diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-03-09 13:19:48 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-03-09 13:20:02 +0000 |
commit | 58daab21cd043e1dc37024a7f99b396788372918 (patch) | |
tree | 96771e43bb69f7c1c2b0b4f7374cb74d7866d0cb /collectors/cgroups.plugin | |
parent | Releasing debian version 1.43.2-1. (diff) | |
download | netdata-58daab21cd043e1dc37024a7f99b396788372918.tar.xz netdata-58daab21cd043e1dc37024a7f99b396788372918.zip |
Merging upstream version 1.44.3.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
22 files changed, 5377 insertions, 4355 deletions
diff --git a/collectors/cgroups.plugin/Makefile.am b/collectors/cgroups.plugin/Makefile.am index 354b9fbdc..0f6062420 100644 --- a/collectors/cgroups.plugin/Makefile.am +++ b/collectors/cgroups.plugin/Makefile.am @@ -3,11 +3,21 @@ AUTOMAKE_OPTIONS = subdir-objects MAINTAINERCLEANFILES = $(srcdir)/Makefile.in +CLEANFILES = \ + cgroup-name.sh \ + cgroup-network-helper.sh \ + $(NULL) + +include $(top_srcdir)/build/subst.inc +SUFFIXES = .in + dist_plugins_SCRIPTS = \ cgroup-name.sh \ cgroup-network-helper.sh \ $(NULL) dist_noinst_DATA = \ + cgroup-name.sh.in \ + cgroup-network-helper.sh.in \ README.md \ $(NULL) diff --git a/collectors/cgroups.plugin/cgroup-charts.c b/collectors/cgroups.plugin/cgroup-charts.c new file mode 100644 index 000000000..a89e8ac45 --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-charts.c @@ -0,0 +1,1526 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "cgroup-internals.h" + +void update_cpu_utilization_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_cpu; + + if (unlikely(!cg->st_cpu)) { + char *title; + char *context; + int prio; + + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services CPU utilization (100%% = 1 core)"; + context = "systemd.service.cpu.utilization"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD; + } else { + title = k8s_is_kubepod(cg) ? "CPU Usage (100%% = 1000 mCPU)" : "CPU Usage (100%% = 1 core)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu" : "cgroup.cpu"; + prio = cgroup_containers_chart_priority; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_cpu = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_STACKED); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + cg->st_cpu_rd_user = rrddim_add(chart, "user", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); + cg->st_cpu_rd_system = rrddim_add(chart, "system", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); + } else { + cg->st_cpu_rd_user = rrddim_add(chart, "user", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); + cg->st_cpu_rd_system = rrddim_add(chart, "system", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); + } + } + + rrddim_set_by_pointer(chart, cg->st_cpu_rd_user, (collected_number)cg->cpuacct_stat.user); + rrddim_set_by_pointer(chart, cg->st_cpu_rd_system, (collected_number)cg->cpuacct_stat.system); + rrdset_done(chart); +} + +void update_cpu_utilization_limit_chart(struct cgroup *cg, NETDATA_DOUBLE cpu_limit) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_cpu_limit; + + if (unlikely(!cg->st_cpu_limit)) { + char *title = "CPU Usage within the limits"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_limit" : "cgroup.cpu_limit"; + int prio = cgroup_containers_chart_priority - 1; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_cpu_limit = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_limit", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) + rrddim_add(chart, "used", NULL, 1, system_hz, RRD_ALGORITHM_ABSOLUTE); + else + rrddim_add(chart, "used", NULL, 1, 1000000, RRD_ALGORITHM_ABSOLUTE); + cg->prev_cpu_usage = (NETDATA_DOUBLE)(cg->cpuacct_stat.user + cg->cpuacct_stat.system) * 100; + } + + NETDATA_DOUBLE cpu_usage = 0; + cpu_usage = (NETDATA_DOUBLE)(cg->cpuacct_stat.user + cg->cpuacct_stat.system) * 100; + NETDATA_DOUBLE cpu_used = 100 * (cpu_usage - cg->prev_cpu_usage) / (cpu_limit * cgroup_update_every); + + rrdset_isnot_obsolete___safe_from_collector_thread(chart); + + rrddim_set(chart, "used", (cpu_used > 0) ? (collected_number)cpu_used : 0); + + cg->prev_cpu_usage = cpu_usage; + + rrdsetvar_custom_chart_variable_set(cg->st_cpu, cg->chart_var_cpu_limit, cpu_limit); + rrdset_done(chart); +} + +void update_cpu_throttled_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_cpu_nr_throttled; + + if (unlikely(!cg->st_cpu_nr_throttled)) { + char *title = "CPU Throttled Runnable Periods"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.throttled" : "cgroup.throttled"; + int prio = cgroup_containers_chart_priority + 10; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_cpu_nr_throttled = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "throttled", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "throttled", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set(chart, "throttled", (collected_number)cg->cpuacct_cpu_throttling.nr_throttled_perc); + rrdset_done(chart); +} + +void update_cpu_throttled_duration_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_cpu_throttled_time; + + if (unlikely(!cg->st_cpu_throttled_time)) { + char *title = "CPU Throttled Time Duration"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.throttled_duration" : "cgroup.throttled_duration"; + int prio = cgroup_containers_chart_priority + 15; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_cpu_throttled_time = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "throttled_duration", + NULL, + "cpu", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "duration", NULL, 1, 1000000, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "duration", (collected_number)cg->cpuacct_cpu_throttling.throttled_time); + rrdset_done(chart); +} + +void update_cpu_shares_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_cpu_shares; + + if (unlikely(!cg->st_cpu_shares)) { + char *title = "CPU Time Relative Share"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_shares" : "cgroup.cpu_shares"; + int prio = cgroup_containers_chart_priority + 20; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_cpu_shares = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_shares", + NULL, + "cpu", + context, + title, + "shares", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "shares", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set(chart, "shares", (collected_number)cg->cpuacct_cpu_shares.shares); + rrdset_done(chart); +} + +void update_cpu_per_core_usage_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + char id[RRD_ID_LENGTH_MAX + 1]; + unsigned int i; + + if (unlikely(!cg->st_cpu_per_core)) { + char *title = k8s_is_kubepod(cg) ? "CPU Usage (100%% = 1000 mCPU) Per Core" : "CPU Usage (100%% = 1 core) Per Core"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_per_core" : "cgroup.cpu_per_core"; + int prio = cgroup_containers_chart_priority + 100; + + char buff[RRD_ID_LENGTH_MAX + 1]; + cg->st_cpu_per_core = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_per_core", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_STACKED); + + rrdset_update_rrdlabels(cg->st_cpu_per_core, cg->chart_labels); + + for (i = 0; i < cg->cpuacct_usage.cpus; i++) { + snprintfz(id, RRD_ID_LENGTH_MAX, "cpu%u", i); + rrddim_add(cg->st_cpu_per_core, id, NULL, 100, 1000000000, RRD_ALGORITHM_INCREMENTAL); + } + } + + for (i = 0; i < cg->cpuacct_usage.cpus; i++) { + snprintfz(id, RRD_ID_LENGTH_MAX, "cpu%u", i); + rrddim_set(cg->st_cpu_per_core, id, (collected_number)cg->cpuacct_usage.cpu_percpu[i]); + } + rrdset_done(cg->st_cpu_per_core); +} + +void update_mem_usage_detailed_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_mem; + + if (unlikely(!cg->st_mem)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Memory"; + context = "systemd.service.memory.ram.usage"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 15; + } else { + title = "Memory Usage"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem" : "cgroup.mem"; + prio = cgroup_containers_chart_priority + 220; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + + chart = cg->st_mem = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem", + NULL, + "mem", + context, + title, + "MiB", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_STACKED); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + rrddim_add(chart, "cache", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "rss", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + + if (cg->memory.detailed_has_swap) + rrddim_add(chart, "swap", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + + rrddim_add(chart, "rss_huge", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "mapped_file", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + } else { + rrddim_add(chart, "anon", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "kernel_stack", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "slab", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "sock", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "anon_thp", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "file", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + } + } + + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + rrddim_set(chart, "cache", (collected_number)cg->memory.total_cache); + collected_number rss = (collected_number)(cg->memory.total_rss - cg->memory.total_rss_huge); + if (rss < 0) + rss = 0; + rrddim_set(chart, "rss", rss); + if (cg->memory.detailed_has_swap) + rrddim_set(chart, "swap", (collected_number)cg->memory.total_swap); + rrddim_set(chart, "rss_huge", (collected_number)cg->memory.total_rss_huge); + rrddim_set(chart, "mapped_file", (collected_number)cg->memory.total_mapped_file); + } else { + rrddim_set(chart, "anon", (collected_number)cg->memory.anon); + rrddim_set(chart, "kernel_stack", (collected_number)cg->memory.kernel_stack); + rrddim_set(chart, "slab", (collected_number)cg->memory.slab); + rrddim_set(chart, "sock", (collected_number)cg->memory.sock); + rrddim_set(chart, "anon_thp", (collected_number)cg->memory.anon_thp); + rrddim_set(chart, "file", (collected_number)cg->memory.total_mapped_file); + } + rrdset_done(chart); +} + +void update_mem_writeback_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_writeback; + + if (unlikely(!cg->st_writeback)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Writeback Memory"; + context = "systemd.service.memory.writeback"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 20; + } else { + title = "Writeback Memory"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.writeback" : "cgroup.writeback"; + prio = cgroup_containers_chart_priority + 300; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_writeback = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "writeback", + NULL, + "mem", + context, + title, + "MiB", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_AREA); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + if (cg->memory.detailed_has_dirty) + rrddim_add(chart, "dirty", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "writeback", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + } + + if (cg->memory.detailed_has_dirty) + rrddim_set(chart, "dirty", (collected_number)cg->memory.total_dirty); + rrddim_set(chart, "writeback", (collected_number)cg->memory.total_writeback); + rrdset_done(chart); +} + +void update_mem_activity_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_mem_activity; + + if (unlikely(!cg->st_mem_activity)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Memory Paging IO"; + context = "systemd.service.memory.paging.io"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 30; + } else { + title = "Memory Activity"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem_activity" : "cgroup.mem_activity"; + prio = cgroup_containers_chart_priority + 400; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_mem_activity = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_activity", + NULL, + "mem", + context, + title, + "MiB/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + // FIXME: systemd just in, out + rrddim_add(chart, "pgpgin", "in", system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); + rrddim_add(chart, "pgpgout", "out", -system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "pgpgin", (collected_number)cg->memory.total_pgpgin); + rrddim_set(chart, "pgpgout", (collected_number)cg->memory.total_pgpgout); + rrdset_done(chart); +} + +void update_mem_pgfaults_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_pgfaults; + + if (unlikely(!cg->st_pgfaults)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Memory Page Faults"; + context = "systemd.service.memory.paging.faults"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 25; + } else { + title = "Memory Page Faults"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.pgfaults" : "cgroup.pgfaults"; + prio = cgroup_containers_chart_priority + 500; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_pgfaults = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "pgfaults", + NULL, + "mem", + context, + title, + "MiB/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "pgfault", NULL, system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); + rrddim_add(chart, "pgmajfault", "swap", -system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "pgfault", (collected_number)cg->memory.total_pgfault); + rrddim_set(chart, "pgmajfault", (collected_number)cg->memory.total_pgmajfault); + rrdset_done(chart); +} + +void update_mem_usage_limit_chart(struct cgroup *cg, unsigned long long memory_limit) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_mem_usage_limit; + + if (unlikely(!cg->st_mem_usage_limit)) { + char *title = "Used RAM within the limits"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem_usage_limit" : "cgroup.mem_usage_limit"; + int prio = cgroup_containers_chart_priority + 200; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_mem_usage_limit = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_usage_limit", + NULL, + "mem", + context, + title, + "MiB", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_STACKED); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + rrddim_add(chart, "available", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "used", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + } + + rrdset_isnot_obsolete___safe_from_collector_thread(chart); + + rrddim_set(chart, "available", (collected_number)(memory_limit - cg->memory.usage_in_bytes)); + rrddim_set(chart, "used", (collected_number)cg->memory.usage_in_bytes); + rrdset_done(chart); +} + +void update_mem_utilization_chart(struct cgroup *cg, unsigned long long memory_limit) { + if (is_cgroup_systemd_service(cg)) + return; + + RRDSET *chart = cg->st_mem_utilization; + + if (unlikely(!cg->st_mem_utilization)) { + char *title = "Memory Utilization"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem_utilization" : "cgroup.mem_utilization"; + int prio = cgroup_containers_chart_priority + 199; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_mem_utilization = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_utilization", + NULL, + "mem", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_AREA); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + rrddim_add(chart, "utilization", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + + rrdset_isnot_obsolete___safe_from_collector_thread(chart); + collected_number util = (collected_number)(cg->memory.usage_in_bytes * 100 / memory_limit); + rrddim_set(chart, "utilization", util); + rrdset_done(chart); +} + +void update_mem_failcnt_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_mem_failcnt; + + if (unlikely(!cg->st_mem_failcnt)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Memory Limit Failures"; + context = "systemd.service.memory.failcnt"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 10; + } else { + title = "Memory Limit Failures"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem_failcnt" : "cgroup.mem_failcnt"; + prio = cgroup_containers_chart_priority + 250; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_mem_failcnt = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_failcnt", + NULL, + "mem", + context, + title, + "count", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "failures", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "failures", (collected_number)cg->memory.failcnt); + rrdset_done(chart); +} + +void update_mem_usage_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_mem_usage; + + if (unlikely(!cg->st_mem_usage)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Used Memory"; + context = "systemd.service.memory.usage"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 5; + } else { + title = "Used Memory"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.mem_usage" : "cgroup.mem_usage"; + prio = cgroup_containers_chart_priority + 210; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_mem_usage = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_usage", + NULL, + "mem", + context, + title, + "MiB", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_STACKED); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + cg->st_mem_rd_ram = rrddim_add(chart, "ram", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + cg->st_mem_rd_swap = rrddim_add(chart, "swap", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, cg->st_mem_rd_ram, (collected_number)cg->memory.usage_in_bytes); + + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + rrddim_set_by_pointer( + chart, + cg->st_mem_rd_swap, + cg->memory.msw_usage_in_bytes > (cg->memory.usage_in_bytes + cg->memory.total_inactive_file) ? + (collected_number)(cg->memory.msw_usage_in_bytes - + (cg->memory.usage_in_bytes + cg->memory.total_inactive_file)) : + 0); + } else { + rrddim_set_by_pointer(chart, cg->st_mem_rd_swap, (collected_number)cg->memory.msw_usage_in_bytes); + } + + rrdset_done(chart); +} + +void update_io_serviced_bytes_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_io; + + if (unlikely(!cg->st_io)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Disk Read/Write Bandwidth"; + context = "systemd.service.disk.io"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 35; + } else { + title = "I/O Bandwidth (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.io" : "cgroup.io"; + prio = cgroup_containers_chart_priority + 1200; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_io = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "io", + NULL, + "disk", + context, + title, + "KiB/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_AREA); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + cg->st_io_rd_read = rrddim_add(chart, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); + cg->st_io_rd_written = rrddim_add(cg->st_io, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, cg->st_io_rd_read, (collected_number)cg->io_service_bytes.Read); + rrddim_set_by_pointer(chart, cg->st_io_rd_written, (collected_number)cg->io_service_bytes.Write); + rrdset_done(chart); +} + +void update_io_serviced_ops_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_serviced_ops; + + if (unlikely(!cg->st_serviced_ops)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Disk Read/Write Operations"; + context = "systemd.service.disk.iops"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 40; + } else { + title = "Serviced I/O Operations (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.serviced_ops" : "cgroup.serviced_ops"; + prio = cgroup_containers_chart_priority + 1200; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_serviced_ops = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "serviced_ops", + NULL, + "disk", + context, + title, + "operations/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + rrddim_add(chart, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "read", (collected_number)cg->io_serviced.Read); + rrddim_set(chart, "write", (collected_number)cg->io_serviced.Write); + rrdset_done(chart); +} + +void update_throttle_io_serviced_bytes_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_throttle_io; + + if (unlikely(!cg->st_throttle_io)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Throttle Disk Read/Write Bandwidth"; + context = "systemd.service.disk.throttle.io"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 45; + } else { + title = "Throttle I/O Bandwidth (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.throttle_io" : "cgroup.throttle_io"; + prio = cgroup_containers_chart_priority + 1200; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_throttle_io = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "throttle_io", + NULL, + "disk", + context, + title, + "KiB/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_AREA); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + + cg->st_throttle_io_rd_read = rrddim_add(chart, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); + cg->st_throttle_io_rd_written = rrddim_add(chart, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, cg->st_throttle_io_rd_read, (collected_number)cg->throttle_io_service_bytes.Read); + rrddim_set_by_pointer(chart, cg->st_throttle_io_rd_written, (collected_number)cg->throttle_io_service_bytes.Write); + rrdset_done(chart); +} + +void update_throttle_io_serviced_ops_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_throttle_serviced_ops; + + if (unlikely(!cg->st_throttle_serviced_ops)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Throttle Disk Read/Write Operations"; + context = "systemd.service.disk.throttle.iops"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 50; + } else { + title = "Throttle Serviced I/O Operations (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.throttle_serviced_ops" : "cgroup.throttle_serviced_ops"; + prio = cgroup_containers_chart_priority + 1200; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_throttle_serviced_ops = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "throttle_serviced_ops", + NULL, + "disk", + context, + title, + "operations/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + rrddim_add(chart, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "read", (collected_number)cg->throttle_io_serviced.Read); + rrddim_set(chart, "write", (collected_number)cg->throttle_io_serviced.Write); + rrdset_done(chart); +} + +void update_io_queued_ops_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_queued_ops; + + if (unlikely(!cg->st_queued_ops)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Queued Disk Read/Write Operations"; + context = "systemd.service.disk.queued_iops"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 55; + } else { + title = "Queued I/O Operations (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.queued_ops" : "cgroup.queued_ops"; + prio = cgroup_containers_chart_priority + 2000; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_queued_ops = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "queued_ops", + NULL, + "disk", + context, + title, + "operations", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "read", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + rrddim_add(chart, "write", NULL, -1, 1, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set(chart, "read", (collected_number)cg->io_queued.Read); + rrddim_set(chart, "write", (collected_number)cg->io_queued.Write); + rrdset_done(chart); +} + +void update_io_merged_ops_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_merged_ops; + + if (unlikely(!cg->st_merged_ops)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Merged Disk Read/Write Operations"; + context = "systemd.service.disk.merged_iops"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 60; + } else { + title = "Merged I/O Operations (all disks)"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.merged_ops" : "cgroup.merged_ops"; + prio = cgroup_containers_chart_priority + 2100; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_merged_ops = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "merged_ops", + NULL, + "disk", + context, + title, + "operations/s", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + rrddim_add(chart, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); + rrddim_add(chart, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set(chart, "read", (collected_number)cg->io_merged.Read); + rrddim_set(chart, "write", (collected_number)cg->io_merged.Write); + rrdset_done(chart); +} + +void update_cpu_some_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->cpu_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "CPU some pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_some_pressure" : "cgroup.cpu_some_pressure"; + int prio = cgroup_containers_chart_priority + 2200; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_some_pressure", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_cpu_some_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->cpu_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "CPU some pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_some_pressure_stall_time" : "cgroup.cpu_some_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2220; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_some_pressure_stall_time", + NULL, + "cpu", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_cpu_full_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->cpu_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "CPU full pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_full_pressure" : "cgroup.cpu_full_pressure"; + int prio = cgroup_containers_chart_priority + 2240; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_full_pressure", + NULL, + "cpu", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_cpu_full_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->cpu_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "CPU full pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_full_pressure_stall_time" : "cgroup.cpu_full_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2260; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "cpu_full_pressure_stall_time", + NULL, + "cpu", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_mem_some_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->memory_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "Memory some pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.memory_some_pressure" : "cgroup.memory_some_pressure"; + int prio = cgroup_containers_chart_priority + 2300; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_some_pressure", + NULL, + "mem", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_mem_some_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->memory_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "Memory some pressure stall time"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.memory_some_pressure_stall_time" : + "cgroup.memory_some_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2320; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "memory_some_pressure_stall_time", + NULL, + "mem", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_mem_full_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->memory_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "Memory full pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.memory_full_pressure" : "cgroup.memory_full_pressure"; + int prio = cgroup_containers_chart_priority + 2340; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "mem_full_pressure", + NULL, + "mem", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_mem_full_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->memory_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "Memory full pressure stall time"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.memory_full_pressure_stall_time" : + "cgroup.memory_full_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2360; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "memory_full_pressure_stall_time", + NULL, + "mem", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_irq_some_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->irq_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "IRQ some pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure" : "cgroup.irq_some_pressure"; + int prio = cgroup_containers_chart_priority + 2310; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "irq_some_pressure", + NULL, + "interrupts", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_irq_some_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->irq_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "IRQ some pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure_stall_time" : "cgroup.irq_some_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2330; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "irq_some_pressure_stall_time", + NULL, + "interrupts", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_irq_full_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->irq_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "IRQ full pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure" : "cgroup.irq_full_pressure"; + int prio = cgroup_containers_chart_priority + 2350; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "irq_full_pressure", + NULL, + "interrupts", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_irq_full_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->irq_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "IRQ full pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure_stall_time" : "cgroup.irq_full_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2370; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "irq_full_pressure_stall_time", + NULL, + "interrupts", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_io_some_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->io_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "I/O some pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.io_some_pressure" : "cgroup.io_some_pressure"; + int prio = cgroup_containers_chart_priority + 2400; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "io_some_pressure", + NULL, + "disk", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_io_some_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->io_pressure; + struct pressure_charts *pcs = &res->some; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "I/O some pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.io_some_pressure_stall_time" : "cgroup.io_some_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2420; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "io_some_pressure_stall_time", + NULL, + "disk", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_io_full_pressure_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->io_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->share_time.st; + + if (unlikely(!pcs->share_time.st)) { + char *title = "I/O full pressure"; + char *context = k8s_is_kubepod(cg) ? "k8s.cgroup.io_full_pressure" : "cgroup.io_full_pressure"; + int prio = cgroup_containers_chart_priority + 2440; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->share_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "io_full_pressure", + NULL, + "disk", + context, + title, + "percentage", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, pcs->share_time.rd10, (collected_number)(pcs->share_time.value10 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd60, (collected_number)(pcs->share_time.value60 * 100)); + rrddim_set_by_pointer(chart, pcs->share_time.rd300, (collected_number)(pcs->share_time.value300 * 100)); + rrdset_done(chart); +} + +void update_io_full_pressure_stall_time_chart(struct cgroup *cg) { + if (is_cgroup_systemd_service(cg)) + return; + + struct pressure *res = &cg->io_pressure; + struct pressure_charts *pcs = &res->full; + RRDSET *chart = pcs->total_time.st; + + if (unlikely(!pcs->total_time.st)) { + char *title = "I/O full pressure stall time"; + char *context = + k8s_is_kubepod(cg) ? "k8s.cgroup.io_full_pressure_stall_time" : "cgroup.io_full_pressure_stall_time"; + int prio = cgroup_containers_chart_priority + 2460; + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = pcs->total_time.st = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "io_full_pressure_stall_time", + NULL, + "disk", + context, + title, + "ms", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + } + + rrddim_set_by_pointer(chart, pcs->total_time.rdtotal, (collected_number)(pcs->total_time.value_total)); + rrdset_done(chart); +} + +void update_pids_current_chart(struct cgroup *cg) { + RRDSET *chart = cg->st_pids; + + if (unlikely(!cg->st_pids)) { + char *title; + char *context; + int prio; + if (is_cgroup_systemd_service(cg)) { + title = "Systemd Services Number of Processes"; + context = "systemd.service.pids.current"; + prio = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD + 70; + } else { + title = "Number of processes"; + context = k8s_is_kubepod(cg) ? "k8s.cgroup.pids_current" : "cgroup.pids_current"; + prio = cgroup_containers_chart_priority + 2150; + } + + char buff[RRD_ID_LENGTH_MAX + 1]; + chart = cg->st_pids = rrdset_create_localhost( + cgroup_chart_type(buff, cg), + "pids_current", + NULL, + "pids", + context, + title, + "pids", + PLUGIN_CGROUPS_NAME, + is_cgroup_systemd_service(cg) ? PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME : PLUGIN_CGROUPS_MODULE_CGROUPS_NAME, + prio, + cgroup_update_every, + RRDSET_TYPE_LINE); + + rrdset_update_rrdlabels(chart, cg->chart_labels); + cg->st_pids_rd_pids_current = rrddim_add(chart, "pids", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + } + + rrddim_set_by_pointer(chart, cg->st_pids_rd_pids_current, (collected_number)cg->pids.pids_current); + rrdset_done(chart); +} diff --git a/collectors/cgroups.plugin/cgroup-discovery.c b/collectors/cgroups.plugin/cgroup-discovery.c new file mode 100644 index 000000000..ede35ed8a --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-discovery.c @@ -0,0 +1,1245 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "cgroup-internals.h" + +// discovery cgroup thread worker jobs +#define WORKER_DISCOVERY_INIT 0 +#define WORKER_DISCOVERY_FIND 1 +#define WORKER_DISCOVERY_PROCESS 2 +#define WORKER_DISCOVERY_PROCESS_RENAME 3 +#define WORKER_DISCOVERY_PROCESS_NETWORK 4 +#define WORKER_DISCOVERY_PROCESS_FIRST_TIME 5 +#define WORKER_DISCOVERY_UPDATE 6 +#define WORKER_DISCOVERY_CLEANUP 7 +#define WORKER_DISCOVERY_COPY 8 +#define WORKER_DISCOVERY_SHARE 9 +#define WORKER_DISCOVERY_LOCK 10 + +#if WORKER_UTILIZATION_MAX_JOB_TYPES < 11 +#error WORKER_UTILIZATION_MAX_JOB_TYPES has to be at least 11 +#endif + +struct cgroup *discovered_cgroup_root = NULL; + +char cgroup_chart_id_prefix[] = "cgroup_"; +char services_chart_id_prefix[] = "systemd_"; +char *cgroups_rename_script = NULL; + + +// ---------------------------------------------------------------------------- + +static inline void free_pressure(struct pressure *res) { + if (res->some.share_time.st) rrdset_is_obsolete___safe_from_collector_thread(res->some.share_time.st); + if (res->some.total_time.st) rrdset_is_obsolete___safe_from_collector_thread(res->some.total_time.st); + if (res->full.share_time.st) rrdset_is_obsolete___safe_from_collector_thread(res->full.share_time.st); + if (res->full.total_time.st) rrdset_is_obsolete___safe_from_collector_thread(res->full.total_time.st); + freez(res->filename); +} + +static inline void cgroup_free_network_interfaces(struct cgroup *cg) { + while(cg->interfaces) { + struct cgroup_network_interface *i = cg->interfaces; + cg->interfaces = i->next; + + // delete the registration of proc_net_dev rename + netdev_rename_device_del(i->host_device); + + freez((void *)i->host_device); + freez((void *)i->container_device); + freez((void *)i); + } +} + +static inline void cgroup_free(struct cgroup *cg) { + netdata_log_debug(D_CGROUP, "Removing cgroup '%s' with chart id '%s' (was %s and %s)", cg->id, cg->chart_id, (cg->enabled)?"enabled":"disabled", (cg->available)?"available":"not available"); + + cgroup_netdev_delete(cg); + + if(cg->st_cpu) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu); + if(cg->st_cpu_limit) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_limit); + if(cg->st_cpu_per_core) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_per_core); + if(cg->st_cpu_nr_throttled) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_nr_throttled); + if(cg->st_cpu_throttled_time) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_throttled_time); + if(cg->st_cpu_shares) rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_shares); + if(cg->st_mem) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem); + if(cg->st_writeback) rrdset_is_obsolete___safe_from_collector_thread(cg->st_writeback); + if(cg->st_mem_activity) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_activity); + if(cg->st_pgfaults) rrdset_is_obsolete___safe_from_collector_thread(cg->st_pgfaults); + if(cg->st_mem_usage) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_usage); + if(cg->st_mem_usage_limit) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_usage_limit); + if(cg->st_mem_utilization) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_utilization); + if(cg->st_mem_failcnt) rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_failcnt); + if(cg->st_io) rrdset_is_obsolete___safe_from_collector_thread(cg->st_io); + if(cg->st_serviced_ops) rrdset_is_obsolete___safe_from_collector_thread(cg->st_serviced_ops); + if(cg->st_throttle_io) rrdset_is_obsolete___safe_from_collector_thread(cg->st_throttle_io); + if(cg->st_throttle_serviced_ops) rrdset_is_obsolete___safe_from_collector_thread(cg->st_throttle_serviced_ops); + if(cg->st_queued_ops) rrdset_is_obsolete___safe_from_collector_thread(cg->st_queued_ops); + if(cg->st_merged_ops) rrdset_is_obsolete___safe_from_collector_thread(cg->st_merged_ops); + if(cg->st_pids) rrdset_is_obsolete___safe_from_collector_thread(cg->st_pids); + + freez(cg->filename_cpuset_cpus); + freez(cg->filename_cpu_cfs_period); + freez(cg->filename_cpu_cfs_quota); + freez(cg->filename_memory_limit); + freez(cg->filename_memoryswap_limit); + + cgroup_free_network_interfaces(cg); + + freez(cg->cpuacct_usage.cpu_percpu); + + freez(cg->cpuacct_stat.filename); + freez(cg->cpuacct_usage.filename); + freez(cg->cpuacct_cpu_throttling.filename); + freez(cg->cpuacct_cpu_shares.filename); + + arl_free(cg->memory.arl_base); + freez(cg->memory.filename_detailed); + freez(cg->memory.filename_failcnt); + freez(cg->memory.filename_usage_in_bytes); + freez(cg->memory.filename_msw_usage_in_bytes); + + freez(cg->io_service_bytes.filename); + freez(cg->io_serviced.filename); + + freez(cg->throttle_io_service_bytes.filename); + freez(cg->throttle_io_serviced.filename); + + freez(cg->io_merged.filename); + freez(cg->io_queued.filename); + freez(cg->pids.pids_current_filename); + + free_pressure(&cg->cpu_pressure); + free_pressure(&cg->io_pressure); + free_pressure(&cg->memory_pressure); + free_pressure(&cg->irq_pressure); + + freez(cg->id); + freez(cg->intermediate_id); + freez(cg->chart_id); + freez(cg->name); + + rrdlabels_destroy(cg->chart_labels); + + freez(cg); + + cgroup_root_count--; +} + +// ---------------------------------------------------------------------------- +// add/remove/find cgroup objects + +#define CGROUP_CHARTID_LINE_MAX 1024 + +static inline char *cgroup_chart_id_strdupz(const char *s) { + if(!s || !