , d->chart_id_net_speed + , NULL + , d->chart_family + , "net.speed" + , "Interface Speed" + , "kilobits/s" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_NETDEV_NAME + , d->priority + 7 + , update_every + , RRDSET_TYPE_LINE + ); + + rrdset_flag_set(d->st_speed, RRDSET_FLAG_DETAIL); + + rrdset_update_labels(d->st_speed, d->chart_labels); + + d->rd_speed = rrddim_add(d->st_speed, "speed", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + else rrdset_next(d->st_speed); + + rrddim_set_by_pointer(d->st_speed, d->rd_speed, (collected_number)d->speed * KILOBITS_IN_A_MEGABIT); + rrdset_done(d->st_speed); } } } } + } - if (d->filename_duplex) { - d->duplex_last_collected_usec += dt; + // -------------------------------------------------------------------- - if (unlikely(d->duplex_last_collected_usec >= (usec_t)dt_to_refresh_duplex)) { - if (unlikely(!d->chart_var_duplex)) { - d->chart_var_duplex = rrdsetvar_custom_chart_variable_create(d->st_bandwidth, "duplex"); - if (!d->chart_var_duplex) { - error("Cannot create interface %s chart variable 'duplex'. Will not update the duplex status anymore.", d->name); - freez(d->filename_duplex); - d->filename_duplex = NULL; - } - } + if(d->do_duplex != CONFIG_BOOLEAN_NO && d->filename_duplex) { + if(unlikely(!d->st_duplex)) { + d->st_duplex = rrdset_create_localhost( + d->chart_type_net_duplex + , d->chart_id_net_duplex + , NULL + , d->chart_family + , "net.duplex" + , "Interface Duplex State" + , "state" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_NETDEV_NAME + , d->priority + 8 + , update_every + , RRDSET_TYPE_LINE + ); - if (d->filename_duplex && d->chart_var_duplex) { - char buffer[32 + 1]; - - if (read_file(d->filename_duplex, buffer, 32)) { - error("Cannot refresh interface %s duplex state by reading '%s'. I will stop updating it.", d->name, d->filename_duplex); - freez(d->filename_duplex); - d->filename_duplex = NULL; - } else { - // values can be unknown, half or full -- just check the first letter for speed - if (buffer[0] == 'f') - d->duplex = 2; - else if (buffer[0] == 'h') - d->duplex = 1; - else - d->duplex = 0; - - rrdsetvar_custom_chart_variable_set(d->chart_var_duplex, (calculated_number)d->duplex); - d->duplex_last_collected_usec = 0; - } - } - } + rrdset_flag_set(d->st_duplex, RRDSET_FLAG_DETAIL); + + rrdset_update_labels(d->st_duplex, d->chart_labels); + + d->rd_duplex = rrddim_add(d->st_duplex, "duplex", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); } + else rrdset_next(d->st_duplex); - if (d->filename_operstate) { - d->operstate_last_collected_usec += dt; - - if (unlikely(d->operstate_last_collected_usec >= (usec_t)dt_to_refresh_operstate)) { - if (unlikely(!d->chart_var_operstate)) { - d->chart_var_operstate = rrdsetvar_custom_chart_variable_create(d->st_bandwidth, "operstate"); - if (!d->chart_var_operstate) { - error( - "Cannot create interface %s chart variable 'operstate'. I will stop updating it.", - d->name); - freez(d->filename_operstate); - d->filename_operstate = NULL; - } - } + rrddim_set_by_pointer(d->st_duplex, d->rd_duplex, (collected_number)d->duplex); + rrdset_done(d->st_duplex); + } - if (d->filename_operstate && d->chart_var_operstate) { - char buffer[32 + 1], *trimmed_buffer; - - if (read_file(d->filename_operstate, buffer, 32)) { - error( - "Cannot refresh %s operstate by reading '%s'. Will not update its status anymore.", - d->name, d->filename_operstate); - freez(d->filename_operstate); - d->filename_operstate = NULL; - } else { - trimmed_buffer = trim(buffer); - d->operstate = get_operstate(trimmed_buffer); - rrdsetvar_custom_chart_variable_set(d->chart_var_operstate, (calculated_number)d->operstate); - d->operstate_last_collected_usec = 0; - } - } - } + // -------------------------------------------------------------------- + + if(d->do_operstate != CONFIG_BOOLEAN_NO && d->filename_operstate) { + if(unlikely(!d->st_operstate)) { + d->st_operstate = rrdset_create_localhost( + d->chart_type_net_operstate + , d->chart_id_net_operstate + , NULL + , d->chart_family + , "net.operstate" + , "Interface Operational State" + , "state" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_NETDEV_NAME + , d->priority + 9 + , update_every + , RRDSET_TYPE_LINE + ); + + rrdset_flag_set(d->st_operstate, RRDSET_FLAG_DETAIL); + + rrdset_update_labels(d->st_operstate, d->chart_labels); + + d->rd_operstate = rrddim_add(d->st_operstate, "state", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + else rrdset_next(d->st_operstate); + + rrddim_set_by_pointer(d->st_operstate, d->rd_operstate, (collected_number)d->operstate); + rrdset_done(d->st_operstate); + } + + // -------------------------------------------------------------------- + + if(d->do_carrier != CONFIG_BOOLEAN_NO && d->filename_carrier) { + if(unlikely(!d->st_carrier)) { + d->st_carrier = rrdset_create_localhost( + d->chart_type_net_carrier + , d->chart_id_net_carrier + , NULL + , d->chart_family + , "net.carrier" + , "Inteface Physical Link State" + , "state" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_NETDEV_NAME + , d->priority + 10 + , update_every + , RRDSET_TYPE_LINE + ); + + rrdset_flag_set(d->st_carrier, RRDSET_FLAG_DETAIL); + + rrdset_update_labels(d->st_carrier, d->chart_labels); + + d->rd_carrier = rrddim_add(d->st_carrier, "carrier", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); } + else rrdset_next(d->st_carrier); + + rrddim_set_by_pointer(d->st_carrier, d->rd_carrier, (collected_number)d->carrier); + rrdset_done(d->st_carrier); + } + + // -------------------------------------------------------------------- + + if(d->do_mtu != CONFIG_BOOLEAN_NO && d->filename_mtu) { + if(unlikely(!d->st_mtu)) { + d->st_mtu = rrdset_create_localhost( + d->chart_type_net_mtu + , d->chart_id_net_mtu + , NULL + , d->chart_family + , "net.mtu" + , "Interface MTU" + , "octets" + , PLUGIN_PROC_NAME + , PLUGIN_PROC_MODULE_NETDEV_NAME + , d->priority + 11 + , update_every + , RRDSET_TYPE_LINE + ); + + rrdset_flag_set(d->st_mtu, RRDSET_FLAG_DETAIL); + + rrdset_update_labels(d->st_mtu, d->chart_labels); + + d->rd_mtu = rrddim_add(d->st_mtu, "mtu", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + else rrdset_next(d->st_mtu); + + rrddim_set_by_pointer(d->st_mtu, d->rd_mtu, (collected_number)d->mtu); + rrdset_done(d->st_mtu); } // -------------------------------------------------------------------- diff --git a/collectors/proc.plugin/proc_self_mountinfo.c b/collectors/proc.plugin/proc_self_mountinfo.c index 3f17ccce2..ca00f8a89 100644 --- a/collectors/proc.plugin/proc_self_mountinfo.c +++ b/collectors/proc.plugin/proc_self_mountinfo.c @@ -47,11 +47,17 @@ // find the mount info with the given major:minor // in the supplied linked list of mountinfo structures -struct mountinfo *mountinfo_find(struct mountinfo *root, unsigned long major, unsigned long minor) { +struct mountinfo *mountinfo_find(struct mountinfo *root, unsigned long major, unsigned long minor, char *device) { struct mountinfo *mi; + uint32_t hash = simple_hash(device); + for(mi = root; mi ; mi = mi->next) - if(unlikely(mi->major == major && mi->minor == minor)) + if (unlikely( + mi->major == major && + mi->minor == minor && + mi->mount_source_name_hash == hash && + !strcmp(mi->mount_source_name, device))) return mi; return NULL; @@ -120,6 +126,7 @@ static void mountinfo_free(struct mountinfo *mi) { */ freez(mi->filesystem); freez(mi->mount_source); + freez(mi->mount_source_name); freez(mi->super_options); freez(mi); } @@ -273,6 +280,9 @@ struct mountinfo *mountinfo_read(int do_statvfs) { mi->mount_source = strdupz_decoding_octal(procfile_lineword(ff, l, w)); w++; mi->mount_source_hash = simple_hash(mi->mount_source); + mi->mount_source_name = strdupz(basename(mi->mount_source)); + mi->mount_source_name_hash = simple_hash(mi->mount_source_name); + mi->super_options = strdupz(procfile_lineword(ff, l, w)); w++; if(unlikely(is_read_only(mi->super_options))) @@ -316,6 +326,9 @@ struct mountinfo *mountinfo_read(int do_statvfs) { mi->mount_source = NULL; mi->mount_source_hash = 0; + mi->mount_source_name = NULL; + mi->mount_source_name_hash = 0; + mi->super_options = NULL; mi->st_dev = 0; diff --git a/collectors/proc.plugin/proc_self_mountinfo.h b/collectors/proc.plugin/proc_self_mountinfo.h index 15d63c786..92918a73d 100644 --- a/collectors/proc.plugin/proc_self_mountinfo.h +++ b/collectors/proc.plugin/proc_self_mountinfo.h @@ -38,6 +38,9 @@ struct mountinfo { char *mount_source; // mount source: filesystem-specific information or "none". uint32_t mount_source_hash; + char *mount_source_name; + uint32_t mount_source_name_hash; + char *super_options; // super options: per-superblock options. uint32_t flags; @@ -47,11 +50,11 @@ struct mountinfo { struct mountinfo *next; }; -extern struct mountinfo *mountinfo_find(struct mountinfo *root, unsigned long major, unsigned long minor); +extern struct mountinfo *mountinfo_find(struct mountinfo *root, unsigned long major, unsigned long minor, char *device); extern struct mountinfo *mountinfo_find_by_filesystem_mount_source(struct mountinfo *root, const char *filesystem, const char *mount_source); extern struct mountinfo *mountinfo_find_by_filesystem_super_option(struct mountinfo *root, const char *filesystem, const char *super_options); extern void mountinfo_free_all(struct mountinfo *mi); extern struct mountinfo *mountinfo_read(int do_statvfs); -#endif /* NETDATA_PROC_SELF_MOUNTINFO_H */ \ No newline at end of file +#endif /* NETDATA_PROC_SELF_MOUNTINFO_H */ diff --git a/collectors/python.d.plugin/README.md b/collectors/python.d.plugin/README.md index a05bc81dd..312986e48 100644 --- a/collectors/python.d.plugin/README.md +++ b/collectors/python.d.plugin/README.md @@ -84,7 +84,12 @@ If you plan to submit the module in a PR, make sure and go through the [PR check For a quick start, you can look at the [example plugin](https://raw.githubusercontent.com/netdata/netdata/master/collectors/python.d.plugin/example/example.chart.py). -**Note**: If you are working 'locally' on a new collector and would like to run it in an already installed and running Netdata (as opposed to having to install Netdata from source again with your new changes) to can copy over the relevant file to where Netdata expects it and then either `sudo service netdata restart` to have it be picked up and used by Netdata or you can just run the updated collector in debug mode by following a process like below (this assumes you have [installed Netdata from a GitHub fork](https://learn.netdata.cloud/docs/agent/packaging/installer/methods/manual) you have made to do your development on). +**Note**: If you are working 'locally' on a new collector and would like to run it in an already installed and running +Netdata (as opposed to having to install Netdata from source again with your new changes) to can copy over the relevant +file to where Netdata expects it and then either `sudo systemctl restart netdata` to have it be picked up and used by +Netdata or you can just run the updated collector in debug mode by following a process like below (this assumes you have +[installed Netdata from a GitHub