*s) s = "/"; + + if(*s == '/' && s[1] != '\0') s++; + + char *r = strdupz(s); + netdata_fix_chart_id(r); + + return r; +} + +// TODO: move the code to cgroup_chart_id_strdupz() when the renaming script is fixed +static inline void substitute_dots_in_id(char *s) { + // dots are used to distinguish chart type and id in streaming, so we should replace them + for (char *d = s; *d; d++) { + if (*d == '.') + *d = '-'; + } +} + +// ---------------------------------------------------------------------------- +// parse k8s labels + +char *cgroup_parse_resolved_name_and_labels(RRDLABELS *labels, char *data) { + // the first word, up to the first space is the name + char *name = strsep_skip_consecutive_separators(&data, " "); + + // the rest are key=value pairs separated by comma + while(data) { + char *pair = strsep_skip_consecutive_separators(&data, ","); + rrdlabels_add_pair(labels, pair, RRDLABEL_SRC_AUTO | RRDLABEL_SRC_K8S); + } + + return name; +} + +static inline void discovery_rename_cgroup(struct cgroup *cg) { + if (!cg->pending_renames) { + return; + } + cg->pending_renames--; + + netdata_log_debug(D_CGROUP, "looking for the name of cgroup '%s' with chart id '%s'", cg->id, cg->chart_id); + netdata_log_debug(D_CGROUP, "executing command %s \"%s\" for cgroup '%s'", cgroups_rename_script, cg->intermediate_id, cg->chart_id); + pid_t cgroup_pid; + + FILE *fp_child_input, *fp_child_output; + (void)netdata_popen_raw_default_flags_and_environment(&cgroup_pid, &fp_child_input, &fp_child_output, cgroups_rename_script, cg->id, cg->intermediate_id); + if (!fp_child_output) { + collector_error("CGROUP: cannot popen(%s \"%s\", \"r\").", cgroups_rename_script, cg->intermediate_id); + cg->pending_renames = 0; + cg->processed = 1; + return; + } + + char buffer[CGROUP_CHARTID_LINE_MAX + 1]; + char *new_name = fgets(buffer, CGROUP_CHARTID_LINE_MAX, fp_child_output); + int exit_code = netdata_pclose(fp_child_input, fp_child_output, cgroup_pid); + + switch (exit_code) { + case 0: + cg->pending_renames = 0; + break; + + case 3: + cg->pending_renames = 0; + cg->processed = 1; + break; + + default: + break; + } + + if (cg->pending_renames || cg->processed) + return; + if (!new_name || !*new_name || *new_name == '\n') + return; + if (!(new_name = trim(new_name))) + return; + + if (!cg->chart_labels) + cg->chart_labels = rrdlabels_create(); + // read the new labels and remove the obsolete ones + rrdlabels_unmark_all(cg->chart_labels); + char *name = cgroup_parse_resolved_name_and_labels(cg->chart_labels, new_name); + rrdlabels_remove_all_unmarked(cg->chart_labels); + + freez(cg->name); + cg->name = strdupz(name); + + freez(cg->chart_id); + cg->chart_id = cgroup_chart_id_strdupz(name); + + substitute_dots_in_id(cg->chart_id); + cg->hash_chart_id = simple_hash(cg->chart_id); +} + +static void is_cgroup_procs_exist(netdata_ebpf_cgroup_shm_body_t *out, char *id) { + struct stat buf; + + snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_cpuset_base, id); + if (likely(stat(out->path, &buf) == 0)) { + return; + } + + snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_blkio_base, id); + if (likely(stat(out->path, &buf) == 0)) { + return; + } + + snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_memory_base, id); + if (likely(stat(out->path, &buf) == 0)) { + return; + } + + snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_devices_base, id); + if (likely(stat(out->path, &buf) == 0)) { + return; + } + + out->path[0] = '\0'; + out->enabled = 0; +} + +static inline void convert_cgroup_to_systemd_service(struct cgroup *cg) { + char buffer[CGROUP_CHARTID_LINE_MAX + 1]; + cg->options |= CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE; + strncpyz(buffer, cg->id, CGROUP_CHARTID_LINE_MAX); + char *s = buffer; + + // skip to the last slash + size_t len = strlen(s); + while (len--) { + if (unlikely(s[len] == '/')) { + break; + } + } + if (len) { + s = &s[len + 1]; + } + + // remove extension + len = strlen(s); + while (len--) { + if (unlikely(s[len] == '.')) { + break; + } + } + if (len) { + s[len] = '\0'; + } + + freez(cg->name); + cg->name = strdupz(s); + + freez(cg->chart_id); + cg->chart_id = cgroup_chart_id_strdupz(s); + substitute_dots_in_id(cg->chart_id); + cg->hash_chart_id = simple_hash(cg->chart_id); +} + +static inline struct cgroup *discovery_cgroup_add(const char *id) { + netdata_log_debug(D_CGROUP, "adding to list, cgroup with id '%s'", id); + + struct cgroup *cg = callocz(1, sizeof(struct cgroup)); + + cg->id = strdupz(id); + cg->hash = simple_hash(cg->id); + + cg->name = strdupz(id); + + cg->intermediate_id = cgroup_chart_id_strdupz(id); + + cg->chart_id = cgroup_chart_id_strdupz(id); + substitute_dots_in_id(cg->chart_id); + cg->hash_chart_id = simple_hash(cg->chart_id); + + if (cgroup_use_unified_cgroups) { + cg->options |= CGROUP_OPTIONS_IS_UNIFIED; + } + + if (!discovered_cgroup_root) + discovered_cgroup_root = cg; + else { + struct cgroup *t; + for (t = discovered_cgroup_root; t->discovered_next; t = t->discovered_next) { + } + t->discovered_next = cg; + } + + return cg; +} + +static inline struct cgroup *discovery_cgroup_find(const char *id) { + netdata_log_debug(D_CGROUP, "searching for cgroup '%s'", id); + + uint32_t hash = simple_hash(id); + + struct cgroup *cg; + for(cg = discovered_cgroup_root; cg ; cg = cg->discovered_next) { + if(hash == cg->hash && strcmp(id, cg->id) == 0) + break; + } + + netdata_log_debug(D_CGROUP, "cgroup '%s' %s in memory", id, (cg)?"found":"not found"); + return cg; +} + +static int calc_cgroup_depth(const char *id) { + int depth = 0; + const char *s; + for (s = id; *s; s++) { + depth += unlikely(*s == '/'); + } + return depth; +} + +static inline void discovery_find_cgroup_in_dir_callback(const char *dir) { + if (!dir || !*dir) { + dir = "/"; + } + + netdata_log_debug(D_CGROUP, "examining cgroup dir '%s'", dir); + + struct cgroup *cg = discovery_cgroup_find(dir); + if (cg) { + cg->available = 1; + return; + } + + if (cgroup_root_count >= cgroup_root_max) { + nd_log_limit_static_global_var(erl, 3600, 0); + nd_log_limit(&erl, NDLS_COLLECTORS, NDLP_WARNING, "CGROUP: maximum number of cgroups reached (%d). No more cgroups will be added.", cgroup_root_count); + return; + } + + if (cgroup_max_depth > 0) { + int depth = calc_cgroup_depth(dir); + if (depth > cgroup_max_depth) { + nd_log_collector(NDLP_DEBUG, "CGROUP: '%s' is too deep (%d, while max is %d)", dir, depth, cgroup_max_depth); + return; + } + } + + cg = discovery_cgroup_add(dir); + cg->available = 1; + cg->first_time_seen = 1; + cg->function_ready = false; + cgroup_root_count++; +} + +static inline int discovery_find_dir_in_subdirs(const char *base, const char *this, void (*callback)(const char *)) { + if(!this) this = base; + netdata_log_debug(D_CGROUP, "searching for directories in '%s' (base '%s')", this?this:"", base); + + size_t dirlen = strlen(this), baselen = strlen(base); + + int ret = -1; + int enabled = -1; + + const char *relative_path = &this[baselen]; + if(!*relative_path) relative_path = "/"; + + DIR *dir = opendir(this); + if(!dir) { + collector_error("CGROUP: cannot read directory '%s'", base); + return ret; + } + ret = 1; + + callback(relative_path); + + struct dirent *de = NULL; + while((de = readdir(dir))) { + if(de->d_type == DT_DIR + && ( + (de->d_name[0] == '.' && de->d_name[1] == '\0') + || (de->d_name[0] == '.' && de->d_name[1] == '.' && de->d_name[2] == '\0') + )) + continue; + + if(de->d_type == DT_DIR) { + if(enabled == -1) { + const char *r = relative_path; + if(*r == '\0') r = "/"; + + // do not decent in directories we are not interested + enabled = matches_search_cgroup_paths(r); + } + + if(enabled) { + char *s = mallocz(dirlen + strlen(de->d_name) + 2); + strcpy(s, this); + strcat(s, "/"); + strcat(s, de->d_name); + int ret2 = discovery_find_dir_in_subdirs(base, s, callback); + if(ret2 > 0) ret += ret2; + freez(s); + } + } + } + + closedir(dir); + return ret; +} + +static inline void discovery_mark_as_unavailable_all_cgroups() { + for (struct cgroup *cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { + cg->available = 0; + } +} + +static inline void discovery_update_filenames_cgroup_v1(struct cgroup *cg) { + char filename[FILENAME_MAX + 1]; + struct stat buf; + + // CPU + if (unlikely(cgroup_enable_cpuacct_stat && !cg->cpuacct_stat.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpuacct.stat", cgroup_cpuacct_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_stat.filename = strdupz(filename); + cg->cpuacct_stat.enabled = cgroup_enable_cpuacct_stat; + snprintfz(filename, FILENAME_MAX, "%s%s/cpuset.cpus", cgroup_cpuset_base, cg->id); + cg->filename_cpuset_cpus = strdupz(filename); + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.cfs_period_us", cgroup_cpuacct_base, cg->id); + cg->filename_cpu_cfs_period = strdupz(filename); + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.cfs_quota_us", cgroup_cpuacct_base, cg->id); + cg->filename_cpu_cfs_quota = strdupz(filename); + } + } + // FIXME: remove usage_percpu + if (unlikely(cgroup_enable_cpuacct_usage && !cg->cpuacct_usage.filename && !is_cgroup_systemd_service(cg))) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpuacct.usage_percpu", cgroup_cpuacct_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_usage.filename = strdupz(filename); + cg->cpuacct_usage.enabled = cgroup_enable_cpuacct_usage; + } + } + if (unlikely( + cgroup_enable_cpuacct_cpu_throttling && !cg->cpuacct_cpu_throttling.filename && + !is_cgroup_systemd_service(cg))) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.stat", cgroup_cpuacct_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_cpu_throttling.filename = strdupz(filename); + cg->cpuacct_cpu_throttling.enabled = cgroup_enable_cpuacct_cpu_throttling; + } + } + if (unlikely( + cgroup_enable_cpuacct_cpu_shares && !cg->cpuacct_cpu_shares.filename && !is_cgroup_systemd_service(cg))) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.shares", cgroup_cpuacct_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_cpu_shares.filename = strdupz(filename); + cg->cpuacct_cpu_shares.enabled = cgroup_enable_cpuacct_cpu_shares; + } + } + + // Memory + if (unlikely( + (cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && + (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !is_cgroup_systemd_service(cg)))) { + 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); + cg->memory.enabled_detailed = + (cgroup_enable_detailed_memory == CONFIG_BOOLEAN_YES) ? CONFIG_BOOLEAN_YES : CONFIG_BOOLEAN_AUTO; + } + } + if (unlikely(cgroup_enable_memory && !cg->memory.filename_usage_in_bytes)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.usage_in_bytes", cgroup_memory_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory.filename_usage_in_bytes = strdupz(filename); + cg->memory.enabled_usage_in_bytes = cgroup_enable_memory; + snprintfz(filename, FILENAME_MAX, "%s%s/memory.limit_in_bytes", cgroup_memory_base, cg->id); + cg->filename_memory_limit = strdupz(filename); + } + } + if (unlikely(cgroup_enable_swap && !cg->memory.filename_msw_usage_in_bytes)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.memsw.usage_in_bytes", cgroup_memory_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory.filename_msw_usage_in_bytes = strdupz(filename); + cg->memory.enabled_msw_usage_in_bytes = cgroup_enable_swap; + snprintfz(filename, FILENAME_MAX, "%s%s/memory.memsw.limit_in_bytes", cgroup_memory_base, cg->id); + cg->filename_memoryswap_limit = strdupz(filename); + } + } + if (unlikely(cgroup_enable_memory_failcnt && !cg->memory.filename_failcnt)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.failcnt", cgroup_memory_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory.filename_failcnt = strdupz(filename); + cg->memory.enabled_failcnt = cgroup_enable_memory_failcnt; + } + } + + // Blkio + if (unlikely(cgroup_enable_blkio_io && !cg->io_service_bytes.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_service_bytes_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->io_service_bytes.filename = strdupz(filename); + cg->io_service_bytes.enabled = cgroup_enable_blkio_io; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_service_bytes", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_service_bytes.filename = strdupz(filename); + cg->io_service_bytes.enabled = cgroup_enable_blkio_io; + } + } + } + if (unlikely(cgroup_enable_blkio_ops && !cg->io_serviced.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_serviced_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->io_serviced.filename = strdupz(filename); + cg->io_serviced.enabled = cgroup_enable_blkio_ops; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_serviced", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_serviced.filename = strdupz(filename); + cg->io_serviced.enabled = cgroup_enable_blkio_ops; + } + } + } + if (unlikely(cgroup_enable_blkio_throttle_io && !cg->throttle_io_service_bytes.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_service_bytes_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->throttle_io_service_bytes.filename = strdupz(filename); + cg->throttle_io_service_bytes.enabled = cgroup_enable_blkio_throttle_io; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_service_bytes", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->throttle_io_service_bytes.filename = strdupz(filename); + cg->throttle_io_service_bytes.enabled = cgroup_enable_blkio_throttle_io; + } + } + } + if (unlikely(cgroup_enable_blkio_throttle_ops && !cg->throttle_io_serviced.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_serviced_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->throttle_io_serviced.filename = strdupz(filename); + cg->throttle_io_serviced.enabled = cgroup_enable_blkio_throttle_ops; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_serviced", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->throttle_io_serviced.filename = strdupz(filename); + cg->throttle_io_serviced.enabled = cgroup_enable_blkio_throttle_ops; + } + } + } + if (unlikely(cgroup_enable_blkio_merged_ops && !cg->io_merged.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_merged_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->io_merged.filename = strdupz(filename); + cg->io_merged.enabled = cgroup_enable_blkio_merged_ops; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_merged", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_merged.filename = strdupz(filename); + cg->io_merged.enabled = cgroup_enable_blkio_merged_ops; + } + } + } + if (unlikely(cgroup_enable_blkio_queued_ops && !cg->io_queued.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_queued_recursive", cgroup_blkio_base, cg->id); + if (unlikely(stat(filename, &buf) != -1)) { + cg->io_queued.filename = strdupz(filename); + cg->io_queued.enabled = cgroup_enable_blkio_queued_ops; + } else { + snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_queued", cgroup_blkio_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_queued.filename = strdupz(filename); + cg->io_queued.enabled = cgroup_enable_blkio_queued_ops; + } + } + } + + // Pids + if (unlikely(!cg->pids.pids_current_filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/pids.current", cgroup_pids_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->pids.pids_current_filename = strdupz(filename); + } + } +} + +static inline void discovery_update_filenames_cgroup_v2(struct cgroup *cg) { + char filename[FILENAME_MAX + 1]; + struct stat buf; + + // CPU + if (unlikely((cgroup_enable_cpuacct_stat || cgroup_enable_cpuacct_cpu_throttling) && !cg->cpuacct_stat.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.stat", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_stat.filename = strdupz(filename); + cg->cpuacct_stat.enabled = cgroup_enable_cpuacct_stat; + cg->cpuacct_cpu_throttling.enabled = cgroup_enable_cpuacct_cpu_throttling; + cg->filename_cpuset_cpus = NULL; + cg->filename_cpu_cfs_period = NULL; + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.max", cgroup_unified_base, cg->id); + cg->filename_cpu_cfs_quota = strdupz(filename); + } + } + if (unlikely(cgroup_enable_cpuacct_cpu_shares && !cg->cpuacct_cpu_shares.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.weight", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpuacct_cpu_shares.filename = strdupz(filename); + cg->cpuacct_cpu_shares.enabled = cgroup_enable_cpuacct_cpu_shares; + } + } + + // Memory + // FIXME: this if condition! + if (unlikely( + (cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && + (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !is_cgroup_systemd_service(cg)))) { + 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); + cg->memory.enabled_detailed = + (cgroup_enable_detailed_memory == CONFIG_BOOLEAN_YES) ? CONFIG_BOOLEAN_YES : CONFIG_BOOLEAN_AUTO; + } + } + + if (unlikely(cgroup_enable_memory && !cg->memory.filename_usage_in_bytes)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.current", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory.filename_usage_in_bytes = strdupz(filename); + cg->memory.enabled_usage_in_bytes = cgroup_enable_memory; + snprintfz(filename, FILENAME_MAX, "%s%s/memory.max", cgroup_unified_base, cg->id); + cg->filename_memory_limit = strdupz(filename); + } + } + + if (unlikely(cgroup_enable_swap && !cg->memory.filename_msw_usage_in_bytes)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.swap.current", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory.filename_msw_usage_in_bytes = strdupz(filename); + cg->memory.enabled_msw_usage_in_bytes = cgroup_enable_swap; + snprintfz(filename, FILENAME_MAX, "%s%s/memory.swap.max", cgroup_unified_base, cg->id); + cg->filename_memoryswap_limit = strdupz(filename); + } + } + + // Blkio + if (unlikely(cgroup_enable_blkio_io && !cg->io_service_bytes.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/io.stat", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_service_bytes.filename = strdupz(filename); + cg->io_service_bytes.enabled = cgroup_enable_blkio_io; + } + } + + if (unlikely(cgroup_enable_blkio_ops && !cg->io_serviced.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/io.stat", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_serviced.filename = strdupz(filename); + cg->io_serviced.enabled = cgroup_enable_blkio_ops; + } + } + + // PSI + if (unlikely(cgroup_enable_pressure_cpu && !cg->cpu_pressure.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/cpu.pressure", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->cpu_pressure.filename = strdupz(filename); + cg->cpu_pressure.some.enabled = cgroup_enable_pressure_cpu; + cg->cpu_pressure.full.enabled = CONFIG_BOOLEAN_NO; + } + } + + if (unlikely((cgroup_enable_pressure_io_some || cgroup_enable_pressure_io_full) && !cg->io_pressure.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/io.pressure", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->io_pressure.filename = strdupz(filename); + cg->io_pressure.some.enabled = cgroup_enable_pressure_io_some; + cg->io_pressure.full.enabled = cgroup_enable_pressure_io_full; + } + } + + if (unlikely( + (cgroup_enable_pressure_memory_some || cgroup_enable_pressure_memory_full) && + !cg->memory_pressure.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/memory.pressure", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->memory_pressure.filename = strdupz(filename); + cg->memory_pressure.some.enabled = cgroup_enable_pressure_memory_some; + cg->memory_pressure.full.enabled = cgroup_enable_pressure_memory_full; + } + } + + if (unlikely((cgroup_enable_pressure_irq_some || cgroup_enable_pressure_irq_full) && !cg->irq_pressure.filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/irq.pressure", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->irq_pressure.filename = strdupz(filename); + cg->irq_pressure.some.enabled = cgroup_enable_pressure_irq_some; + cg->irq_pressure.full.enabled = cgroup_enable_pressure_irq_full; + } + } + + // Pids + if (unlikely(!cg->pids.pids_current_filename)) { + snprintfz(filename, FILENAME_MAX, "%s%s/pids.current", cgroup_unified_base, cg->id); + if (likely(stat(filename, &buf) != -1)) { + cg->pids.pids_current_filename = strdupz(filename); + } + } +} + +static inline void discovery_update_filenames_all_cgroups() { + for (struct cgroup *cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { + if (unlikely(!cg->available || !cg->enabled || cg->pending_renames)) + continue; + + if (!cgroup_use_unified_cgroups) + discovery_update_filenames_cgroup_v1(cg); + else if (likely(cgroup_unified_exist)) + discovery_update_filenames_cgroup_v2(cg); + } +} + +static inline void discovery_cleanup_all_cgroups() { + struct cgroup *cg = discovered_cgroup_root, *last = NULL; + + for(; cg ;) { + if(!cg->available) { + // enable the first duplicate cgroup + { + struct cgroup *t; + for (t = discovered_cgroup_root; t; t = t->discovered_next) { + if (t != cg && t->available && !t->enabled && t->options & CGROUP_OPTIONS_DISABLED_DUPLICATE && + (is_cgroup_systemd_service(t) == is_cgroup_systemd_service(cg)) && + t->hash_chart_id == cg->hash_chart_id && !strcmp(t->chart_id, cg->chart_id)) { + netdata_log_debug(D_CGROUP, "Enabling duplicate of cgroup '%s' with id '%s', because the original with id '%s' stopped.", t->chart_id, t->id, cg->id); + t->enabled = 1; + t->options &= ~CGROUP_OPTIONS_DISABLED_DUPLICATE; + break; + } + } + } + + if(!last) + discovered_cgroup_root = cg->discovered_next; + else + last->discovered_next = cg->discovered_next; + + cgroup_free(cg); + + if(!last) + cg = discovered_cgroup_root; + else + cg = last->discovered_next; + } + else { + last = cg; + cg = cg->discovered_next; + } + } +} + +static inline void discovery_copy_discovered_cgroups_to_reader() { + netdata_log_debug(D_CGROUP, "copy discovered cgroups to the main group list"); + + struct cgroup *cg; + + for (cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { + cg->next = cg->discovered_next; + } + + cgroup_root = discovered_cgroup_root; +} + +static inline void discovery_share_cgroups_with_ebpf() { + struct cgroup *cg; + int count; + struct stat buf; + + if (shm_mutex_cgroup_ebpf == SEM_FAILED) { + return; + } + sem_wait(shm_mutex_cgroup_ebpf); + + for (cg = cgroup_root, count = 0; cg; cg = cg->next, count++) { + netdata_ebpf_cgroup_shm_body_t *ptr = &shm_cgroup_ebpf.body[count]; + char *prefix = (is_cgroup_systemd_service(cg)) ? services_chart_id_prefix : cgroup_chart_id_prefix; + snprintfz(ptr->name, CGROUP_EBPF_NAME_SHARED_LENGTH - 1, "%s%s", prefix, cg->chart_id); + ptr->hash = simple_hash(ptr->name); + ptr->options = cg->options; + ptr->enabled = cg->enabled; + if (cgroup_use_unified_cgroups) { + snprintfz(ptr->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_unified_base, cg->id); + if (likely(stat(ptr->path, &buf) == -1)) { + ptr->path[0] = '\0'; + ptr->enabled = 0; + } + } else { + is_cgroup_procs_exist(ptr, cg->id); + } + + netdata_log_debug(D_CGROUP, "cgroup shared: NAME=%s, ENABLED=%d", ptr->name, ptr->enabled); + } + + shm_cgroup_ebpf.header->cgroup_root_count = count; + sem_post(shm_mutex_cgroup_ebpf); +} + +static inline void discovery_find_all_cgroups_v1() { + if (cgroup_enable_cpuacct_stat || cgroup_enable_cpuacct_usage) { + if (discovery_find_dir_in_subdirs(cgroup_cpuacct_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { + cgroup_enable_cpuacct_stat = cgroup_enable_cpuacct_usage = CONFIG_BOOLEAN_NO; + collector_error("CGROUP: disabled cpu statistics."); + } + } + + if (cgroup_enable_blkio_io || cgroup_enable_blkio_ops || cgroup_enable_blkio_throttle_io || + cgroup_enable_blkio_throttle_ops || cgroup_enable_blkio_merged_ops || cgroup_enable_blkio_queued_ops) { + if (discovery_find_dir_in_subdirs(cgroup_blkio_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { + cgroup_enable_blkio_io = cgroup_enable_blkio_ops = cgroup_enable_blkio_throttle_io = + cgroup_enable_blkio_throttle_ops = cgroup_enable_blkio_merged_ops = cgroup_enable_blkio_queued_ops = + CONFIG_BOOLEAN_NO; + collector_error("CGROUP: disabled blkio statistics."); + } + } + + if (cgroup_enable_memory || cgroup_enable_detailed_memory || cgroup_enable_swap || cgroup_enable_memory_failcnt) { + if (discovery_find_dir_in_subdirs(cgroup_memory_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { + cgroup_enable_memory = cgroup_enable_detailed_memory = cgroup_enable_swap = cgroup_enable_memory_failcnt = + CONFIG_BOOLEAN_NO; + collector_error("CGROUP: disabled memory statistics."); + } + } + + if (cgroup_search_in_devices) { + if (discovery_find_dir_in_subdirs(cgroup_devices_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { + cgroup_search_in_devices = 0; + collector_error("CGROUP: disabled devices statistics."); + } + } +} + +static inline void discovery_find_all_cgroups_v2() { + if (discovery_find_dir_in_subdirs(cgroup_unified_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { + cgroup_unified_exist = CONFIG_BOOLEAN_NO; + collector_error("CGROUP: disabled unified cgroups statistics."); + } +} + +static int is_digits_only(const char *s) { + do { + if (!isdigit(*s++)) { + return 0; + } + } while (*s); + + return 1; +} + +static int is_cgroup_k8s_container(const char *id) { + // examples: + // https://github.com/netdata/netdata/blob/0fc101679dcd12f1cb8acdd07bb4c85d8e553e53/collectors/cgroups.plugin/cgroup-name.sh#L121-L147 + const char *p = id; + const char *pp = NULL; + int i = 0; + size_t l = 3; // pod + while ((p = strstr(p, "pod"))) { + i++; + p += l; + pp = p; + } + return !(i < 2 || !pp || !(pp = strchr(pp, '/')) || !pp++ || !*pp); +} + +#define TASK_COMM_LEN 16 + +static int k8s_get_container_first_proc_comm(const char *id, char *comm) { + if (!is_cgroup_k8s_container(id)) { + return 1; + } + + static procfile *ff = NULL; + + char filename[FILENAME_MAX + 1]; + snprintfz(filename, FILENAME_MAX, "%s/%s/cgroup.procs", cgroup_cpuacct_base, id); + + ff = procfile_reopen(ff, filename, NULL, CGROUP_PROCFILE_FLAG); + if (unlikely(!ff)) { + netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot open file '%s'.", filename); + return 1; + } + + ff = procfile_readall(ff); + if (unlikely(!ff)) { + netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot read file '%s'.", filename); + return 1; + } + + unsigned long lines = procfile_lines(ff); + if (likely(lines < 2)) { + return 1; + } + + char *pid = procfile_lineword(ff, 0, 0); + if (!pid || !*pid) { + return 1; + } + + snprintfz(filename, FILENAME_MAX, "%s/proc/%s/comm", netdata_configured_host_prefix, pid); + + ff = procfile_reopen(ff, filename, NULL, PROCFILE_FLAG_DEFAULT); + if (unlikely(!ff)) { + netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot open file '%s'.", filename); + return 1; + } + + ff = procfile_readall(ff); + if (unlikely(!ff)) { + netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot read file '%s'.", filename); + return 1; + } + + lines = procfile_lines(ff); + if (unlikely(lines != 2)) { + return 1; + } + + char *proc_comm = procfile_lineword(ff, 0, 0); + if (!proc_comm || !*proc_comm) { + return 1; + } + + strncpyz(comm, proc_comm, TASK_COMM_LEN); + return 0; +} + +static inline void discovery_process_first_time_seen_cgroup(struct cgroup *cg) { + if (!cg->first_time_seen) { + return; + } + cg->first_time_seen = 0; + + char comm[TASK_COMM_LEN + 1]; + + if (cg->container_orchestrator == CGROUPS_ORCHESTRATOR_UNSET) { + if (strstr(cg->id, "kubepods")) { + cg->container_orchestrator = CGROUPS_ORCHESTRATOR_K8S; + } else { + cg->container_orchestrator = CGROUPS_ORCHESTRATOR_UNKNOWN; + } + } + + if (is_inside_k8s && !k8s_get_container_first_proc_comm(cg->id, comm)) { + // container initialization may take some time when CPU % is high + // seen on GKE: comm is '6' before 'runc:[2:INIT]' (dunno if it could be another number) + if (is_digits_only(comm) || matches_entrypoint_parent_process_comm(comm)) { + cg->first_time_seen = 1; + return; + } + if (!strcmp(comm, "pause")) { + // a container that holds the network namespace for the pod + // we don't need to collect its metrics + cg->processed = 1; + return; + } + } + + if (cgroup_enable_systemd_services && matches_systemd_services_cgroups(cg->id)) { + netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') matches 'cgroups to match as systemd services'", cg->id, cg->chart_id); + convert_cgroup_to_systemd_service(cg); + return; + } + + if (matches_enabled_cgroup_renames(cg->id)) { + netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') matches 'run script to rename cgroups matching', will try to rename it", cg->id, cg->chart_id); + if (is_inside_k8s && is_cgroup_k8s_container(cg->id)) { + // it may take up to a minute for the K8s API to return data for the container + // tested on AWS K8s cluster with 100% CPU utilization + cg->pending_renames = 9; // 1.5 minute + } else { + cg->pending_renames = 2; + } + } +} + +static int discovery_is_cgroup_duplicate(struct cgroup *cg) { + // https://github.com/netdata/netdata/issues/797#issuecomment-241248884 + struct cgroup *c; + for (c = discovered_cgroup_root; c; c = c->discovered_next) { + if (c != cg && c->enabled && (is_cgroup_systemd_service(c) == is_cgroup_systemd_service(cg)) && + c->hash_chart_id == cg->hash_chart_id && !strcmp(c->chart_id, cg->chart_id)) { + collector_error( + "CGROUP: chart id '%s' already exists with id '%s' and is enabled and available. Disabling cgroup with id '%s'.", + cg->chart_id, + c->id, + cg->id); + return 1; + } + } + return 0; +} + +// ---------------------------------------------------------------------------- +// cgroup network interfaces + +#define CGROUP_NETWORK_INTERFACE_MAX_LINE 2048 + +static inline void read_cgroup_network_interfaces(struct cgroup *cg) { + netdata_log_debug(D_CGROUP, "looking for the network interfaces of cgroup '%s' with chart id '%s'", cg->id, cg->chart_id); + + pid_t cgroup_pid; + char cgroup_identifier[CGROUP_NETWORK_INTERFACE_MAX_LINE + 1]; + + if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + snprintfz(cgroup_identifier, CGROUP_NETWORK_INTERFACE_MAX_LINE, "%s%s", cgroup_cpuacct_base, cg->id); + } + else { + snprintfz(cgroup_identifier, CGROUP_NETWORK_INTERFACE_MAX_LINE, "%s%s", cgroup_unified_base, cg->id); + } + + netdata_log_debug(D_CGROUP, "executing cgroup_identifier %s --cgroup '%s' for cgroup '%s'", cgroups_network_interface_script, cgroup_identifier, cg->id); + FILE *fp_child_input, *fp_child_output; + (void)netdata_popen_raw_default_flags_and_environment(&cgroup_pid, &fp_child_input, &fp_child_output, cgroups_network_interface_script, "--cgroup", cgroup_identifier); + if(!fp_child_output) { + collector_error("CGROUP: cannot popen(%s --cgroup \"%s\", \"r\").", cgroups_network_interface_script, cgroup_identifier); + return; + } + + char *s; + char buffer[CGROUP_NETWORK_INTERFACE_MAX_LINE + 1]; + while((s = fgets(buffer, CGROUP_NETWORK_INTERFACE_MAX_LINE, fp_child_output))) { + trim(s); + + if(*s && *s != '\n') { + char *t = s; + while(*t && *t != ' ') t++; + if(*t == ' ') { + *t = '\0'; + t++; + } + + if(!*s) { + collector_error("CGROUP: empty host interface returned by script"); + continue; + } + + if(!*t) { + collector_error("CGROUP: empty guest interface returned by script"); + continue; + } + + struct cgroup_network_interface *i = callocz(1, sizeof(struct cgroup_network_interface)); + i->host_device = strdupz(s); + i->container_device = strdupz(t); + i->next = cg->interfaces; + cg->interfaces = i; + + collector_info("CGROUP: cgroup '%s' has network interface '%s' as '%s'", cg->id, i->host_device, i->container_device); + + // register a device rename to proc_net_dev.c + netdev_rename_device_add(i->host_device, i->container_device, cg->chart_id, cg->chart_labels, + k8s_is_kubepod(cg) ? "k8s." : "", cgroup_netdev_get(cg)); + } + } + + netdata_pclose(fp_child_input, fp_child_output, cgroup_pid); + // netdata_log_debug(D_CGROUP, "closed cgroup_identifier for cgroup '%s'", cg->id); +} + +static inline void discovery_process_cgroup(struct cgroup *cg) { + if (!cg->available || cg->processed) { + return; + } + + if (cg->first_time_seen) { + worker_is_busy(WORKER_DISCOVERY_PROCESS_FIRST_TIME); + discovery_process_first_time_seen_cgroup(cg); + if (unlikely(cg->first_time_seen || cg->processed)) { + return; + } + } + + if (cg->pending_renames) { + worker_is_busy(WORKER_DISCOVERY_PROCESS_RENAME); + discovery_rename_cgroup(cg); + if (unlikely(cg->pending_renames || cg->processed)) { + return; + } + } + + cg->processed = 1; + + if ((strlen(cg->chart_id) + strlen(cgroup_chart_id_prefix)) >= RRD_ID_LENGTH_MAX) { + collector_info("cgroup '%s' (chart id '%s') disabled because chart_id exceeds the limit (RRD_ID_LENGTH_MAX)", cg->id, cg->chart_id); + return; + } + + if (is_cgroup_systemd_service(cg)) { + if (discovery_is_cgroup_duplicate(cg)) { + cg->enabled = 0; + cg->options |= CGROUP_OPTIONS_DISABLED_DUPLICATE; + return; + } + if (!cg->chart_labels) + cg->chart_labels = rrdlabels_create(); + rrdlabels_add(cg->chart_labels, "service_name", cg->name, RRDLABEL_SRC_AUTO); + cg->enabled = 1; + return; + } + + if (!(cg->enabled = matches_enabled_cgroup_names(cg->name))) { + netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') disabled by 'enable by default cgroups names matching'", cg->id, cg->name); + return; + } + + if (!(cg->enabled = matches_enabled_cgroup_paths(cg->id))) { + netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') disabled by 'enable by default cgroups matching'", cg->id, cg->name); + return; + } + + if (discovery_is_cgroup_duplicate(cg)) { + cg->enabled = 0; + cg->options |= CGROUP_OPTIONS_DISABLED_DUPLICATE; + return; + } + + if (!cg->chart_labels) + cg->chart_labels = rrdlabels_create(); + + if (!k8s_is_kubepod(cg)) { + rrdlabels_add(cg->chart_labels, "cgroup_name", cg->name, RRDLABEL_SRC_AUTO); + if (!rrdlabels_exist(cg->chart_labels, "image")) + rrdlabels_add(cg->chart_labels, "image", "", RRDLABEL_SRC_AUTO); + } + + worker_is_busy(WORKER_DISCOVERY_PROCESS_NETWORK); + read_cgroup_network_interfaces(cg); +} + +static inline void discovery_find_all_cgroups() { + netdata_log_debug(D_CGROUP, "searching for cgroups"); + + worker_is_busy(WORKER_DISCOVERY_INIT); + discovery_mark_as_unavailable_all_cgroups(); + + worker_is_busy(WORKER_DISCOVERY_FIND); + if (!cgroup_use_unified_cgroups) { + discovery_find_all_cgroups_v1(); + } else { + discovery_find_all_cgroups_v2(); + } + + for (struct cgroup *cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { + worker_is_busy(WORKER_DISCOVERY_PROCESS); + discovery_process_cgroup(cg); + } + + worker_is_busy(WORKER_DISCOVERY_UPDATE); + discovery_update_filenames_all_cgroups(); + + worker_is_busy(WORKER_DISCOVERY_LOCK); + uv_mutex_lock(&cgroup_root_mutex); + + worker_is_busy(WORKER_DISCOVERY_CLEANUP); + discovery_cleanup_all_cgroups(); + + worker_is_busy(WORKER_DISCOVERY_COPY); + discovery_copy_discovered_cgroups_to_reader(); + + uv_mutex_unlock(&cgroup_root_mutex); + + worker_is_busy(WORKER_DISCOVERY_SHARE); + discovery_share_cgroups_with_ebpf(); + + netdata_log_debug(D_CGROUP, "done searching for cgroups"); +} + +void cgroup_discovery_worker(void *ptr) +{ + UNUSED(ptr); + + worker_register("CGROUPSDISC"); + worker_register_job_name(WORKER_DISCOVERY_INIT, "init"); + worker_register_job_name(WORKER_DISCOVERY_FIND, "find"); + worker_register_job_name(WORKER_DISCOVERY_PROCESS, "process"); + worker_register_job_name(WORKER_DISCOVERY_PROCESS_RENAME, "rename"); + worker_register_job_name(WORKER_DISCOVERY_PROCESS_NETWORK, "network"); + worker_register_job_name(WORKER_DISCOVERY_PROCESS_FIRST_TIME, "new"); + worker_register_job_name(WORKER_DISCOVERY_UPDATE, "update"); + worker_register_job_name(WORKER_DISCOVERY_CLEANUP, "cleanup"); + worker_register_job_name(WORKER_DISCOVERY_COPY, "copy"); + worker_register_job_name(WORKER_DISCOVERY_SHARE, "share"); + worker_register_job_name(WORKER_DISCOVERY_LOCK, "lock"); + + entrypoint_parent_process_comm = simple_pattern_create( + " runc:[* " // http://terenceli.github.io/%E6%8A%80%E6%9C%AF/2021/12/28/runc-internals-3) + " exe ", // https://github.com/falcosecurity/falco/blob/9d41b0a151b83693929d3a9c84f7c5c85d070d3a/rules/falco_rules.yaml#L1961 + NULL, + SIMPLE_PATTERN_EXACT, true); + + service_register(SERVICE_THREAD_TYPE_LIBUV, NULL, NULL, NULL, false); + + while (service_running(SERVICE_COLLECTORS)) { + worker_is_idle(); + + uv_mutex_lock(&discovery_thread.mutex); + uv_cond_wait(&discovery_thread.cond_var, &discovery_thread.mutex); + uv_mutex_unlock(&discovery_thread.mutex); + + if (unlikely(!service_running(SERVICE_COLLECTORS))) + break; + + discovery_find_all_cgroups(); + } + collector_info("discovery thread stopped"); + worker_unregister(); + service_exits(); + __atomic_store_n(&discovery_thread.exited,1,__ATOMIC_RELAXED); +} diff --git a/collectors/cgroups.plugin/cgroup-internals.h b/collectors/cgroups.plugin/cgroup-internals.h new file mode 100644 index 000000000..a69802240 --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-internals.h @@ -0,0 +1,514 @@ +#include "sys_fs_cgroup.h" + +#ifndef NETDATA_CGROUP_INTERNALS_H +#define NETDATA_CGROUP_INTERNALS_H 1 + +#ifdef NETDATA_INTERNAL_CHECKS +#define CGROUP_PROCFILE_FLAG PROCFILE_FLAG_DEFAULT +#else +#define CGROUP_PROCFILE_FLAG PROCFILE_FLAG_NO_ERROR_ON_FILE_IO +#endif + +struct blkio { + int updated; + int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + int delay_counter; + + char *filename; + + unsigned long long Read; + unsigned long long Write; +/* + unsigned long long Sync; + unsigned long long Async; + unsigned long long Total; +*/ +}; + +struct pids { + char *pids_current_filename; + int pids_current_updated; + unsigned long long pids_current; +}; + +// https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt +struct memory { + ARL_BASE *arl_base; + ARL_ENTRY *arl_dirty; + ARL_ENTRY *arl_swap; + + int updated_detailed; + int updated_usage_in_bytes; + int updated_msw_usage_in_bytes; + int updated_failcnt; + + int enabled_detailed; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + int enabled_usage_in_bytes; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + int enabled_msw_usage_in_bytes; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + int enabled_failcnt; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + + int delay_counter_detailed; + int delay_counter_failcnt; + + char *filename_detailed; + char *filename_usage_in_bytes; + char *filename_msw_usage_in_bytes; + char *filename_failcnt; + + int detailed_has_dirty; + int detailed_has_swap; + + // detailed metrics +/* + unsigned long long cache; + unsigned long long rss; + unsigned long long rss_huge; + unsigned long long mapped_file; + unsigned long long writeback; + unsigned long long dirty; + unsigned long long swap; + unsigned long long pgpgin; + unsigned long long pgpgout; + unsigned long long pgfault; + unsigned long long pgmajfault; + unsigned long long inactive_anon; + unsigned long long active_anon; + unsigned long long inactive_file; + unsigned long long active_file; + unsigned long long unevictable; + unsigned long long hierarchical_memory_limit; +*/ + //unified cgroups metrics + unsigned long long anon; + unsigned long long kernel_stack; + unsigned long long slab; + unsigned long long sock; + // unsigned long long shmem; + unsigned long long anon_thp; + //unsigned long long file_writeback; + //unsigned long long file_dirty; + //unsigned long long file; + + unsigned long long total_cache; + unsigned long long total_rss; + unsigned long long total_rss_huge; + unsigned long long total_mapped_file; + unsigned long long total_writeback; + unsigned long long total_dirty; + unsigned long long total_swap; + unsigned long long total_pgpgin; + unsigned long long total_pgpgout; + unsigned long long total_pgfault; + unsigned long long total_pgmajfault; +/* + 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; +*/ + + // single file metrics + unsigned long long usage_in_bytes; + unsigned long long msw_usage_in_bytes; + unsigned long long failcnt; +}; + +// https://www.kernel.org/doc/Documentation/cgroup-v1/cpuacct.txt +struct cpuacct_stat { + int updated; + int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + + char *filename; + + unsigned long long user; // v1, v2(user_usec) + unsigned long long system; // v1, v2(system_usec) +}; + +// https://www.kernel.org/doc/Documentation/cgroup-v1/cpuacct.txt +struct cpuacct_usage { + int updated; + int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + + char *filename; + + unsigned int cpus; + unsigned long long *cpu_percpu; +}; + +// represents cpuacct/cpu.stat, for v2 'cpuacct_stat' is used for 'user_usec', 'system_usec' +struct cpuacct_cpu_throttling { + int updated; + int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + + char *filename; + + unsigned long long nr_periods; + unsigned long long nr_throttled; + unsigned long long throttled_time; + + unsigned long long nr_throttled_perc; +}; + +// https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/6/html/resource_management_guide/sec-cpu#sect-cfs +// https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/8/html/managing_monitoring_and_updating_the_kernel/using-cgroups-v2-to-control-distribution-of-cpu-time-for-applications_managing-monitoring-and-updating-the-kernel#proc_controlling-distribution-of-cpu-time-for-applications-by-adjusting-cpu-weight_using-cgroups-v2-to-control-distribution-of-cpu-time-for-applications +struct cpuacct_cpu_shares { + int updated; + int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO + + char *filename; + + unsigned long long shares; +}; + +struct cgroup_network_interface { + const char *host_device; + const char *container_device; + struct cgroup_network_interface *next; +}; + +enum cgroups_container_orchestrator { + CGROUPS_ORCHESTRATOR_UNSET, + CGROUPS_ORCHESTRATOR_UNKNOWN, + CGROUPS_ORCHESTRATOR_K8S +}; + + +// *** WARNING *** The fields are not thread safe. Take care of safe usage. +struct cgroup { + uint32_t options; + + int first_time_seen; // first time seen by the discoverer + int processed; // the discoverer is done processing a cgroup (resolved name, set 'enabled' option) + + char available; // found in the filesystem + char enabled; // enabled in the config + + bool function_ready; // true after the first iteration of chart creation/update + + char pending_renames; + + char *id; + uint32_t hash; + + char *intermediate_id; // TODO: remove it when the renaming script is fixed + + char *chart_id; + uint32_t hash_chart_id; + + // 'cgroup_name' label value. + // by default this is the *id (path), later changed to the resolved name (cgroup-name.sh) or systemd service name. + char *name; + + RRDLABELS *chart_labels; + + int container_orchestrator; + + struct cpuacct_stat cpuacct_stat; + struct cpuacct_usage cpuacct_usage; + struct cpuacct_cpu_throttling cpuacct_cpu_throttling; + struct cpuacct_cpu_shares cpuacct_cpu_shares; + + struct memory memory; + + struct blkio io_service_bytes; // bytes + struct blkio io_serviced; // operations + + struct blkio throttle_io_service_bytes; // bytes + struct blkio throttle_io_serviced; // operations + + struct blkio io_merged; // operations + struct blkio io_queued; // operations + + struct pids pids; + + struct cgroup_network_interface *interfaces; + + struct pressure cpu_pressure; + struct pressure io_pressure; + struct pressure memory_pressure; + struct pressure irq_pressure; + + // Cpu + RRDSET *st_cpu; + RRDDIM *st_cpu_rd_user; + RRDDIM *st_cpu_rd_system; + + RRDSET *st_cpu_limit; + RRDSET *st_cpu_per_core; + RRDSET *st_cpu_nr_throttled; + RRDSET *st_cpu_throttled_time; + RRDSET *st_cpu_shares; + + // Memory + RRDSET *st_mem; + RRDDIM *st_mem_rd_ram; + RRDDIM *st_mem_rd_swap; + + RRDSET *st_mem_utilization; + RRDSET *st_writeback; + RRDSET *st_mem_activity; + RRDSET *st_pgfaults; + RRDSET *st_mem_usage; + RRDSET *st_mem_usage_limit; + RRDSET *st_mem_failcnt; + + // Blkio + RRDSET *st_io; + RRDDIM *st_io_rd_read; + RRDDIM *st_io_rd_written; + + RRDSET *st_serviced_ops; + + RRDSET *st_throttle_io; + RRDDIM *st_throttle_io_rd_read; + RRDDIM *st_throttle_io_rd_written; + + RRDSET *st_throttle_serviced_ops; + + RRDSET *st_queued_ops; + RRDSET *st_merged_ops; + + // Pids + RRDSET *st_pids; + RRDDIM *st_pids_rd_pids_current; + + // per cgroup chart variables + char *filename_cpuset_cpus; + unsigned long long cpuset_cpus; + + char *filename_cpu_cfs_period; + unsigned long long cpu_cfs_period; + + char *filename_cpu_cfs_quota; + unsigned long long cpu_cfs_quota; + + const RRDSETVAR_ACQUIRED *chart_var_cpu_limit; + NETDATA_DOUBLE prev_cpu_usage; + + char *filename_memory_limit; + unsigned long long memory_limit; + const RRDSETVAR_ACQUIRED *chart_var_memory_limit; + + char *filename_memoryswap_limit; + unsigned long long memoryswap_limit; + const RRDSETVAR_ACQUIRED *chart_var_memoryswap_limit; + + const DICTIONARY_ITEM *cgroup_netdev_link; + + struct cgroup *next; + struct cgroup *discovered_next; + +}; + +struct discovery_thread { + uv_thread_t thread; + uv_mutex_t mutex; + uv_cond_t cond_var; + int exited; +}; + +extern struct discovery_thread discovery_thread; + +extern char *cgroups_rename_script; +extern char cgroup_chart_id_prefix[]; +extern char services_chart_id_prefix[]; +extern uv_mutex_t cgroup_root_mutex; + +void cgroup_discovery_worker(void *ptr); + +extern int is_inside_k8s; +extern long system_page_size; +extern int cgroup_enable_cpuacct_stat; +extern int cgroup_enable_cpuacct_usage; +extern int cgroup_enable_cpuacct_cpu_throttling; +extern int cgroup_enable_cpuacct_cpu_shares; +extern int cgroup_enable_memory; +extern int cgroup_enable_detailed_memory; +extern int cgroup_enable_memory_failcnt; +extern int cgroup_enable_swap; +extern int cgroup_enable_blkio_io; +extern int cgroup_enable_blkio_ops; +extern int cgroup_enable_blkio_throttle_io; +extern int cgroup_enable_blkio_throttle_ops; +extern int cgroup_enable_blkio_merged_ops; +extern int cgroup_enable_blkio_queued_ops; +extern int cgroup_enable_pressure_cpu; +extern int cgroup_enable_pressure_io_some; +extern int cgroup_enable_pressure_io_full; +extern int cgroup_enable_pressure_memory_some; +extern int cgroup_enable_pressure_memory_full; +extern int cgroup_enable_pressure_irq_some; +extern int cgroup_enable_pressure_irq_full; +extern int cgroup_enable_systemd_services; +extern int cgroup_enable_systemd_services_detailed_memory; +extern int cgroup_used_memory; +extern int cgroup_use_unified_cgroups; +extern int cgroup_unified_exist; +extern int cgroup_search_in_devices; +extern int cgroup_check_for_new_every; +extern int cgroup_update_every; +extern int cgroup_containers_chart_priority; +extern int cgroup_recheck_zero_blkio_every_iterations; +extern int cgroup_recheck_zero_mem_failcnt_every_iterations; +extern int cgroup_recheck_zero_mem_detailed_every_iterations; +extern char *cgroup_cpuacct_base; +extern char *cgroup_cpuset_base; +extern char *cgroup_blkio_base; +extern char *cgroup_memory_base; +extern char *cgroup_pids_base; +extern char *cgroup_devices_base; +extern char *cgroup_unified_base; +extern int cgroup_root_count; +extern int cgroup_root_max; +extern int cgroup_max_depth; +extern SIMPLE_PATTERN *enabled_cgroup_paths; +extern SIMPLE_PATTERN *enabled_cgroup_names; +extern SIMPLE_PATTERN *search_cgroup_paths; +extern SIMPLE_PATTERN *enabled_cgroup_renames; +extern SIMPLE_PATTERN *systemd_services_cgroups; +extern SIMPLE_PATTERN *entrypoint_parent_process_comm; +extern char *cgroups_network_interface_script; +extern int cgroups_check; +extern uint32_t Read_hash; +extern uint32_t Write_hash; +extern uint32_t user_hash; +extern uint32_t system_hash; +extern uint32_t user_usec_hash; +extern uint32_t system_usec_hash; +extern uint32_t nr_periods_hash; +extern uint32_t nr_throttled_hash; +extern uint32_t throttled_time_hash; +extern uint32_t throttled_usec_hash; +extern struct cgroup *cgroup_root; + +extern netdata_ebpf_cgroup_shm_t shm_cgroup_ebpf; +extern int shm_fd_cgroup_ebpf; +extern sem_t *shm_mutex_cgroup_ebpf; + +enum cgroups_type { CGROUPS_AUTODETECT_FAIL, CGROUPS_V1, CGROUPS_V2 }; + +enum cgroups_systemd_setting { + SYSTEMD_CGROUP_ERR, + SYSTEMD_CGROUP_LEGACY, + SYSTEMD_CGROUP_HYBRID, + SYSTEMD_CGROUP_UNIFIED +}; + +struct cgroups_systemd_config_setting { + char *name; + enum cgroups_systemd_setting setting; +}; + +extern struct cgroups_systemd_config_setting cgroups_systemd_options[]; + +static inline int matches_enabled_cgroup_paths(char *id) { + return simple_pattern_matches(enabled_cgroup_paths, id); +} + +static inline int matches_enabled_cgroup_names(char *name) { + return simple_pattern_matches(enabled_cgroup_names, name); +} + +static inline int matches_enabled_cgroup_renames(char *id) { + return simple_pattern_matches(enabled_cgroup_renames, id); +} + +static inline int matches_systemd_services_cgroups(char *id) { + return simple_pattern_matches(systemd_services_cgroups, id); +} + +static inline int matches_search_cgroup_paths(const char *dir) { + return simple_pattern_matches(search_cgroup_paths, dir); +} + +static inline int matches_entrypoint_parent_process_comm(const char *comm) { + return simple_pattern_matches(entrypoint_parent_process_comm, comm); +} + +static inline int is_cgroup_systemd_service(struct cgroup *cg) { + return (int)(cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE); +} + +static inline int k8s_is_kubepod(struct cgroup *cg) { + return cg->container_orchestrator == CGROUPS_ORCHESTRATOR_K8S; +} + +static inline char *cgroup_chart_type(char *buffer, struct cgroup *cg) { + buffer[0] = '\0'; + + if (cg->chart_id[0] == '\0' || (cg->chart_id[0] == '/' && cg->chart_id[1] == '\0')) + strncpy(buffer, "cgroup_root", RRD_ID_LENGTH_MAX); + else if (is_cgroup_systemd_service(cg)) + snprintfz(buffer, RRD_ID_LENGTH_MAX, "%s%s", services_chart_id_prefix, cg->chart_id); + else + snprintfz(buffer, RRD_ID_LENGTH_MAX, "%s%s", cgroup_chart_id_prefix, cg->chart_id); + + return buffer; +} + +#define RRDFUNCTIONS_CGTOP_HELP "View running containers" + +int cgroup_function_cgroup_top(BUFFER *wb, int timeout, const char *function, void *collector_data, + rrd_function_result_callback_t result_cb, void *result_cb_data, + rrd_function_is_cancelled_cb_t is_cancelled_cb, void *is_cancelled_cb_data, + rrd_function_register_canceller_cb_t register_canceller_cb, void *register_canceller_cb_data); +int cgroup_function_systemd_top(BUFFER *wb, int timeout, const char *function, void *collector_data, + rrd_function_result_callback_t result_cb, void *result_cb_data, + rrd_function_is_cancelled_cb_t is_cancelled_cb, void *is_cancelled_cb_data, + rrd_function_register_canceller_cb_t register_canceller_cb, void *register_canceller_cb_data); + +void cgroup_netdev_link_init(void); +const DICTIONARY_ITEM *cgroup_netdev_get(struct cgroup *cg); +void cgroup_netdev_delete(struct cgroup *cg); + +void update_cpu_utilization_chart(struct cgroup *cg); +void update_cpu_utilization_limit_chart(struct cgroup *cg, NETDATA_DOUBLE cpu_limit); +void update_cpu_throttled_chart(struct cgroup *cg); +void update_cpu_throttled_duration_chart(struct cgroup *cg); +void update_cpu_shares_chart(struct cgroup *cg); +void update_cpu_per_core_usage_chart(struct cgroup *cg); + +void update_mem_usage_limit_chart(struct cgroup *cg, unsigned long long memory_limit); +void update_mem_utilization_chart(struct cgroup *cg, unsigned long long memory_limit); +void update_mem_usage_detailed_chart(struct cgroup *cg); +void update_mem_writeback_chart(struct cgroup *cg); +void update_mem_activity_chart(struct cgroup *cg); +void update_mem_pgfaults_chart(struct cgroup *cg); +void update_mem_failcnt_chart(struct cgroup *cg); +void update_mem_usage_chart(struct cgroup *cg); + +void update_io_serviced_bytes_chart(struct cgroup *cg); +void update_io_serviced_ops_chart(struct cgroup *cg); +void update_throttle_io_serviced_bytes_chart(struct cgroup *cg); +void update_throttle_io_serviced_ops_chart(struct cgroup *cg); +void update_io_queued_ops_chart(struct cgroup *cg); +void update_io_merged_ops_chart(struct cgroup *cg); + +void update_pids_current_chart(struct cgroup *cg); + +void update_cpu_some_pressure_chart(struct cgroup *cg); +void update_cpu_some_pressure_stall_time_chart(struct cgroup *cg); +void update_cpu_full_pressure_chart(struct cgroup *cg); +void update_cpu_full_pressure_stall_time_chart(struct cgroup *cg); + +void update_mem_some_pressure_chart(struct cgroup *cg); +void update_mem_some_pressure_stall_time_chart(struct cgroup *cg); +void update_mem_full_pressure_chart(struct cgroup *cg); +void update_mem_full_pressure_stall_time_chart(struct cgroup *cg); + +void update_irq_some_pressure_chart(struct cgroup *cg); +void update_irq_some_pressure_stall_time_chart(struct cgroup *cg); +void update_irq_full_pressure_chart(struct cgroup *cg); +void update_irq_full_pressure_stall_time_chart(struct cgroup *cg); + +void update_io_some_pressure_chart(struct cgroup *cg); +void update_io_some_pressure_stall_time_chart(struct cgroup *cg); +void update_io_full_pressure_chart(struct cgroup *cg); +void update_io_full_pressure_stall_time_chart(struct cgroup *cg); + +#endif // NETDATA_CGROUP_INTERNALS_H
\ No newline at end of file diff --git a/collectors/cgroups.plugin/cgroup-name.sh b/collectors/cgroups.plugin/cgroup-name.sh deleted file mode 100755 index c0f3d0cb6..000000000 --- a/collectors/cgroups.plugin/cgroup-name.sh +++ /dev/null @@ -1,659 +0,0 @@ -#!/usr/bin/env bash -#shellcheck disable=SC2001 - -# netdata -# real-time performance and health monitoring, done right! -# (C) 2016 Costa Tsaousis <costa@tsaousis.gr> -# SPDX-License-Identifier: GPL-3.0-or-later -# -# Script to find a better name for cgroups -# - -export PATH="${PATH}:/sbin:/usr/sbin:/usr/local/sbin" -export LC_ALL=C - -# ----------------------------------------------------------------------------- - -PROGRAM_NAME="$(basename "${0}")" - -LOG_LEVEL_ERR=1 -LOG_LEVEL_WARN=2 -LOG_LEVEL_INFO=3 -LOG_LEVEL="$LOG_LEVEL_INFO" - -set_log_severity_level() { - case ${NETDATA_LOG_SEVERITY_LEVEL,,} in - "info") LOG_LEVEL="$LOG_LEVEL_INFO";; - "warn" | "warning") LOG_LEVEL="$LOG_LEVEL_WARN";; - "err" | "error") LOG_LEVEL="$LOG_LEVEL_ERR";; - esac -} - -set_log_severity_level - -logdate() { - date "+%Y-%m-%d %H:%M:%S" -} - -log() { - local status="${1}" - shift - - echo >&2 "$(logdate): ${PROGRAM_NAME}: ${status}: ${*}" - -} - -info() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_INFO" -gt "$LOG_LEVEL" ]] && return - log INFO "${@}" -} - -warning() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_WARN" -gt "$LOG_LEVEL" ]] && return - log WARNING "${@}" -} - -error() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_ERR" -gt "$LOG_LEVEL" ]] && return - log ERROR "${@}" -} - -fatal() { - log FATAL "${@}" - exit 1 -} - -function parse_docker_like_inspect_output() { - local output="${1}" - eval "$(grep -E "^(NOMAD_NAMESPACE|NOMAD_JOB_NAME|NOMAD_TASK_NAME|NOMAD_SHORT_ALLOC_ID|CONT_NAME|IMAGE_NAME)=" <<<"$output")" - if [ -n "$NOMAD_NAMESPACE" ] && [ -n "$NOMAD_JOB_NAME" ] && [ -n "$NOMAD_TASK_NAME" ] && [ -n "$NOMAD_SHORT_ALLOC_ID" ]; then - NAME="${NOMAD_NAMESPACE}-${NOMAD_JOB_NAME}-${NOMAD_TASK_NAME}-${NOMAD_SHORT_ALLOC_ID}" - else - NAME=$(echo "${CONT_NAME}" | sed 's|^/||') - fi - if [ -n "${IMAGE_NAME}" ]; then - LABELS="image=\"${IMAGE_NAME}\"" - fi -} - -function docker_like_get_name_command() { - local command="${1}" - local id="${2}" - info "Running command: ${command} inspect --format='{{range .Config.Env}}{{println .}}{{end}}CONT_NAME={{ .Name}}' \"${id}\"" - if OUTPUT="$(${command} inspect --format='{{range .Config.Env}}{{println .}}{{end}}CONT_NAME={{ .Name}}{{println}}IMAGE_NAME={{ .Config.Image}}' "${id}")" && - [ -n "$OUTPUT" ]; then - parse_docker_like_inspect_output "$OUTPUT" - fi - return 0 -} - -function docker_like_get_name_api() { - local host_var="${1}" - local host="${!host_var}" - local path="/containers/${2}/json" - if [ -z "${host}" ]; then - warning "No ${host_var} is set" - return 1 - fi - if ! command -v jq >/dev/null 2>&1; then - warning "Can't find jq command line tool. jq is required for netdata to retrieve container name using ${host} API, falling back to docker ps" - return 1 - fi - if [ -S "${host}" ]; then - info "Running API command: curl --unix-socket \"${host}\" http://localhost${path}" - JSON=$(curl -sS --unix-socket "${host}" "http://localhost${path}") - else - info "Running API command: curl \"${host}${path}\"" - JSON=$(curl -sS "${host}${path}") - fi - if OUTPUT=$(echo "${JSON}" | jq -r '.Config.Env[],"CONT_NAME=\(.Name)","IMAGE_NAME=\(.Config.Image)"') && [ -n "$OUTPUT" ]; then - parse_docker_like_inspect_output "$OUTPUT" - fi - return 0 -} - -# get_lbl_val returns the value for the label with the given name. -# Returns "null" string if the label doesn't exist. -# Expected labels format: 'name="value",...'. -function get_lbl_val() { - local labels want_name - labels="${1}" - want_name="${2}" - - IFS=, read -ra labels <<< "$labels" - - local lname lval - for l in "${labels[@]}"; do - IFS="=" read -r lname lval <<< "$l" - if [ "$want_name" = "$lname" ] && [ -n "$lval" ]; then - echo "${lval:1:-1}" # trim " - return 0 - fi - done - - echo "null" - return 1 -} - -function add_lbl_prefix() { - local orig_labels prefix - orig_labels="${1}" - prefix="${2}" - - IFS=, read -ra labels <<< "$orig_labels" - - local new_labels - for l in "${labels[@]}"; do - new_labels+="${prefix}${l}," - done - - echo "${new_labels:0:-1}" # trim last ',' -} - -function remove_lbl() { - local orig_labels lbl_name - orig_labels="${1}" - lbl_name="${2}" - - IFS=, read -ra labels <<< "$orig_labels" - - local new_labels - for l in "${labels[@]}"; do - IFS="=" read -r lname lval <<< "$l" - [ "$lbl_name" != "$lname" ] && new_labels+="${l}," - done - - echo "${new_labels:0:-1}" # trim last ',' -} - -function k8s_is_pause_container() { - local cgroup_path="${1}" - - local file - if [ -d "${NETDATA_HOST_PREFIX}/sys/fs/cgroup/cpuacct" ]; then - file="${NETDATA_HOST_PREFIX}/sys/fs/cgroup/cpuacct/$cgroup_path/cgroup.procs" - else - file="${NETDATA_HOST_PREFIX}/sys/fs/cgroup/$cgroup_path/cgroup.procs" - fi - - [ ! -f "$file" ] && return 1 - - local procs - IFS= read -rd' ' procs 2>/dev/null <"$file" - #shellcheck disable=SC2206 - procs=($procs) - - [ "${#procs[@]}" -ne 1 ] && return 1 - - IFS= read -r comm 2>/dev/null <"/proc/${procs[0]}/comm" - - [ "$comm" == "pause" ] - return -} - -function k8s_gcp_get_cluster_name() { - local header url id loc name - header="Metadata-Flavor: Google" - url="http://metadata/computeMetadata/v1" - if id=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/project/project-id") && - loc=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/instance/attributes/cluster-location") && - name=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/instance/attributes/cluster-name") && - [ -n "$id" ] && [ -n "$loc" ] && [ -n "$name" ]; then - echo "gke_${id}_${loc}_${name}" - return 0 - fi - return 1 -} - -# k8s_get_kubepod_name resolves */kubepods/* cgroup name. -# pod level cgroup name format: 'pod_<namespace>_<pod_name>' -# container level cgroup name format: 'cntr_<namespace>_<pod_name>_<container_name>' -function k8s_get_kubepod_name() { - # GKE /sys/fs/cgroup/*/ (cri=docker, cgroups=v1): - # |-- kubepods - # | |-- burstable - # | | |-- pod98cee708-023b-11eb-933d-42010a800193 - # | | | |-- 922161c98e6ea450bf665226cdc64ca2aa3e889934c2cff0aec4325f8f78ac03 - # | `-- pode314bbac-d577-11ea-a171-42010a80013b - # | |-- 7d505356b04507de7b710016d540b2759483ed5f9136bb01a80872b08f771930 - # - # GKE /sys/fs/cgroup/*/ (cri=containerd, cgroups=v1): - # |-- kubepods.slice - # | |-- kubepods-besteffort.slice - # | | |-- kubepods-besteffort-pode1465238_4518_4c21_832f_fd9f87033dad.slice - # | | | |-- cri-containerd-66be9b2efdf4d85288c319b8c1a2f50d2439b5617e36f45d9d0d0be1381113be.scope - # | `-- kubepods-pod91f5b561_369f_4103_8015_66391059996a.slice - # | |-- cri-containerd-24c53b774a586f06abc058619b47f71d9d869ac50c92898adbd199106fd0aaeb.scope - # - # GKE /sys/fs/cgroup/*/ (cri=crio, cgroups=v1): - # |-- kubepods.slice - # | |-- kubepods-besteffort.slice - # | | |-- kubepods-besteffort-podad412dfe_3589_4056_965a_592356172968.slice - # | | | |-- crio-77b019312fd9825828b70214b2c94da69c30621af2a7ee06f8beace4bc9439e5.scope - # - # Minikube (v1.8.2) /sys/fs/cgroup/*/ (cri=docker, cgroups=v1): - # |-- kubepods.slice - # | |-- kubepods-besteffort.slice - # | | |-- kubepods-besteffort-pod10fb5647_c724_400c_b9cc_0e6eae3110e7.slice - # | | | |-- docker-36e5eb5056dfdf6dbb75c0c44a1ecf23217fe2c50d606209d8130fcbb19fb5a7.scope - # - # kind v0.14.0 - # |-- kubelet.slice - # | |-- kubelet-kubepods.slice - # | | |-- kubelet-kubepods-besteffort.slice - # | | | |-- kubelet-kubepods-besteffort-pod7881ed9e_c63e_4425_b5e0_ac55a08ae939.slice - # | | | | |-- cri-containerd-00c7939458bffc416bb03451526e9fde13301d6654cfeadf5b4964a7fb5be1a9.scope - # - # NOTE: cgroups plugin - # - uses '_' to join dir names (so it is <parent>_<child>_<child>_...) - # - replaces '.' with '-' - - local fn="${FUNCNAME[0]}" - local cgroup_path="${1}" - local id="${2}" - - if [[ ! $id =~ ^.*kubepods.* ]]; then - warning "${fn}: '${id}' is not kubepod cgroup." - return 1 - fi - - local clean_id="$id" - clean_id=${clean_id//.slice/} - clean_id=${clean_id//.scope/} - - local name pod_uid cntr_id - if [[ $clean_id == "kubepods" ]]; then - name="$clean_id" - elif [[ $clean_id =~ .+(besteffort|burstable|guaranteed)$ ]]; then - # kubepods_<QOS_CLASS> - # kubepods_kubepods-<QOS_CLASS> - name=${clean_id//-/_} - name=${name/#kubepods_kubepods/kubepods} - elif [[ $clean_id =~ .+pod[a-f0-9_-]+_(docker|crio|cri-containerd)-([a-f0-9]+)$ ]]; then - # ...pod<POD_UID>_(docker|crio|cri-containerd)-<CONTAINER_ID> (POD_UID w/ "_") - cntr_id=${BASH_REMATCH[2]} - elif [[ $clean_id =~ .+pod[a-f0-9-]+_([a-f0-9]+)$ ]]; then - # ...pod<POD_UID>_<CONTAINER_ID> - cntr_id=${BASH_REMATCH[1]} - elif [[ $clean_id =~ .+pod([a-f0-9_-]+)$ ]]; then - # ...pod<POD_UID> (POD_UID w/ and w/o "_") - pod_uid=${BASH_REMATCH[1]} - pod_uid=${pod_uid//_/-} - fi - - if [ -n "$name" ]; then - echo "$name" - return 0 - fi - - if [ -z "$pod_uid" ] && [ -z "$cntr_id" ]; then - warning "${fn}: can't extract pod_uid or container_id from the cgroup '$id'." - return 3 - fi - - [ -n "$pod_uid" ] && info "${fn}: cgroup '$id' is a pod(uid:$pod_uid)" - [ -n "$cntr_id" ] && info "${fn}: cgroup '$id' is a container(id:$cntr_id)" - - if [ -n "$cntr_id" ] && k8s_is_pause_container "$cgroup_path"; then - return 3 - fi - - if ! command -v jq > /dev/null 2>&1; then - warning "${fn}: 'jq' command not available." - return 1 - fi - - local tmp_kube_cluster_name="${TMPDIR:-"/tmp"}/netdata-cgroups-k8s-cluster-name" - local tmp_kube_system_ns_uid_file="${TMPDIR:-"/tmp"}/netdata-cgroups-kubesystem-uid" - local tmp_kube_containers_file="${TMPDIR:-"/tmp"}/netdata-cgroups-containers" - - local kube_cluster_name - local kube_system_uid - local labels - - if [ -n "$cntr_id" ] && - [ -f "$tmp_kube_cluster_name" ] && - [ -f "$tmp_kube_system_ns_uid_file" ] && - [ -f "$tmp_kube_containers_file" ] && - labels=$(grep "$cntr_id" "$tmp_kube_containers_file" 2>/dev/null); then - IFS= read -r kube_system_uid 2>/dev/null <"$tmp_kube_system_ns_uid_file" - IFS= read -r kube_cluster_name 2>/dev/null <"$tmp_kube_cluster_name" - else - IFS= read -r kube_system_uid 2>/dev/null <"$tmp_kube_system_ns_uid_file" - IFS= read -r kube_cluster_name 2>/dev/null <"$tmp_kube_cluster_name" - [ -z "$kube_cluster_name" ] && ! kube_cluster_name=$(k8s_gcp_get_cluster_name) && kube_cluster_name="unknown" - - local kube_system_ns - local pods - - if [ -n "${KUBERNETES_SERVICE_HOST}" ] && [ -n "${KUBERNETES_PORT_443_TCP_PORT}" ]; then - local token header host url - token="$(</var/run/secrets/kubernetes.io/serviceaccount/token)" - header="Authorization: Bearer $token" - host="$KUBERNETES_SERVICE_HOST:$KUBERNETES_PORT_443_TCP_PORT" - - if [ -z "$kube_system_uid" ]; then - url="https://$host/api/v1/namespaces/kube-system" - # FIX: check HTTP response code - if ! kube_system_ns=$(curl --fail -sSk -H "$header" "$url" 2>&1); then - warning "${fn}: error on curl '${url}': ${kube_system_ns}." - fi - fi - - local url - if [ -n "${USE_KUBELET_FOR_PODS_METADATA}" ]; then - url="${KUBELET_URL:-https://localhost:10250}/pods" - else - url="https://$host/api/v1/pods" - [ -n "$MY_NODE_NAME" ] && url+="?fieldSelector=spec.nodeName==$MY_NODE_NAME" - fi - - # FIX: check HTTP response code - if ! pods=$(curl --fail -sSk -H "$header" "$url" 2>&1); then - warning "${fn}: error on curl '${url}': ${pods}." - return 1 - fi - elif ps -C kubelet >/dev/null 2>&1 && command -v kubectl >/dev/null 2>&1; then - if [ -z "$kube_system_uid" ]; then - if ! kube_system_ns=$(kubectl --kubeconfig="$KUBE_CONFIG" get namespaces kube-system -o json 2>&1); then - warning "${fn}: error on 'kubectl': ${kube_system_ns}." - fi - fi - - [[ -z ${KUBE_CONFIG+x} ]] && KUBE_CONFIG="/etc/kubernetes/admin.conf" - if ! pods=$(kubectl --kubeconfig="$KUBE_CONFIG" get pods --all-namespaces -o json 2>&1); then - warning "${fn}: error on 'kubectl': ${pods}." - return 1 - fi - else - warning "${fn}: not inside the k8s cluster and 'kubectl' command not available." - return 1 - fi - - if [ -n "$kube_system_ns" ] && ! kube_system_uid=$(jq -r '.metadata.uid' <<<"$kube_system_ns" 2>&1); then - warning "${fn}: error on 'jq' parse kube_system_ns: ${kube_system_uid}." - fi - - local jq_filter - jq_filter+='.items[] | "' - jq_filter+='namespace=\"\(.metadata.namespace)\",' - jq_filter+='pod_name=\"\(.metadata.name)\",' - jq_filter+='pod_uid=\"\(.metadata.uid)\",' - #jq_filter+='\(.metadata.labels | to_entries | map("pod_label_"+.key+"=\""+.value+"\"") | join(",") | if length > 0 then .+"," else . end)' - jq_filter+='\((.metadata.ownerReferences[]? | select(.controller==true) | "controller_kind=\""+.kind+"\",controller_name=\""+.name+"\",") // "")' - jq_filter+='node_name=\"\(.spec.nodeName)\",' - jq_filter+='" + ' - jq_filter+='(.status.containerStatuses[]? | "' - jq_filter+='container_name=\"\(.name)\",' - jq_filter+='container_id=\"\(.containerID)\"' - jq_filter+='") | ' - jq_filter+='sub("(docker|cri-o|containerd)://";"")' # containerID: docker://a346da9bc0e3eaba6b295f64ac16e02f2190db2cef570835706a9e7a36e2c722 - - local containers - if ! containers=$(jq -r "${jq_filter}" <<<"$pods" 2>&1); then - warning "${fn}: error on 'jq' parse pods: ${containers}." - return 1 - fi - - [ -n "$kube_cluster_name" ] && echo "$kube_cluster_name" >"$tmp_kube_cluster_name" 2>/dev/null - [ -n "$kube_system_ns" ] && [ -n "$kube_system_uid" ] && echo "$kube_system_uid" >"$tmp_kube_system_ns_uid_file" 2>/dev/null - echo "$containers" >"$tmp_kube_containers_file" 2>/dev/null - fi - - local qos_class - if [[ $clean_id =~ .+(besteffort|burstable) ]]; then - qos_class="${BASH_REMATCH[1]}" - else - qos_class="guaranteed" - fi - - # available labels: - # namespace, pod_name, pod_uid, container_name, container_id, node_name - if [ -n "$cntr_id" ]; then - if [ -n "$labels" ] || labels=$(grep "$cntr_id" <<< "$containers" 2> /dev/null); then - labels+=',kind="container"' - labels+=",qos_class=\"$qos_class\"" - [ -n "$kube_system_uid" ] && [ "$kube_system_uid" != "null" ] && labels+=",cluster_id=\"$kube_system_uid\"" - [ -n "$kube_cluster_name" ] && [ "$kube_cluster_name" != "unknown" ] && labels+=",cluster_name=\"$kube_cluster_name\"" - name="cntr" - name+="_$(get_lbl_val "$labels" namespace)" - name+="_$(get_lbl_val "$labels" pod_name)" - name+="_$(get_lbl_val "$labels" container_name)" - labels=$(remove_lbl "$labels" "container_id") - labels=$(remove_lbl "$labels" "pod_uid") - labels=$(add_lbl_prefix "$labels" "k8s_") - name+=" $labels" - else - return 2 - fi - elif [ -n "$pod_uid" ]; then - if labels=$(grep "$pod_uid" -m 1 <<< "$containers" 2> /dev/null); then - labels="${labels%%,container_*}" - labels+=',kind="pod"' - labels+=",qos_class=\"$qos_class\"" - [ -n "$kube_system_uid" ] && [ "$kube_system_uid" != "null" ] && labels+=",cluster_id=\"$kube_system_uid\"" - [ -n "$kube_cluster_name" ] && [ "$kube_cluster_name" != "unknown" ] && labels+=",cluster_name=\"$kube_cluster_name\"" - name="pod" - name+="_$(get_lbl_val "$labels" namespace)" - name+="_$(get_lbl_val "$labels" pod_name)" - labels=$(remove_lbl "$labels" "pod_uid") - labels=$(add_lbl_prefix "$labels" "k8s_") - name+=" $labels" - else - return 2 - fi - fi - - # jq filter nonexistent field and nonexistent label value is 'null' - if [[ $name =~ _null(_|$) ]]; then - warning "${fn}: invalid name: $name (cgroup '$id')" - if [ -n "${USE_KUBELET_FOR_PODS_METADATA}" ]; then - # local data is cached and may not contain the correct id - return 2 - fi - return 1 - fi - - echo "$name" - [ -n "$name" ] - return -} - -function k8s_get_name() { - local fn="${FUNCNAME[0]}" - local cgroup_path="${1}" - local id="${2}" - local kubepod_name="" - - kubepod_name=$(k8s_get_kubepod_name "$cgroup_path" "$id") - - case "$?" in - 0) - kubepod_name="k8s_${kubepod_name}" - - local name labels - name=${kubepod_name%% *} - labels=${kubepod_name#* } - - if [ "$name" != "$labels" ]; then - info "${fn}: cgroup '${id}' has chart name '${name}', labels '${labels}" - NAME="$name" - LABELS="$labels" - else - info "${fn}: cgroup '${id}' has chart name '${NAME}'" - NAME="$name" - fi - EXIT_CODE=$EXIT_SUCCESS - ;; - 1) - NAME="k8s_${id}" - warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and enabling it." - EXIT_CODE=$EXIT_SUCCESS - ;; - 2) - NAME="k8s_${id}" - warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and asking for retry." - EXIT_CODE=$EXIT_RETRY - ;; - *) - NAME="k8s_${id}" - warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and disabling it." - EXIT_CODE=$EXIT_DISABLE - ;; - esac -} - -function docker_get_name() { - local id="${1}" - # See https://github.com/netdata/netdata/pull/13523 for details - if command -v snap >/dev/null 2>&1 && snap list docker >/dev/null 2>&1; then - docker_like_get_name_api DOCKER_HOST "${id}" - elif hash docker 2> /dev/null; then - docker_like_get_name_command docker "${id}" - else - docker_like_get_name_api DOCKER_HOST "${id}" || docker_like_get_name_command podman "${id}" - fi - if [ -z "${NAME}" ]; then - warning "cannot find the name of docker container '${id}'" - EXIT_CODE=$EXIT_RETRY - NAME="${id:0:12}" - else - info "docker container '${id}' is named '${NAME}'" - fi -} - -function docker_validate_id() { - local id="${1}" - if [ -n "${id}" ] && { [ ${#id} -eq 64 ] || [ ${#id} -eq 12 ]; }; then - docker_get_name "${id}" - else - error "a docker id cannot be extracted from docker cgroup '${CGROUP}'." - fi -} - -function podman_get_name() { - local id="${1}" - - # for Podman, prefer using the API if we can, as netdata will not normally have access - # to other users' containers, so they will not be visible when running `podman ps` - docker_like_get_name_api PODMAN_HOST "${id}" || docker_like_get_name_command podman "${id}" - - if [ -z "${NAME}" ]; then - warning "cannot find the name of podman container '${id}'" - EXIT_CODE=$EXIT_RETRY - NAME="${id:0:12}" - else - info "podman container '${id}' is named '${NAME}'" - fi -} - -function podman_validate_id() { - local id="${1}" - if [ -n "${id}" ] && [ ${#id} -eq 64 ]; then - podman_get_name "${id}" - else - error "a podman id cannot be extracted from docker cgroup '${CGROUP}'." - fi -} - -# ----------------------------------------------------------------------------- - -DOCKER_HOST="${DOCKER_HOST:=/var/run/docker.sock}" -PODMAN_HOST="${PODMAN_HOST:=/run/podman/podman.sock}" -CGROUP_PATH="${1}" # the path as it is (e.g. '/docker/efcf4c409') -CGROUP="${2}" # the modified path (e.g. 'docker_efcf4c409') -EXIT_SUCCESS=0 -EXIT_RETRY=2 -EXIT_DISABLE=3 -EXIT_CODE=$EXIT_SUCCESS -NAME= -LABELS= - -# ----------------------------------------------------------------------------- - -if [ -z "${CGROUP}" ]; then - fatal "called without a cgroup name. Nothing to do." -fi - -if [ -z "${NAME}" ]; then - if [[ ${CGROUP} =~ ^.*kubepods.* ]]; then - k8s_get_name "${CGROUP_PATH}" "${CGROUP}" - fi -fi - -if [ -z "${NAME}" ]; then - if [[ ${CGROUP} =~ ^.*docker[-_/\.][a-fA-F0-9]+[-_\.]?.*$ ]]; then - # docker containers - #shellcheck disable=SC1117 - DOCKERID="$(echo "${CGROUP}" | sed "s|^.*docker[-_/]\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" - docker_validate_id "${DOCKERID}" - elif [[ ${CGROUP} =~ ^.*ecs[-_/\.][a-fA-F0-9]+[-_\.]?.*$ ]]; then - # ECS - #shellcheck disable=SC1117 - DOCKERID="$(echo "${CGROUP}" | sed "s|^.*ecs[-_/].*[-_/]\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" - docker_validate_id "${DOCKERID}" - elif [[ ${CGROUP} =~ system.slice_containerd.service_cpuset_[a-fA-F0-9]+[-_\.]?.*$ ]]; then - # docker containers under containerd - #shellcheck disable=SC1117 - DOCKERID="$(echo "${CGROUP}" | sed "s|^.*ystem.slice_containerd.service_cpuset_\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" - docker_validate_id "${DOCKERID}" - elif [[ ${CGROUP} =~ ^.*libpod-[a-fA-F0-9]+.