fork](https://learn.netdata.cloud/docs/agent/packaging/installer/methods/manual) you +have made to do your development on). ```bash # clone your fork (done once at the start but shown here for clarity) diff --git a/collectors/python.d.plugin/adaptec_raid/README.md b/collectors/python.d.plugin/adaptec_raid/README.md index b14e8f9ba..4e99508b3 100644 --- a/collectors/python.d.plugin/adaptec_raid/README.md +++ b/collectors/python.d.plugin/adaptec_raid/README.md @@ -60,8 +60,8 @@ cd /etc/netdata # Replace this path with your Netdata config directory, if dif sudo ./edit-config python.d.conf ``` -Change the value of the `adaptec_raid` setting to `yes`. Save the file and restart the Netdata Agent -with `sudo systemctl restart netdata`, or the appropriate method for your system. +Change the value of the `adaptec_raid` setting to `yes`. Save the file and restart the Netdata Agent with `sudo +systemctl restart netdata`, or the [appropriate method](/docs/configure/start-stop-restart.md) for your system. ## Configuration diff --git a/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py index 564c2ce87..bb59d88e1 100644 --- a/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py +++ b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py @@ -23,20 +23,22 @@ ORDER = [ CHARTS = { 'ld_status': { - 'options': [None, 'Status Is Not OK', 'bool', 'logical devices', 'adapter_raid.ld_status', 'line'], + 'options': [None, 'Status of logical devices (1: Failed or Degraded)', 'bool', 'logical devices', + 'adaptec_raid.ld_status', 'line'], 'lines': [] }, 'pd_state': { - 'options': [None, 'State Is Not OK', 'bool', 'physical devices', 'adapter_raid.pd_state', 'line'], + 'options': [None, 'State of physical devices (1: not Online)', 'bool', 'physical devices', + 'adaptec_raid.pd_state', 'line'], 'lines': [] }, 'pd_smart_warnings': { 'options': [None, 'S.M.A.R.T warnings', 'count', 'physical devices', - 'adapter_raid.smart_warnings', 'line'], + 'adaptec_raid.smart_warnings', 'line'], 'lines': [] }, 'pd_temperature': { - 'options': [None, 'Temperature', 'celsius', 'physical devices', 'adapter_raid.temperature', 'line'], + 'options': [None, 'Temperature', 'celsius', 'physical devices', 'adaptec_raid.temperature', 'line'], 'lines': [] }, } diff --git a/collectors/python.d.plugin/alarms/README.md b/collectors/python.d.plugin/alarms/README.md index ea96061cc..3f2a8176e 100644 --- a/collectors/python.d.plugin/alarms/README.md +++ b/collectors/python.d.plugin/alarms/README.md @@ -23,7 +23,7 @@ Below is an example of the chart produced when running `stress-ng --all 2` for a ## Configuration -Enable the collector and restart Netdata. +Enable the collector and [restart Netdata](/docs/configure/start-stop-restart.md). ```bash cd /etc/netdata/ @@ -51,6 +51,8 @@ local: CLEAR: 0 WARNING: 1 CRITICAL: 2 + # set to true to include a chart with calculated alarm values over time + collect_alarm_values: false ``` It will default to pulling all alarms at each time step from the Netdata rest api at `http://127.0.0.1:19999/api/v1/alarms?all` diff --git a/collectors/python.d.plugin/alarms/alarms.chart.py b/collectors/python.d.plugin/alarms/alarms.chart.py index 973a1f382..1eec40450 100644 --- a/collectors/python.d.plugin/alarms/alarms.chart.py +++ b/collectors/python.d.plugin/alarms/alarms.chart.py @@ -11,36 +11,44 @@ update_every = 10 disabled_by_default = True -def charts_template(sm): +def charts_template(sm, alarm_status_chart_type='line'): order = [ 'alarms', + 'values' ] mappings = ', '.join(['{0}={1}'.format(k, v) for k, v in sm.items()]) charts = { 'alarms': { - 'options': [None, 'Alarms ({0})'.format(mappings), 'status', 'alarms', 'alarms.status', 'line'], + 'options': [None, 'Alarms ({0})'.format(mappings), 'status', 'status', 'alarms.status', alarm_status_chart_type], 'lines': [], 'variables': [ ['alarms_num'], ] + }, + 'values': { + 'options': [None, 'Alarm Values', 'value', 'value', 'alarms.value', 'line'], + 'lines': [], } } return order, charts DEFAULT_STATUS_MAP = {'CLEAR': 0, 'WARNING': 1, 'CRITICAL': 2} - DEFAULT_URL = 'http://127.0.0.1:19999/api/v1/alarms?all' +DEFAULT_COLLECT_ALARM_VALUES = False +DEFAULT_ALARM_STATUS_CHART_TYPE = 'line' class Service(UrlService): def __init__(self, configuration=None, name=None): UrlService.__init__(self, configuration=configuration, name=name) self.sm = self.configuration.get('status_map', DEFAULT_STATUS_MAP) - self.order, self.definitions = charts_template(self.sm) + self.alarm_status_chart_type = self.configuration.get('alarm_status_chart_type', DEFAULT_ALARM_STATUS_CHART_TYPE) + self.order, self.definitions = charts_template(self.sm, self.alarm_status_chart_type) self.url = self.configuration.get('url', DEFAULT_URL) - self.collected_alarms = set() + self.collect_alarm_values = bool(self.configuration.get('collect_alarm_values', DEFAULT_COLLECT_ALARM_VALUES)) + self.collected_dims = {'alarms': set(), 'values': set()} def _get_data(self): raw_data = self._get_raw_data() @@ -51,21 +59,26 @@ class Service(UrlService): alarms = raw_data.get('alarms', {}) data = {a: self.sm[alarms[a]['status']] for a in alarms if alarms[a]['status'] in self.sm} - self.update_charts(alarms, data) + self.update_charts('alarms', data) data['alarms_num'] = len(data) + if self.collect_alarm_values: + data_values = {'{}_value'.format(a): alarms[a]['value'] * 100 for a in alarms if 'value' in alarms[a] and alarms[a]['value'] is not None} + self.update_charts('values', data_values, divisor=100) + data.update(data_values) + return data - def update_charts(self, alarms, data): + def update_charts(self, chart, data, algorithm='absolute', multiplier=1, divisor=1): if