*$ ]]; then - # Podman - PODMANID="$(echo "${CGROUP}" | sed "s|^.*libpod-\([a-fA-F0-9]\+\).*$|\1|")" - podman_validate_id "${PODMANID}" - - elif [[ ${CGROUP} =~ machine.slice[_/].*\.service ]]; then - # systemd-nspawn - NAME="$(echo "${CGROUP}" | sed 's/.*machine.slice[_\/]\(.*\)\.service/\1/g')" - - elif [[ ${CGROUP} =~ machine.slice_machine.*-lxc ]]; then - # libvirtd / lxc containers - # machine.slice machine-lxc/x2d969/x2dhubud0xians01.scope => lxc/hubud0xians01 - # machine.slice_machine-lxc/x2d969/x2dhubud0xians01.scope/libvirt_init.scope => lxc/hubud0xians01/libvirt_init - NAME="lxc/$(echo "${CGROUP}" | sed 's/machine.slice_machine.*-lxc//; s/[\/_]x2d[[:digit:]]*//; s/[\/_]x2d//g; s/\.scope//g')" - elif [[ ${CGROUP} =~ machine.slice_machine.*-qemu ]]; then - # libvirtd / qemu virtual machines - # machine.slice_machine-qemu_x2d1_x2dopnsense.scope => qemu_opnsense - NAME="qemu_$(echo "${CGROUP}" | sed 's/machine.slice_machine.*-qemu//; s/[\/_]x2d[[:digit:]]*//; s/[\/_]x2d//g; s/\.scope//g')" - - elif [[ ${CGROUP} =~ machine_.*\.libvirt-qemu ]]; then - # libvirtd / qemu virtual machines - NAME="qemu_$(echo "${CGROUP}" | sed 's/^machine_//; s/\.libvirt-qemu$//; s/-/_/;')" - - elif [[ ${CGROUP} =~ qemu.slice_([0-9]+).scope && -d /etc/pve ]]; then - # Proxmox VMs - - FILENAME="/etc/pve/qemu-server/${BASH_REMATCH[1]}.conf" - if [[ -f $FILENAME && -r $FILENAME ]]; then - NAME="qemu_$(grep -e '^name: ' "/etc/pve/qemu-server/${BASH_REMATCH[1]}.conf" | head -1 | sed -rn 's|\s*name\s*:\s*(.*)?$|\1|p')" - else - error "proxmox config file missing ${FILENAME} or netdata does not have read access. Please ensure netdata is a member of www-data group." - fi - elif [[ ${CGROUP} =~ lxc_([0-9]+) && -d /etc/pve ]]; then - # Proxmox Containers (LXC) - - FILENAME="/etc/pve/lxc/${BASH_REMATCH[1]}.conf" - if [[ -f ${FILENAME} && -r ${FILENAME} ]]; then - NAME=$(grep -e '^hostname: ' "/etc/pve/lxc/${BASH_REMATCH[1]}.conf" | head -1 | sed -rn 's|\s*hostname\s*:\s*(.*)?$|\1|p') - else - error "proxmox config file missing ${FILENAME} or netdata does not have read access. Please ensure netdata is a member of www-data group." - fi - elif [[ ${CGROUP} =~ lxc.payload.* ]]; then - # LXC 4.0 - NAME="$(echo "${CGROUP}" | sed 's/lxc\.payload\.\(.*\)/\1/g')" - fi - - [ -z "${NAME}" ] && NAME="${CGROUP}" - [ ${#NAME} -gt 100 ] && NAME="${NAME:0:100}" -fi - -NAME="${NAME// /_}" - -info "cgroup '${CGROUP}' is called '${NAME}', labels '${LABELS}'" -if [ -n "$LABELS" ]; then - echo "${NAME} ${LABELS}" -else - echo "${NAME}" -fi - -exit ${EXIT_CODE} diff --git a/collectors/cgroups.plugin/cgroup-name.sh.in b/collectors/cgroups.plugin/cgroup-name.sh.in new file mode 100755 index 000000000..0f8b63256 --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-name.sh.in @@ -0,0 +1,706 @@ +#!/usr/bin/env bash +#shellcheck disable=SC2001 + +# netdata +# real-time performance and health monitoring, done right! +# (C) 2023 Netdata Inc. +# SPDX-License-Identifier: GPL-3.0-or-later +# +# Script to find a better name for cgroups +# + +export PATH="${PATH}:/sbin:/usr/sbin:/usr/local/sbin:@sbindir_POST@" +export LC_ALL=C + +cmd_line="'${0}' $(printf "'%s' " "${@}")" + +# ----------------------------------------------------------------------------- +# logging + +PROGRAM_NAME="$(basename "${0}")" + +# these should be the same with syslog() priorities +NDLP_EMERG=0 # system is unusable +NDLP_ALERT=1 # action must be taken immediately +NDLP_CRIT=2 # critical conditions +NDLP_ERR=3 # error conditions +NDLP_WARN=4 # warning conditions +NDLP_NOTICE=5 # normal but significant condition +NDLP_INFO=6 # informational +NDLP_DEBUG=7 # debug-level messages + +# the max (numerically) log level we will log +LOG_LEVEL=$NDLP_INFO + +set_log_min_priority() { + case "${NETDATA_LOG_LEVEL,,}" in + "emerg" | "emergency") + LOG_LEVEL=$NDLP_EMERG + ;; + + "alert") + LOG_LEVEL=$NDLP_ALERT + ;; + + "crit" | "critical") + LOG_LEVEL=$NDLP_CRIT + ;; + + "err" | "error") + LOG_LEVEL=$NDLP_ERR + ;; + + "warn" | "warning") + LOG_LEVEL=$NDLP_WARN + ;; + + "notice") + LOG_LEVEL=$NDLP_NOTICE + ;; + + "info") + LOG_LEVEL=$NDLP_INFO + ;; + + "debug") + LOG_LEVEL=$NDLP_DEBUG + ;; + esac +} + +set_log_min_priority + +log() { + local level="${1}" + shift 1 + + [[ -n "$level" && -n "$LOG_LEVEL" && "$level" -gt "$LOG_LEVEL" ]] && return + + systemd-cat-native --log-as-netdata --newline="--NEWLINE--" <<EOFLOG +INVOCATION_ID=${NETDATA_INVOCATION_ID} +SYSLOG_IDENTIFIER=${PROGRAM_NAME} +PRIORITY=${level} +THREAD_TAG=cgroup-name +ND_LOG_SOURCE=collector +ND_REQUEST=${cmd_line} +MESSAGE=${*//\\n/--NEWLINE--} + +EOFLOG + # AN EMPTY LINE IS NEEDED ABOVE +} + +info() { + log "$NDLP_INFO" "${@}" +} + +warning() { + log "$NDLP_WARN" "${@}" +} + +error() { + log "$NDLP_ERR" "${@}" +} + +fatal() { + log "$NDLP_ALERT" "${@}" + exit 1 +} + +debug() { + log "$NDLP_DEBUG" "${@}" +} + +# ----------------------------------------------------------------------------- + +function parse_docker_like_inspect_output() { + local output="${1}" + eval "$(grep -E "^(NOMAD_NAMESPACE|NOMAD_JOB_NAME|NOMAD_TASK_NAME|NOMAD_SHORT_ALLOC_ID|CONT_NAME|IMAGE_NAME)=" <<<"$output")" + if [ -n "$NOMAD_NAMESPACE" ] && [ -n "$NOMAD_JOB_NAME" ] && [ -n "$NOMAD_TASK_NAME" ] && [ -n "$NOMAD_SHORT_ALLOC_ID" ]; then + NAME="${NOMAD_NAMESPACE}-${NOMAD_JOB_NAME}-${NOMAD_TASK_NAME}-${NOMAD_SHORT_ALLOC_ID}" + else + NAME=$(echo "${CONT_NAME}" | sed 's|^/||') + fi + if [ -n "${IMAGE_NAME}" ]; then + LABELS="image=\"${IMAGE_NAME}\"" + fi +} + +function docker_like_get_name_command() { + local command="${1}" + local id="${2}" + info "Running command: ${command} inspect --format='{{range .Config.Env}}{{println .}}{{end}}CONT_NAME={{ .Name}}' \"${id}\"" + if OUTPUT="$(${command} inspect --format='{{range .Config.Env}}{{println .}}{{end}}CONT_NAME={{ .Name}}{{println}}IMAGE_NAME={{ .Config.Image}}' "${id}")" && + [ -n "$OUTPUT" ]; then + parse_docker_like_inspect_output "$OUTPUT" + fi + return 0 +} + +function docker_like_get_name_api() { + local host_var="${1}" + local host="${!host_var}" + local path="/containers/${2}/json" + if [ -z "${host}" ]; then + warning "No ${host_var} is set" + return 1 + fi + if ! command -v jq >/dev/null 2>&1; then + warning "Can't find jq command line tool. jq is required for netdata to retrieve container name using ${host} API, falling back to docker ps" + return 1 + fi + if [ -S "${host}" ]; then + info "Running API command: curl --unix-socket \"${host}\" http://localhost${path}" + JSON=$(curl -sS --unix-socket "${host}" "http://localhost${path}") + else + info "Running API command: curl \"${host}${path}\"" + JSON=$(curl -sS "${host}${path}") + fi + if OUTPUT=$(echo "${JSON}" | jq -r '.Config.Env[],"CONT_NAME=\(.Name)","IMAGE_NAME=\(.Config.Image)"') && [ -n "$OUTPUT" ]; then + parse_docker_like_inspect_output "$OUTPUT" + fi + return 0 +} + +# get_lbl_val returns the value for the label with the given name. +# Returns "null" string if the label doesn't exist. +# Expected labels format: 'name="value",...'. +function get_lbl_val() { + local labels want_name + labels="${1}" + want_name="${2}" + + IFS=, read -ra labels <<< "$labels" + + local lname lval + for l in "${labels[@]}"; do + IFS="=" read -r lname lval <<< "$l" + if [ "$want_name" = "$lname" ] && [ -n "$lval" ]; then + echo "${lval:1:-1}" # trim " + return 0 + fi + done + + echo "null" + return 1 +} + +function add_lbl_prefix() { + local orig_labels prefix + orig_labels="${1}" + prefix="${2}" + + IFS=, read -ra labels <<< "$orig_labels" + + local new_labels + for l in "${labels[@]}"; do + new_labels+="${prefix}${l}," + done + + echo "${new_labels:0:-1}" # trim last ',' +} + +function remove_lbl() { + local orig_labels lbl_name + orig_labels="${1}" + lbl_name="${2}" + + IFS=, read -ra labels <<< "$orig_labels" + + local new_labels + for l in "${labels[@]}"; do + IFS="=" read -r lname lval <<< "$l" + [ "$lbl_name" != "$lname" ] && new_labels+="${l}," + done + + echo "${new_labels:0:-1}" # trim last ',' +} + +function k8s_is_pause_container() { + local cgroup_path="${1}" + + local file + if [ -d "${NETDATA_HOST_PREFIX}/sys/fs/cgroup/cpuacct" ]; then + file="${NETDATA_HOST_PREFIX}/sys/fs/cgroup/cpuacct/$cgroup_path/cgroup.procs" + else + file="${NETDATA_HOST_PREFIX}/sys/fs/cgroup/$cgroup_path/cgroup.procs" + fi + + [ ! -f "$file" ] && return 1 + + local procs + IFS= read -rd' ' procs 2>/dev/null <"$file" + #shellcheck disable=SC2206 + procs=($procs) + + [ "${#procs[@]}" -ne 1 ] && return 1 + + IFS= read -r comm 2>/dev/null <"/proc/${procs[0]}/comm" + + [ "$comm" == "pause" ] + return +} + +function k8s_gcp_get_cluster_name() { + local header url id loc name + header="Metadata-Flavor: Google" + url="http://metadata/computeMetadata/v1" + if id=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/project/project-id") && + loc=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/instance/attributes/cluster-location") && + name=$(curl --fail -s -m 3 --noproxy "*" -H "$header" "$url/instance/attributes/cluster-name") && + [ -n "$id" ] && [ -n "$loc" ] && [ -n "$name" ]; then + echo "gke_${id}_${loc}_${name}" + return 0 + fi + return 1 +} + +# k8s_get_kubepod_name resolves */kubepods/* cgroup name. +# pod level cgroup name format: 'pod_<namespace>_<pod_name>' +# container level cgroup name format: 'cntr_<namespace>_<pod_name>_<container_name>' +function k8s_get_kubepod_name() { + # GKE /sys/fs/cgroup/*/ (cri=docker, cgroups=v1): + # |-- kubepods + # | |-- burstable + # | | |-- pod98cee708-023b-11eb-933d-42010a800193 + # | | | |-- 922161c98e6ea450bf665226cdc64ca2aa3e889934c2cff0aec4325f8f78ac03 + # | `-- pode314bbac-d577-11ea-a171-42010a80013b + # | |-- 7d505356b04507de7b710016d540b2759483ed5f9136bb01a80872b08f771930 + # + # GKE /sys/fs/cgroup/*/ (cri=containerd, cgroups=v1): + # |-- kubepods.slice + # | |-- kubepods-besteffort.slice + # | | |-- kubepods-besteffort-pode1465238_4518_4c21_832f_fd9f87033dad.slice + # | | | |-- cri-containerd-66be9b2efdf4d85288c319b8c1a2f50d2439b5617e36f45d9d0d0be1381113be.scope + # | `-- kubepods-pod91f5b561_369f_4103_8015_66391059996a.slice + # | |-- cri-containerd-24c53b774a586f06abc058619b47f71d9d869ac50c92898adbd199106fd0aaeb.scope + # + # GKE /sys/fs/cgroup/*/ (cri=crio, cgroups=v1): + # |-- kubepods.slice + # | |-- kubepods-besteffort.slice + # | | |-- kubepods-besteffort-podad412dfe_3589_4056_965a_592356172968.slice + # | | | |-- crio-77b019312fd9825828b70214b2c94da69c30621af2a7ee06f8beace4bc9439e5.scope + # + # Minikube (v1.8.2) /sys/fs/cgroup/*/ (cri=docker, cgroups=v1): + # |-- kubepods.slice + # | |-- kubepods-besteffort.slice + # | | |-- kubepods-besteffort-pod10fb5647_c724_400c_b9cc_0e6eae3110e7.slice + # | | | |-- docker-36e5eb5056dfdf6dbb75c0c44a1ecf23217fe2c50d606209d8130fcbb19fb5a7.scope + # + # kind v0.14.0 + # |-- kubelet.slice + # | |-- kubelet-kubepods.slice + # | | |-- kubelet-kubepods-besteffort.slice + # | | | |-- kubelet-kubepods-besteffort-pod7881ed9e_c63e_4425_b5e0_ac55a08ae939.slice + # | | | | |-- cri-containerd-00c7939458bffc416bb03451526e9fde13301d6654cfeadf5b4964a7fb5be1a9.scope + # + # NOTE: cgroups plugin + # - uses '_' to join dir names (so it is <parent>_<child>_<child>_...) + # - replaces '.' with '-' + + local fn="${FUNCNAME[0]}" + local cgroup_path="${1}" + local id="${2}" + + if [[ ! $id =~ ^.*kubepods.* ]]; then + warning "${fn}: '${id}' is not kubepod cgroup." + return 1 + fi + + local clean_id="$id" + clean_id=${clean_id//.slice/} + clean_id=${clean_id//.scope/} + + local name pod_uid cntr_id + if [[ $clean_id == "kubepods" ]]; then + name="$clean_id" + elif [[ $clean_id =~ .+(besteffort|burstable|guaranteed)$ ]]; then + # kubepods_<QOS_CLASS> + # kubepods_kubepods-<QOS_CLASS> + name=${clean_id//-/_} + name=${name/#kubepods_kubepods/kubepods} + elif [[ $clean_id =~ .+pod[a-f0-9_-]+_(docker|crio|cri-containerd)-([a-f0-9]+)$ ]]; then + # ...pod<POD_UID>_(docker|crio|cri-containerd)-<CONTAINER_ID> (POD_UID w/ "_") + cntr_id=${BASH_REMATCH[2]} + elif [[ $clean_id =~ .+pod[a-f0-9-]+_([a-f0-9]+)$ ]]; then + # ...pod<POD_UID>_<CONTAINER_ID> + cntr_id=${BASH_REMATCH[1]} + elif [[ $clean_id =~ .+pod([a-f0-9_-]+)$ ]]; then + # ...pod<POD_UID> (POD_UID w/ and w/o "_") + pod_uid=${BASH_REMATCH[1]} + pod_uid=${pod_uid//_/-} + fi + + if [ -n "$name" ]; then + echo "$name" + return 0 + fi + + if [ -z "$pod_uid" ] && [ -z "$cntr_id" ]; then + warning "${fn}: can't extract pod_uid or container_id from the cgroup '$id'." + return 3 + fi + + [ -n "$pod_uid" ] && info "${fn}: cgroup '$id' is a pod(uid:$pod_uid)" + [ -n "$cntr_id" ] && info "${fn}: cgroup '$id' is a container(id:$cntr_id)" + + if [ -n "$cntr_id" ] && k8s_is_pause_container "$cgroup_path"; then + return 3 + fi + + if ! command -v jq > /dev/null 2>&1; then + warning "${fn}: 'jq' command not available." + return 1 + fi + + local tmp_kube_cluster_name="${TMPDIR:-"/tmp"}/netdata-cgroups-k8s-cluster-name" + local tmp_kube_system_ns_uid_file="${TMPDIR:-"/tmp"}/netdata-cgroups-kubesystem-uid" + local tmp_kube_containers_file="${TMPDIR:-"/tmp"}/netdata-cgroups-containers" + + local kube_cluster_name + local kube_system_uid + local labels + + if [ -n "$cntr_id" ] && + [ -f "$tmp_kube_cluster_name" ] && + [ -f "$tmp_kube_system_ns_uid_file" ] && + [ -f "$tmp_kube_containers_file" ] && + labels=$(grep "$cntr_id" "$tmp_kube_containers_file" 2>/dev/null); then + IFS= read -r kube_system_uid 2>/dev/null <"$tmp_kube_system_ns_uid_file" + IFS= read -r kube_cluster_name 2>/dev/null <"$tmp_kube_cluster_name" + else + IFS= read -r kube_system_uid 2>/dev/null <"$tmp_kube_system_ns_uid_file" + IFS= read -r kube_cluster_name 2>/dev/null <"$tmp_kube_cluster_name" + [ -z "$kube_cluster_name" ] && ! kube_cluster_name=$(k8s_gcp_get_cluster_name) && kube_cluster_name="unknown" + + local kube_system_ns + local pods + + if [ -n "${KUBERNETES_SERVICE_HOST}" ] && [ -n "${KUBERNETES_PORT_443_TCP_PORT}" ]; then + local token header host url + token="$(</var/run/secrets/kubernetes.io/serviceaccount/token)" + header="Authorization: Bearer $token" + host="$KUBERNETES_SERVICE_HOST:$KUBERNETES_PORT_443_TCP_PORT" + + if [ -z "$kube_system_uid" ]; then + url="https://$host/api/v1/namespaces/kube-system" + # FIX: check HTTP response code + if ! kube_system_ns=$(curl --fail -sSk -H "$header" "$url" 2>&1); then + warning "${fn}: error on curl '${url}': ${kube_system_ns}." + fi + fi + + local url + if [ -n "${USE_KUBELET_FOR_PODS_METADATA}" ]; then + url="${KUBELET_URL:-https://localhost:10250}/pods" + else + url="https://$host/api/v1/pods" + [ -n "$MY_NODE_NAME" ] && url+="?fieldSelector=spec.nodeName==$MY_NODE_NAME" + fi + + # FIX: check HTTP response code + if ! pods=$(curl --fail -sSk -H "$header" "$url" 2>&1); then + warning "${fn}: error on curl '${url}': ${pods}." + return 1 + fi + elif ps -C kubelet >/dev/null 2>&1 && command -v kubectl >/dev/null 2>&1; then + if [ -z "$kube_system_uid" ]; then + if ! kube_system_ns=$(kubectl --kubeconfig="$KUBE_CONFIG" get namespaces kube-system -o json 2>&1); then + warning "${fn}: error on 'kubectl': ${kube_system_ns}." + fi + fi + + [[ -z ${KUBE_CONFIG+x} ]] && KUBE_CONFIG="/etc/kubernetes/admin.conf" + if ! pods=$(kubectl --kubeconfig="$KUBE_CONFIG" get pods --all-namespaces -o json 2>&1); then + warning "${fn}: error on 'kubectl': ${pods}." + return 1 + fi + else + warning "${fn}: not inside the k8s cluster and 'kubectl' command not available." + return 1 + fi + + if [ -n "$kube_system_ns" ] && ! kube_system_uid=$(jq -r '.metadata.uid' <<<"$kube_system_ns" 2>&1); then + warning "${fn}: error on 'jq' parse kube_system_ns: ${kube_system_uid}." + fi + + local jq_filter + jq_filter+='.items[] | "' + jq_filter+='namespace=\"\(.metadata.namespace)\",' + jq_filter+='pod_name=\"\(.metadata.name)\",' + jq_filter+='pod_uid=\"\(.metadata.uid)\",' + #jq_filter+='\(.metadata.labels | to_entries | map("pod_label_"+.key+"=\""+.value+"\"") | join(",") | if length > 0 then .+"," else . end)' + jq_filter+='\((.metadata.ownerReferences[]? | select(.controller==true) | "controller_kind=\""+.kind+"\",controller_name=\""+.name+"\",") // "")' + jq_filter+='node_name=\"\(.spec.nodeName)\",' + jq_filter+='" + ' + jq_filter+='(.status.containerStatuses[]? | "' + jq_filter+='container_name=\"\(.name)\",' + jq_filter+='container_id=\"\(.containerID)\"' + jq_filter+='") | ' + jq_filter+='sub("(docker|cri-o|containerd)://";"")' # containerID: docker://a346da9bc0e3eaba6b295f64ac16e02f2190db2cef570835706a9e7a36e2c722 + + local containers + if ! containers=$(jq -r "${jq_filter}" <<<"$pods" 2>&1); then + warning "${fn}: error on 'jq' parse pods: ${containers}." + return 1 + fi + + [ -n "$kube_cluster_name" ] && echo "$kube_cluster_name" >"$tmp_kube_cluster_name" 2>/dev/null + [ -n "$kube_system_ns" ] && [ -n "$kube_system_uid" ] && echo "$kube_system_uid" >"$tmp_kube_system_ns_uid_file" 2>/dev/null + echo "$containers" >"$tmp_kube_containers_file" 2>/dev/null + fi + + local qos_class + if [[ $clean_id =~ .+(besteffort|burstable) ]]; then + qos_class="${BASH_REMATCH[1]}" + else + qos_class="guaranteed" + fi + + # available labels: + # namespace, pod_name, pod_uid, container_name, container_id, node_name + if [ -n "$cntr_id" ]; then + if [ -n "$labels" ] || labels=$(grep "$cntr_id" <<< "$containers" 2> /dev/null); then + labels+=',kind="container"' + labels+=",qos_class=\"$qos_class\"" + [ -n "$kube_system_uid" ] && [ "$kube_system_uid" != "null" ] && labels+=",cluster_id=\"$kube_system_uid\"" + [ -n "$kube_cluster_name" ] && [ "$kube_cluster_name" != "unknown" ] && labels+=",cluster_name=\"$kube_cluster_name\"" + name="cntr" + name+="_$(get_lbl_val "$labels" namespace)" + name+="_$(get_lbl_val "$labels" pod_name)" + name+="_$(get_lbl_val "$labels" container_name)" + labels=$(remove_lbl "$labels" "container_id") + labels=$(remove_lbl "$labels" "pod_uid") + labels=$(add_lbl_prefix "$labels" "k8s_") + name+=" $labels" + else + return 2 + fi + elif [ -n "$pod_uid" ]; then + if labels=$(grep "$pod_uid" -m 1 <<< "$containers" 2> /dev/null); then + labels="${labels%%,container_*}" + labels+=',kind="pod"' + labels+=",qos_class=\"$qos_class\"" + [ -n "$kube_system_uid" ] && [ "$kube_system_uid" != "null" ] && labels+=",cluster_id=\"$kube_system_uid\"" + [ -n "$kube_cluster_name" ] && [ "$kube_cluster_name" != "unknown" ] && labels+=",cluster_name=\"$kube_cluster_name\"" + name="pod" + name+="_$(get_lbl_val "$labels" namespace)" + name+="_$(get_lbl_val "$labels" pod_name)" + labels=$(remove_lbl "$labels" "pod_uid") + labels=$(add_lbl_prefix "$labels" "k8s_") + name+=" $labels" + else + return 2 + fi + fi + + # jq filter nonexistent field and nonexistent label value is 'null' + if [[ $name =~ _null(_|$) ]]; then + warning "${fn}: invalid name: $name (cgroup '$id')" + if [ -n "${USE_KUBELET_FOR_PODS_METADATA}" ]; then + # local data is cached and may not contain the correct id + return 2 + fi + return 1 + fi + + echo "$name" + [ -n "$name" ] + return +} + +function k8s_get_name() { + local fn="${FUNCNAME[0]}" + local cgroup_path="${1}" + local id="${2}" + local kubepod_name="" + + kubepod_name=$(k8s_get_kubepod_name "$cgroup_path" "$id") + + case "$?" in + 0) + kubepod_name="k8s_${kubepod_name}" + + local name labels + name=${kubepod_name%% *} + labels=${kubepod_name#* } + + if [ "$name" != "$labels" ]; then + info "${fn}: cgroup '${id}' has chart name '${name}', labels '${labels}" + NAME="$name" + LABELS="$labels" + else + info "${fn}: cgroup '${id}' has chart name '${NAME}'" + NAME="$name" + fi + EXIT_CODE=$EXIT_SUCCESS + ;; + 1) + NAME="k8s_${id}" + warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and enabling it." + EXIT_CODE=$EXIT_SUCCESS + ;; + 2) + NAME="k8s_${id}" + warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and asking for retry." + EXIT_CODE=$EXIT_RETRY + ;; + *) + NAME="k8s_${id}" + warning "${fn}: cannot find the name of cgroup with id '${id}'. Setting name to ${NAME} and disabling it." + EXIT_CODE=$EXIT_DISABLE + ;; + esac +} + +function docker_get_name() { + local id="${1}" + # See https://github.com/netdata/netdata/pull/13523 for details + if command -v snap >/dev/null 2>&1 && snap list docker >/dev/null 2>&1; then + docker_like_get_name_api DOCKER_HOST "${id}" + elif hash docker 2> /dev/null; then + docker_like_get_name_command docker "${id}" + else + docker_like_get_name_api DOCKER_HOST "${id}" || docker_like_get_name_command podman "${id}" + fi + if [ -z "${NAME}" ]; then + warning "cannot find the name of docker container '${id}'" + EXIT_CODE=$EXIT_RETRY + NAME="${id:0:12}" + else + info "docker container '${id}' is named '${NAME}'" + fi +} + +function docker_validate_id() { + local id="${1}" + if [ -n "${id}" ] && { [ ${#id} -eq 64 ] || [ ${#id} -eq 12 ]; }; then + docker_get_name "${id}" + else + error "a docker id cannot be extracted from docker cgroup '${CGROUP}'." + fi +} + +function podman_get_name() { + local id="${1}" + + # for Podman, prefer using the API if we can, as netdata will not normally have access + # to other users' containers, so they will not be visible when running `podman ps` + docker_like_get_name_api PODMAN_HOST "${id}" || docker_like_get_name_command podman "${id}" + + if [ -z "${NAME}" ]; then + warning "cannot find the name of podman container '${id}'" + EXIT_CODE=$EXIT_RETRY + NAME="${id:0:12}" + else + info "podman container '${id}' is named '${NAME}'" + fi +} + +function podman_validate_id() { + local id="${1}" + if [ -n "${id}" ] && [ ${#id} -eq 64 ]; then + podman_get_name "${id}" + else + error "a podman id cannot be extracted from docker cgroup '${CGROUP}'." + fi +} + +# ----------------------------------------------------------------------------- + +DOCKER_HOST="${DOCKER_HOST:=/var/run/docker.sock}" +PODMAN_HOST="${PODMAN_HOST:=/run/podman/podman.sock}" +CGROUP_PATH="${1}" # the path as it is (e.g. '/docker/efcf4c409') +CGROUP="${2}" # the modified path (e.g. 'docker_efcf4c409') +EXIT_SUCCESS=0 +EXIT_RETRY=2 +EXIT_DISABLE=3 +EXIT_CODE=$EXIT_SUCCESS +NAME= +LABELS= + +# ----------------------------------------------------------------------------- + +if [ -z "${CGROUP}" ]; then + fatal "called without a cgroup name. Nothing to do." +fi + +if [ -z "${NAME}" ]; then + if [[ ${CGROUP} =~ ^.*kubepods.* ]]; then + k8s_get_name "${CGROUP_PATH}" "${CGROUP}" + fi +fi + +if [ -z "${NAME}" ]; then + if [[ ${CGROUP} =~ ^.*docker[-_/\.][a-fA-F0-9]+[-_\.]?.*$ ]]; then + # docker containers + #shellcheck disable=SC1117 + DOCKERID="$(echo "${CGROUP}" | sed "s|^.*docker[-_/]\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" + docker_validate_id "${DOCKERID}" + elif [[ ${CGROUP} =~ ^.*ecs[-_/\.][a-fA-F0-9]+[-_\.]?.*$ ]]; then + # ECS + #shellcheck disable=SC1117 + DOCKERID="$(echo "${CGROUP}" | sed "s|^.*ecs[-_/].*[-_/]\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" + docker_validate_id "${DOCKERID}" + elif [[ ${CGROUP} =~ system.slice_containerd.service_cpuset_[a-fA-F0-9]+[-_\.]?.*$ ]]; then + # docker containers under containerd + #shellcheck disable=SC1117 + DOCKERID="$(echo "${CGROUP}" | sed "s|^.*ystem.slice_containerd.service_cpuset_\([a-fA-F0-9]\+\)[-_\.]\?.*$|\1|")" + docker_validate_id "${DOCKERID}" + elif [[ ${CGROUP} =~ ^.*libpod-[a-fA-F0-9]+.*$ ]]; then + # Podman + PODMANID="$(echo "${CGROUP}" | sed "s|^.*libpod-\([a-fA-F0-9]\+\).*$|\1|")" + podman_validate_id "${PODMANID}" + + elif [[ ${CGROUP} =~ machine.slice[_/].*\.service ]]; then + # systemd-nspawn + NAME="$(echo "${CGROUP}" | sed 's/.*machine.slice[_\/]\(.*\)\.service/\1/g')" + + elif [[ ${CGROUP} =~ machine.slice_machine.*-lxc ]]; then + # libvirtd / lxc containers + # machine.slice machine-lxc/x2d969/x2dhubud0xians01.scope => lxc/hubud0xians01 + # machine.slice_machine-lxc/x2d969/x2dhubud0xians01.scope/libvirt_init.scope => lxc/hubud0xians01/libvirt_init + NAME="lxc/$(echo "${CGROUP}" | sed 's/machine.slice_machine.*-lxc//; s/[\/_]x2d[[:digit:]]*//; s/[\/_]x2d//g; s/\.scope//g')" + elif [[ ${CGROUP} =~ machine.slice_machine.*-qemu ]]; then + # libvirtd / qemu virtual machines + # machine.slice_machine-qemu_x2d1_x2dopnsense.scope => qemu_opnsense + NAME="qemu_$(echo "${CGROUP}" | sed 's/machine.slice_machine.*-qemu//; s/[\/_]x2d[[:digit:]]*//; s/[\/_]x2d//g; s/\.scope//g')" + + elif [[ ${CGROUP} =~ machine_.*\.libvirt-qemu ]]; then + # libvirtd / qemu virtual machines + NAME="qemu_$(echo "${CGROUP}" | sed 's/^machine_//; s/\.libvirt-qemu$//; s/-/_/;')" + + elif [[ ${CGROUP} =~ qemu.slice_([0-9]+).scope && -d "${NETDATA_HOST_PREFIX}/etc/pve" ]]; then + # Proxmox VMs + FILENAME="${NETDATA_HOST_PREFIX}/etc/pve/qemu-server/${BASH_REMATCH[1]}.conf" + if [[ -f $FILENAME && -r $FILENAME ]]; then + NAME="qemu_$(grep -e '^name: ' "${FILENAME}" | head -1 | sed -rn 's|\s*name\s*:\s*(.*)?$|\1|p')" + else + error "proxmox config file missing ${FILENAME} or netdata does not have read access. Please ensure netdata is a member of www-data group." + fi + elif [[ ${CGROUP} =~ lxc_([0-9]+) && -d "${NETDATA_HOST_PREFIX}/etc/pve" ]]; then + # Proxmox Containers (LXC) + FILENAME="${NETDATA_HOST_PREFIX}/etc/pve/lxc/${BASH_REMATCH[1]}.conf" + if [[ -f ${FILENAME} && -r ${FILENAME} ]]; then + NAME=$(grep -e '^hostname: ' "${FILENAME}" | head -1 | sed -rn 's|\s*hostname\s*:\s*(.*)?$|\1|p') + else + error "proxmox config file missing ${FILENAME} or netdata does not have read access. Please ensure netdata is a member of www-data group." + fi + elif [[ ${CGROUP} =~ lxc.payload.* ]]; then + # LXC 4.0 + NAME="$(echo "${CGROUP}" | sed 's/lxc\.payload\.\(.*\)/\1/g')" + fi + + [ -z "${NAME}" ] && NAME="${CGROUP}" + [ ${#NAME} -gt 100 ] && NAME="${NAME:0:100}" +fi + +NAME="${NAME// /_}" + +info "cgroup '${CGROUP}' is called '${NAME}', labels '${LABELS}'" +if [ -n "$LABELS" ]; then + echo "${NAME} ${LABELS}" +else + echo "${NAME}" +fi + +exit ${EXIT_CODE} diff --git a/collectors/cgroups.plugin/cgroup-network-helper.sh b/collectors/cgroups.plugin/cgroup-network-helper.sh deleted file mode 100755 index 008bc987f..000000000 --- a/collectors/cgroups.plugin/cgroup-network-helper.sh +++ /dev/null @@ -1,320 +0,0 @@ -#!/usr/bin/env bash -# shellcheck disable=SC1117 - -# cgroup-network-helper.sh -# detect container and virtual machine interfaces -# -# (C) 2017 Costa Tsaousis -# SPDX-License-Identifier: GPL-3.0-or-later -# -# This script is called as root (by cgroup-network), with either a pid, or a cgroup path. -# It tries to find all the network interfaces that belong to the same cgroup. -# -# It supports several method for this detection: -# -# 1. cgroup-network (the binary father of this script) detects veth network interfaces, -# by examining iflink and ifindex IDs and switching namespaces -# (it also detects the interface name as it is used by the container). -# -# 2. this script, uses /proc/PID/fdinfo to find tun/tap network interfaces. -# -# 3. this script, calls virsh to find libvirt network interfaces. -# - -# ----------------------------------------------------------------------------- - -# the system path is cleared by cgroup-network -# shellcheck source=/dev/null -[ -f /etc/profile ] && source /etc/profile - -export LC_ALL=C - -PROGRAM_NAME="$(basename "${0}")" - -LOG_LEVEL_ERR=1 -LOG_LEVEL_WARN=2 -LOG_LEVEL_INFO=3 -LOG_LEVEL="$LOG_LEVEL_INFO" - -set_log_severity_level() { - case ${NETDATA_LOG_SEVERITY_LEVEL,,} in - "info") LOG_LEVEL="$LOG_LEVEL_INFO";; - "warn" | "warning") LOG_LEVEL="$LOG_LEVEL_WARN";; - "err" | "error") LOG_LEVEL="$LOG_LEVEL_ERR";; - esac -} - -set_log_severity_level - -logdate() { - date "+%Y-%m-%d %H:%M:%S" -} - -log() { - local status="${1}" - shift - - echo >&2 "$(logdate): ${PROGRAM_NAME}: ${status}: ${*}" - -} - -info() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_INFO" -gt "$LOG_LEVEL" ]] && return - log INFO "${@}" -} - -warning() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_WARN" -gt "$LOG_LEVEL" ]] && return - log WARNING "${@}" -} - -error() { - [[ -n "$LOG_LEVEL" && "$LOG_LEVEL_ERR" -gt "$LOG_LEVEL" ]] && return - log ERROR "${@}" -} - -fatal() { - log FATAL "${@}" - exit 1 -} - -debug=${NETDATA_CGROUP_NETWORK_HELPER_DEBUG=0} -debug() { - [ "${debug}" = "1" ] && log DEBUG "${@}" -} - -# ----------------------------------------------------------------------------- -# check for BASH v4+ (required for associative arrays) - -[ $(( BASH_VERSINFO[0] )) -lt 4 ] && \ - fatal "BASH version 4 or later is required (this is ${BASH_VERSION})." - -# ----------------------------------------------------------------------------- -# parse the arguments - -pid= -cgroup= -while [ -n "${1}" ] -do - case "${1}" in - --cgroup) cgroup="${2}"; shift 1;; - --pid|-p) pid="${2}"; shift 1;; - --debug|debug) debug=1;; - *) fatal "Cannot understand argument '${1}'";; - esac - - shift -done - -if [ -z "${pid}" ] && [ -z "${cgroup}" ] -then - fatal "Either --pid or --cgroup is required" -fi - -# ----------------------------------------------------------------------------- - -set_source() { - [ ${debug} -eq 1 ] && echo "SRC ${*}" -} - - -# ----------------------------------------------------------------------------- -# veth interfaces via cgroup - -# cgroup-network can detect veth interfaces by itself (written in C). -# If you seek for a shell version of what it does, check this: -# https://github.com/netdata/netdata/issues/474#issuecomment-317866709 - - -# ----------------------------------------------------------------------------- -# tun/tap interfaces via /proc/PID/fdinfo - -# find any tun/tap devices linked to a pid -proc_pid_fdinfo_iff() { - local p="${1}" # the pid - - debug "Searching for tun/tap interfaces for pid ${p}..." - set_source "fdinfo" - grep "^iff:.*" "${NETDATA_HOST_PREFIX}/proc/${p}/fdinfo"/* 2>/dev/null | cut -f 2 -} - -find_tun_tap_interfaces_for_cgroup() { - local c="${1}" # the cgroup path - [ -d "${c}/emulator" ] && c="${c}/emulator" # check for 'emulator' subdirectory - c="${c}/cgroup.procs" # make full path - - # for each pid of the cgroup - # find any tun/tap devices linked to the pid - if [ -f "${c}" ] - then - local p - for p in $(< "${c}" ) - do - proc_pid_fdinfo_iff "${p}" - done - else - debug "Cannot find file '${c}', not searching for tun/tap interfaces." - fi -} - - -# ----------------------------------------------------------------------------- -# virsh domain network interfaces - -virsh_cgroup_to_domain_name() { - local c="${1}" # the cgroup path - - debug "extracting a possible virsh domain from cgroup ${c}..." - - # extract for the cgroup path - sed -n -e "s|.*/machine-qemu\\\\x2d[0-9]\+\\\\x2d\(.*\)\.scope$|\1|p" \ - -e "s|.*/machine/qemu-[0-9]\+-\(.*\)\.libvirt-qemu$|\1|p" \ - -e "s|.*/machine/\(.*\)\.libvirt-qemu$|\1|p" \ - <<EOF -${c} -EOF -} - -virsh_find_all_interfaces_for_cgroup() { - local c="${1}" # the cgroup path - - # the virsh command - local virsh - # shellcheck disable=SC2230 - virsh="$(which virsh 2>/dev/null || command -v virsh 2>/dev/null)" - - if [ -n "${virsh}" ] - then - local d - d="$(virsh_cgroup_to_domain_name "${c}")" - # convert hex to character - # e.g.: vm01\x2dweb => vm01-web (https://github.com/netdata/netdata/issues/11088#issuecomment-832618149) - d="$(printf '%b' "${d}")" - - if [ -n "${d}" ] - then - debug "running: virsh domiflist ${d}; to find the network interfaces" - - # 'virsh -r domiflist <domain>' example output - # Interface Type Source Model MAC - #-------------------------------------------------------------- - # vnet3 bridge br0 virtio 52:54:00:xx:xx:xx - # vnet4 network default virtio 52:54:00:yy:yy:yy - - # match only 'network' interfaces from virsh output - set_source "virsh" - "${virsh}" -r domiflist "${d}" |\ - sed -n \ - -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+network[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" \ - -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+bridge[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" - else - debug "no virsh domain extracted from cgroup ${c}" - fi - else - debug "virsh command is not available" - fi -} - -# ----------------------------------------------------------------------------- -# netnsid detected interfaces - -netnsid_find_all_interfaces_for_pid() { - local pid="${1}" - [ -z "${pid}" ] && return 1 - - local nsid - nsid=$(lsns -t net -p "${pid}" -o NETNSID -nr 2>/dev/null) - if [ -z "${nsid}" ] || [ "${nsid}" = "unassigned" ]; then - return 1 - fi - - set_source "netnsid" - ip link show |\ - grep -B 1 -E " link-netnsid ${nsid}($| )" |\ - sed -n -e "s|^[[:space:]]*[0-9]\+:[[:space:]]\+\([A-Za-z0-9_]\+\)\(@[A-Za-z0-9_]\+\)*:[[:space:]].*$|\1|p" -} - -netnsid_find_all_interfaces_for_cgroup() { - local c="${1}" # the cgroup path - - if [ -f "${c}/cgroup.procs" ]; then - netnsid_find_all_interfaces_for_pid "$(head -n 1 "${c}/cgroup.procs" 2>/dev/null)" - else - debug "Cannot find file '${c}/cgroup.procs', not searching for netnsid interfaces." - fi -} - -# ----------------------------------------------------------------------------- - -find_all_interfaces_of_pid_or_cgroup() { - local p="${1}" c="${2}" # the pid and the cgroup path - - if [ -n "${pid}" ] - then - # we have been called with a pid - - proc_pid_fdinfo_iff "${p}" - netnsid_find_all_interfaces_for_pid "${p}" - - elif [ -n "${c}" ] - then - # we have been called with a cgroup - - info "searching for network interfaces of cgroup '${c}'" - - find_tun_tap_interfaces_for_cgroup "${c}" - virsh_find_all_interfaces_for_cgroup "${c}" - netnsid_find_all_interfaces_for_cgroup "${c}" - - else - - error "Either a pid or a cgroup path is needed" - return 1 - - fi - - return 0 -} - -# ----------------------------------------------------------------------------- - -# an associative array to store the interfaces -# the index is the interface name as seen by the host -# the value is the interface name as seen by the guest / container -declare -A devs=() - -# store all interfaces found in the associative array -# this will also give the unique devices, as seen by the host -last_src= -# shellcheck disable=SC2162 -while read host_device guest_device -do - [ -z "${host_device}" ] && continue - - [ "${host_device}" = "SRC" ] && last_src="${guest_device}" && continue - - # the default guest_device is the host_device - [ -z "${guest_device}" ] && guest_device="${host_device}" - - # when we run in debug, show the source - debug "Found host device '${host_device}', guest device '${guest_device}', detected via '${last_src}'" - - if [ -z "${devs[${host_device}]}" ] || [ "${devs[${host_device}]}" = "${host_device}" ]; then - devs[${host_device}]="${guest_device}" - fi - -done < <( find_all_interfaces_of_pid_or_cgroup "${pid}" "${cgroup}" ) - -# print the interfaces found, in the format netdata expects them -found=0 -for x in "${!devs[@]}" -do - found=$((found + 1)) - echo "${x} ${devs[${x}]}" -done - -debug "found ${found} network interfaces for pid '${pid}', cgroup '${cgroup}', run as ${USER}, ${UID}" - -# let netdata know if we found any -[ ${found} -eq 0 ] && exit 1 -exit 0 diff --git a/collectors/cgroups.plugin/cgroup-network-helper.sh.in b/collectors/cgroups.plugin/cgroup-network-helper.sh.in new file mode 100755 index 000000000..da9b9162a --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-network-helper.sh.in @@ -0,0 +1,376 @@ +#!/usr/bin/env bash +# shellcheck disable=SC1117 + +# cgroup-network-helper.sh +# detect container and virtual machine interfaces +# +# (C) 2023 Netdata Inc. +# SPDX-License-Identifier: GPL-3.0-or-later +# +# This script is called as root (by cgroup-network), with either a pid, or a cgroup path. +# It tries to find all the network interfaces that belong to the same cgroup. +# +# It supports several method for this detection: +# +# 1. cgroup-network (the binary father of this script) detects veth network interfaces, +# by examining iflink and ifindex IDs and switching namespaces +# (it also detects the interface name as it is used by the container). +# +# 2. this script, uses /proc/PID/fdinfo to find tun/tap network interfaces. +# +# 3. this script, calls virsh to find libvirt network interfaces. +# + +# ----------------------------------------------------------------------------- + +# the system path is cleared by cgroup-network +# shellcheck source=/dev/null +[ -f /etc/profile ] && source /etc/profile +export PATH="${PATH}:@sbindir_POST@" + +export LC_ALL=C + +cmd_line="'${0}' $(printf "'%s' " "${@}")" + +# ----------------------------------------------------------------------------- +# logging + +PROGRAM_NAME="$(basename "${0}")" + +# these should be the same with syslog() priorities +NDLP_EMERG=0 # system is unusable +NDLP_ALERT=1 # action must be taken immediately +NDLP_CRIT=2 # critical conditions +NDLP_ERR=3 # error conditions +NDLP_WARN=4 # warning conditions +NDLP_NOTICE=5 # normal but significant condition +NDLP_INFO=6 # informational +NDLP_DEBUG=7 # debug-level messages + +# the max (numerically) log level we will log +LOG_LEVEL=$NDLP_INFO + +set_log_min_priority() { + case "${NETDATA_LOG_LEVEL,,}" in + "emerg" | "emergency") + LOG_LEVEL=$NDLP_EMERG + ;; + + "alert") + LOG_LEVEL=$NDLP_ALERT + ;; + + "crit" | "critical") + LOG_LEVEL=$NDLP_CRIT + ;; + + "err" | "error") + LOG_LEVEL=$NDLP_ERR + ;; + + "warn" | "warning") + LOG_LEVEL=$NDLP_WARN + ;; + + "notice") + LOG_LEVEL=$NDLP_NOTICE + ;; + + "info") + LOG_LEVEL=$NDLP_INFO + ;; + + "debug") + LOG_LEVEL=$NDLP_DEBUG + ;; + esac +} + +set_log_min_priority + +log() { + local level="${1}" + shift 1 + + [[ -n "$level" && -n "$LOG_LEVEL" && "$level" -gt "$LOG_LEVEL" ]] && return + + systemd-cat-native --log-as-netdata --newline="--NEWLINE--" <<EOFLOG +INVOCATION_ID=${NETDATA_INVOCATION_ID} +SYSLOG_IDENTIFIER=${PROGRAM_NAME} +PRIORITY=${level} +THREAD_TAG=cgroup-network-helper +ND_LOG_SOURCE=collector +ND_REQUEST=${cmd_line} +MESSAGE=${*//\\n/--NEWLINE--} + +EOFLOG + # AN EMPTY LINE IS NEEDED ABOVE +} + +info() { + log "$NDLP_INFO" "${@}" +} + +warning() { + log "$NDLP_WARN" "${@}" +} + +error() { + log "$NDLP_ERR" "${@}" +} + +fatal() { + log "$NDLP_ALERT" "${@}" + exit 1 +} + +debug() { + log "$NDLP_DEBUG" "${@}" +} + +debug=0 +if [ "${NETDATA_CGROUP_NETWORK_HELPER_DEBUG-0}" = "1" ]; then + debug=1 + LOG_LEVEL=$NDLP_DEBUG +fi + +# ----------------------------------------------------------------------------- +# check for BASH v4+ (required for associative arrays) + +if [ ${BASH_VERSINFO[0]} -lt 4 ]; then + echo >&2 "BASH version 4 or later is required (this is ${BASH_VERSION})." + exit 1 +fi + +# ----------------------------------------------------------------------------- +# parse the arguments + +pid= +cgroup= +while [ -n "${1}" ] +do + case "${1}" in + --cgroup) cgroup="${2}"; shift 1;; + --pid|-p) pid="${2}"; shift 1;; + --debug|debug) + debug=1 + LOG_LEVEL=$NDLP_DEBUG + ;; + *) fatal "Cannot understand argument '${1}'";; + esac + + shift +done + +if [ -z "${pid}" ] && [ -z "${cgroup}" ] +then + fatal "Either --pid or --cgroup is required" +fi + +# ----------------------------------------------------------------------------- + +set_source() { + [ ${debug} -eq 1 ] && echo "SRC ${*}" +} + + +# ----------------------------------------------------------------------------- +# veth interfaces via cgroup + +# cgroup-network can detect veth interfaces by itself (written in C). +# If you seek for a shell version of what it does, check this: +# https://github.com/netdata/netdata/issues/474#issuecomment-317866709 + + +# ----------------------------------------------------------------------------- +# tun/tap interfaces via /proc/PID/fdinfo + +# find any tun/tap devices linked to a pid +proc_pid_fdinfo_iff() { + local p="${1}" # the pid + + debug "Searching for tun/tap interfaces for pid ${p}..." + set_source "fdinfo" + grep "^iff:.*" "${NETDATA_HOST_PREFIX}/proc/${p}/fdinfo"/* 2>/dev/null | cut -f 2 +} + +find_tun_tap_interfaces_for_cgroup() { + local c="${1}" # the cgroup path + [ -d "${c}/emulator" ] && c="${c}/emulator" # check for 'emulator' subdirectory + c="${c}/cgroup.procs" # make full path + + # for each pid of the cgroup + # find any tun/tap devices linked to the pid + if [ -f "${c}" ] + then + local p + for p in $(< "${c}" ) + do + proc_pid_fdinfo_iff "${p}" + done + else + debug "Cannot find file '${c}', not searching for tun/tap interfaces." + fi +} + + +# ----------------------------------------------------------------------------- +# virsh domain network interfaces + +virsh_cgroup_to_domain_name() { + local c="${1}" # the cgroup path + + debug "extracting a possible virsh domain from cgroup ${c}..." + + # extract for the cgroup path + sed -n -e "s|.*/machine-qemu\\\\x2d[0-9]\+\\\\x2d\(.*\)\.scope$|\1|p" \ + -e "s|.*/machine/qemu-[0-9]\+-\(.*\)\.libvirt-qemu$|\1|p" \ + -e "s|.*/machine/\(.*\)\.libvirt-qemu$|\1|p" \ + <<EOF +${c} +EOF +} + +virsh_find_all_interfaces_for_cgroup() { + local c="${1}" # the cgroup path + + # the virsh command + local virsh + # shellcheck disable=SC2230 + virsh="$(which virsh 2>/dev/null || command -v virsh 2>/dev/null)" + + if [ -n "${virsh}" ] + then + local d + d="$(virsh_cgroup_to_domain_name "${c}")" + # convert hex to character + # e.g.: vm01\x2dweb => vm01-web (https://github.com/netdata/netdata/issues/11088#issuecomment-832618149) + d="$(printf '%b' "${d}")" + + if [ -n "${d}" ] + then + debug "running: virsh domiflist ${d}; to find the network interfaces" + + # 'virsh -r domiflist <domain>' example output + # Interface Type Source Model MAC + #-------------------------------------------------------------- + # vnet3 bridge br0 virtio 52:54:00:xx:xx:xx + # vnet4 network default virtio 52:54:00:yy:yy:yy + + # match only 'network' interfaces from virsh output + set_source "virsh" + "${virsh}" -r domiflist "${d}" |\ + sed -n \ + -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+network[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" \ + -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+bridge[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" + else + debug "no virsh domain extracted from cgroup ${c}" + fi + else + debug "virsh command is not available" + fi +} + +# ----------------------------------------------------------------------------- +# netnsid detected interfaces + +netnsid_find_all_interfaces_for_pid() { + local pid="${1}" + [ -z "${pid}" ] && return 1 + + local nsid + nsid=$(lsns -t net -p "${pid}" -o NETNSID -nr 2>/dev/null) + if [ -z "${nsid}" ] || [ "${nsid}" = "unassigned" ]; then + return 1 + fi + + set_source "netnsid" + ip link show |\ + grep -B 1 -E " link-netnsid ${nsid}($| )" |\ + sed -n -e "s|^[[:space:]]*[0-9]\+:[[:space:]]\+\([A-Za-z0-9_]\+\)\(@[A-Za-z0-9_]\+\)*:[[:space:]].*$|\1|p" +} + +netnsid_find_all_interfaces_for_cgroup() { + local c="${1}" # the cgroup path + + if [ -f "${c}/cgroup.procs" ]; then + netnsid_find_all_interfaces_for_pid "$(head -n 1 "${c}/cgroup.procs" 2>/dev/null)" + else + debug "Cannot find file '${c}/cgroup.procs', not searching for netnsid interfaces." + fi +} + +# ----------------------------------------------------------------------------- + +find_all_interfaces_of_pid_or_cgroup() { + local p="${1}" c="${2}" # the pid and the cgroup path + + if [ -n "${pid}" ] + then + # we have been called with a pid + + proc_pid_fdinfo_iff "${p}" + netnsid_find_all_interfaces_for_pid "${p}" + + elif [ -n "${c}" ] + then + # we have been called with a cgroup + + info "searching for network interfaces of cgroup '${c}'" + + find_tun_tap_interfaces_for_cgroup "${c}" + virsh_find_all_interfaces_for_cgroup "${c}" + netnsid_find_all_interfaces_for_cgroup "${c}" + + else + + error "Either a pid or a cgroup path is needed" + return 1 + + fi + + return 0 +} + +# ----------------------------------------------------------------------------- + +# an associative array to store the interfaces +# the index is the interface name as seen by the host +# the value is the interface name as seen by the guest / container +declare -A devs=() + +# store all interfaces found in the associative array +# this will also give the unique devices, as seen by the host +last_src= +# shellcheck disable=SC2162 +while read host_device guest_device +do + [ -z "${host_device}" ] && continue + + [ "${host_device}" = "SRC" ] && last_src="${guest_device}" && continue + + # the default guest_device is the host_device + [ -z "${guest_device}" ] && guest_device="${host_device}" + + # when we run in debug, show the source + debug "Found host device '${host_device}', guest device '${guest_device}', detected via '${last_src}'" + + if [ -z "${devs[${host_device}]}" ] || [ "${devs[${host_device}]}" = "${host_device}" ]; then + devs[${host_device}]="${guest_device}" + fi + +done < <( find_all_interfaces_of_pid_or_cgroup "${pid}" "${cgroup}" ) + +# print the interfaces found, in the format netdata expects them +found=0 +for x in "${!devs[@]}" +do + found=$((found + 1)) + echo "${x} ${devs[${x}]}" +done + +debug "found ${found} network interfaces for pid '${pid}', cgroup '${cgroup}', run as ${USER}, ${UID}" + +# let netdata know if we found any +[ ${found} -eq 0 ] && exit 1 +exit 0 diff --git a/collectors/cgroups.plugin/cgroup-network.c b/collectors/cgroups.plugin/cgroup-network.c index b00f246bb..508ea07c6 100644 --- a/collectors/cgroups.plugin/cgroup-network.c +++ b/collectors/cgroups.plugin/cgroup-network.c @@ -10,12 +10,16 @@ #include <sched.h> #endif -char environment_variable2[FILENAME_MAX + 50] = ""; -char environment_variable3[FILENAME_MAX + 50] = ""; +char env_netdata_host_prefix[FILENAME_MAX + 50] = ""; +char env_netdata_log_method[FILENAME_MAX + 50] = ""; +char env_netdata_log_format[FILENAME_MAX + 50] = ""; +char env_netdata_log_level[FILENAME_MAX + 50] = ""; char *environment[] = { "PATH=/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin:/usr/local/sbin", - environment_variable2, - environment_variable3, + env_netdata_host_prefix, + env_netdata_log_method, + env_netdata_log_format, + env_netdata_log_level, NULL }; @@ -288,7 +292,8 @@ int switch_namespace(const char *prefix, pid_t pid) { pid_t read_pid_from_cgroup_file(const char *filename) { int fd = open(filename, procfile_open_flags); if(fd == -1) { - collector_error("Cannot open pid_from_cgroup() file '%s'.", filename); + if (errno != ENOENT) + collector_error("Cannot open pid_from_cgroup() file '%s'.", filename); return 0; } @@ -648,12 +653,11 @@ void usage(void) { } int main(int argc, char **argv) { - stderror = stderr; pid_t pid = 0; - program_name = argv[0]; program_version = VERSION; - error_log_syslog = 0; + clocks_init(); + nd_log_initialize_for_external_plugins("cgroup-network"); // since cgroup-network runs as root, prevent it from opening symbolic links procfile_open_flags = O_RDONLY|O_NOFOLLOW; @@ -662,7 +666,7 @@ int main(int argc, char **argv) { // make sure NETDATA_HOST_PREFIX is safe netdata_configured_host_prefix = getenv("NETDATA_HOST_PREFIX"); - if(verify_netdata_host_prefix() == -1) exit(1); + if(verify_netdata_host_prefix(false) == -1) exit(1); if(netdata_configured_host_prefix[0] != '\0' && verify_path(netdata_configured_host_prefix) == -1) fatal("invalid NETDATA_HOST_PREFIX '%s'", netdata_configured_host_prefix); @@ -671,11 +675,20 @@ int main(int argc, char **argv) { // build a safe environment for our script // the first environment variable is a fixed PATH= - snprintfz(environment_variable2, sizeof(environment_variable2) - 1, "NETDATA_HOST_PREFIX=%s", netdata_configured_host_prefix); + snprintfz(env_netdata_host_prefix, sizeof(env_netdata_host_prefix) - 1, "NETDATA_HOST_PREFIX=%s", netdata_configured_host_prefix); - char *s = getenv("NETDATA_LOG_SEVERITY_LEVEL"); + char *s; + + s = getenv("NETDATA_LOG_METHOD"); + snprintfz(env_netdata_log_method, sizeof(env_netdata_log_method) - 1, "NETDATA_LOG_METHOD=%s", nd_log_method_for_external_plugins(s)); + + s = getenv("NETDATA_LOG_FORMAT"); + if (s) + snprintfz(env_netdata_log_format, sizeof(env_netdata_log_format) - 1, "NETDATA_LOG_FORMAT=%s", s); + + s = getenv("NETDATA_LOG_LEVEL"); if (s) - snprintfz(environment_variable3, sizeof(environment_variable3) - 1, "NETDATA_LOG_SEVERITY_LEVEL=%s", s); + snprintfz(env_netdata_log_level, sizeof(env_netdata_log_level) - 1, "NETDATA_LOG_LEVEL=%s", s); // ------------------------------------------------------------------------ @@ -686,8 +699,6 @@ int main(int argc, char **argv) { if(argc != 3) usage(); - - log_set_global_severity_for_external_plugins(); int arg = 1; int helper = 1; diff --git a/collectors/cgroups.plugin/cgroup-top.c b/collectors/cgroups.plugin/cgroup-top.c new file mode 100644 index 000000000..8d44d3b56 --- /dev/null +++ b/collectors/cgroups.plugin/cgroup-top.c @@ -0,0 +1,520 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "cgroup-internals.h" + +struct cgroup_netdev_link { + size_t read_slot; + NETDATA_DOUBLE received[2]; + NETDATA_DOUBLE sent[2]; +}; + +static DICTIONARY *cgroup_netdev_link_dict = NULL; + +void cgroup_netdev_link_init(void) { + cgroup_netdev_link_dict = dictionary_create_advanced(DICT_OPTION_FIXED_SIZE|DICT_OPTION_DONT_OVERWRITE_VALUE, NULL, sizeof(struct cgroup_netdev_link)); +} + +const DICTIONARY_ITEM *cgroup_netdev_get(struct cgroup *cg) { + if(!cg->cgroup_netdev_link) { + struct cgroup_netdev_link t = { + .read_slot = 0, + .received = {NAN, NAN}, + .sent = {NAN, NAN}, + }; + + cg->cgroup_netdev_link = + dictionary_set_and_acquire_item(cgroup_netdev_link_dict, cg->id, &t, sizeof(struct cgroup_netdev_link)); + } + + return dictionary_acquired_item_dup(cgroup_netdev_link_dict, cg->cgroup_netdev_link); +} + +void cgroup_netdev_delete(struct cgroup *cg) { + if(cg->cgroup_netdev_link) { + dictionary_acquired_item_release(cgroup_netdev_link_dict, cg->cgroup_netdev_link); + dictionary_del(cgroup_netdev_link_dict, cg->id); + dictionary_garbage_collect(cgroup_netdev_link_dict); + cg->cgroup_netdev_link = NULL; + } +} + +void cgroup_netdev_release(const DICTIONARY_ITEM *link) { + if(link) + dictionary_acquired_item_release(cgroup_netdev_link_dict, link); +} + +const void *cgroup_netdev_dup(const DICTIONARY_ITEM *link) { + return dictionary_acquired_item_dup(cgroup_netdev_link_dict, link); +} + +void cgroup_netdev_reset_all(void) { + struct cgroup_netdev_link *t; + dfe_start_read(cgroup_netdev_link_dict, t) { + if(t->read_slot >= 1) { + t->read_slot = 0; + t->received[1] = NAN; + t->sent[1] = NAN; + } + else { + t->read_slot = 1; + t->received[0] = NAN; + t->sent[0] = NAN; + } + } + dfe_done(t); +} + +void cgroup_netdev_add_bandwidth(const DICTIONARY_ITEM *link, NETDATA_DOUBLE received, NETDATA_DOUBLE sent) { + if(!link) + return; + + struct cgroup_netdev_link *t = dictionary_acquired_item_value(link); + + size_t slot = (t->read_slot) ? 0 : 1; + + if(isnan(t->received[slot])) + t->received[slot] = received; + else + t->received[slot] += received; + + if(isnan(t->sent[slot])) + t->sent[slot] = sent; + else + t->sent[slot] += sent; +} + +void cgroup_netdev_get_bandwidth(struct cgroup *cg, NETDATA_DOUBLE *received, NETDATA_DOUBLE *sent) { + if(!cg->cgroup_netdev_link) { + *received = NAN; + *sent = NAN; + return; + } + + struct cgroup_netdev_link *t = dictionary_acquired_item_value(cg->cgroup_netdev_link); + + size_t slot = (t->read_slot) ? 1 : 0; + + *received = t->received[slot]; + *sent = t->sent[slot]; +} + +int cgroup_function_cgroup_top(BUFFER *wb, int timeout __maybe_unused, const char *function __maybe_unused, + void *collector_data __maybe_unused, + rrd_function_result_callback_t result_cb, void *result_cb_data, + rrd_function_is_cancelled_cb_t is_cancelled_cb, void *is_cancelled_cb_data, + rrd_function_register_canceller_cb_t register_canceller_cb __maybe_unused, + void *register_canceller_cb_data __maybe_unused) { + + buffer_flush(wb); + wb->content_type = CT_APPLICATION_JSON; + buffer_json_initialize(wb, "\"", "\"", 0, true, BUFFER_JSON_OPTIONS_DEFAULT); + + buffer_json_member_add_string(wb, "hostname", rrdhost_hostname(localhost)); + buffer_json_member_add_uint64(wb, "status", HTTP_RESP_OK); + buffer_json_member_add_string(wb, "type", "table"); + buffer_json_member_add_time_t(wb, "update_every", 1); + buffer_json_member_add_string(wb, "help", RRDFUNCTIONS_CGTOP_HELP); + buffer_json_member_add_array(wb, "data"); + + double max_pids = 0.0; + double max_cpu = 0.0; + double max_ram = 0.0; + double max_disk_io_read = 0.0; + double max_disk_io_written = 0.0; + double max_net_received = 0.0; + double max_net_sent = 0.0; + + RRDDIM *rd = NULL; + + uv_mutex_lock(&cgroup_root_mutex); + + for(struct cgroup *cg = cgroup_root; cg ; cg = cg->next) { + if(unlikely(!cg->enabled || cg->pending_renames || !cg->function_ready || is_cgroup_systemd_service(cg))) + continue; + + buffer_json_add_array_item_array(wb); + + buffer_json_add_array_item_string(wb, cg->name); // Name + + if(k8s_is_kubepod(cg)) + buffer_json_add_array_item_string(wb, "k8s"); // Kind + else + buffer_json_add_array_item_string(wb, "cgroup"); // Kind + + double pids_current = rrddim_get_last_stored_value(cg->st_pids_rd_pids_current, &max_pids, 1.0); + + double cpu = NAN; + if (cg->st_cpu_rd_user && cg->st_cpu_rd_system) { + cpu = cg->st_cpu_rd_user->collector.last_stored_value + cg->st_cpu_rd_system->collector.last_stored_value; + max_cpu = MAX(max_cpu, cpu); + } + + double ram = rrddim_get_last_stored_value(cg->st_mem_rd_ram, &max_ram, 1.0); + + rd = cg->st_throttle_io_rd_read ? cg->st_throttle_io_rd_read : cg->st_io_rd_read; + double disk_io_read = rrddim_get_last_stored_value(rd, &max_disk_io_read, 1024.0); + rd = cg->st_throttle_io_rd_written ? cg->st_throttle_io_rd_written : cg->st_io_rd_written; + double disk_io_written = rrddim_get_last_stored_value(rd, &max_disk_io_written, 1024.0); + + NETDATA_DOUBLE received, sent; + cgroup_netdev_get_bandwidth(cg, &received, &sent); + if (!isnan(received) && !isnan(sent)) { + received /= 1000.0; + sent /= 1000.0; + max_net_received = MAX(max_net_received, received); + max_net_sent = MAX(max_net_sent, sent); + } + + buffer_json_add_array_item_double(wb, pids_current); + buffer_json_add_array_item_double(wb, cpu); + buffer_json_add_array_item_double(wb, ram); + buffer_json_add_array_item_double(wb, disk_io_read); + buffer_json_add_array_item_double(wb, disk_io_written); + buffer_json_add_array_item_double(wb, received); + buffer_json_add_array_item_double(wb, sent); + + buffer_json_array_close(wb); + } + + uv_mutex_unlock(&cgroup_root_mutex); + + buffer_json_array_close(wb); // data + buffer_json_member_add_object(wb, "columns"); + { + size_t field_id = 0; + + // Node + buffer_rrdf_table_add_field(wb, field_id++, "Name", "CGROUP Name", + RRDF_FIELD_TYPE_STRING, RRDF_FIELD_VISUAL_VALUE, RRDF_FIELD_TRANSFORM_NONE, + 0, NULL, NAN, RRDF_FIELD_SORT_ASCENDING, NULL, + RRDF_FIELD_SUMMARY_COUNT, RRDF_FIELD_FILTER_MULTISELECT, + RRDF_FIELD_OPTS_VISIBLE | RRDF_FIELD_OPTS_UNIQUE_KEY | RRDF_FIELD_OPTS_STICKY | RRDF_FIELD_OPTS_FULL_WIDTH, + NULL); + + // Kind + buffer_rrdf_table_add_field(wb, field_id++, "Kind", "CGROUP Kind", + RRDF_FIELD_TYPE_STRING, RRDF_FIELD_VISUAL_VALUE, RRDF_FIELD_TRANSFORM_NONE, + 0, NULL, NAN, RRDF_FIELD_SORT_ASCENDING, NULL, + RRDF_FIELD_SUMMARY_COUNT, RRDF_FIELD_FILTER_MULTISELECT, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // PIDs + buffer_rrdf_table_add_field(wb, field_id++, "PIDs", "Number of Processes Currently in the CGROUP", + RRDF_FIELD_TYPE_INTEGER, RRDF_FIELD_VISUAL_VALUE, RRDF_FIELD_TRANSFORM_NUMBER, + 0, "pids", max_pids, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // CPU + buffer_rrdf_table_add_field(wb, field_id++, "CPU", "CPU Usage", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "%", max_cpu, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // RAM + buffer_rrdf_table_add_field(wb, field_id++, "RAM", "RAM Usage", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_ram, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Disk IO Reads + buffer_rrdf_table_add_field(wb, field_id++, "Reads", "Disk Read Data", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_disk_io_read, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Disk IO Writes + buffer_rrdf_table_add_field(wb, field_id++, "Writes", "Disk Written Data", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_disk_io_written, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Network Received + buffer_rrdf_table_add_field(wb, field_id++, "Received", "Network Traffic Received", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "Mbps", max_net_received, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Network Sent + buffer_rrdf_table_add_field(wb, field_id++, "Sent", "Network Traffic Sent ", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "Mbps", max_net_sent, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + } + buffer_json_object_close(wb); // columns + buffer_json_member_add_string(wb, "default_sort_column", "CPU"); + + buffer_json_member_add_object(wb, "charts"); + { + buffer_json_member_add_object(wb, "CPU"); + { + buffer_json_member_add_string(wb, "name", "CPU"); + buffer_json_member_add_string(wb, "type", "stacked-bar"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "CPU"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + + buffer_json_member_add_object(wb, "Memory"); + { + buffer_json_member_add_string(wb, "name", "Memory"); + buffer_json_member_add_string(wb, "type", "stacked-bar"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "RAM"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + + buffer_json_member_add_object(wb, "Traffic"); + { + buffer_json_member_add_string(wb, "name", "Traffic"); + buffer_json_member_add_string(wb, "type", "stacked-bar"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "Received"); + buffer_json_add_array_item_string(wb, "Sent"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + } + buffer_json_object_close(wb); // charts + + buffer_json_member_add_array(wb, "default_charts"); + { + buffer_json_add_array_item_array(wb); + buffer_json_add_array_item_string(wb, "CPU"); + buffer_json_add_array_item_string(wb, "Name"); + buffer_json_array_close(wb); + + buffer_json_add_array_item_array(wb); + buffer_json_add_array_item_string(wb, "Memory"); + buffer_json_add_array_item_string(wb, "Name"); + buffer_json_array_close(wb); + } + buffer_json_array_close(wb); + + buffer_json_member_add_object(wb, "group_by"); + { + buffer_json_member_add_object(wb, "Kind"); + { + buffer_json_member_add_string(wb, "name", "Kind"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "Kind"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + } + buffer_json_object_close(wb); // group_by + + buffer_json_member_add_time_t(wb, "expires", now_realtime_sec() + 1); + buffer_json_finalize(wb); + + int response = HTTP_RESP_OK; + if(is_cancelled_cb && is_cancelled_cb(is_cancelled_cb_data)) { + buffer_flush(wb); + response = HTTP_RESP_CLIENT_CLOSED_REQUEST; + } + + if(result_cb) + result_cb(wb, response, result_cb_data); + + return response; +} + +int cgroup_function_systemd_top(BUFFER *wb, int timeout __maybe_unused, const char *function __maybe_unused, + void *collector_data __maybe_unused, + rrd_function_result_callback_t result_cb, void *result_cb_data, + rrd_function_is_cancelled_cb_t is_cancelled_cb, void *is_cancelled_cb_data, + rrd_function_register_canceller_cb_t register_canceller_cb __maybe_unused, + void *register_canceller_cb_data __maybe_unused) { + + buffer_flush(wb); + wb->content_type = CT_APPLICATION_JSON; + buffer_json_initialize(wb, "\"", "\"", 0, true, BUFFER_JSON_OPTIONS_DEFAULT); + + buffer_json_member_add_string(wb, "hostname", rrdhost_hostname(localhost)); + buffer_json_member_add_uint64(wb, "status", HTTP_RESP_OK); + buffer_json_member_add_string(wb, "type", "table"); + buffer_json_member_add_time_t(wb, "update_every", 1); + buffer_json_member_add_string(wb, "help", RRDFUNCTIONS_CGTOP_HELP); + buffer_json_member_add_array(wb, "data"); + + double max_pids = 0.0; + double max_cpu = 0.0; + double max_ram = 0.0; + double max_disk_io_read = 0.0; + double max_disk_io_written = 0.0; + + RRDDIM *rd = NULL; + + uv_mutex_lock(&cgroup_root_mutex); + + for(struct cgroup *cg = cgroup_root; cg ; cg = cg->next) { + if(unlikely(!cg->enabled || cg->pending_renames || !cg->function_ready || !is_cgroup_systemd_service(cg))) + continue; + + buffer_json_add_array_item_array(wb); + + buffer_json_add_array_item_string(wb, cg->name); + + double pids_current = rrddim_get_last_stored_value(cg->st_pids_rd_pids_current, &max_pids, 1.0); + + double cpu = NAN; + if (cg->st_cpu_rd_user && cg->st_cpu_rd_system) { + cpu = cg->st_cpu_rd_user->collector.last_stored_value + cg->st_cpu_rd_system->collector.last_stored_value; + max_cpu = MAX(max_cpu, cpu); + } + + double ram = rrddim_get_last_stored_value(cg->st_mem_rd_ram, &max_ram, 1.0); + + rd = cg->st_throttle_io_rd_read ? cg->st_throttle_io_rd_read : cg->st_io_rd_read; + double disk_io_read = rrddim_get_last_stored_value(rd, &max_disk_io_read, 1024.0); + rd = cg->st_throttle_io_rd_written ? cg->st_throttle_io_rd_written : cg->st_io_rd_written; + double disk_io_written = rrddim_get_last_stored_value(rd, &max_disk_io_written, 1024.0); + + buffer_json_add_array_item_double(wb, pids_current); + buffer_json_add_array_item_double(wb, cpu); + buffer_json_add_array_item_double(wb, ram); + buffer_json_add_array_item_double(wb, disk_io_read); + buffer_json_add_array_item_double(wb, disk_io_written); + + buffer_json_array_close(wb); + } + + uv_mutex_unlock(&cgroup_root_mutex); + + buffer_json_array_close(wb); // data + buffer_json_member_add_object(wb, "columns"); + { + size_t field_id = 0; + + // Node + buffer_rrdf_table_add_field(wb, field_id++, "Name", "Systemd Service Name", + RRDF_FIELD_TYPE_STRING, RRDF_FIELD_VISUAL_VALUE, RRDF_FIELD_TRANSFORM_NONE, + 0, NULL, NAN, RRDF_FIELD_SORT_ASCENDING, NULL, + RRDF_FIELD_SUMMARY_COUNT, RRDF_FIELD_FILTER_MULTISELECT, + RRDF_FIELD_OPTS_VISIBLE | RRDF_FIELD_OPTS_UNIQUE_KEY | RRDF_FIELD_OPTS_STICKY | RRDF_FIELD_OPTS_FULL_WIDTH, + NULL); + + // PIDs + buffer_rrdf_table_add_field(wb, field_id++, "PIDs", "Number of Processes Currently in the CGROUP", + RRDF_FIELD_TYPE_INTEGER, RRDF_FIELD_VISUAL_VALUE, RRDF_FIELD_TRANSFORM_NUMBER, + 0, "pids", max_pids, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // CPU + buffer_rrdf_table_add_field(wb, field_id++, "CPU", "CPU Usage", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "%", max_cpu, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // RAM + buffer_rrdf_table_add_field(wb, field_id++, "RAM", "RAM Usage", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_ram, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Disk IO Reads + buffer_rrdf_table_add_field(wb, field_id++, "Reads", "Disk Read Data", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_disk_io_read, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + + // Disk IO Writes + buffer_rrdf_table_add_field(wb, field_id++, "Writes", "Disk Written Data", + RRDF_FIELD_TYPE_BAR_WITH_INTEGER, RRDF_FIELD_VISUAL_BAR, RRDF_FIELD_TRANSFORM_NUMBER, + 2, "MiB", max_disk_io_written, RRDF_FIELD_SORT_DESCENDING, NULL, + RRDF_FIELD_SUMMARY_SUM, RRDF_FIELD_FILTER_NONE, + RRDF_FIELD_OPTS_VISIBLE, + NULL); + } + + buffer_json_object_close(wb); // columns + buffer_json_member_add_string(wb, "default_sort_column", "CPU"); + + buffer_json_member_add_object(wb, "charts"); + { + buffer_json_member_add_object(wb, "CPU"); + { + buffer_json_member_add_string(wb, "name", "CPU"); + buffer_json_member_add_string(wb, "type", "stacked-bar"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "CPU"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + + buffer_json_member_add_object(wb, "Memory"); + { + buffer_json_member_add_string(wb, "name", "Memory"); + buffer_json_member_add_string(wb, "type", "stacked-bar"); + buffer_json_member_add_array(wb, "columns"); + { + buffer_json_add_array_item_string(wb, "RAM"); + } + buffer_json_array_close(wb); + } + buffer_json_object_close(wb); + } + buffer_json_object_close(wb); // charts + + buffer_json_member_add_array(wb, "default_charts"); + { + buffer_json_add_array_item_array(wb); + buffer_json_add_array_item_string(wb, "CPU"); + buffer_json_add_array_item_string(wb, "Name"); + buffer_json_array_close(wb); + + buffer_json_add_array_item_array(wb); + buffer_json_add_array_item_string(wb, "Memory"); + buffer_json_add_array_item_string(wb, "Name"); + buffer_json_array_close(wb); + } + buffer_json_array_close(wb); + + buffer_json_member_add_time_t(wb, "expires", now_realtime_sec() + 1); + buffer_json_finalize(wb); + + int response = HTTP_RESP_OK; + if(is_cancelled_cb && is_cancelled_cb(is_cancelled_cb_data)) { + buffer_flush(wb); + response = HTTP_RESP_CLIENT_CLOSED_REQUEST; + } + + if(result_cb) + result_cb(wb, response, result_cb_data); + + return response; +} diff --git a/collectors/cgroups.plugin/integrations/containers.md b/collectors/cgroups.plugin/integrations/containers.md index 6dec9ce2b..6273d1e91 100644 --- a/collectors/cgroups.plugin/integrations/containers.md +++ b/collectors/cgroups.plugin/integrations/containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Containers" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/kubernetes_containers.md b/collectors/cgroups.plugin/integrations/kubernetes_containers.md index 4bfa55c6d..9be32a12a 100644 --- a/collectors/cgroups.plugin/integrations/kubernetes_containers.md +++ b/collectors/cgroups.plugin/integrations/kubernetes_containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Kubernetes Containers" learn_status: "Published" learn_rel_path: "Data Collection/Kubernetes" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -54,23 +55,21 @@ The scope defines the instance that the metric belongs to. An instance is unique ### Per k8s cgroup - +These metrics refer to the Pod container. Labels: | Label | Description | |:-----------|:----------------| -| k8s_namespace | TBD | -| k8s_pod_name | TBD | -| k8s_pod_uid | TBD | -| k8s_controller_kind | TBD | -| k8s_controller_name | TBD | -| k8s_node_name | TBD | -| k8s_container_name | TBD | -| k8s_container_id | TBD | -| k8s_kind | TBD | -| k8s_qos_class | TBD | -| k8s_cluster_id | TBD | +| k8s_node_name | Node name. The value of _pod.spec.nodeName_. | +| k8s_namespace | Namespace name. The value of _pod.metadata.namespace_. | +| k8s_controller_kind | Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_. | +| k8s_controller_name | Controller name.The value of _pod.OwnerReferences.Controller.Name_. | +| k8s_pod_name | Pod name. The value of _pod.metadata.name_. | +| k8s_container_name | Container name. The value of _pod.spec.containers.name_. | +| k8s_kind | Instance kind: "pod" or "container". | +| k8s_qos_class | QoS class (guaranteed, burstable, besteffort). | +| k8s_cluster_id | Cluster ID. The value of kube-system namespace _namespace.metadata.uid_. | Metrics: @@ -108,28 +107,28 @@ Metrics: | k8s.cgroup.io_some_pressure_stall_time | time | ms | | k8s.cgroup.io_full_pressure | some10, some60, some300 | percentage | | k8s.cgroup.io_full_pressure_stall_time | time | ms | +| k8s.cgroup.pids_current | pids | pids | ### Per k8s cgroup network device - +These metrics refer to the Pod container network interface. Labels: | Label | Description | |:-----------|:----------------| -| device | TBD | -| interface_type | TBD | -| k8s_namespace | TBD | -| k8s_pod_name | TBD | -| k8s_pod_uid | TBD | -| k8s_controller_kind | TBD | -| k8s_controller_name | TBD | -| k8s_node_name | TBD | -| k8s_container_name | TBD | -| k8s_container_id | TBD | -| k8s_kind | TBD | -| k8s_qos_class | TBD | -| k8s_cluster_id | TBD | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | +| k8s_node_name | Node name. The value of _pod.spec.nodeName_. | +| k8s_namespace | Namespace name. The value of _pod.metadata.namespace_. | +| k8s_controller_kind | Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_. | +| k8s_controller_name | Controller name.The value of _pod.OwnerReferences.Controller.Name_. | +| k8s_pod_name | Pod name. The value of _pod.metadata.name_. | +| k8s_container_name | Container name. The value of _pod.spec.containers.name_. | +| k8s_kind | Instance kind: "pod" or "container". | +| k8s_qos_class | QoS class (guaranteed, burstable, besteffort). | +| k8s_cluster_id | Cluster ID. The value of kube-system namespace _namespace.metadata.uid_. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/libvirt_containers.md b/collectors/cgroups.plugin/integrations/libvirt_containers.md index af0310b10..fed454698 100644 --- a/collectors/cgroups.plugin/integrations/libvirt_containers.md +++ b/collectors/cgroups.plugin/integrations/libvirt_containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Libvirt Containers" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/lxc_containers.md b/collectors/cgroups.plugin/integrations/lxc_containers.md index becc9ae17..3f05ffd5f 100644 --- a/collectors/cgroups.plugin/integrations/lxc_containers.md +++ b/collectors/cgroups.plugin/integrations/lxc_containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "LXC Containers" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/ovirt_containers.md b/collectors/cgroups.plugin/integrations/ovirt_containers.md index c9f6d74b7..5771aeea1 100644 --- a/collectors/cgroups.plugin/integrations/ovirt_containers.md +++ b/collectors/cgroups.plugin/integrations/ovirt_containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "oVirt Containers" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/proxmox_containers.md b/collectors/cgroups.plugin/integrations/proxmox_containers.md index 2caad5eac..1804a40ca 100644 --- a/collectors/cgroups.plugin/integrations/proxmox_containers.md +++ b/collectors/cgroups.plugin/integrations/proxmox_containers.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Proxmox Containers" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/integrations/systemd_services.md b/collectors/cgroups.plugin/integrations/systemd_services.md index b71060050..0ce906366 100644 --- a/collectors/cgroups.plugin/integrations/systemd_services.md +++ b/collectors/cgroups.plugin/integrations/systemd_services.