not self.charts: return - for a in data: - if a not in self.collected_alarms: - self.collected_alarms.add(a) - self.charts['alarms'].add_dimension([a, a, 'absolute', '1', '1']) + for dim in data: + if dim not in self.collected_dims[chart]: + self.collected_dims[chart].add(dim) + self.charts[chart].add_dimension([dim, dim, algorithm, multiplier, divisor]) - for a in list(self.collected_alarms): - if a not in alarms: - self.collected_alarms.remove(a) - self.charts['alarms'].del_dimension(a, hide=False) + for dim in list(self.collected_dims[chart]): + if dim not in data: + self.collected_dims[chart].remove(dim) + self.charts[chart].del_dimension(dim, hide=False) diff --git a/collectors/python.d.plugin/alarms/alarms.conf b/collectors/python.d.plugin/alarms/alarms.conf index fd7780c59..5e83d8f56 100644 --- a/collectors/python.d.plugin/alarms/alarms.conf +++ b/collectors/python.d.plugin/alarms/alarms.conf @@ -48,3 +48,7 @@ local: CLEAR: 0 WARNING: 1 CRITICAL: 2 + # set to true to include a chart with calculated alarm values over time + collect_alarm_values: false + # define the type of chart for plotting status over time e.g. 'line' or 'stacked' + alarm_status_chart_type: 'line' diff --git a/collectors/python.d.plugin/anomalies/README.md b/collectors/python.d.plugin/anomalies/README.md index 862f4f345..bcbfdbcd7 100644 --- a/collectors/python.d.plugin/anomalies/README.md +++ b/collectors/python.d.plugin/anomalies/README.md @@ -45,7 +45,8 @@ pip3 install --user netdata-pandas==0.0.32 numba==0.50.1 scikit-learn==0.23.2 py ## Configuration -Install the Python requirements above, enable the collector and restart Netdata. +Install the Python requirements above, enable the collector and [restart +Netdata](/docs/configure/start-stop-restart.md). ```bash cd /etc/netdata/ diff --git a/collectors/python.d.plugin/chrony/README.md b/collectors/python.d.plugin/chrony/README.md index b1e7ec35c..4681b4f6d 100644 --- a/collectors/python.d.plugin/chrony/README.md +++ b/collectors/python.d.plugin/chrony/README.md @@ -55,7 +55,7 @@ local: command: 'chronyc -n tracking' ``` -Save the file and restart the Netdata Agent with `sudo systemctl restart netdata`, or the appropriate method for your -system, to finish configuring the `chrony` collector. +Save the file and restart the Netdata Agent with `sudo systemctl restart netdata`, or the [appropriate +method](/docs/configure/start-stop-restart.md) for your system, to finish configuring the `chrony` collector. [![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fcollectors%2Fpython.d.plugin%2Fchrony%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/collectors/python.d.plugin/example/example.chart.py b/collectors/python.d.plugin/example/example.chart.py index 61ae47f22..d6c0b6658 100644 --- a/collectors/python.d.plugin/example/example.chart.py +++ b/collectors/python.d.plugin/example/example.chart.py @@ -29,6 +29,9 @@ class Service(SimpleService): self.order = ORDER self.definitions = CHARTS self.random = SystemRandom() + self.num_lines = self.configuration.get('num_lines', 4) + self.lower = self.configuration.get('lower', 0) + self.upper = self.configuration.get('upper', 100) @staticmethod def check(): @@ -37,12 +40,12 @@ class Service(SimpleService): def get_data(self): data = dict() - for i in range(1, 4): + for i in range(0, self.num_lines): dimension_id = ''.join(['random', str(i)]) if dimension_id not in self.charts['random']: self.charts['random'].add_dimension([dimension_id]) - data[dimension_id] = self.random.randint(0, 100) + data[dimension_id] = self.random.randint(self.lower, self.upper) return data diff --git a/collectors/python.d.plugin/example/example.conf b/collectors/python.d.plugin/example/example.conf index 3d8435173..31261b840 100644 --- a/collectors/python.d.plugin/example/example.conf +++ b/collectors/python.d.plugin/example/example.conf @@ -51,7 +51,7 @@ # predefined parameters. These are: # # job_name: -# name: myname # the JOB's name as it will appear at the +# name: myname # the JOB's name as it will appear on the dashboard # # dashboard (by default is the job_name) # # JOBs sharing a name are mutually exclusive # update_every: 1 # the JOB's data collection frequency @@ -61,8 +61,27 @@ # # Additionally to the above, example also supports the following: # -# - none +# num_lines: 4 # the number of lines to create +# lower: 0 # the lower bound of numbers to randomly sample from +# upper: 100 # the upper bound of numbers to randomly sample from # # ---------------------------------------------------------------------- # AUTO-DETECTION JOBS -# only one of them will run (they have the same name) + +four_lines: + name: "Four Lines" # the JOB's name as it will appear on the dashboard + update_every: 1 # the JOB's data collection frequency + priority: 60000 # the JOB's order on the dashboard + penalty: yes # the JOB's penalty + autodetection_retry: 0 # the JOB's re-check interval in seconds + num_lines: 4 # the number of lines to create + lower: 0 # the lower bound of numbers to randomly sample from + upper: 100 # the upper bound of numbers to randomly sample from + +# if you wanted to make another job to run in addition to the one above then +# you would just uncomment the job configuration below. +# two_lines: +# name: "Two Lines" # the JOB's name as it will appear on the dashboard +# num_lines: 2 # the number of lines to create +# lower: 50 # the lower bound of numbers to randomly sample from +# upper: 75 # the upper bound of numbers to randomly sample from diff --git