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Systemd Services" learn_status: "Published" learn_rel_path: "Data Collection/Systemd" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -79,6 +80,7 @@ Metrics: | systemd.service.disk.throttle.iops | read, write | operations/s | | systemd.service.disk.queued_iops | read, write | operations/s | | systemd.service.disk.merged_iops | read, write | operations/s | +| systemd.service.pids.current | pids | pids | diff --git a/collectors/cgroups.plugin/integrations/virtual_machines.md b/collectors/cgroups.plugin/integrations/virtual_machines.md index 3bb79c128..6a64923c4 100644 --- a/collectors/cgroups.plugin/integrations/virtual_machines.md +++ b/collectors/cgroups.plugin/integrations/virtual_machines.md @@ -4,6 +4,7 @@ meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/cgroups.pl sidebar_label: "Virtual Machines" learn_status: "Published" learn_rel_path: "Data Collection/Containers and VMs" +most_popular: True message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" endmeta--> @@ -60,8 +61,8 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | Metrics: @@ -99,6 +100,7 @@ Metrics: | cgroup.io_some_pressure_stall_time | time | ms | | cgroup.io_full_pressure | some10, some60, some300 | percentage | | cgroup.io_full_pressure_stall_time | time | ms | +| cgroup.pids_current | pids | pids | ### Per cgroup network device @@ -108,10 +110,11 @@ Labels: | Label | Description | |:-----------|:----------------| -| container_name | TBD | -| image | TBD | -| device | TBD | -| interface_type | TBD | +| container_name | The container name or group path if name resolution fails. | +| image | Docker/Podman container image name. | +| device | The name of the host network interface linked to the container's network interface. | +| container_device | Container network interface name. | +| interface_type | Network interface type. Always "virtual" for the containers. | Metrics: diff --git a/collectors/cgroups.plugin/metadata.yaml b/collectors/cgroups.plugin/metadata.yaml index ec6228ea2..a1abbb5a9 100644 --- a/collectors/cgroups.plugin/metadata.yaml +++ b/collectors/cgroups.plugin/metadata.yaml @@ -86,9 +86,9 @@ modules: description: "" labels: - name: container_name - description: TBD + description: The container name or group path if name resolution fails. - name: image - description: TBD + description: Docker/Podman container image name. metrics: - name: cgroup.cpu_limit description: CPU Usage within the limits @@ -310,17 +310,25 @@ modules: chart_type: line dimensions: - name: time + - name: cgroup.pids_current + description: Number of processes + unit: "pids" + chart_type: line + dimensions: + - name: pids - name: cgroup network device description: "" labels: - name: container_name - description: TBD + description: The container name or group path if name resolution fails. - name: image - description: TBD + description: Docker/Podman container image name. - name: device - description: TBD + description: "The name of the host network interface linked to the container's network interface." + - name: container_device + description: Container network interface name. - name: interface_type - description: TBD + description: 'Network interface type. Always "virtual" for the containers.' metrics: - name: cgroup.net_net description: Bandwidth @@ -445,30 +453,26 @@ modules: availability: [] scopes: - name: k8s cgroup - description: "" + description: These metrics refer to the Pod container. labels: + - name: k8s_node_name + description: 'Node name. The value of _pod.spec.nodeName_.' - name: k8s_namespace - description: TBD - - name: k8s_pod_name - description: TBD - - name: k8s_pod_uid - description: TBD + description: 'Namespace name. The value of _pod.metadata.namespace_.' - name: k8s_controller_kind - description: TBD + description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' - name: k8s_controller_name - description: TBD - - name: k8s_node_name - description: TBD + description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' + - name: k8s_pod_name + description: 'Pod name. The value of _pod.metadata.name_.' - name: k8s_container_name - description: TBD - - name: k8s_container_id - description: TBD + description: 'Container name. The value of _pod.spec.containers.name_.' - name: k8s_kind - description: TBD + description: 'Instance kind: "pod" or "container".' - name: k8s_qos_class - description: TBD + description: 'QoS class (guaranteed, burstable, besteffort).' - name: k8s_cluster_id - description: TBD + description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' metrics: - name: k8s.cgroup.cpu_limit description: CPU Usage within the limits @@ -690,35 +694,39 @@ modules: chart_type: line dimensions: - name: time + - name: k8s.cgroup.pids_current + description: Number of processes + unit: "pids" + chart_type: line + dimensions: + - name: pids - name: k8s cgroup network device - description: "" + description: These metrics refer to the Pod container network interface. labels: - name: device - description: TBD + description: "The name of the host network interface linked to the container's network interface." + - name: container_device + description: Container network interface name. - name: interface_type - description: TBD + description: 'Network interface type. Always "virtual" for the containers.' + - name: k8s_node_name + description: 'Node name. The value of _pod.spec.nodeName_.' - name: k8s_namespace - description: TBD - - name: k8s_pod_name - description: TBD - - name: k8s_pod_uid - description: TBD + description: 'Namespace name. The value of _pod.metadata.namespace_.' - name: k8s_controller_kind - description: TBD + description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' - name: k8s_controller_name - description: TBD - - name: k8s_node_name - description: TBD + description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' + - name: k8s_pod_name + description: 'Pod name. The value of _pod.metadata.name_.' - name: k8s_container_name - description: TBD - - name: k8s_container_id - description: TBD + description: 'Container name. The value of _pod.spec.containers.name_.' - name: k8s_kind - description: TBD + description: 'Instance kind: "pod" or "container".' - name: k8s_qos_class - description: TBD + description: 'QoS class (guaranteed, burstable, besteffort).' - name: k8s_cluster_id - description: TBD + description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' metrics: - name: k8s.cgroup.net_net description: Bandwidth @@ -919,6 +927,12 @@ modules: dimensions: - name: read - name: write + - name: systemd.service.pids.current + description: Systemd Services Number of Processes + unit: pids + chart_type: line + dimensions: + - name: pids - <<: *module meta: <<: *meta diff --git a/collectors/cgroups.plugin/sys_fs_cgroup.c b/collectors/cgroups.plugin/sys_fs_cgroup.c index 6196e7603..705edf6f7 100644 --- a/collectors/cgroups.plugin/sys_fs_cgroup.c +++ b/collectors/cgroups.plugin/sys_fs_cgroup.c @@ -1,149 +1,98 @@ // SPDX-License-Identifier: GPL-3.0-or-later -#include "sys_fs_cgroup.h" - -#define PLUGIN_CGROUPS_NAME "cgroups.plugin" -#define PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME "systemd" -#define PLUGIN_CGROUPS_MODULE_CGROUPS_NAME "/sys/fs/cgroup" - -#ifdef NETDATA_INTERNAL_CHECKS -#define CGROUP_PROCFILE_FLAG PROCFILE_FLAG_DEFAULT -#else -#define CGROUP_PROCFILE_FLAG PROCFILE_FLAG_NO_ERROR_ON_FILE_IO -#endif +#include "cgroup-internals.h" // main cgroups thread worker jobs #define WORKER_CGROUPS_LOCK 0 #define WORKER_CGROUPS_READ 1 #define WORKER_CGROUPS_CHART 2 -// discovery cgroup thread worker jobs -#define WORKER_DISCOVERY_INIT 0 -#define WORKER_DISCOVERY_FIND 1 -#define WORKER_DISCOVERY_PROCESS 2 -#define WORKER_DISCOVERY_PROCESS_RENAME 3 -#define WORKER_DISCOVERY_PROCESS_NETWORK 4 -#define WORKER_DISCOVERY_PROCESS_FIRST_TIME 5 -#define WORKER_DISCOVERY_UPDATE 6 -#define WORKER_DISCOVERY_CLEANUP 7 -#define WORKER_DISCOVERY_COPY 8 -#define WORKER_DISCOVERY_SHARE 9 -#define WORKER_DISCOVERY_LOCK 10 - -#if WORKER_UTILIZATION_MAX_JOB_TYPES < 11 -#error WORKER_UTILIZATION_MAX_JOB_TYPES has to be at least 11 -#endif - // ---------------------------------------------------------------------------- // cgroup globals +unsigned long long host_ram_total = 0; +int is_inside_k8s = 0; +long system_page_size = 4096; // system will be queried via sysconf() in configuration() +int cgroup_enable_cpuacct_stat = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_cpuacct_usage = CONFIG_BOOLEAN_NO; +int cgroup_enable_cpuacct_cpu_throttling = CONFIG_BOOLEAN_YES; +int cgroup_enable_cpuacct_cpu_shares = CONFIG_BOOLEAN_NO; +int cgroup_enable_memory = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_detailed_memory = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_memory_failcnt = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_swap = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_io = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_ops = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_throttle_io = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_throttle_ops = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_merged_ops = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_blkio_queued_ops = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_cpu = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_io_some = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_io_full = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_memory_some = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_memory_full = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_pressure_irq_some = CONFIG_BOOLEAN_NO; +int cgroup_enable_pressure_irq_full = CONFIG_BOOLEAN_AUTO; +int cgroup_enable_systemd_services = CONFIG_BOOLEAN_YES; +int cgroup_enable_systemd_services_detailed_memory = CONFIG_BOOLEAN_NO; +int cgroup_used_memory = CONFIG_BOOLEAN_YES; +int cgroup_use_unified_cgroups = CONFIG_BOOLEAN_NO; +int cgroup_unified_exist = CONFIG_BOOLEAN_AUTO; +int cgroup_search_in_devices = 1; +int cgroup_check_for_new_every = 10; +int cgroup_update_every = 1; +int cgroup_containers_chart_priority = NETDATA_CHART_PRIO_CGROUPS_CONTAINERS; +int cgroup_recheck_zero_blkio_every_iterations = 10; +int cgroup_recheck_zero_mem_failcnt_every_iterations = 10; +int cgroup_recheck_zero_mem_detailed_every_iterations = 10; +char *cgroup_cpuacct_base = NULL; +char *cgroup_cpuset_base = NULL; +char *cgroup_blkio_base = NULL; +char *cgroup_memory_base = NULL; +char *cgroup_devices_base = NULL; +char *cgroup_pids_base = NULL; +char *cgroup_unified_base = NULL; +int cgroup_root_count = 0; +int cgroup_root_max = 1000; +int cgroup_max_depth = 0; +SIMPLE_PATTERN *enabled_cgroup_paths = NULL; +SIMPLE_PATTERN *enabled_cgroup_names = NULL; +SIMPLE_PATTERN *search_cgroup_paths = NULL; +SIMPLE_PATTERN *enabled_cgroup_renames = NULL; +SIMPLE_PATTERN *systemd_services_cgroups = NULL; +SIMPLE_PATTERN *entrypoint_parent_process_comm = NULL; +char *cgroups_network_interface_script = NULL; +int cgroups_check = 0; +uint32_t Read_hash = 0; +uint32_t Write_hash = 0; +uint32_t user_hash = 0; +uint32_t system_hash = 0; +uint32_t user_usec_hash = 0; +uint32_t system_usec_hash = 0; +uint32_t nr_periods_hash = 0; +uint32_t nr_throttled_hash = 0; +uint32_t throttled_time_hash = 0; +uint32_t throttled_usec_hash = 0; -static char cgroup_chart_id_prefix[] = "cgroup_"; -static char services_chart_id_prefix[] = "systemd_"; - -static int is_inside_k8s = 0; - -static long system_page_size = 4096; // system will be queried via sysconf() in configuration() - -static int cgroup_enable_cpuacct_stat = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_cpuacct_usage = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_cpuacct_cpu_throttling = CONFIG_BOOLEAN_YES; -static int cgroup_enable_cpuacct_cpu_shares = CONFIG_BOOLEAN_NO; -static int cgroup_enable_memory = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_detailed_memory = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_memory_failcnt = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_swap = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_io = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_ops = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_throttle_io = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_throttle_ops = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_merged_ops = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_blkio_queued_ops = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_cpu = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_io_some = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_io_full = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_memory_some = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_memory_full = CONFIG_BOOLEAN_AUTO; -static int cgroup_enable_pressure_irq_some = CONFIG_BOOLEAN_NO; -static int cgroup_enable_pressure_irq_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 = CONFIG_BOOLEAN_YES; - -static int cgroup_use_unified_cgroups = CONFIG_BOOLEAN_NO; -static int cgroup_unified_exist = CONFIG_BOOLEAN_AUTO; - -static int cgroup_search_in_devices = 1; - -static int cgroup_check_for_new_every = 10; -static int cgroup_update_every = 1; -static int cgroup_containers_chart_priority = NETDATA_CHART_PRIO_CGROUPS_CONTAINERS; - -static int cgroup_recheck_zero_blkio_every_iterations = 10; -static int cgroup_recheck_zero_mem_failcnt_every_iterations = 10; -static int cgroup_recheck_zero_mem_detailed_every_iterations = 10; - -static char *cgroup_cpuacct_base = NULL; -static char *cgroup_cpuset_base = NULL; -static char *cgroup_blkio_base = NULL; -static char *cgroup_memory_base = NULL; -static char *cgroup_devices_base = NULL; -static char *cgroup_unified_base = NULL; - -static int cgroup_root_count = 0; -static int cgroup_root_max = 1000; -static int cgroup_max_depth = 0; - -static SIMPLE_PATTERN *enabled_cgroup_paths = NULL; -static SIMPLE_PATTERN *enabled_cgroup_names = NULL; -static SIMPLE_PATTERN *search_cgroup_paths = NULL; -static SIMPLE_PATTERN *enabled_cgroup_renames = NULL; -static SIMPLE_PATTERN *systemd_services_cgroups = NULL; - -static SIMPLE_PATTERN *entrypoint_parent_process_comm = NULL; - -static char *cgroups_rename_script = NULL; -static char *cgroups_network_interface_script = NULL; - -static int cgroups_check = 0; - -static uint32_t Read_hash = 0; -static uint32_t Write_hash = 0; -static uint32_t user_hash = 0; -static uint32_t system_hash = 0; -static uint32_t user_usec_hash = 0; -static uint32_t system_usec_hash = 0; -static uint32_t nr_periods_hash = 0; -static uint32_t nr_throttled_hash = 0; -static uint32_t throttled_time_hash = 0; -static uint32_t throttled_usec_hash = 0; - -enum cgroups_type { CGROUPS_AUTODETECT_FAIL, CGROUPS_V1, CGROUPS_V2 }; - -enum cgroups_systemd_setting { - SYSTEMD_CGROUP_ERR, - SYSTEMD_CGROUP_LEGACY, - SYSTEMD_CGROUP_HYBRID, - SYSTEMD_CGROUP_UNIFIED -}; - -struct cgroups_systemd_config_setting { - char *name; - enum cgroups_systemd_setting setting; -}; +// *** WARNING *** The fields are not thread safe. Take care of safe usage. +struct cgroup *cgroup_root = NULL; +uv_mutex_t cgroup_root_mutex; -static struct cgroups_systemd_config_setting cgroups_systemd_options[] = { - { .name = "legacy", .setting = SYSTEMD_CGROUP_LEGACY }, - { .name = "hybrid", .setting = SYSTEMD_CGROUP_HYBRID }, - { .name = "unified", .setting = SYSTEMD_CGROUP_UNIFIED }, - { .name = NULL, .setting = SYSTEMD_CGROUP_ERR }, +struct cgroups_systemd_config_setting cgroups_systemd_options[] = { + { .name = "legacy", .setting = SYSTEMD_CGROUP_LEGACY }, + { .name = "hybrid", .setting = SYSTEMD_CGROUP_HYBRID }, + { .name = "unified", .setting = SYSTEMD_CGROUP_UNIFIED }, + { .name = NULL, .setting = SYSTEMD_CGROUP_ERR }, }; // Shared memory with information from detected cgroups netdata_ebpf_cgroup_shm_t shm_cgroup_ebpf = {NULL, NULL}; -static int shm_fd_cgroup_ebpf = -1; +int shm_fd_cgroup_ebpf = -1; sem_t *shm_mutex_cgroup_ebpf = SEM_FAILED; +struct discovery_thread discovery_thread; + + /* on Fed systemd is not in PATH for some reason */ #define SYSTEMD_CMD_RHEL "/usr/lib/systemd/systemd --version" #define SYSTEMD_HIERARCHY_STRING "default-hierarchy=" @@ -362,54 +311,70 @@ void read_cgroup_plugin_configuration() { cgroup_enable_pressure_memory_full = CONFIG_BOOLEAN_NO; mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "cpuacct"); - if(!mi) mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "cpuacct"); - if(!mi) { + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "cpuacct"); + if (!mi) { collector_error("CGROUP: cannot find cpuacct mountinfo. Assuming default: /sys/fs/cgroup/cpuacct"); s = "/sys/fs/cgroup/cpuacct"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; set_cgroup_base_path(filename, s); cgroup_cpuacct_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/cpuacct", filename); mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "cpuset"); - if(!mi) mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "cpuset"); - if(!mi) { + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "cpuset"); + if (!mi) { collector_error("CGROUP: cannot find cpuset mountinfo. Assuming default: /sys/fs/cgroup/cpuset"); s = "/sys/fs/cgroup/cpuset"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; set_cgroup_base_path(filename, s); cgroup_cpuset_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/cpuset", filename); mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "blkio"); - if(!mi) mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "blkio"); - if(!mi) { + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "blkio"); + if (!mi) { collector_error("CGROUP: cannot find blkio mountinfo. Assuming default: /sys/fs/cgroup/blkio"); s = "/sys/fs/cgroup/blkio"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; set_cgroup_base_path(filename, s); cgroup_blkio_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/blkio", filename); mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "memory"); - if(!mi) mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "memory"); - if(!mi) { + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "memory"); + if (!mi) { collector_error("CGROUP: cannot find memory mountinfo. Assuming default: /sys/fs/cgroup/memory"); s = "/sys/fs/cgroup/memory"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; set_cgroup_base_path(filename, s); cgroup_memory_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/memory", filename); mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "devices"); - if(!mi) mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "devices"); - if(!mi) { + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "devices"); + if (!mi) { collector_error("CGROUP: cannot find devices mountinfo. Assuming default: /sys/fs/cgroup/devices"); s = "/sys/fs/cgroup/devices"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; set_cgroup_base_path(filename, s); cgroup_devices_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/devices", filename); + + mi = mountinfo_find_by_filesystem_super_option(root, "cgroup", "pids"); + if (!mi) + mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup", "pids"); + if (!mi) { + collector_error("CGROUP: cannot find pids mountinfo. Assuming default: /sys/fs/cgroup/pids"); + s = "/sys/fs/cgroup/pids"; + } else + s = mi->mount_point; + set_cgroup_base_path(filename, s); + cgroup_pids_base = config_get("plugin:cgroups", "path to /sys/fs/cgroup/pids", filename); } else { //cgroup_enable_cpuacct_stat = @@ -429,22 +394,19 @@ void read_cgroup_plugin_configuration() { 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 - if(mi) - netdata_log_debug(D_CGROUP, "found unified cgroup root using super options, with path: '%s'", mi->mount_point); - if(!mi) { + //there is no cgroup2 specific super option - for now use 'rw' option + mi = mountinfo_find_by_filesystem_super_option(root, "cgroup2", "rw"); + if (!mi) { mi = mountinfo_find_by_filesystem_mount_source(root, "cgroup2", "cgroup"); - if(mi) - netdata_log_debug(D_CGROUP, "found unified cgroup root using mountsource info, with path: '%s'", mi->mount_point); } - if(!mi) { + if (!mi) { collector_error("CGROUP: cannot find cgroup2 mountinfo. Assuming default: /sys/fs/cgroup"); s = "/sys/fs/cgroup"; - } - else s = mi->mount_point; + } else + s = mi->mount_point; + set_cgroup_base_path(filename, s); cgroup_unified_base = config_get("plugin:cgroups", "path to unified cgroups", filename); - netdata_log_debug(D_CGROUP, "using cgroup root: '%s'", cgroup_unified_base); } cgroup_root_max = (int)config_get_number("plugin:cgroups", "max cgroups to allow", cgroup_root_max); @@ -621,395 +583,6 @@ end_init_shm: shm_unlink(NETDATA_SHARED_MEMORY_EBPF_CGROUP_NAME); } -// ---------------------------------------------------------------------------- -// cgroup objects - -struct blkio { - int updated; - int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - int delay_counter; - - char *filename; - - unsigned long long Read; - unsigned long long Write; -/* - unsigned long long Sync; - unsigned long long Async; - unsigned long long Total; -*/ -}; - -// https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt -struct memory { - ARL_BASE *arl_base; - ARL_ENTRY *arl_dirty; - ARL_ENTRY *arl_swap; - - int updated_detailed; - int updated_usage_in_bytes; - int updated_msw_usage_in_bytes; - int updated_failcnt; - - int enabled_detailed; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - int enabled_usage_in_bytes; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - int enabled_msw_usage_in_bytes; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - int enabled_failcnt; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - - int delay_counter_detailed; - int delay_counter_failcnt; - - char *filename_detailed; - char *filename_usage_in_bytes; - char *filename_msw_usage_in_bytes; - char *filename_failcnt; - - int detailed_has_dirty; - int detailed_has_swap; - - // detailed metrics -/* - unsigned long long cache; - unsigned long long rss; - unsigned long long rss_huge; - unsigned long long mapped_file; - unsigned long long writeback; - unsigned long long dirty; - unsigned long long swap; - unsigned long long pgpgin; - unsigned long long pgpgout; - unsigned long long pgfault; - unsigned long long pgmajfault; - unsigned long long inactive_anon; - unsigned long long active_anon; - unsigned long long inactive_file; - unsigned long long active_file; - unsigned long long unevictable; - unsigned long long hierarchical_memory_limit; -*/ - //unified cgroups metrics - unsigned long long anon; - unsigned long long kernel_stack; - unsigned long long slab; - unsigned long long sock; - unsigned long long shmem; - unsigned long long anon_thp; - //unsigned long long file_writeback; - //unsigned long long file_dirty; - //unsigned long long file; - - unsigned long long total_cache; - unsigned long long total_rss; - unsigned long long total_rss_huge; - unsigned long long total_mapped_file; - unsigned long long total_writeback; - unsigned long long total_dirty; - unsigned long long total_swap; - unsigned long long total_pgpgin; - unsigned long long total_pgpgout; - unsigned long long total_pgfault; - unsigned long long total_pgmajfault; -/* - 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; -*/ - - // single file metrics - unsigned long long usage_in_bytes; - unsigned long long msw_usage_in_bytes; - unsigned long long failcnt; -}; - -// https://www.kernel.org/doc/Documentation/cgroup-v1/cpuacct.txt -struct cpuacct_stat { - int updated; - int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - - char *filename; - - unsigned long long user; // v1, v2(user_usec) - unsigned long long system; // v1, v2(system_usec) -}; - -// https://www.kernel.org/doc/Documentation/cgroup-v1/cpuacct.txt -struct cpuacct_usage { - int updated; - int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - - char *filename; - - unsigned int cpus; - unsigned long long *cpu_percpu; -}; - -// represents cpuacct/cpu.stat, for v2 'cpuacct_stat' is used for 'user_usec', 'system_usec' -struct cpuacct_cpu_throttling { - int updated; - int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - - char *filename; - - unsigned long long nr_periods; - unsigned long long nr_throttled; - unsigned long long throttled_time; - - unsigned long long nr_throttled_perc; -}; - -// https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/6/html/resource_management_guide/sec-cpu#sect-cfs -// https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux/8/html/managing_monitoring_and_updating_the_kernel/using-cgroups-v2-to-control-distribution-of-cpu-time-for-applications_managing-monitoring-and-updating-the-kernel#proc_controlling-distribution-of-cpu-time-for-applications-by-adjusting-cpu-weight_using-cgroups-v2-to-control-distribution-of-cpu-time-for-applications -struct cpuacct_cpu_shares { - int updated; - int enabled; // CONFIG_BOOLEAN_YES or CONFIG_BOOLEAN_AUTO - - char *filename; - - unsigned long long shares; -}; - -struct cgroup_network_interface { - const char *host_device; - const char *container_device; - struct cgroup_network_interface *next; -}; - -enum cgroups_container_orchestrator { - CGROUPS_ORCHESTRATOR_UNSET, - CGROUPS_ORCHESTRATOR_UNKNOWN, - CGROUPS_ORCHESTRATOR_K8S -}; - -// *** WARNING *** The fields are not thread safe. Take care of safe usage. -struct cgroup { - uint32_t options; - - int first_time_seen; // first time seen by the discoverer - int processed; // the discoverer is done processing a cgroup (resolved name, set 'enabled' option) - - char available; // found in the filesystem - char enabled; // enabled in the config - - char pending_renames; - - char *id; - uint32_t hash; - - char *intermediate_id; // TODO: remove it when the renaming script is fixed - - char *chart_id; - uint32_t hash_chart_id; - - // 'cgroup_name' label value. - // By default this is the *id (path), later changed to the resolved name (cgroup-name.sh) or systemd service name. - char *name; - - RRDLABELS *chart_labels; - - int container_orchestrator; - - struct cpuacct_stat cpuacct_stat; - struct cpuacct_usage cpuacct_usage; - struct cpuacct_cpu_throttling cpuacct_cpu_throttling; - struct cpuacct_cpu_shares cpuacct_cpu_shares; - - struct memory memory; - - struct blkio io_service_bytes; // bytes - struct blkio io_serviced; // operations - - struct blkio throttle_io_service_bytes; // bytes - struct blkio throttle_io_serviced; // operations - - struct blkio io_merged; // operations - struct blkio io_queued; // operations - - struct cgroup_network_interface *interfaces; - - struct pressure cpu_pressure; - struct pressure io_pressure; - struct pressure memory_pressure; - struct pressure irq_pressure; - - // per cgroup charts - RRDSET *st_cpu; - RRDSET *st_cpu_limit; - RRDSET *st_cpu_per_core; - RRDSET *st_cpu_nr_throttled; - RRDSET *st_cpu_throttled_time; - RRDSET *st_cpu_shares; - - RRDSET *st_mem; - RRDSET *st_mem_utilization; - RRDSET *st_writeback; - RRDSET *st_mem_activity; - RRDSET *st_pgfaults; - RRDSET *st_mem_usage; - RRDSET *st_mem_usage_limit; - RRDSET *st_mem_failcnt; - - RRDSET *st_io; - RRDSET *st_serviced_ops; - RRDSET *st_throttle_io; - RRDSET *st_throttle_serviced_ops; - RRDSET *st_queued_ops; - RRDSET *st_merged_ops; - - // per cgroup chart variables - char *filename_cpuset_cpus; - unsigned long long cpuset_cpus; - - char *filename_cpu_cfs_period; - unsigned long long cpu_cfs_period; - - char *filename_cpu_cfs_quota; - unsigned long long cpu_cfs_quota; - - const RRDSETVAR_ACQUIRED *chart_var_cpu_limit; - NETDATA_DOUBLE prev_cpu_usage; - - char *filename_memory_limit; - unsigned long long memory_limit; - const RRDSETVAR_ACQUIRED *chart_var_memory_limit; - - char *filename_memoryswap_limit; - unsigned long long memoryswap_limit; - const RRDSETVAR_ACQUIRED *chart_var_memoryswap_limit; - - struct cgroup *next; - struct cgroup *discovered_next; - -} *cgroup_root = NULL; - -uv_mutex_t cgroup_root_mutex; - -struct cgroup *discovered_cgroup_root = NULL; - -struct discovery_thread { - uv_thread_t thread; - uv_mutex_t mutex; - uv_cond_t cond_var; - int exited; -} discovery_thread; - -// --------------------------------------------------------------------------------------------- - -static inline int matches_enabled_cgroup_paths(char *id) { - return simple_pattern_matches(enabled_cgroup_paths, id); -} - -static inline int matches_enabled_cgroup_names(char *name) { - return simple_pattern_matches(enabled_cgroup_names, name); -} - -static inline int matches_enabled_cgroup_renames(char *id) { - return simple_pattern_matches(enabled_cgroup_renames, id); -} - -static inline int matches_systemd_services_cgroups(char *id) { - return simple_pattern_matches(systemd_services_cgroups, id); -} - -static inline int matches_search_cgroup_paths(const char *dir) { - return simple_pattern_matches(search_cgroup_paths, dir); -} - -static inline int matches_entrypoint_parent_process_comm(const char *comm) { - return simple_pattern_matches(entrypoint_parent_process_comm, comm); -} - -static inline int is_cgroup_systemd_service(struct cgroup *cg) { - return (cg->options & CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE); -} - -// --------------------------------------------------------------------------------------------- -static int k8s_is_kubepod(struct cgroup *cg) { - return cg->container_orchestrator == CGROUPS_ORCHESTRATOR_K8S; -} - -static int k8s_is_container(const char *id) { - // examples: - // https://github.com/netdata/netdata/blob/0fc101679dcd12f1cb8acdd07bb4c85d8e553e53/collectors/cgroups.plugin/cgroup-name.sh#L121-L147 - const char *p = id; - const char *pp = NULL; - int i = 0; - size_t l = 3; // pod - while ((p = strstr(p, "pod"))) { - i++; - p += l; - pp = p; - } - return !(i < 2 || !pp || !(pp = strchr(pp, '/')) || !pp++ || !*pp); -} - -#define TASK_COMM_LEN 16 - -static int k8s_get_container_first_proc_comm(const char *id, char *comm) { - if (!k8s_is_container(id)) { - return 1; - } - - static procfile *ff = NULL; - - char filename[FILENAME_MAX + 1]; - snprintfz(filename, FILENAME_MAX, "%s/%s/cgroup.procs", cgroup_cpuacct_base, id); - - ff = procfile_reopen(ff, filename, NULL, CGROUP_PROCFILE_FLAG); - if (unlikely(!ff)) { - netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot open file '%s'.", filename); - return 1; - } - - ff = procfile_readall(ff); - if (unlikely(!ff)) { - netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot read file '%s'.", filename); - return 1; - } - - unsigned long lines = procfile_lines(ff); - if (likely(lines < 2)) { - return 1; - } - - char *pid = procfile_lineword(ff, 0, 0); - if (!pid || !*pid) { - return 1; - } - - snprintfz(filename, FILENAME_MAX, "%s/proc/%s/comm", netdata_configured_host_prefix, pid); - - ff = procfile_reopen(ff, filename, NULL, PROCFILE_FLAG_DEFAULT); - if (unlikely(!ff)) { - netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot open file '%s'.", filename); - return 1; - } - - ff = procfile_readall(ff); - if (unlikely(!ff)) { - netdata_log_debug(D_CGROUP, "CGROUP: k8s_is_pause_container(): cannot read file '%s'.", filename); - return 1; - } - - lines = procfile_lines(ff); - if (unlikely(lines != 2)) { - return 1; - } - - char *proc_comm = procfile_lineword(ff, 0, 0); - if (!proc_comm || !*proc_comm) { - return 1; - } - - strncpyz(comm, proc_comm, TASK_COMM_LEN); - return 0; -} - // --------------------------------------------------------------------------------------------- static unsigned long long calc_delta(unsigned long long curr, unsigned long long prev) { @@ -1023,16 +596,7 @@ static unsigned long long calc_percentage(unsigned long long value, unsigned lon if (total == 0) { return 0; } - return (NETDATA_DOUBLE)value / (NETDATA_DOUBLE)total * 100; -} - -static int calc_cgroup_depth(const char *id) { - int depth = 0; - const char *s; - for (s = id; *s; s++) { - depth += unlikely(*s == '/'); - } - return depth; + return (unsigned long long)((NETDATA_DOUBLE)value / (NETDATA_DOUBLE)total * 100); } // ---------------------------------------------------------------------------- @@ -1596,6 +1160,15 @@ memory_next: } } +static void cgroup_read_pids_current(struct pids *pids) { + pids->pids_current_updated = 0; + + if (unlikely(!pids->pids_current_filename)) + return; + + pids->pids_current_updated = !read_single_number_file(pids->pids_current_filename, &pids->pids_current); +} + static inline void read_cgroup(struct cgroup *cg) { netdata_log_debug(D_CGROUP, "reading metrics for cgroups '%s'", cg->id); if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { @@ -1610,6 +1183,7 @@ static inline void read_cgroup(struct cgroup *cg) { cgroup_read_blkio(&cg->throttle_io_serviced); cgroup_read_blkio(&cg->io_merged); cgroup_read_blkio(&cg->io_queued); + cgroup_read_pids_current(&cg->pids); } else { //TODO: io_service_bytes and io_serviced use same file merge into 1 function @@ -1622,6 +1196,7 @@ static inline void read_cgroup(struct cgroup *cg) { cgroup2_read_pressure(&cg->memory_pressure); cgroup2_read_pressure(&cg->irq_pressure); cgroup_read_memory(&cg->memory, 1); + cgroup_read_pids_current(&cg->pids); } } @@ -1636,1583 +1211,7 @@ static inline void read_all_discovered_cgroups(struct cgroup *root) { } } -// ---------------------------------------------------------------------------- -// cgroup network interfaces - -#define CGROUP_NETWORK_INTERFACE_MAX_LINE 2048 -static inline void read_cgroup_network_interfaces(struct cgroup *cg) { - netdata_log_debug(D_CGROUP, "looking for the network interfaces of cgroup '%s' with chart id '%s'", cg->id, cg->chart_id); - - pid_t cgroup_pid; - char cgroup_identifier[CGROUP_NETWORK_INTERFACE_MAX_LINE + 1]; - - if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - snprintfz(cgroup_identifier, CGROUP_NETWORK_INTERFACE_MAX_LINE, "%s%s", cgroup_cpuacct_base, cg->id); - } - else { - snprintfz(cgroup_identifier, CGROUP_NETWORK_INTERFACE_MAX_LINE, "%s%s", cgroup_unified_base, cg->id); - } - - netdata_log_debug(D_CGROUP, "executing cgroup_identifier %s --cgroup '%s' for cgroup '%s'", cgroups_network_interface_script, cgroup_identifier, cg->id); - FILE *fp_child_input, *fp_child_output; - (void)netdata_popen_raw_default_flags_and_environment(&cgroup_pid, &fp_child_input, &fp_child_output, cgroups_network_interface_script, "--cgroup", cgroup_identifier); - if(!fp_child_output) { - collector_error("CGROUP: cannot popen(%s --cgroup \"%s\", \"r\").", cgroups_network_interface_script, cgroup_identifier); - return; - } - - char *s; - char buffer[CGROUP_NETWORK_INTERFACE_MAX_LINE + 1]; - while((s = fgets(buffer, CGROUP_NETWORK_INTERFACE_MAX_LINE, fp_child_output))) { - trim(s); - - if(*s && *s != '\n') { - char *t = s; - while(*t && *t != ' ') t++; - if(*t == ' ') { - *t = '\0'; - t++; - } - - if(!*s) { - collector_error("CGROUP: empty host interface returned by script"); - continue; - } - - if(!*t) { - collector_error("CGROUP: empty guest interface returned by script"); - continue; - } - - struct cgroup_network_interface *i = callocz(1, sizeof(struct cgroup_network_interface)); - i->host_device = strdupz(s); - i->container_device = strdupz(t); - i->next = cg->interfaces; - cg->interfaces = i; - - collector_info("CGROUP: cgroup '%s' has network interface '%s' as '%s'", cg->id, i->host_device, i->container_device); - - // register a device rename to proc_net_dev.c - netdev_rename_device_add( - i->host_device, i->container_device, cg->chart_id, cg->chart_labels, k8s_is_kubepod(cg) ? "k8s." : ""); - } - } - - netdata_pclose(fp_child_input, fp_child_output, cgroup_pid); - // netdata_log_debug(D_CGROUP, "closed cgroup_identifier for cgroup '%s'", cg->id); -} - -static inline void free_cgroup_network_interfaces(struct cgroup *cg) { - while(cg->interfaces) { - struct cgroup_network_interface *i = cg->interfaces; - cg->interfaces = i->next; - - // delete the registration of proc_net_dev rename - netdev_rename_device_del(i->host_device); - - freez((void *)i->host_device); - freez((void *)i->container_device); - freez((void *)i); - } -} - -// ---------------------------------------------------------------------------- -// add/remove/find cgroup objects - -#define CGROUP_CHARTID_LINE_MAX 1024 - -static inline char *cgroup_chart_id_strdupz(const char *s) { - if(!s || !*s) s = "/"; - - if(*s == '/' && s[1] != '\0') s++; - - char *r = strdupz(s); - netdata_fix_chart_id(r); - - return r; -} - -// TODO: move the code to cgroup_chart_id_strdupz() when the renaming script is fixed -static inline void substitute_dots_in_id(char *s) { - // dots are used to distinguish chart type and id in streaming, so we should replace them - for (char *d = s; *d; d++) { - if (*d == '.') - *d = '-'; - } -} - -// ---------------------------------------------------------------------------- -// parse k8s labels - -char *cgroup_parse_resolved_name_and_labels(RRDLABELS *labels, char *data) { - // the first word, up to the first space is the name - char *name = strsep_skip_consecutive_separators(&data, " "); - - // the rest are key=value pairs separated by comma - while(data) { - char *pair = strsep_skip_consecutive_separators(&data, ","); - rrdlabels_add_pair(labels, pair, RRDLABEL_SRC_AUTO | RRDLABEL_SRC_K8S); - } - - return name; -} - -// ---------------------------------------------------------------------------- - -static inline void free_pressure(struct pressure *res) { - if (res->some.share_time.st) rrdset_is_obsolete(res->some.share_time.st); - if (res->some.total_time.st) rrdset_is_obsolete(res->some.total_time.st); - if (res->full.share_time.st) rrdset_is_obsolete(res->full.share_time.st); - if (res->full.total_time.st) rrdset_is_obsolete(res->full.total_time.st); - freez(res->filename); -} - -static inline void cgroup_free(struct cgroup *cg) { - netdata_log_debug(D_CGROUP, "Removing cgroup '%s' with chart id '%s' (was %s and %s)", cg->id, cg->chart_id, (cg->enabled)?"enabled":"disabled", (cg->available)?"available":"not available"); - - if(cg->st_cpu) rrdset_is_obsolete(cg->st_cpu); - if(cg->st_cpu_limit) rrdset_is_obsolete(cg->st_cpu_limit); - if(cg->st_cpu_per_core) rrdset_is_obsolete(cg->st_cpu_per_core); - if(cg->st_cpu_nr_throttled) rrdset_is_obsolete(cg->st_cpu_nr_throttled); - if(cg->st_cpu_throttled_time) rrdset_is_obsolete(cg->st_cpu_throttled_time); - if(cg->st_cpu_shares) rrdset_is_obsolete(cg->st_cpu_shares); - if(cg->st_mem) rrdset_is_obsolete(cg->st_mem); - if(cg->st_writeback) rrdset_is_obsolete(cg->st_writeback); - if(cg->st_mem_activity) rrdset_is_obsolete(cg->st_mem_activity); - 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); - if(cg->st_throttle_io) rrdset_is_obsolete(cg->st_throttle_io); - if(cg->st_throttle_serviced_ops) rrdset_is_obsolete(cg->st_throttle_serviced_ops); - if(cg->st_queued_ops) rrdset_is_obsolete(cg->st_queued_ops); - if(cg->st_merged_ops) rrdset_is_obsolete(cg->st_merged_ops); - - freez(cg->filename_cpuset_cpus); - freez(cg->filename_cpu_cfs_period); - freez(cg->filename_cpu_cfs_quota); - freez(cg->filename_memory_limit); - freez(cg->filename_memoryswap_limit); - - free_cgroup_network_interfaces(cg); - - freez(cg->cpuacct_usage.cpu_percpu); - - freez(cg->cpuacct_stat.filename); - freez(cg->cpuacct_usage.filename); - freez(cg->cpuacct_cpu_throttling.filename); - freez(cg->cpuacct_cpu_shares.filename); - - arl_free(cg->memory.arl_base); - freez(cg->memory.filename_detailed); - freez(cg->memory.filename_failcnt); - freez(cg->memory.filename_usage_in_bytes); - freez(cg->memory.filename_msw_usage_in_bytes); - - freez(cg->io_service_bytes.filename); - freez(cg->io_serviced.filename); - - freez(cg->throttle_io_service_bytes.filename); - freez(cg->throttle_io_serviced.filename); - - freez(cg->io_merged.filename); - freez(cg->io_queued.filename); - - free_pressure(&cg->cpu_pressure); - free_pressure(&cg->io_pressure); - free_pressure(&cg->memory_pressure); - free_pressure(&cg->irq_pressure); - - freez(cg->id); - freez(cg->intermediate_id); - freez(cg->chart_id); - freez(cg->name); - - rrdlabels_destroy(cg->chart_labels); - - freez(cg); - - cgroup_root_count--; -} - -// ---------------------------------------------------------------------------- - -static inline void discovery_rename_cgroup(struct cgroup *cg) { - if (!cg->pending_renames) { - return; - } - cg->pending_renames--; - - netdata_log_debug(D_CGROUP, "looking for the name of cgroup '%s' with chart id '%s'", cg->id, cg->chart_id); - netdata_log_debug(D_CGROUP, "executing command %s \"%s\" for cgroup '%s'", cgroups_rename_script, cg->intermediate_id, cg->chart_id); - pid_t cgroup_pid; - - FILE *fp_child_input, *fp_child_output; - (void)netdata_popen_raw_default_flags_and_environment(&cgroup_pid, &fp_child_input, &fp_child_output, cgroups_rename_script, cg->id, cg->intermediate_id); - if (!fp_child_output) { - collector_error("CGROUP: cannot popen(%s \"%s\", \"r\").", cgroups_rename_script, cg->intermediate_id); - cg->pending_renames = 0; - cg->processed = 1; - return; - } - - char buffer[CGROUP_CHARTID_LINE_MAX + 1]; - char *new_name = fgets(buffer, CGROUP_CHARTID_LINE_MAX, fp_child_output); - int exit_code = netdata_pclose(fp_child_input, fp_child_output, cgroup_pid); - - switch (exit_code) { - case 0: - cg->pending_renames = 0; - break; - - case 3: - cg->pending_renames = 0; - cg->processed = 1; - break; - } - - if (cg->pending_renames || cg->processed) - return; - if (!new_name || !*new_name || *new_name == '\n') - return; - if (!