a/collectors/python.d.plugin/hpssa/README.md b/collectors/python.d.plugin/hpssa/README.md index af8c4378e..69c8d8a33 100644 --- a/collectors/python.d.plugin/hpssa/README.md +++ b/collectors/python.d.plugin/hpssa/README.md @@ -59,8 +59,8 @@ cd /etc/netdata # Replace this path with your Netdata config directory, if dif sudo ./edit-config python.d.conf ``` -Change the value of the `hpssa` setting to `yes`. Save the file and restart the Netdata Agent -with `sudo systemctl restart netdata`, or the appropriate method for your system. +Change the value of the `hpssa` setting to `yes`. Save the file and restart the Netdata Agent with `sudo systemctl +restart netdata`, or the [appropriate method](/docs/configure/start-stop-restart.md) for your system. ## Configuration @@ -78,4 +78,7 @@ If `ssacli` cannot be found in the `PATH`, configure it in `hpssa.conf`. ssacli_path: /usr/sbin/ssacli ``` +Save the file and restart the Netdata Agent with `sudo systemctl restart netdata`, or the [appropriate +method](/docs/configure/start-stop-restart.md) for your system. + [![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fcollectors%2Fpython.d.plugin%2Fhpssa%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)]() diff --git a/collectors/python.d.plugin/megacli/README.md b/collectors/python.d.plugin/megacli/README.md index 4fb7eb1c2..e411c4c11 100644 --- a/collectors/python.d.plugin/megacli/README.md +++ b/collectors/python.d.plugin/megacli/README.md @@ -80,6 +80,7 @@ Battery stats disabled by default. To enable them, modify `megacli.conf`. do_battery: yes ``` ---- +Save the file and restart the Netdata Agent with `sudo systemctl restart netdata`, or the [appropriate +method](/docs/configure/start-stop-restart.md) for your system. [![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fcollectors%2Fpython.d.plugin%2Fmegacli%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/collectors/python.d.plugin/samba/README.md b/collectors/python.d.plugin/samba/README.md index a5126510f..04cb7dcf7 100644 --- a/collectors/python.d.plugin/samba/README.md +++ b/collectors/python.d.plugin/samba/README.md @@ -103,8 +103,8 @@ cd /etc/netdata # Replace this path with your Netdata config directory, if dif sudo ./edit-config python.d.conf ``` -Change the value of the `samba` setting to `yes`. Save the file and restart the Netdata Agent -with `sudo systemctl restart netdata`, or the appropriate method for your system. +Change the value of the `samba` setting to `yes`. Save the file and restart the Netdata Agent with `sudo systemctl +restart netdata`, or the [appropriate method](/docs/configure/start-stop-restart.md) for your system. ## Configuration diff --git a/collectors/python.d.plugin/smartd_log/smartd_log.chart.py b/collectors/python.d.plugin/smartd_log/smartd_log.chart.py index 8f10a5351..e4a19d411 100644 --- a/collectors/python.d.plugin/smartd_log/smartd_log.chart.py +++ b/collectors/python.d.plugin/smartd_log/smartd_log.chart.py @@ -49,6 +49,7 @@ ATTR198 = '198' ATTR199 = '199' ATTR202 = '202' ATTR206 = '206' +ATTR233 = '233' ATTR_READ_ERR_COR = 'read-total-err-corrected' ATTR_READ_ERR_UNC = 'read-total-unc-errors' ATTR_WRITE_ERR_COR = 'write-total-err-corrected' @@ -111,6 +112,7 @@ ORDER = [ 'current_pending_sector_count', 'offline_uncorrectable_sector_count', 'percent_lifetime_used', + 'media_wearout_indicator', ] CHARTS = { @@ -322,6 +324,12 @@ CHARTS = { 'lines': [], 'attrs': [ATTR202], 'algo': ABSOLUTE, + }, + 'media_wearout_indicator': { + 'options': [None, 'Media Wearout Indicator', 'percentage', 'wear', 'smartd_log.media_wearout_indicator', 'line'], + 'lines': [], + 'attrs': [ATTR233], + 'algo': ABSOLUTE, } } @@ -506,6 +514,7 @@ def ata_attribute_factory(value): ATTR7, ATTR202, ATTR206, + ATTR233, ]: return AtaNormalized(*value) diff --git a/collectors/statsd.plugin/Makefile.am b/collectors/statsd.plugin/Makefile.am index b01302d16..71f2d468d 100644 --- a/collectors/statsd.plugin/Makefile.am +++ b/collectors/statsd.plugin/Makefile.am @@ -10,6 +10,7 @@ dist_noinst_DATA = \ statsdconfigdir=$(libconfigdir)/statsd.d dist_statsdconfig_DATA = \ example.conf \ + k6.conf \ $(NULL) userstatsdconfigdir=$(configdir)/statsd.d diff --git a/collectors/statsd.plugin/README.md b/collectors/statsd.plugin/README.md index 070bfc554..0e9c954fc 100644 --- a/collectors/statsd.plugin/README.md +++ b/collectors/statsd.plugin/README.md @@ -1,6 +1,6 @@ @@ -10,7 +10,6 @@ StatsD is a system to collect data from any application. Applications send metri If you want to learn more about the StatsD protocol, we have written a [blog post](https://www.netdata.cloud/blog/introduction-to-statsd/) about it! -There is a [plethora of client libraries](https://github.com/etsy/statsd/wiki#client-implementations) for embedding statsd metrics to any application framework. This makes statsd quite popular for custom application metrics. Netdata is a fully featured statsd server. It can collect statsd formatted metrics, visualize them on its dashboards and store them in it's database for long-term retention. @@ -22,11 +21,11 @@ Netdata statsd is fast. It can collect more than **1.200.000 metrics per second* ## Metrics supported by Netdata -Netdata fully supports the statsd protocol. All statsd client libraries can be used with Netdata too. +Netdata fully supports the StatsD protocol. All StatsD client libraries can be used with Netdata too. - **Gauges** - The application sends `name:value|g`, where `value` is any **decimal/fractional** number, statsd reports the latest value collected and the number of times it was updated (events). + The application sends `name:value|g`, where `value` is any **decimal/fractional** number, StatsD reports the latest value collected and the number of times it was updated (events). The application may increment or decrement a previous value, by setting the first character of the value to `+` or `-` (so, the only way to set a gauge to an absolute negative value, is to first set it to zero). @@ -36,11 +35,11 @@ Netdata fully supports the statsd protocol. All statsd client libraries can be u - **Counters** and **Meters** - The application sends `name:value|c`, `name:value|C` or `name:value|m`, where `value` is a positive or negative **integer** number of events occurred, statsd reports the **rate** and the number of times it was updated (events). + The application sends `name:value|c`, `name:value|C` or `name:value|m`, where `value` is a positive or negative **integer** number of events occurred, StatsD reports the **rate** and the number of times it was updated (events). - `:value` can be omitted and statsd will assume it is `1`. `|c`, `|C` and `|m` can be omitted an statsd will assume it is `|m`. So, the application may send just `name` and statsd will parse it as `name:1|m`. + `:value` can be omitted and StatsD will assume it is `1`. `|c`, `|C` and `|m` can be omitted an StatsD will assume it is `|m`. So, the application may send just `name` and StatsD will parse it as `name:1|m`. - - Counters use `|c` (etsy/statsd compatible) or `|C` (brubeck compatible) + - Counters use `|c` (etsy/StatsD compatible) or `|C` (brubeck compatible) - Meters use `|m` [Sampling rate](#sampling-rates) is supported. @@ -49,7 +48,7 @@ Netdata fully supports the statsd protocol. All statsd client libraries can be u - **Timers** and **Histograms** - The application sends `name:value|ms` or `name:value|h`, where `value` is any **decimal/fractional** number, statsd reports **min**, **max**, **average**, **sum**, **95th percentile**, **median** and **standard deviation** and the total number of times it was updated (events). + The application sends `name:value|ms` or `name:value|h`, where `value` is any **decimal/fractional** number, StatsD reports **min**, **max**, **average**, **sum**, **95th percentile**, **median** and **standard deviation** and the total number of times it was updated (events). - Timers use `|ms` - Histograms use `|h` @@ -62,7 +61,7 @@ Netdata fully supports the statsd protocol. All statsd client libraries can be u - **Sets** - The application sends `name:value|s`, where `value` is anything (**number or text**, leading and trailing spaces are removed), statsd reports the number of unique values sent and the number of times it was updated (events). + The application sends `name:value|s`, where `value` is anything (**number or text**, leading and trailing spaces are removed), StatsD reports the number of unique values sent and the number of times it was updated (events). Sampling rate is **not** supported for Sets. `value` is always considered text. @@ -88,7 +87,7 @@ On disconnect, Netdata will process the entire buffer, even if it is not termina #### UDP packets -When sending multiple packets over UDP, it is important not to exceed the network MTU, usually about 1500 packets. +When sending multiple packets over UDP, it is important not to exceed the network MTU, which is usually 1500 bytes. Netdata will accept UDP packets up to 9000 bytes, but the underlying network will not exceed MTU. @@ -152,7 +151,7 @@ Netdata can visualize StatsD collected metrics in 2 ways: ### Private metric charts -Private charts are controlled with `create private charts for metrics matching = *`. This setting accepts a space separated list of [simple patterns](/libnetdata/simple_pattern/README.md). Netdata will create private charts for all metrics **by default** +Private charts are controlled with `create private charts for metrics matching = *`. This setting accepts a space-separated list of [simple patterns](/libnetdata/simple_pattern/README.md). Netdata will create private charts for all metrics **by default**. For example, to render charts for all `myapp.*` metrics, except `myapp.*.badmetric`, use: @@ -166,7 +165,8 @@ The default behavior is to use the same settings as the rest of the Netdata Agen - `private charts memory mode` - `private charts history` -### Optimise private metric charts visualization and storage +### Optimize private metric charts visualization and storage + If you have thousands of metrics, each with its own private chart, you may notice that your web browser becomes slow when you view the Netdata dashboard (this is a web browser issue we need to address at the Netdata UI). So, Netdata has a protection to stop creating charts when `max private charts allowed = 200` (soft limit) is reached. @@ -246,16 +246,15 @@ Synthetic charts are organized in For each application you need to create a `.conf` file in `/etc/netdata/statsd.d`. -For example, if you want to monitor the application `myapp` using StatD and Netdata, create the file `/etc/netdata/statsd.d/myapp.conf`, with this content: - +For example, if you want to monitor the application `myapp` using StatsD and Netdata, create the file `/etc/netdata/statsd.d/myapp.conf`, with this content: ``` [app] name = myapp metrics = myapp.