(new_name = trim(new_name))) - return; - - char *name = new_name; - - if (!cg->chart_labels) - cg->chart_labels = rrdlabels_create(); - // read the new labels and remove the obsolete ones - rrdlabels_unmark_all(cg->chart_labels); - name = cgroup_parse_resolved_name_and_labels(cg->chart_labels, new_name); - rrdlabels_remove_all_unmarked(cg->chart_labels); - - freez(cg->name); - cg->name = strdupz(name); - - freez(cg->chart_id); - cg->chart_id = cgroup_chart_id_strdupz(name); - - substitute_dots_in_id(cg->chart_id); - cg->hash_chart_id = simple_hash(cg->chart_id); -} - -static void is_cgroup_procs_exist(netdata_ebpf_cgroup_shm_body_t *out, char *id) { - struct stat buf; - - snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_cpuset_base, id); - if (likely(stat(out->path, &buf) == 0)) { - return; - } - - snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_blkio_base, id); - if (likely(stat(out->path, &buf) == 0)) { - return; - } - - snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_memory_base, id); - if (likely(stat(out->path, &buf) == 0)) { - return; - } - - snprintfz(out->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_devices_base, id); - if (likely(stat(out->path, &buf) == 0)) { - return; - } - - out->path[0] = '\0'; - out->enabled = 0; -} - -static inline void convert_cgroup_to_systemd_service(struct cgroup *cg) { - char buffer[CGROUP_CHARTID_LINE_MAX + 1]; - cg->options |= CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE; - strncpyz(buffer, cg->id, CGROUP_CHARTID_LINE_MAX); - char *s = buffer; - - // skip to the last slash - size_t len = strlen(s); - while (len--) { - if (unlikely(s[len] == '/')) { - break; - } - } - if (len) { - s = &s[len + 1]; - } - - // remove extension - len = strlen(s); - while (len--) { - if (unlikely(s[len] == '.')) { - break; - } - } - if (len) { - s[len] = '\0'; - } - - freez(cg->name); - cg->name = strdupz(s); - - freez(cg->chart_id); - cg->chart_id = cgroup_chart_id_strdupz(s); - substitute_dots_in_id(cg->chart_id); - cg->hash_chart_id = simple_hash(cg->chart_id); -} - -static inline struct cgroup *discovery_cgroup_add(const char *id) { - netdata_log_debug(D_CGROUP, "adding to list, cgroup with id '%s'", id); - - struct cgroup *cg = callocz(1, sizeof(struct cgroup)); - - cg->id = strdupz(id); - cg->hash = simple_hash(cg->id); - - cg->name = strdupz(id); - - cg->intermediate_id = cgroup_chart_id_strdupz(id); - - cg->chart_id = cgroup_chart_id_strdupz(id); - substitute_dots_in_id(cg->chart_id); - cg->hash_chart_id = simple_hash(cg->chart_id); - - if (cgroup_use_unified_cgroups) { - cg->options |= CGROUP_OPTIONS_IS_UNIFIED; - } - - if (!discovered_cgroup_root) - discovered_cgroup_root = cg; - else { - struct cgroup *t; - for (t = discovered_cgroup_root; t->discovered_next; t = t->discovered_next) { - } - t->discovered_next = cg; - } - - return cg; -} - -static inline struct cgroup *discovery_cgroup_find(const char *id) { - netdata_log_debug(D_CGROUP, "searching for cgroup '%s'", id); - - uint32_t hash = simple_hash(id); - - struct cgroup *cg; - for(cg = discovered_cgroup_root; cg ; cg = cg->discovered_next) { - if(hash == cg->hash && strcmp(id, cg->id) == 0) - break; - } - - netdata_log_debug(D_CGROUP, "cgroup '%s' %s in memory", id, (cg)?"found":"not found"); - return cg; -} - -static inline void discovery_find_cgroup_in_dir_callback(const char *dir) { - if (!dir || !*dir) { - dir = "/"; - } - netdata_log_debug(D_CGROUP, "examining cgroup dir '%s'", dir); - - struct cgroup *cg = discovery_cgroup_find(dir); - if (cg) { - cg->available = 1; - return; - } - - if (cgroup_root_count >= cgroup_root_max) { - collector_info("CGROUP: maximum number of cgroups reached (%d). Not adding cgroup '%s'", cgroup_root_count, dir); - return; - } - - if (cgroup_max_depth > 0) { - int depth = calc_cgroup_depth(dir); - if (depth > cgroup_max_depth) { - collector_info("CGROUP: '%s' is too deep (%d, while max is %d)", dir, depth, cgroup_max_depth); - return; - } - } - - cg = discovery_cgroup_add(dir); - cg->available = 1; - cg->first_time_seen = 1; - cgroup_root_count++; -} - -static inline int discovery_find_dir_in_subdirs(const char *base, const char *this, void (*callback)(const char *)) { - if(!this) this = base; - netdata_log_debug(D_CGROUP, "searching for directories in '%s' (base '%s')", this?this:"", base); - - size_t dirlen = strlen(this), baselen = strlen(base); - - int ret = -1; - int enabled = -1; - - const char *relative_path = &this[baselen]; - if(!*relative_path) relative_path = "/"; - - DIR *dir = opendir(this); - if(!dir) { - collector_error("CGROUP: cannot read directory '%s'", base); - return ret; - } - ret = 1; - - callback(relative_path); - - struct dirent *de = NULL; - while((de = readdir(dir))) { - if(de->d_type == DT_DIR - && ( - (de->d_name[0] == '.' && de->d_name[1] == '\0') - || (de->d_name[0] == '.' && de->d_name[1] == '.' && de->d_name[2] == '\0') - )) - continue; - - if(de->d_type == DT_DIR) { - if(enabled == -1) { - const char *r = relative_path; - if(*r == '\0') r = "/"; - - // do not decent in directories we are not interested - enabled = matches_search_cgroup_paths(r); - } - - if(enabled) { - char *s = mallocz(dirlen + strlen(de->d_name) + 2); - strcpy(s, this); - strcat(s, "/"); - strcat(s, de->d_name); - int ret2 = discovery_find_dir_in_subdirs(base, s, callback); - if(ret2 > 0) ret += ret2; - freez(s); - } - } - } - - closedir(dir); - return ret; -} - -static inline void discovery_mark_all_cgroups_as_unavailable() { - netdata_log_debug(D_CGROUP, "marking all cgroups as not available"); - struct cgroup *cg; - for (cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { - cg->available = 0; - } -} - -static inline void discovery_update_filenames() { - struct cgroup *cg; - struct stat buf; - for(cg = discovered_cgroup_root; cg ; cg = cg->discovered_next) { - if(unlikely(!cg->available || !cg->enabled || cg->pending_renames)) - continue; - - netdata_log_debug(D_CGROUP, "checking paths for cgroup '%s'", cg->id); - - // check for newly added cgroups - // and update the filenames they read - char filename[FILENAME_MAX + 1]; - if(!cgroup_use_unified_cgroups) { - if(unlikely(cgroup_enable_cpuacct_stat && !cg->cpuacct_stat.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpuacct.stat", cgroup_cpuacct_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->cpuacct_stat.filename = strdupz(filename); - cg->cpuacct_stat.enabled = cgroup_enable_cpuacct_stat; - snprintfz(filename, FILENAME_MAX, "%s%s/cpuset.cpus", cgroup_cpuset_base, cg->id); - cg->filename_cpuset_cpus = strdupz(filename); - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.cfs_period_us", cgroup_cpuacct_base, cg->id); - cg->filename_cpu_cfs_period = strdupz(filename); - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.cfs_quota_us", cgroup_cpuacct_base, cg->id); - cg->filename_cpu_cfs_quota = strdupz(filename); - netdata_log_debug(D_CGROUP, "cpuacct.stat filename for cgroup '%s': '%s'", cg->id, cg->cpuacct_stat.filename); - } - else - netdata_log_debug(D_CGROUP, "cpuacct.stat file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_cpuacct_usage && !cg->cpuacct_usage.filename && !is_cgroup_systemd_service(cg))) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpuacct.usage_percpu", cgroup_cpuacct_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->cpuacct_usage.filename = strdupz(filename); - cg->cpuacct_usage.enabled = cgroup_enable_cpuacct_usage; - netdata_log_debug(D_CGROUP, "cpuacct.usage_percpu filename for cgroup '%s': '%s'", cg->id, cg->cpuacct_usage.filename); - } - else - netdata_log_debug(D_CGROUP, "cpuacct.usage_percpu file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - if(unlikely(cgroup_enable_cpuacct_cpu_throttling && !cg->cpuacct_cpu_throttling.filename && !is_cgroup_systemd_service(cg))) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.stat", cgroup_cpuacct_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->cpuacct_cpu_throttling.filename = strdupz(filename); - cg->cpuacct_cpu_throttling.enabled = cgroup_enable_cpuacct_cpu_throttling; - netdata_log_debug(D_CGROUP, "cpu.stat filename for cgroup '%s': '%s'", cg->id, cg->cpuacct_cpu_throttling.filename); - } - else - netdata_log_debug(D_CGROUP, "cpu.stat file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - if (unlikely( - cgroup_enable_cpuacct_cpu_shares && !cg->cpuacct_cpu_shares.filename && - !is_cgroup_systemd_service(cg))) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.shares", cgroup_cpuacct_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->cpuacct_cpu_shares.filename = strdupz(filename); - cg->cpuacct_cpu_shares.enabled = cgroup_enable_cpuacct_cpu_shares; - netdata_log_debug( - D_CGROUP, "cpu.shares filename for cgroup '%s': '%s'", cg->id, cg->cpuacct_cpu_shares.filename); - } else - netdata_log_debug(D_CGROUP, "cpu.shares file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !is_cgroup_systemd_service(cg)))) { - 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); - cg->memory.enabled_detailed = (cgroup_enable_detailed_memory == CONFIG_BOOLEAN_YES)?CONFIG_BOOLEAN_YES:CONFIG_BOOLEAN_AUTO; - netdata_log_debug(D_CGROUP, "memory.stat filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_detailed); - } - else - netdata_log_debug(D_CGROUP, "memory.stat file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_memory && !cg->memory.filename_usage_in_bytes)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.usage_in_bytes", cgroup_memory_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->memory.filename_usage_in_bytes = strdupz(filename); - cg->memory.enabled_usage_in_bytes = cgroup_enable_memory; - netdata_log_debug(D_CGROUP, "memory.usage_in_bytes filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_usage_in_bytes); - snprintfz(filename, FILENAME_MAX, "%s%s/memory.limit_in_bytes", cgroup_memory_base, cg->id); - cg->filename_memory_limit = strdupz(filename); - } - else - netdata_log_debug(D_CGROUP, "memory.usage_in_bytes file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_swap && !cg->memory.filename_msw_usage_in_bytes)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.memsw.usage_in_bytes", cgroup_memory_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->memory.filename_msw_usage_in_bytes = strdupz(filename); - cg->memory.enabled_msw_usage_in_bytes = cgroup_enable_swap; - snprintfz(filename, FILENAME_MAX, "%s%s/memory.memsw.limit_in_bytes", cgroup_memory_base, cg->id); - cg->filename_memoryswap_limit = strdupz(filename); - netdata_log_debug(D_CGROUP, "memory.msw_usage_in_bytes filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_msw_usage_in_bytes); - } - else - netdata_log_debug(D_CGROUP, "memory.msw_usage_in_bytes file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_memory_failcnt && !cg->memory.filename_failcnt)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.failcnt", cgroup_memory_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->memory.filename_failcnt = strdupz(filename); - cg->memory.enabled_failcnt = cgroup_enable_memory_failcnt; - netdata_log_debug(D_CGROUP, "memory.failcnt filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_failcnt); - } - else - netdata_log_debug(D_CGROUP, "memory.failcnt file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_blkio_io && !cg->io_service_bytes.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_service_bytes_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->io_service_bytes.filename = strdupz(filename); - cg->io_service_bytes.enabled = cgroup_enable_blkio_io; - netdata_log_debug(D_CGROUP, "blkio.io_service_bytes_recursive filename for cgroup '%s': '%s'", cg->id, cg->io_service_bytes.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_service_bytes_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_service_bytes", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_service_bytes.filename = strdupz(filename); - cg->io_service_bytes.enabled = cgroup_enable_blkio_io; - netdata_log_debug(D_CGROUP, "blkio.io_service_bytes filename for cgroup '%s': '%s'", cg->id, cg->io_service_bytes.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_service_bytes file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - - if (unlikely(cgroup_enable_blkio_ops && !cg->io_serviced.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_serviced_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->io_serviced.filename = strdupz(filename); - cg->io_serviced.enabled = cgroup_enable_blkio_ops; - netdata_log_debug(D_CGROUP, "blkio.io_serviced_recursive filename for cgroup '%s': '%s'", cg->id, cg->io_serviced.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_serviced_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_serviced", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_serviced.filename = strdupz(filename); - cg->io_serviced.enabled = cgroup_enable_blkio_ops; - netdata_log_debug(D_CGROUP, "blkio.io_serviced filename for cgroup '%s': '%s'", cg->id, cg->io_serviced.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_serviced file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - - if (unlikely(cgroup_enable_blkio_throttle_io && !cg->throttle_io_service_bytes.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_service_bytes_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->throttle_io_service_bytes.filename = strdupz(filename); - cg->throttle_io_service_bytes.enabled = cgroup_enable_blkio_throttle_io; - netdata_log_debug(D_CGROUP,"blkio.throttle.io_service_bytes_recursive filename for cgroup '%s': '%s'", cg->id, cg->throttle_io_service_bytes.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.throttle.io_service_bytes_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz( - filename, FILENAME_MAX, "%s%s/blkio.throttle.io_service_bytes", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->throttle_io_service_bytes.filename = strdupz(filename); - cg->throttle_io_service_bytes.enabled = cgroup_enable_blkio_throttle_io; - netdata_log_debug(D_CGROUP, "blkio.throttle.io_service_bytes filename for cgroup '%s': '%s'", cg->id, cg->throttle_io_service_bytes.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.throttle.io_service_bytes file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - - if (unlikely(cgroup_enable_blkio_throttle_ops && !cg->throttle_io_serviced.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_serviced_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->throttle_io_serviced.filename = strdupz(filename); - cg->throttle_io_serviced.enabled = cgroup_enable_blkio_throttle_ops; - netdata_log_debug(D_CGROUP, "blkio.throttle.io_serviced_recursive filename for cgroup '%s': '%s'", cg->id, cg->throttle_io_serviced.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.throttle.io_serviced_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.throttle.io_serviced", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->throttle_io_serviced.filename = strdupz(filename); - cg->throttle_io_serviced.enabled = cgroup_enable_blkio_throttle_ops; - netdata_log_debug(D_CGROUP, "blkio.throttle.io_serviced filename for cgroup '%s': '%s'", cg->id, cg->throttle_io_serviced.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.throttle.io_serviced file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - - if (unlikely(cgroup_enable_blkio_merged_ops && !cg->io_merged.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_merged_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->io_merged.filename = strdupz(filename); - cg->io_merged.enabled = cgroup_enable_blkio_merged_ops; - netdata_log_debug(D_CGROUP, "blkio.io_merged_recursive filename for cgroup '%s': '%s'", cg->id, cg->io_merged.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_merged_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_merged", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_merged.filename = strdupz(filename); - cg->io_merged.enabled = cgroup_enable_blkio_merged_ops; - netdata_log_debug(D_CGROUP, "blkio.io_merged filename for cgroup '%s': '%s'", cg->id, cg->io_merged.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_merged file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - - if (unlikely(cgroup_enable_blkio_queued_ops && !cg->io_queued.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_queued_recursive", cgroup_blkio_base, cg->id); - if (unlikely(stat(filename, &buf) != -1)) { - cg->io_queued.filename = strdupz(filename); - cg->io_queued.enabled = cgroup_enable_blkio_queued_ops; - netdata_log_debug(D_CGROUP, "blkio.io_queued_recursive filename for cgroup '%s': '%s'", cg->id, cg->io_queued.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_queued_recursive file for cgroup '%s': '%s' does not exist.", cg->id, filename); - snprintfz(filename, FILENAME_MAX, "%s%s/blkio.io_queued", cgroup_blkio_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_queued.filename = strdupz(filename); - cg->io_queued.enabled = cgroup_enable_blkio_queued_ops; - netdata_log_debug(D_CGROUP, "blkio.io_queued filename for cgroup '%s': '%s'", cg->id, cg->io_queued.filename); - } else { - netdata_log_debug(D_CGROUP, "blkio.io_queued file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - } - } - } - else if(likely(cgroup_unified_exist)) { - if(unlikely(cgroup_enable_blkio_io && !cg->io_service_bytes.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/io.stat", cgroup_unified_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->io_service_bytes.filename = strdupz(filename); - cg->io_service_bytes.enabled = cgroup_enable_blkio_io; - netdata_log_debug(D_CGROUP, "io.stat filename for unified cgroup '%s': '%s'", cg->id, cg->io_service_bytes.filename); - } else - netdata_log_debug(D_CGROUP, "io.stat file for unified cgroup '%s': '%s' does not exist.", cg->id, filename); - } - if (unlikely(cgroup_enable_blkio_ops && !cg->io_serviced.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/io.stat", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_serviced.filename = strdupz(filename); - cg->io_serviced.enabled = cgroup_enable_blkio_ops; - netdata_log_debug(D_CGROUP, "io.stat filename for unified cgroup '%s': '%s'", cg->id, cg->io_service_bytes.filename); - } else - netdata_log_debug(D_CGROUP, "io.stat file for unified cgroup '%s': '%s' does not exist.", cg->id, filename); - } - if (unlikely( - (cgroup_enable_cpuacct_stat || cgroup_enable_cpuacct_cpu_throttling) && - !cg->cpuacct_stat.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.stat", cgroup_unified_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->cpuacct_stat.filename = strdupz(filename); - cg->cpuacct_stat.enabled = cgroup_enable_cpuacct_stat; - cg->cpuacct_cpu_throttling.enabled = cgroup_enable_cpuacct_cpu_throttling; - cg->filename_cpuset_cpus = NULL; - cg->filename_cpu_cfs_period = NULL; - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.max", cgroup_unified_base, cg->id); - cg->filename_cpu_cfs_quota = strdupz(filename); - netdata_log_debug(D_CGROUP, "cpu.stat filename for unified cgroup '%s': '%s'", cg->id, cg->cpuacct_stat.filename); - } - else - netdata_log_debug(D_CGROUP, "cpu.stat file for unified cgroup '%s': '%s' does not exist.", cg->id, filename); - } - if (unlikely(cgroup_enable_cpuacct_cpu_shares && !cg->cpuacct_cpu_shares.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.weight", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->cpuacct_cpu_shares.filename = strdupz(filename); - cg->cpuacct_cpu_shares.enabled = cgroup_enable_cpuacct_cpu_shares; - netdata_log_debug(D_CGROUP, "cpu.weight filename for cgroup '%s': '%s'", cg->id, cg->cpuacct_cpu_shares.filename); - } else - netdata_log_debug(D_CGROUP, "cpu.weight file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely((cgroup_enable_detailed_memory || cgroup_used_memory) && !cg->memory.filename_detailed && (cgroup_used_memory || cgroup_enable_systemd_services_detailed_memory || !is_cgroup_systemd_service(cg)))) { - 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); - cg->memory.enabled_detailed = (cgroup_enable_detailed_memory == CONFIG_BOOLEAN_YES)?CONFIG_BOOLEAN_YES:CONFIG_BOOLEAN_AUTO; - netdata_log_debug(D_CGROUP, "memory.stat filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_detailed); - } - else - netdata_log_debug(D_CGROUP, "memory.stat file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_memory && !cg->memory.filename_usage_in_bytes)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.current", cgroup_unified_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->memory.filename_usage_in_bytes = strdupz(filename); - cg->memory.enabled_usage_in_bytes = cgroup_enable_memory; - netdata_log_debug(D_CGROUP, "memory.current filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_usage_in_bytes); - snprintfz(filename, FILENAME_MAX, "%s%s/memory.max", cgroup_unified_base, cg->id); - cg->filename_memory_limit = strdupz(filename); - } - else - netdata_log_debug(D_CGROUP, "memory.current file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if(unlikely(cgroup_enable_swap && !cg->memory.filename_msw_usage_in_bytes)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.swap.current", cgroup_unified_base, cg->id); - if(likely(stat(filename, &buf) != -1)) { - cg->memory.filename_msw_usage_in_bytes = strdupz(filename); - cg->memory.enabled_msw_usage_in_bytes = cgroup_enable_swap; - snprintfz(filename, FILENAME_MAX, "%s%s/memory.swap.max", cgroup_unified_base, cg->id); - cg->filename_memoryswap_limit = strdupz(filename); - netdata_log_debug(D_CGROUP, "memory.swap.current filename for cgroup '%s': '%s'", cg->id, cg->memory.filename_msw_usage_in_bytes); - } - else - netdata_log_debug(D_CGROUP, "memory.swap file for cgroup '%s': '%s' does not exist.", cg->id, filename); - } - - if (unlikely(cgroup_enable_pressure_cpu && !cg->cpu_pressure.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/cpu.pressure", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->cpu_pressure.filename = strdupz(filename); - cg->cpu_pressure.some.enabled = cgroup_enable_pressure_cpu; - cg->cpu_pressure.full.enabled = CONFIG_BOOLEAN_NO; - netdata_log_debug(D_CGROUP, "cpu.pressure filename for cgroup '%s': '%s'", cg->id, cg->cpu_pressure.filename); - } else { - netdata_log_debug(D_CGROUP, "cpu.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); - } - } - - if (unlikely((cgroup_enable_pressure_io_some || cgroup_enable_pressure_io_full) && !cg->io_pressure.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/io.pressure", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->io_pressure.filename = strdupz(filename); - cg->io_pressure.some.enabled = cgroup_enable_pressure_io_some; - cg->io_pressure.full.enabled = cgroup_enable_pressure_io_full; - netdata_log_debug(D_CGROUP, "io.pressure filename for cgroup '%s': '%s'", cg->id, cg->io_pressure.filename); - } else { - netdata_log_debug(D_CGROUP, "io.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); - } - } - - if (unlikely((cgroup_enable_pressure_memory_some || cgroup_enable_pressure_memory_full) && !cg->memory_pressure.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/memory.pressure", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->memory_pressure.filename = strdupz(filename); - cg->memory_pressure.some.enabled = cgroup_enable_pressure_memory_some; - cg->memory_pressure.full.enabled = cgroup_enable_pressure_memory_full; - netdata_log_debug(D_CGROUP, "memory.pressure filename for cgroup '%s': '%s'", cg->id, cg->memory_pressure.filename); - } else { - netdata_log_debug(D_CGROUP, "memory.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); - } - } - - if (unlikely((cgroup_enable_pressure_irq_some || cgroup_enable_pressure_irq_full) && !cg->irq_pressure.filename)) { - snprintfz(filename, FILENAME_MAX, "%s%s/irq.pressure", cgroup_unified_base, cg->id); - if (likely(stat(filename, &buf) != -1)) { - cg->irq_pressure.filename = strdupz(filename); - cg->irq_pressure.some.enabled = cgroup_enable_pressure_irq_some; - cg->irq_pressure.full.enabled = cgroup_enable_pressure_irq_full; - netdata_log_debug(D_CGROUP, "irq.pressure filename for cgroup '%s': '%s'", cg->id, cg->irq_pressure.filename); - } else { - netdata_log_debug(D_CGROUP, "irq.pressure file for cgroup '%s': '%s' does not exist", cg->id, filename); - } - } - } - } -} - -static inline void discovery_cleanup_all_cgroups() { - struct cgroup *cg = discovered_cgroup_root, *last = NULL; - - for(; cg ;) { - if(!cg->available) { - // enable the first duplicate cgroup - { - struct cgroup *t; - for (t = discovered_cgroup_root; t; t = t->discovered_next) { - if (t != cg && t->available && !t->enabled && t->options & CGROUP_OPTIONS_DISABLED_DUPLICATE && - (is_cgroup_systemd_service(t) == is_cgroup_systemd_service(cg)) && - t->hash_chart_id == cg->hash_chart_id && !strcmp(t->chart_id, cg->chart_id)) { - netdata_log_debug(D_CGROUP, "Enabling duplicate of cgroup '%s' with id '%s', because the original with id '%s' stopped.", t->chart_id, t->id, cg->id); - t->enabled = 1; - t->options &= ~CGROUP_OPTIONS_DISABLED_DUPLICATE; - break; - } - } - } - - if(!last) - discovered_cgroup_root = cg->discovered_next; - else - last->discovered_next = cg->discovered_next; - - cgroup_free(cg); - - if(!last) - cg = discovered_cgroup_root; - else - cg = last->discovered_next; - } - else { - last = cg; - cg = cg->discovered_next; - } - } -} - -static inline void discovery_copy_discovered_cgroups_to_reader() { - netdata_log_debug(D_CGROUP, "copy discovered cgroups to the main group list"); - - struct cgroup *cg; - - for (cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { - cg->next = cg->discovered_next; - } - - cgroup_root = discovered_cgroup_root; -} - -static inline void discovery_share_cgroups_with_ebpf() { - struct cgroup *cg; - int count; - struct stat buf; - - if (shm_mutex_cgroup_ebpf == SEM_FAILED) { - return; - } - sem_wait(shm_mutex_cgroup_ebpf); - - for (cg = cgroup_root, count = 0; cg; cg = cg->next, count++) { - netdata_ebpf_cgroup_shm_body_t *ptr = &shm_cgroup_ebpf.body[count]; - char *prefix = (is_cgroup_systemd_service(cg)) ? services_chart_id_prefix : cgroup_chart_id_prefix; - snprintfz(ptr->name, CGROUP_EBPF_NAME_SHARED_LENGTH - 1, "%s%s", prefix, cg->chart_id); - ptr->hash = simple_hash(ptr->name); - ptr->options = cg->options; - ptr->enabled = cg->enabled; - if (cgroup_use_unified_cgroups) { - snprintfz(ptr->path, FILENAME_MAX, "%s%s/cgroup.procs", cgroup_unified_base, cg->id); - if (likely(stat(ptr->path, &buf) == -1)) { - ptr->path[0] = '\0'; - ptr->enabled = 0; - } - } else { - is_cgroup_procs_exist(ptr, cg->id); - } - - netdata_log_debug(D_CGROUP, "cgroup shared: NAME=%s, ENABLED=%d", ptr->name, ptr->enabled); - } - - shm_cgroup_ebpf.header->cgroup_root_count = count; - sem_post(shm_mutex_cgroup_ebpf); -} - -static inline void discovery_find_all_cgroups_v1() { - if (cgroup_enable_cpuacct_stat || cgroup_enable_cpuacct_usage) { - if (discovery_find_dir_in_subdirs(cgroup_cpuacct_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { - cgroup_enable_cpuacct_stat = cgroup_enable_cpuacct_usage = CONFIG_BOOLEAN_NO; - collector_error("CGROUP: disabled cpu statistics."); - } - } - - if (cgroup_enable_blkio_io || cgroup_enable_blkio_ops || cgroup_enable_blkio_throttle_io || - cgroup_enable_blkio_throttle_ops || cgroup_enable_blkio_merged_ops || cgroup_enable_blkio_queued_ops) { - if (discovery_find_dir_in_subdirs(cgroup_blkio_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { - cgroup_enable_blkio_io = cgroup_enable_blkio_ops = cgroup_enable_blkio_throttle_io = - cgroup_enable_blkio_throttle_ops = cgroup_enable_blkio_merged_ops = cgroup_enable_blkio_queued_ops = - CONFIG_BOOLEAN_NO; - collector_error("CGROUP: disabled blkio statistics."); - } - } - - if (cgroup_enable_memory || cgroup_enable_detailed_memory || cgroup_enable_swap || cgroup_enable_memory_failcnt) { - if (discovery_find_dir_in_subdirs(cgroup_memory_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { - cgroup_enable_memory = cgroup_enable_detailed_memory = cgroup_enable_swap = cgroup_enable_memory_failcnt = - CONFIG_BOOLEAN_NO; - collector_error("CGROUP: disabled memory statistics."); - } - } - - if (cgroup_search_in_devices) { - if (discovery_find_dir_in_subdirs(cgroup_devices_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { - cgroup_search_in_devices = 0; - collector_error("CGROUP: disabled devices statistics."); - } - } -} - -static inline void discovery_find_all_cgroups_v2() { - if (discovery_find_dir_in_subdirs(cgroup_unified_base, NULL, discovery_find_cgroup_in_dir_callback) == -1) { - cgroup_unified_exist = CONFIG_BOOLEAN_NO; - collector_error("CGROUP: disabled unified cgroups statistics."); - } -} - -static int is_digits_only(const char *s) { - do { - if (!isdigit(*s++)) { - return 0; - } - } while (*s); - - return 1; -} - -static inline void discovery_process_first_time_seen_cgroup(struct cgroup *cg) { - if (!cg->first_time_seen) { - return; - } - cg->first_time_seen = 0; - - char comm[TASK_COMM_LEN + 1]; - - if (cg->container_orchestrator == CGROUPS_ORCHESTRATOR_UNSET) { - if (strstr(cg->id, "kubepods")) { - cg->container_orchestrator = CGROUPS_ORCHESTRATOR_K8S; - } else { - cg->container_orchestrator = CGROUPS_ORCHESTRATOR_UNKNOWN; - } - } - - if (is_inside_k8s && !k8s_get_container_first_proc_comm(cg->id, comm)) { - // container initialization may take some time when CPU % is high - // seen on GKE: comm is '6' before 'runc:[2:INIT]' (dunno if it could be another number) - if (is_digits_only(comm) || matches_entrypoint_parent_process_comm(comm)) { - cg->first_time_seen = 1; - return; - } - if (!strcmp(comm, "pause")) { - // a container that holds the network namespace for the pod - // we don't need to collect its metrics - cg->processed = 1; - return; - } - } - - if (cgroup_enable_systemd_services && matches_systemd_services_cgroups(cg->id)) { - netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') matches 'cgroups to match as systemd services'", cg->id, cg->chart_id); - convert_cgroup_to_systemd_service(cg); - return; - } - - if (matches_enabled_cgroup_renames(cg->id)) { - netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') matches 'run script to rename cgroups matching', will try to rename it", cg->id, cg->chart_id); - if (is_inside_k8s && k8s_is_container(cg->id)) { - // it may take up to a minute for the K8s API to return data for the container - // tested on AWS K8s cluster with 100% CPU utilization - cg->pending_renames = 9; // 1.5 minute - } else { - cg->pending_renames = 2; - } - } -} - -static int discovery_is_cgroup_duplicate(struct cgroup *cg) { - // https://github.com/netdata/netdata/issues/797#issuecomment-241248884 - struct cgroup *c; - for (c = discovered_cgroup_root; c; c = c->discovered_next) { - if (c != cg && c->enabled && (is_cgroup_systemd_service(c) == is_cgroup_systemd_service(cg)) && - c->hash_chart_id == cg->hash_chart_id && !strcmp(c->chart_id, cg->chart_id)) { - collector_error( - "CGROUP: chart id '%s' already exists with id '%s' and is enabled and available. Disabling cgroup with id '%s'.", - cg->chart_id, - c->id, - cg->id); - return 1; - } - } - return 0; -} - -static inline void discovery_process_cgroup(struct cgroup *cg) { - if (!cg) { - netdata_log_debug(D_CGROUP, "discovery_process_cgroup() received NULL"); - return; - } - if (!cg->available || cg->processed) { - return; - } - - if (cg->first_time_seen) { - worker_is_busy(WORKER_DISCOVERY_PROCESS_FIRST_TIME); - discovery_process_first_time_seen_cgroup(cg); - if (unlikely(cg->first_time_seen || cg->processed)) { - return; - } - } - - if (cg->pending_renames) { - worker_is_busy(WORKER_DISCOVERY_PROCESS_RENAME); - discovery_rename_cgroup(cg); - if (unlikely(cg->pending_renames || cg->processed)) { - return; - } - } - - cg->processed = 1; - - if ((strlen(cg->chart_id) + strlen(cgroup_chart_id_prefix)) >= RRD_ID_LENGTH_MAX) { - collector_info("cgroup '%s' (chart id '%s') disabled because chart_id exceeds the limit (RRD_ID_LENGTH_MAX)", cg->id, cg->chart_id); - return; - } - - if (is_cgroup_systemd_service(cg)) { - if (discovery_is_cgroup_duplicate(cg)) { - cg->enabled = 0; - cg->options |= CGROUP_OPTIONS_DISABLED_DUPLICATE; - return; - } - if (!cg->chart_labels) - cg->chart_labels = rrdlabels_create(); - rrdlabels_add(cg->chart_labels, "service_name", cg->name, RRDLABEL_SRC_AUTO); - cg->enabled = 1; - return; - } - - if (!(cg->enabled = matches_enabled_cgroup_names(cg->name))) { - netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') disabled by 'enable by default cgroups names matching'", cg->id, cg->name); - return; - } - - if (!(cg->enabled = matches_enabled_cgroup_paths(cg->id))) { - netdata_log_debug(D_CGROUP, "cgroup '%s' (name '%s') disabled by 'enable by default cgroups matching'", cg->id, cg->name); - return; - } - - if (discovery_is_cgroup_duplicate(cg)) { - cg->enabled = 0; - cg->options |= CGROUP_OPTIONS_DISABLED_DUPLICATE; - return; - } - - if (!cg->chart_labels) - cg->chart_labels = rrdlabels_create(); - - if (!k8s_is_kubepod(cg)) { - rrdlabels_add(cg->chart_labels, "cgroup_name", cg->name, RRDLABEL_SRC_AUTO); - if (!rrdlabels_exist(cg->chart_labels, "image")) - rrdlabels_add(cg->chart_labels, "image", "", RRDLABEL_SRC_AUTO); - } - - worker_is_busy(WORKER_DISCOVERY_PROCESS_NETWORK); - read_cgroup_network_interfaces(cg); -} - -static inline void discovery_find_all_cgroups() { - netdata_log_debug(D_CGROUP, "searching for cgroups"); - - worker_is_busy(WORKER_DISCOVERY_INIT); - discovery_mark_all_cgroups_as_unavailable(); - - worker_is_busy(WORKER_DISCOVERY_FIND); - if (!cgroup_use_unified_cgroups) { - discovery_find_all_cgroups_v1(); - } else { - discovery_find_all_cgroups_v2(); - } - - struct cgroup *cg; - for (cg = discovered_cgroup_root; cg; cg = cg->discovered_next) { - worker_is_busy(WORKER_DISCOVERY_PROCESS); - discovery_process_cgroup(cg); - } - - worker_is_busy(WORKER_DISCOVERY_UPDATE); - discovery_update_filenames(); - - worker_is_busy(WORKER_DISCOVERY_LOCK); - uv_mutex_lock(&cgroup_root_mutex); - - worker_is_busy(WORKER_DISCOVERY_CLEANUP); - discovery_cleanup_all_cgroups(); - - worker_is_busy(WORKER_DISCOVERY_COPY); - discovery_copy_discovered_cgroups_to_reader(); - - uv_mutex_unlock(&cgroup_root_mutex); - - worker_is_busy(WORKER_DISCOVERY_SHARE); - discovery_share_cgroups_with_ebpf(); - - netdata_log_debug(D_CGROUP, "done searching for cgroups"); -} - -static inline char *cgroup_chart_type(char *buffer, struct cgroup *cg) { - if(buffer[0]) return buffer; - - if (cg->chart_id[0] == '\0' || (cg->chart_id[0] == '/' && cg->chart_id[1] == '\0')) - strncpy(buffer, "cgroup_root", RRD_ID_LENGTH_MAX); - else if (is_cgroup_systemd_service(cg)) - snprintfz(buffer, RRD_ID_LENGTH_MAX, "%s%s", services_chart_id_prefix, cg->chart_id); - else - snprintfz(buffer, RRD_ID_LENGTH_MAX, "%s%s", cgroup_chart_id_prefix, cg->chart_id); - - return buffer; -} - -void cgroup_discovery_worker(void *ptr) -{ - UNUSED(ptr); - - worker_register("CGROUPSDISC"); - worker_register_job_name(WORKER_DISCOVERY_INIT, "init"); - worker_register_job_name(WORKER_DISCOVERY_FIND, "find"); - worker_register_job_name(WORKER_DISCOVERY_PROCESS, "process"); - worker_register_job_name(WORKER_DISCOVERY_PROCESS_RENAME, "rename"); - worker_register_job_name(WORKER_DISCOVERY_PROCESS_NETWORK, "network"); - worker_register_job_name(WORKER_DISCOVERY_PROCESS_FIRST_TIME, "new"); - worker_register_job_name(WORKER_DISCOVERY_UPDATE, "update"); - worker_register_job_name(WORKER_DISCOVERY_CLEANUP, "cleanup"); - worker_register_job_name(WORKER_DISCOVERY_COPY, "copy"); - worker_register_job_name(WORKER_DISCOVERY_SHARE, "share"); - worker_register_job_name(WORKER_DISCOVERY_LOCK, "lock"); - - entrypoint_parent_process_comm = simple_pattern_create( - " runc:[* " // http://terenceli.github.io/%E6%8A%80%E6%9C%AF/2021/12/28/runc-internals-3) - " exe ", // https://github.com/falcosecurity/falco/blob/9d41b0a151b83693929d3a9c84f7c5c85d070d3a/rules/falco_rules.yaml#L1961 - NULL, - SIMPLE_PATTERN_EXACT, true); - - service_register(SERVICE_THREAD_TYPE_LIBUV, NULL, NULL, NULL, false); - - while (service_running(SERVICE_COLLECTORS)) { - worker_is_idle(); - - uv_mutex_lock(&discovery_thread.mutex); - uv_cond_wait(&discovery_thread.cond_var, &discovery_thread.mutex); - uv_mutex_unlock(&discovery_thread.mutex); - - if (unlikely(!service_running(SERVICE_COLLECTORS))) - break; - - discovery_find_all_cgroups(); - } - collector_info("discovery thread stopped"); - worker_unregister(); - service_exits(); - __atomic_store_n(&discovery_thread.exited,1,__ATOMIC_RELAXED); -} - -// ---------------------------------------------------------------------------- -// generate charts - -#define CHART_TITLE_MAX 300 - -void update_systemd_services_charts( - int update_every, - int do_cpu, - int do_mem_usage, - int do_mem_detailed, - int do_mem_failcnt, - int do_swap_usage, - int do_io, - int do_io_ops, - int do_throttle_io, - int do_throttle_ops, - int do_queued_ops, - int do_merged_ops) -{ - // update the values - struct cgroup *cg; - int systemd_cgroup_chart_priority = NETDATA_CHART_PRIO_CGROUPS_SYSTEMD; - char type[RRD_ID_LENGTH_MAX + 1]; - - for (cg = cgroup_root; cg; cg = cg->next) { - if (unlikely(!cg->enabled || cg->pending_renames || !is_cgroup_systemd_service(cg))) - continue; - - type[0] = '\0'; - if (likely(do_cpu && cg->cpuacct_stat.updated)) { - if (unlikely(!cg->st_cpu)) { - cg->st_cpu = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "cpu_utilization", - NULL, - "cpu", - "systemd.service.cpu.utilization", - "Systemd Services CPU utilization (100%% = 1 core)", - "percentage", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority, - update_every, - RRDSET_TYPE_STACKED); - - rrdset_update_rrdlabels(cg->st_cpu, cg->chart_labels); - if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - rrddim_add(cg->st_cpu, "user", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_cpu, "system", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); - } else { - rrddim_add(cg->st_cpu, "user", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_cpu, "system", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); - } - } - - // complete the iteration - rrddim_set(cg->st_cpu, "user", cg->cpuacct_stat.user); - rrddim_set(cg->st_cpu, "system", cg->cpuacct_stat.system); - rrdset_done(cg->st_cpu); - } - - if (unlikely(do_mem_usage && cg->memory.updated_usage_in_bytes)) { - if (unlikely(!cg->st_mem_usage)) { - cg->st_mem_usage = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_usage", - NULL, - "mem", - "systemd.service.memory.usage", - "Systemd