* private charts = no gaps when not collected = no - memory mode = ram history = 60 +# memory mode = ram [dictionary] m1 = metric1 @@ -283,8 +282,9 @@ Using the above configuration `myapp` should get its own section on the dashboar - `metrics` is a Netdata [simple pattern](/libnetdata/simple_pattern/README.md). This pattern should match all the possible StatsD metrics that will be participating in the application `myapp`. - `private charts = yes|no`, enables or disables private charts for the metrics matched. - `gaps when not collected = yes|no`, enables or disables gaps on the charts of the application in case that no metrics are collected. -- `memory mode` sets the memory mode for all charts of the application. The default is the global default for Netdata (not the global default for StatsD private charts). -- `history` sets the size of the round robin database for this application. The default is the global default for Netdata (not the global default for StatsD private charts). This is only relevant if you use `memory mode = save`. Read more on our guide: [longer metrics storage](https://learn.netdata.cloud/guides/longer-metrics-storage). +- `memory mode` sets the memory mode for all charts of the application. The default is the global default for Netdata (not the global default for StatsD private charts). We suggest not to use this (we have commented it out in the example) and let your app use the global default for Netdata, which is our dbengine. + +- `history` sets the size of the round robin database for this application. The default is the global default for Netdata (not the global default for StatsD private charts). This is only relevant if you use `memory mode = save`. Read more on our [metrics storage(]/docs/store/change-metrics-storage.md) doc. `[dictionary]` defines name-value associations. These are used to renaming metrics, when added to synthetic charts. Metric names are also defined at each `dimension` line. However, using the dictionary dimension names can be declared globally, for each app and is the only way to rename dimensions when using patterns. Of course the dictionary can be empty or missing. @@ -526,7 +526,7 @@ You can also use StatsD with: ### Shell -Getting the proper support for a programming language is not always easy, but shell is always available on most UNIX systems. You can use shell and `nc` to easily instrument your systems and send metric data to Netdata StatsD. Here is how: +Getting the proper support for a programming language is not always easy, but the Unix shell is available on most Unix systems. You can use shell and `nc` to instrument your systems and send metric data to Netdata's StatsD implementation. Here's how: The command you need to run is: @@ -600,6 +600,6 @@ StatsD "metric1:10|g" "metric2:10|c" ... ``` The function is smart enough to call `nc` just once and pass all the metrics to it. It will also automatically switch to TCP if the metrics to send are above 1000 bytes. -If you have gotten thus far, make sure to check out our [Community Forums](https://community.netdata.cloud) to share your experience using Netdata with StatsD. +If you have gotten thus far, make sure to check out our [community forums](https://community.netdata.cloud) to share your experience using Netdata with StatsD. [![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fcollectors%2Fstatsd.plugin%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>) diff --git a/collectors/statsd.plugin/k6.conf b/collectors/statsd.plugin/k6.conf new file mode 100644 index 000000000..775f53060 --- /dev/null +++ b/collectors/statsd.plugin/k6.conf @@ -0,0 +1,104 @@ +[app] + name = k6 + metrics = k6* + private charts = no + gaps when not collected = yes + +[dictionary] + http_reqs = HTTP Requests + vus = Virtual active users + vus_max = max Virtual active users + iteration_duration = iteration duration + iteration_duration_max = max iteration duration + iteration_duration_min = min iteration duration + iteration_duration_avg = avg iteration duration + dropped_iterations = Dropped iterations + http_req_blocked = Blocked HTTP requests + http_req_connecting = Connecting HTTP requests + http_req_sending = Sending HTTP requests + http_req_receiving = Receiving HTTP requests + http_req_waiting = Waiting HTTP requests + http_req_duration_median = Median HTTP req duration + http_req_duration_average = AVG HTTP req duration + http_req_duration = HTTP req duration + http_req_duration_max = max HTTP req duration + http_req_duration_min = min HTTP req duration + http_req_duration_p95 = 95 percentile of HTTP req duration + data_received = Received data + data_sent = Sent data + + +[http_reqs] + name = http_reqs + title = HTTP Requests + family = http requests + context = k6.http_requests + dimension = k6.http_reqs http_reqs last 1 1 sum + type = line + units = requests/s + +[vus] + name = vus + title = Virtual Active Users + family = k6_metrics + dimension = k6.vus vus last 1 1 + dimension = k6.vus_max vus_max last 1 1 + type = line + units = vus + +[iteration_duration] + name = iteration_duration_2 + title = Iteration duration + family = k6_metrics + dimension = k6.iteration_duration iteration_duration last 1 1 + dimension = k6.iteration_duration iteration_duration_max max 1 1 + dimension = k6.iteration_duration iteration_duration_min min 1 1 + dimension = k6.iteration_duration iteration_duration_avg avg 1 1 + type = line + units = s + +[dropped_iterations] + name = dropped_iterations + title = Dropped Iterations + family = k6_metrics + dimension = k6.dropped_iterations dropped_iterations last 1 1 + units = iterations + type = line + +[data] + name = data + title = K6 Data + family = k6_metrics + dimension = k6.data_received data_received last 1 1 + dimension = k6.data_sent data_sent last -1 1 + units = kb/s + type = area + +[http_req_status] + name = http_req_status + title = Time spent on HTTP + family = http requests + dimension = k6.http_req_blocked http_req_blocked last 1 1 + dimension = k6.http_req_connecting http_req_connecting last 1 1 + units = ms + type = line + +[http_req_duration_types] + name = http_req_duration_types + title = Time spent on HTTP connection states + family = http requests + dimension = k6.http_req_sending http_req_sending last 1 1 + dimension = k6.http_req_waiting http_req_waiting last 1 1 + dimension = k6.http_req_receiving http_req_receiving last 1 1 + units = ms + type = stacked + +[http_req_duration] + name = http_req_duration + title = Total time for HTTP request + family = http requests + dimension = k6.http_req_duration http_req_duration_median median 1 1 + dimension = k6.http_req_duration http_req_duration_max max 1 1 + dimension = k6.http_req_duration http_req_duration_average avg 1 1 + dimension = k6.http_req_duration http_req_duration_min min 1 1 + dimension = k6.http_req_duration httP_req_duration_p95 percentile 1 1 diff --git a/collectors/statsd.plugin/statsd.c b/collectors/statsd.plugin/statsd.c index a8f94130a..e89585719 100644 --- a/collectors/statsd.plugin/statsd.c +++ b/collectors/statsd.plugin/statsd.c @@ -107,7 +107,7 @@ typedef enum statsd_metric_type { typedef struct statsd_metric { - avl avl; // indexing - has to be first + avl_t avl; // indexing - has to be first const char *name; // the name of the metric uint32_t hash; // hash of the name @@ -376,7 +376,7 @@ static inline STATSD_METRIC *statsd_metric_index_find(STATSD_INDEX *index, const tmp.name = name; tmp.hash = (hash)?hash:simple_hash(tmp.name); - return (STATSD_METRIC *)STATSD_AVL_SEARCH(&index->index, (avl *)&tmp); + return (STATSD_METRIC *)STATSD_AVL_SEARCH(&index->index, (avl_t *)&tmp); } static inline STATSD_METRIC *statsd_find_or_add_metric(STATSD_INDEX *index, const char *name, STATSD_METRIC_TYPE type) { @@ -398,7 +398,7 @@ static inline STATSD_METRIC *statsd_find_or_add_metric(STATSD_INDEX *index, cons m->histogram.ext = callocz(sizeof(STATSD_METRIC_HISTOGRAM_EXTENSIONS), 1); netdata_mutex_init(&m->histogram.ext->mutex); } - STATSD_METRIC *n = (STATSD_METRIC *)STATSD_AVL_INSERT(&index->index, (avl *)m); + STATSD_METRIC *n = (STATSD_METRIC *)STATSD_AVL_INSERT(&index->index, (avl_t *)m); if(unlikely(n != m)) { freez((void *)m->histogram.ext); freez((void *)m->name); diff --git a/collectors/tc.plugin/plugin_tc.c b/collectors/tc.plugin/plugin_tc.c index b92450efe..26affee09 100644 --- a/collectors/tc.plugin/plugin_tc.c +++ b/collectors/tc.plugin/plugin_tc.c @@ -12,7 +12,7 @@ #define TC_LINE_MAX 1024 struct tc_class { - avl avl; + avl_t avl; char *id; uint32_t hash; @@ -56,7 +56,7 @@ struct tc_class { }; struct tc_device { - avl avl; + avl_t avl; char *id; uint32_t hash; @@ -107,15 +107,15 @@ avl_tree_type tc_device_root_index = { tc_device_compare }; -#define tc_device_index_add(st) (struct tc_device *)avl_insert(&tc_device_root_index, (avl *)(st)) -#define tc_device_index_del(st) (struct tc_device *)avl_remove(&tc_device_root_index, (avl *)(st)) +#define tc_device_index_add(st) (struct tc_device *)avl_insert(&tc_device_root_index, (avl_t *)(st)) +#define tc_device_index_del(st) (struct tc_device *)avl_remove(&tc_device_root_index, (avl_t *)(st)) static inline struct tc_device *tc_device_index_find(const char *id, uint32_t hash) { struct tc_device tmp; tmp.id = (char *)id; tmp.hash = (hash)?hash:simple_hash(tmp.id); - return (struct tc_device *)avl_search(&(tc_device_root_index), (avl *)&tmp); + return (struct tc_device *)avl_search(&(tc_device_root_index), (avl_t *)&tmp); } @@ -128,15 +128,15 @@ static int tc_class_compare(void* a, void* b) { else return strcmp(((struct tc_class *)a)->id, ((struct tc_class *)b)->id); } -#define tc_class_index_add(st, rd) (struct tc_class *)avl_insert(&((st)->classes_index), (avl *)(rd)) -#define tc_class_index_del(st, rd) (struct tc_class *)avl_remove(&((st)->classes_index), (avl *)(rd)) +#define tc_class_index_add(st, rd) (struct tc_class *)avl_insert(&((st)->classes_index), (avl_t *)(rd)) +#define tc_class_index_del(st, rd) (struct tc_class *)avl_remove(&((st)->classes_index), (avl_t *)(rd)) static inline struct tc_class *tc_class_index_find(struct tc_device *st, const char *id, uint32_t hash) { struct tc_class tmp; tmp.id = (char *)id; tmp.hash = (hash)?hash:simple_hash(tmp.id); - return (struct tc_class *)avl_search(&(st->classes_index), (avl *) &tmp); + return (struct tc_class *)avl_search(&(st->classes_index), (avl_t *) &tmp); } // ---------------------------------------------------------------------------- diff --git a/collectors/xenstat.plugin/xenstat_plugin.c b/collectors/xenstat.plugin/xenstat_plugin.c index 647ac1db7..a322dd1c1 100644 --- a/collectors/xenstat.plugin/xenstat_plugin.c +++ b/collectors/xenstat.plugin/xenstat_plugin.c @@ -2,6 +2,9 @@ #include "../../libnetdata/libnetdata.h" +#include +#include + #define PLUGIN_XENSTAT_NAME "xenstat.plugin" #define NETDATA_CHART_PRIO_XENSTAT_NODE_CPUS 30001 @@ -62,15 +65,9 @@ int health_variable_lookup(const char *variable, uint32_t hash, struct rrdcalc * char *netdata_configured_host_prefix = ""; // Variables - static int debug = 0; - static int netdata_update_every = 1; -#ifdef HAVE_LIBXENSTAT -#include -#include - struct vcpu_metrics { unsigned int id; @@ -1093,14 +1090,3 @@ int main(int argc, char **argv) { xenstat_uninit(xhandle); info("XENSTAT process exiting"); } - -#else // !HAVE_LIBXENSTAT - -int main(int argc, char **argv) { - (void)argc; - (void)argv; - - fatal("xenstat.plugin is not compiled."); -} - -#endif // !HAVE_LIBXENSTAT -- cgit v1.2.3