Services Used Memory", - "MiB", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 5, - update_every, - RRDSET_TYPE_STACKED); - - rrdset_update_rrdlabels(cg->st_mem_usage, cg->chart_labels); - rrddim_add(cg->st_mem_usage, "ram", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - if (likely(do_swap_usage)) - rrddim_add(cg->st_mem_usage, "swap", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - rrddim_set(cg->st_mem_usage, "ram", cg->memory.usage_in_bytes); - if (likely(do_swap_usage)) { - 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.total_inactive_file) ? - cg->memory.msw_usage_in_bytes - - (cg->memory.usage_in_bytes + cg->memory.total_inactive_file) : - 0); - } else { - rrddim_set(cg->st_mem_usage, "swap", cg->memory.msw_usage_in_bytes); - } - } - rrdset_done(cg->st_mem_usage); - } - - if (likely(do_mem_failcnt && cg->memory.updated_failcnt)) { - if (unlikely(do_mem_failcnt && !cg->st_mem_failcnt)) { - cg->st_mem_failcnt = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_failcnt", - NULL, - "mem", - "systemd.service.memory.failcnt", - "Systemd Services Memory Limit Failures", - "failures/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 10, - update_every, - RRDSET_TYPE_LINE); - - rrdset_update_rrdlabels(cg->st_mem_failcnt, cg->chart_labels); - rrddim_add(cg->st_mem_failcnt, "fail", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_mem_failcnt, "fail", cg->memory.failcnt); - rrdset_done(cg->st_mem_failcnt); - } - - if (likely(do_mem_detailed && cg->memory.updated_detailed)) { - if (unlikely(!cg->st_mem)) { - cg->st_mem = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_ram_usage", - NULL, - "mem", - "systemd.service.memory.ram.usage", - "Systemd Services Memory", - "MiB", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 15, - update_every, - RRDSET_TYPE_STACKED); - - rrdset_update_rrdlabels(cg->st_mem, cg->chart_labels); - rrddim_add(cg->st_mem, "rss", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "cache", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "mapped_file", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "rss_huge", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - rrddim_set(cg->st_mem, "rss", cg->memory.total_rss); - rrddim_set(cg->st_mem, "cache", cg->memory.total_cache); - rrddim_set(cg->st_mem, "mapped_file", cg->memory.total_mapped_file); - rrddim_set(cg->st_mem, "rss_huge", cg->memory.total_rss_huge); - rrdset_done(cg->st_mem); - - if (unlikely(!cg->st_writeback)) { - cg->st_writeback = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_writeback", - NULL, - "mem", - "systemd.service.memory.writeback", - "Systemd Services Writeback Memory", - "MiB", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 20, - update_every, - RRDSET_TYPE_STACKED); - - rrdset_update_rrdlabels(cg->st_writeback, cg->chart_labels); - rrddim_add(cg->st_writeback, "writeback", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_writeback, "dirty", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - rrddim_set(cg->st_writeback, "writeback", cg->memory.total_writeback); - rrddim_set(cg->st_writeback, "dirty", cg->memory.total_dirty); - rrdset_done(cg->st_writeback); - - if (unlikely(!cg->st_pgfaults)) { - cg->st_pgfaults = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_pgfault", - NULL, - "mem", - "systemd.service.memory.paging.faults", - "Systemd Services Memory Minor and Major Page Faults", - "MiB/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 25, - update_every, - RRDSET_TYPE_AREA); - - rrdset_update_rrdlabels(cg->st_pgfaults, cg->chart_labels); - rrddim_add(cg->st_pgfaults, "minor", NULL, system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_pgfaults, "major", NULL, system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_pgfaults, "minor", cg->memory.total_pgfault); - rrddim_set(cg->st_pgfaults, "major", cg->memory.total_pgmajfault); - rrdset_done(cg->st_pgfaults); - - if (unlikely(!cg->st_mem_activity)) { - cg->st_mem_activity = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "mem_paging_io", - NULL, - "mem", - "systemd.service.memory.paging.io", - "Systemd Services Memory Paging IO", - "MiB/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 30, - update_every, - RRDSET_TYPE_AREA); - - rrdset_update_rrdlabels(cg->st_mem_activity, cg->chart_labels); - rrddim_add(cg->st_mem_activity, "in", NULL, system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_mem_activity, "out", NULL, -system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_mem_activity, "in", cg->memory.total_pgpgin); - rrddim_set(cg->st_mem_activity, "out", cg->memory.total_pgpgout); - rrdset_done(cg->st_mem_activity); - } - - if (likely(do_io && cg->io_service_bytes.updated)) { - if (unlikely(!cg->st_io)) { - cg->st_io = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_io", - NULL, - "disk", - "systemd.service.disk.io", - "Systemd Services Disk Read/Write Bandwidth", - "KiB/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 35, - update_every, - RRDSET_TYPE_AREA); - - rrdset_update_rrdlabels(cg->st_io, cg->chart_labels); - rrddim_add(cg->st_io, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_io, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_io, "read", cg->io_service_bytes.Read); - rrddim_set(cg->st_io, "write", cg->io_service_bytes.Write); - rrdset_done(cg->st_io); - } - - if (likely(do_io_ops && cg->io_serviced.updated)) { - if (unlikely(!cg->st_serviced_ops)) { - cg->st_serviced_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_iops", - NULL, - "disk", - "systemd.service.disk.iops", - "Systemd Services Disk Read/Write Operations", - "operations/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 40, - update_every, - RRDSET_TYPE_LINE); - - rrdset_update_rrdlabels(cg->st_serviced_ops, cg->chart_labels); - rrddim_add(cg->st_serviced_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_serviced_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_serviced_ops, "read", cg->io_serviced.Read); - rrddim_set(cg->st_serviced_ops, "write", cg->io_serviced.Write); - rrdset_done(cg->st_serviced_ops); - } - - if (likely(do_throttle_io && cg->throttle_io_service_bytes.updated)) { - if (unlikely(!cg->st_throttle_io)) { - cg->st_throttle_io = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_throttle_io", - NULL, - "disk", - "systemd.service.disk.throttle.io", - "Systemd Services Throttle Disk Read/Write Bandwidth", - "KiB/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 45, - update_every, - RRDSET_TYPE_AREA); - - rrdset_update_rrdlabels(cg->st_throttle_io, cg->chart_labels); - rrddim_add(cg->st_throttle_io, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_throttle_io, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_throttle_io, "read", cg->throttle_io_service_bytes.Read); - rrddim_set(cg->st_throttle_io, "write", cg->throttle_io_service_bytes.Write); - rrdset_done(cg->st_throttle_io); - } - - if (likely(do_throttle_ops && cg->throttle_io_serviced.updated)) { - if (unlikely(!cg->st_throttle_serviced_ops)) { - cg->st_throttle_serviced_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_throttle_iops", - NULL, - "disk", - "systemd.service.disk.throttle.iops", - "Systemd Services Throttle Disk Read/Write Operations", - "operations/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 50, - update_every, - RRDSET_TYPE_LINE); - - rrdset_update_rrdlabels(cg->st_throttle_serviced_ops, cg->chart_labels); - rrddim_add(cg->st_throttle_serviced_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_throttle_serviced_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_throttle_serviced_ops, "read", cg->throttle_io_serviced.Read); - rrddim_set(cg->st_throttle_serviced_ops, "write", cg->throttle_io_serviced.Write); - rrdset_done(cg->st_throttle_serviced_ops); - } - - if (likely(do_queued_ops && cg->io_queued.updated)) { - if (unlikely(!cg->st_queued_ops)) { - cg->st_queued_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_queued_iops", - NULL, - "disk", - "systemd.service.disk.queued_iops", - "Systemd Services Queued Disk Read/Write Operations", - "operations/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 55, - update_every, - RRDSET_TYPE_LINE); - - rrdset_update_rrdlabels(cg->st_queued_ops, cg->chart_labels); - rrddim_add(cg->st_queued_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_queued_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_queued_ops, "read", cg->io_queued.Read); - rrddim_set(cg->st_queued_ops, "write", cg->io_queued.Write); - rrdset_done(cg->st_queued_ops); - } - - if (likely(do_merged_ops && cg->io_merged.updated)) { - if (unlikely(!cg->st_merged_ops)) { - cg->st_merged_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg), - "disk_merged_iops", - NULL, - "disk", - "systemd.service.disk.merged_iops", - "Systemd Services Merged Disk Read/Write Operations", - "operations/s", - PLUGIN_CGROUPS_NAME, - PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME, - systemd_cgroup_chart_priority + 60, - update_every, - RRDSET_TYPE_LINE); - - rrdset_update_rrdlabels(cg->st_merged_ops, cg->chart_labels); - rrddim_add(cg->st_merged_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_merged_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - rrddim_set(cg->st_merged_ops, "read", cg->io_merged.Read); - rrddim_set(cg->st_merged_ops, "write", cg->io_merged.Write); - rrdset_done(cg->st_merged_ops); - } - } -} +// update CPU and memory limits static inline void update_cpu_limits(char **filename, unsigned long long *value, struct cgroup *cg) { if(*filename) { @@ -3225,10 +1224,7 @@ static inline void update_cpu_limits(char **filename, unsigned long long *value, ret = 0; } } - else if(value == &cg->cpu_cfs_period) { - ret = read_single_number_file(*filename, value); - } - else if(value == &cg->cpu_cfs_quota) { + else if(value == &cg->cpu_cfs_period || value == &cg->cpu_cfs_quota) { ret = read_single_number_file(*filename, value); } else ret = -1; @@ -3282,12 +1278,16 @@ cpu_limits2_err: } } -static inline int update_memory_limits(char **filename, const RRDSETVAR_ACQUIRED **chart_var, unsigned long long *value, const char *chart_var_name, struct cgroup *cg) { +static inline int update_memory_limits(struct cgroup *cg) { + char **filename = &cg->filename_memory_limit; + const RRDSETVAR_ACQUIRED **chart_var = &cg->chart_var_memory_limit; + unsigned long long *value = &cg->memory_limit; + if(*filename) { if(unlikely(!*chart_var)) { - *chart_var = rrdsetvar_custom_chart_variable_add_and_acquire(cg->st_mem_usage, chart_var_name); + *chart_var = rrdsetvar_custom_chart_variable_add_and_acquire(cg->st_mem_usage, "memory_limit"); if(!*chart_var) { - collector_error("Cannot create cgroup %s chart variable '%s'. Will not update its limit anymore.", cg->id, chart_var_name); + collector_error("Cannot create cgroup %s chart variable '%s'. Will not update its limit anymore.", cg->id, "memory_limit"); freez(*filename); *filename = NULL; } @@ -3301,7 +1301,7 @@ static inline int update_memory_limits(char **filename, const RRDSETVAR_ACQUIRED *filename = NULL; } else { - rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value / (1024 * 1024))); + rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value) / (1024.0 * 1024.0)); return 1; } } else { @@ -3316,11 +1316,11 @@ static inline int update_memory_limits(char **filename, const RRDSETVAR_ACQUIRED char *s = "max\n\0"; if(strcmp(s, buffer) == 0){ *value = UINT64_MAX; - rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value / (1024 * 1024))); + rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value) / (1024.0 * 1024.0)); return 1; } *value = str2ull(buffer, NULL); - rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value / (1024 * 1024))); + rrdsetvar_custom_chart_variable_set(cg->st_mem_usage, *chart_var, (NETDATA_DOUBLE)(*value) / (1024.0 * 1024.0)); return 1; } } @@ -3328,85 +1328,65 @@ static inline int update_memory_limits(char **filename, const RRDSETVAR_ACQUIRED return 0; } -void update_cgroup_charts(int update_every) { - netdata_log_debug(D_CGROUP, "updating cgroups charts"); - - char type[RRD_ID_LENGTH_MAX + 1]; - char title[CHART_TITLE_MAX + 1]; - - int services_do_cpu = 0, - services_do_mem_usage = 0, - services_do_mem_detailed = 0, - services_do_mem_failcnt = 0, - services_do_swap_usage = 0, - services_do_io = 0, - services_do_io_ops = 0, - services_do_throttle_io = 0, - services_do_throttle_ops = 0, - services_do_queued_ops = 0, - services_do_merged_ops = 0; +// ---------------------------------------------------------------------------- +// generate charts - struct cgroup *cg; - for(cg = cgroup_root; cg ; cg = cg->next) { - if(unlikely(!cg->enabled || cg->pending_renames)) +void update_cgroup_systemd_services_charts() { + for (struct cgroup *cg = cgroup_root; cg; cg = cg->next) { + if (unlikely(!cg->enabled || cg->pending_renames || !is_cgroup_systemd_service(cg))) continue; - if(likely(cgroup_enable_systemd_services && is_cgroup_systemd_service(cg))) { - if(cg->cpuacct_stat.updated && cg->cpuacct_stat.enabled == CONFIG_BOOLEAN_YES) services_do_cpu++; - - if(cgroup_enable_systemd_services_detailed_memory && cg->memory.updated_detailed && cg->memory.enabled_detailed) services_do_mem_detailed++; - if(cg->memory.updated_usage_in_bytes && cg->memory.enabled_usage_in_bytes == CONFIG_BOOLEAN_YES) services_do_mem_usage++; - if(cg->memory.updated_failcnt && cg->memory.enabled_failcnt == CONFIG_BOOLEAN_YES) services_do_mem_failcnt++; - if(cg->memory.updated_msw_usage_in_bytes && cg->memory.enabled_msw_usage_in_bytes == CONFIG_BOOLEAN_YES) services_do_swap_usage++; + if (likely(cg->cpuacct_stat.updated)) { + update_cpu_utilization_chart(cg); + } + if (likely(cg->memory.updated_msw_usage_in_bytes)) { + update_mem_usage_chart(cg); + } + if (likely(cg->memory.updated_failcnt)) { + update_mem_failcnt_chart(cg); + } + if (likely(cg->memory.updated_detailed)) { + update_mem_usage_detailed_chart(cg); + update_mem_writeback_chart(cg); + update_mem_pgfaults_chart(cg); + if (!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { + update_mem_activity_chart(cg); + } + } + if (likely(cg->io_service_bytes.updated)) { + update_io_serviced_bytes_chart(cg); + } + if (likely(cg->io_serviced.updated)) { + update_io_serviced_ops_chart(cg); + } + if (likely(cg->throttle_io_service_bytes.updated)) { + update_throttle_io_serviced_bytes_chart(cg); + } + if (likely(cg->throttle_io_serviced.updated)) { + update_throttle_io_serviced_ops_chart(cg); + } + if (likely(cg->io_queued.updated)) { + update_io_queued_ops_chart(cg); + } + if (likely(cg->io_merged.updated)) { + update_io_merged_ops_chart(cg); + } - if(cg->io_service_bytes.updated && cg->io_service_bytes.enabled == CONFIG_BOOLEAN_YES) services_do_io++; - if(cg->io_serviced.updated && cg->io_serviced.enabled == CONFIG_BOOLEAN_YES) services_do_io_ops++; - if(cg->throttle_io_service_bytes.updated && cg->throttle_io_service_bytes.enabled == CONFIG_BOOLEAN_YES) services_do_throttle_io++; - if(cg->throttle_io_serviced.updated && cg->throttle_io_serviced.enabled == CONFIG_BOOLEAN_YES) services_do_throttle_ops++; - if(cg->io_queued.updated && cg->io_queued.enabled == CONFIG_BOOLEAN_YES) services_do_queued_ops++; - if(cg->io_merged.updated && cg->io_merged.enabled == CONFIG_BOOLEAN_YES) services_do_merged_ops++; - continue; + if (likely(cg->pids.pids_current_updated)) { + update_pids_current_chart(cg); } - type[0] = '\0'; - - if(likely(cg->cpuacct_stat.updated && cg->cpuacct_stat.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_cpu)) { - snprintfz( - title, - CHART_TITLE_MAX, - k8s_is_kubepod(cg) ? "CPU Usage (100%% = 1000 mCPU)" : "CPU Usage (100%% = 1 core)"); - - cg->st_cpu = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu" : "cgroup.cpu" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority - , update_every - , RRDSET_TYPE_STACKED - ); - - rrdset_update_rrdlabels(cg->st_cpu, cg->chart_labels); + cg->function_ready = true; + } +} - if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - rrddim_add(cg->st_cpu, "user", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_cpu, "system", NULL, 100, system_hz, RRD_ALGORITHM_INCREMENTAL); - } - else { - rrddim_add(cg->st_cpu, "user", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_cpu, "system", NULL, 100, 1000000, RRD_ALGORITHM_INCREMENTAL); - } - } +void update_cgroup_charts() { + for (struct cgroup *cg = cgroup_root; cg; cg = cg->next) { + if(unlikely(!cg->enabled || cg->pending_renames || is_cgroup_systemd_service(cg))) + continue; - rrddim_set(cg->st_cpu, "user", cg->cpuacct_stat.user); - rrddim_set(cg->st_cpu, "system", cg->cpuacct_stat.system); - rrdset_done(cg->st_cpu); + if (likely(cg->cpuacct_stat.updated && cg->cpuacct_stat.enabled == CONFIG_BOOLEAN_YES)) { + update_cpu_utilization_chart(cg); if(likely(cg->filename_cpuset_cpus || cg->filename_cpu_cfs_period || cg->filename_cpu_cfs_quota)) { if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { @@ -3428,8 +1408,7 @@ void update_cgroup_charts(int update_every) { if(cg->filename_cpu_cfs_quota) freez(cg->filename_cpu_cfs_quota); cg->filename_cpu_cfs_quota = NULL; } - } - else { + } else { NETDATA_DOUBLE value = 0, quota = 0; if(likely( ((!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) && (cg->filename_cpuset_cpus || (cg->filename_cpu_cfs_period && cg->filename_cpu_cfs_quota))) @@ -3443,49 +1422,10 @@ void update_cgroup_charts(int update_every) { value = (NETDATA_DOUBLE)cg->cpuset_cpus * 100; } if(likely(value)) { - if(unlikely(!cg->st_cpu_limit)) { - snprintfz(title, CHART_TITLE_MAX, "CPU Usage within the limits"); - - cg->st_cpu_limit = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_limit" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_limit" : "cgroup.cpu_limit" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority - 1 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_cpu_limit, cg->chart_labels); - - if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) - rrddim_add(cg->st_cpu_limit, "used", NULL, 1, system_hz, RRD_ALGORITHM_ABSOLUTE); - else - rrddim_add(cg->st_cpu_limit, "used", NULL, 1, 1000000, RRD_ALGORITHM_ABSOLUTE); - cg->prev_cpu_usage = (NETDATA_DOUBLE)(cg->cpuacct_stat.user + cg->cpuacct_stat.system) * 100; - } - - NETDATA_DOUBLE cpu_usage = 0; - cpu_usage = (NETDATA_DOUBLE)(cg->cpuacct_stat.user + cg->cpuacct_stat.system) * 100; - NETDATA_DOUBLE cpu_used = 100 * (cpu_usage - cg->prev_cpu_usage) / (value * update_every); - - rrdset_isnot_obsolete(cg->st_cpu_limit); - - rrddim_set(cg->st_cpu_limit, "used", (cpu_used > 0)?cpu_used:0); - - cg->prev_cpu_usage = cpu_usage; - - rrdsetvar_custom_chart_variable_set(cg->st_cpu, cg->chart_var_cpu_limit, value); - rrdset_done(cg->st_cpu_limit); - } - else { - if(unlikely(cg->st_cpu_limit)) { - rrdset_is_obsolete(cg->st_cpu_limit); + update_cpu_utilization_limit_chart(cg, value); + } else { + if (unlikely(cg->st_cpu_limit)) { + rrdset_is_obsolete___safe_from_collector_thread(cg->st_cpu_limit); cg->st_cpu_limit = NULL; } rrdsetvar_custom_chart_variable_set(cg->st_cpu, cg->chart_var_cpu_limit, NAN); @@ -3495,1056 +1435,137 @@ void update_cgroup_charts(int update_every) { } if (likely(cg->cpuacct_cpu_throttling.updated && cg->cpuacct_cpu_throttling.enabled == CONFIG_BOOLEAN_YES)) { - if (unlikely(!cg->st_cpu_nr_throttled)) { - snprintfz(title, CHART_TITLE_MAX, "CPU Throttled Runnable Periods"); - - cg->st_cpu_nr_throttled = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "throttled" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.throttled" : "cgroup.throttled" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 10 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_cpu_nr_throttled, cg->chart_labels); - rrddim_add(cg->st_cpu_nr_throttled, "throttled", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); - } else { - rrddim_set(cg->st_cpu_nr_throttled, "throttled", cg->cpuacct_cpu_throttling.nr_throttled_perc); - rrdset_done(cg->st_cpu_nr_throttled); - } - - if (unlikely(!cg->st_cpu_throttled_time)) { - snprintfz(title, CHART_TITLE_MAX, "CPU Throttled Time Duration"); - - cg->st_cpu_throttled_time = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "throttled_duration" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.throttled_duration" : "cgroup.throttled_duration" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 15 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_cpu_throttled_time, cg->chart_labels); - rrddim_add(cg->st_cpu_throttled_time, "duration", NULL, 1, 1000000, RRD_ALGORITHM_INCREMENTAL); - } else { - rrddim_set(cg->st_cpu_throttled_time, "duration", cg->cpuacct_cpu_throttling.throttled_time); - rrdset_done(cg->st_cpu_throttled_time); - } + update_cpu_throttled_chart(cg); + update_cpu_throttled_duration_chart(cg); } if (likely(cg->cpuacct_cpu_shares.updated && cg->cpuacct_cpu_shares.enabled == CONFIG_BOOLEAN_YES)) { - if (unlikely(!cg->st_cpu_shares)) { - snprintfz(title, CHART_TITLE_MAX, "CPU Time Relative Share"); - - cg->st_cpu_shares = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_shares" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_shares" : "cgroup.cpu_shares" - , title - , "shares" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 20 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_cpu_shares, cg->chart_labels); - rrddim_add(cg->st_cpu_shares, "shares", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); - } else { - rrddim_set(cg->st_cpu_shares, "shares", cg->cpuacct_cpu_shares.shares); - rrdset_done(cg->st_cpu_shares); - } + update_cpu_shares_chart(cg); } - if(likely(cg->cpuacct_usage.updated && cg->cpuacct_usage.enabled == CONFIG_BOOLEAN_YES)) { - char id[RRD_ID_LENGTH_MAX + 1]; - unsigned int i; - - if(unlikely(!cg->st_cpu_per_core)) { - snprintfz( - title, - CHART_TITLE_MAX, - k8s_is_kubepod(cg) ? "CPU Usage (100%% = 1000 mCPU) Per Core" : - "CPU Usage (100%% = 1 core) Per Core"); - - cg->st_cpu_per_core = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_per_core" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_per_core" : "cgroup.cpu_per_core" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 100 - , update_every - , RRDSET_TYPE_STACKED - ); - - rrdset_update_rrdlabels(cg->st_cpu_per_core, cg->chart_labels); - - for(i = 0; i < cg->cpuacct_usage.cpus; i++) { - snprintfz(id, RRD_ID_LENGTH_MAX, "cpu%u", i); - rrddim_add(cg->st_cpu_per_core, id, NULL, 100, 1000000000, RRD_ALGORITHM_INCREMENTAL); - } - } - - for(i = 0; i < cg->cpuacct_usage.cpus ;i++) { - snprintfz(id, RRD_ID_LENGTH_MAX, "cpu%u", i); - rrddim_set(cg->st_cpu_per_core, id, cg->cpuacct_usage.cpu_percpu[i]); - } - rrdset_done(cg->st_cpu_per_core); + if (likely(cg->cpuacct_usage.updated && cg->cpuacct_usage.enabled == CONFIG_BOOLEAN_YES)) { + update_cpu_per_core_usage_chart(cg); } - if(likely(cg->memory.updated_detailed && cg->memory.enabled_detailed == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_mem)) { - snprintfz(title, CHART_TITLE_MAX, "Memory Usage"); - - cg->st_mem = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem" : "cgroup.mem" - , title - , "MiB" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 220 - , update_every - , RRDSET_TYPE_STACKED - ); - - rrdset_update_rrdlabels(cg->st_mem, cg->chart_labels); - - if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - rrddim_add(cg->st_mem, "cache", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "rss", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - - if(cg->memory.detailed_has_swap) - rrddim_add(cg->st_mem, "swap", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - - rrddim_add(cg->st_mem, "rss_huge", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "mapped_file", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } else { - rrddim_add(cg->st_mem, "anon", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "kernel_stack", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "slab", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "sock", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "anon_thp", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem, "file", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - } - - if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - rrddim_set(cg->st_mem, "cache", cg->memory.total_cache); - rrddim_set(cg->st_mem, "rss", (cg->memory.total_rss > cg->memory.total_rss_huge)?(cg->memory.total_rss - cg->memory.total_rss_huge):0); - - if(cg->memory.detailed_has_swap) - rrddim_set(cg->st_mem, "swap", cg->memory.total_swap); - - rrddim_set(cg->st_mem, "rss_huge", cg->memory.total_rss_huge); - rrddim_set(cg->st_mem, "mapped_file", cg->memory.total_mapped_file); - } else { - rrddim_set(cg->st_mem, "anon", cg->memory.anon); - rrddim_set(cg->st_mem, "kernel_stack", cg->memory.kernel_stack); - rrddim_set(cg->st_mem, "slab", cg->memory.slab); - rrddim_set(cg->st_mem, "sock", cg->memory.sock); - rrddim_set(cg->st_mem, "anon_thp", cg->memory.anon_thp); - rrddim_set(cg->st_mem, "file", cg->memory.total_mapped_file); - } - rrdset_done(cg->st_mem); - - if(unlikely(!cg->st_writeback)) { - snprintfz(title, CHART_TITLE_MAX, "Writeback Memory"); - - cg->st_writeback = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "writeback" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.writeback" : "cgroup.writeback" - , title - , "MiB" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 300 - , update_every - , RRDSET_TYPE_AREA - ); - - rrdset_update_rrdlabels(cg->st_writeback, cg->chart_labels); - - if(cg->memory.detailed_has_dirty) - rrddim_add(cg->st_writeback, "dirty", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - - rrddim_add(cg->st_writeback, "writeback", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - if(cg->memory.detailed_has_dirty) - rrddim_set(cg->st_writeback, "dirty", cg->memory.total_dirty); - - rrddim_set(cg->st_writeback, "writeback", cg->memory.total_writeback); - rrdset_done(cg->st_writeback); + if (likely(cg->memory.updated_detailed && cg->memory.enabled_detailed == CONFIG_BOOLEAN_YES)) { + update_mem_usage_detailed_chart(cg); + update_mem_writeback_chart(cg); if(!(cg->options & CGROUP_OPTIONS_IS_UNIFIED)) { - if(unlikely(!cg->st_mem_activity)) { - snprintfz(title, CHART_TITLE_MAX, "Memory Activity"); - - cg->st_mem_activity = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_activity" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem_activity" : "cgroup.mem_activity" - , title - , "MiB/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 400 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_mem_activity, cg->chart_labels); - - rrddim_add(cg->st_mem_activity, "pgpgin", "in", system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_mem_activity, "pgpgout", "out", -system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_mem_activity, "pgpgin", cg->memory.total_pgpgin); - rrddim_set(cg->st_mem_activity, "pgpgout", cg->memory.total_pgpgout); - rrdset_done(cg->st_mem_activity); - } - - if(unlikely(!cg->st_pgfaults)) { - snprintfz(title, CHART_TITLE_MAX, "Memory Page Faults"); - - cg->st_pgfaults = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "pgfaults" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.pgfaults" : "cgroup.pgfaults" - , title - , "MiB/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 500 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_pgfaults, cg->chart_labels); - - rrddim_add(cg->st_pgfaults, "pgfault", NULL, system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_pgfaults, "pgmajfault", "swap", -system_page_size, 1024 * 1024, RRD_ALGORITHM_INCREMENTAL); + update_mem_activity_chart(cg); } - rrddim_set(cg->st_pgfaults, "pgfault", cg->memory.total_pgfault); - rrddim_set(cg->st_pgfaults, "pgmajfault", cg->memory.total_pgmajfault); - rrdset_done(cg->st_pgfaults); + update_mem_pgfaults_chart(cg); } - 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"); - - cg->st_mem_usage = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_usage" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem_usage" : "cgroup.mem_usage" - , title - , "MiB" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 210 - , update_every - , RRDSET_TYPE_STACKED - ); - - rrdset_update_rrdlabels(cg->st_mem_usage, cg->chart_labels); - - rrddim_add(cg->st_mem_usage, "ram", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem_usage, "swap", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - 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.total_inactive_file) ? - cg->memory.msw_usage_in_bytes - (cg->memory.usage_in_bytes + cg->memory.total_inactive_file) : 0); - } else { - rrddim_set(cg->st_mem_usage, "swap", cg->memory.msw_usage_in_bytes); - } - rrdset_done(cg->st_mem_usage); - - if (likely(update_memory_limits(&cg->filename_memory_limit, &cg->chart_var_memory_limit, &cg->memory_limit, "memory_limit", cg))) { - static unsigned long long ram_total = 0; - - if(unlikely(!ram_total)) { - procfile *ff = NULL; - - char filename[FILENAME_MAX + 1]; - snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/proc/meminfo"); - ff = procfile_open(config_get("plugin:cgroups", "meminfo filename to monitor", filename), " \t:", PROCFILE_FLAG_DEFAULT); - - if(likely(ff)) - ff = procfile_readall(ff); - if(likely(ff && procfile_lines(ff) && !strncmp(procfile_word(ff, 0), "MemTotal", 8))) - ram_total = str2ull(procfile_word(ff, 1), NULL) * 1024; - else { - collector_error("Cannot read file %s. Will not update cgroup %s RAM limit anymore.", filename, cg->id); - freez(cg->filename_memory_limit); - cg->filename_memory_limit = NULL; - } + if (likely(cg->memory.updated_usage_in_bytes && cg->memory.enabled_usage_in_bytes == CONFIG_BOOLEAN_YES)) { + update_mem_usage_chart(cg); - procfile_close(ff); - } - - if(likely(ram_total)) { - unsigned long long memory_limit = ram_total; + // FIXME: this if should be only for unlimited charts + if(likely(host_ram_total)) { + // FIXME: do we need to update mem limits on every data collection? + if (likely(update_memory_limits(cg))) { - if(unlikely(cg->memory_limit < ram_total)) + unsigned long long memory_limit = host_ram_total; + if (unlikely(cg->memory_limit < host_ram_total)) memory_limit = cg->memory_limit; - if(unlikely(!cg->st_mem_usage_limit)) { - snprintfz(title, CHART_TITLE_MAX, "Used RAM within the limits"); - - cg->st_mem_usage_limit = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_usage_limit" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem_usage_limit": "cgroup.mem_usage_limit" - , title - , "MiB" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 200 - , update_every - , RRDSET_TYPE_STACKED - ); - - rrdset_update_rrdlabels(cg->st_mem_usage_limit, cg->chart_labels); - - rrddim_add(cg->st_mem_usage_limit, "available", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_mem_usage_limit, "used", NULL, 1, 1024 * 1024, RRD_ALGORITHM_ABSOLUTE); - } - - rrdset_isnot_obsolete(cg->st_mem_usage_limit); - - 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) - , "mem_utilization" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem_utilization" : "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_rrdlabels(cg->st_mem_utilization, cg->chart_labels); - - rrddim_add(cg->st_mem_utilization, "utilization", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); + update_mem_usage_limit_chart(cg, memory_limit); + update_mem_utilization_chart(cg, memory_limit); + } else { + if (unlikely(cg->st_mem_usage_limit)) { + rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_usage_limit); + cg->st_mem_usage_limit = NULL; } - 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); + if (unlikely(cg->st_mem_utilization)) { + rrdset_is_obsolete___safe_from_collector_thread(cg->st_mem_utilization); + cg->st_mem_utilization = NULL; } } } - else { - if(unlikely(cg->st_mem_usage_limit)) { - 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); } - if(likely(cg->memory.updated_failcnt && cg->memory.enabled_failcnt == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_mem_failcnt)) { - snprintfz(title, CHART_TITLE_MAX, "Memory Limit Failures"); - - cg->st_mem_failcnt = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_failcnt" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.mem_failcnt" : "cgroup.mem_failcnt" - , title - , "count" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 250 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_mem_failcnt, cg->chart_labels); - - rrddim_add(cg->st_mem_failcnt, "failures", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_mem_failcnt, "failures", cg->memory.failcnt); - rrdset_done(cg->st_mem_failcnt); + if (likely(cg->memory.updated_failcnt && cg->memory.enabled_failcnt == CONFIG_BOOLEAN_YES)) { + update_mem_failcnt_chart(cg); } - if(likely(cg->io_service_bytes.updated && cg->io_service_bytes.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_io)) { - snprintfz(title, CHART_TITLE_MAX, "I/O Bandwidth (all disks)"); - - cg->st_io = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "io" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.io" : "cgroup.io" - , title - , "KiB/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 1200 - , update_every - , RRDSET_TYPE_AREA - ); - - rrdset_update_rrdlabels(cg->st_io, cg->chart_labels); - - rrddim_add(cg->st_io, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_io, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_io, "read", cg->io_service_bytes.Read); - rrddim_set(cg->st_io, "write", cg->io_service_bytes.Write); - rrdset_done(cg->st_io); + if (likely(cg->io_service_bytes.updated && cg->io_service_bytes.enabled == CONFIG_BOOLEAN_YES)) { + update_io_serviced_bytes_chart(cg); } - if(likely(cg->io_serviced.updated && cg->io_serviced.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_serviced_ops)) { - snprintfz(title, CHART_TITLE_MAX, "Serviced I/O Operations (all disks)"); - - cg->st_serviced_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "serviced_ops" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.serviced_ops" : "cgroup.serviced_ops" - , title - , "operations/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 1200 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_serviced_ops, cg->chart_labels); - - rrddim_add(cg->st_serviced_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_serviced_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_serviced_ops, "read", cg->io_serviced.Read); - rrddim_set(cg->st_serviced_ops, "write", cg->io_serviced.Write); - rrdset_done(cg->st_serviced_ops); + if (likely(cg->io_serviced.updated && cg->io_serviced.enabled == CONFIG_BOOLEAN_YES)) { + update_io_serviced_ops_chart(cg); } - if(likely(cg->throttle_io_service_bytes.updated && cg->throttle_io_service_bytes.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_throttle_io)) { - snprintfz(title, CHART_TITLE_MAX, "Throttle I/O Bandwidth (all disks)"); - - cg->st_throttle_io = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "throttle_io" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.throttle_io" : "cgroup.throttle_io" - , title - , "KiB/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 1200 - , update_every - , RRDSET_TYPE_AREA - ); - - rrdset_update_rrdlabels(cg->st_throttle_io, cg->chart_labels); - - rrddim_add(cg->st_throttle_io, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_throttle_io, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_throttle_io, "read", cg->throttle_io_service_bytes.Read); - rrddim_set(cg->st_throttle_io, "write", cg->throttle_io_service_bytes.Write); - rrdset_done(cg->st_throttle_io); + if (likely(cg->throttle_io_service_bytes.updated && cg->throttle_io_service_bytes.enabled == CONFIG_BOOLEAN_YES)) { + update_throttle_io_serviced_bytes_chart(cg); } - if(likely(cg->throttle_io_serviced.updated && cg->throttle_io_serviced.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_throttle_serviced_ops)) { - snprintfz(title, CHART_TITLE_MAX, "Throttle Serviced I/O Operations (all disks)"); - - cg->st_throttle_serviced_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "throttle_serviced_ops" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.throttle_serviced_ops" : "cgroup.throttle_serviced_ops" - , title - , "operations/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 1200 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_throttle_serviced_ops, cg->chart_labels); - - rrddim_add(cg->st_throttle_serviced_ops, "read", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_throttle_serviced_ops, "write", NULL, -1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - rrddim_set(cg->st_throttle_serviced_ops, "read", cg->throttle_io_serviced.Read); - rrddim_set(cg->st_throttle_serviced_ops, "write", cg->throttle_io_serviced.Write); - rrdset_done(cg->st_throttle_serviced_ops); + if (likely(cg->throttle_io_serviced.updated && cg->throttle_io_serviced.enabled == CONFIG_BOOLEAN_YES)) { + update_throttle_io_serviced_ops_chart(cg); } - if(likely(cg->io_queued.updated && cg->io_queued.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_queued_ops)) { - snprintfz(title, CHART_TITLE_MAX, "Queued I/O Operations (all disks)"); - - cg->st_queued_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "queued_ops" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.queued_ops" : "cgroup.queued_ops" - , title - , "operations" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2000 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_queued_ops, cg->chart_labels); - - rrddim_add(cg->st_queued_ops, "read", NULL, 1, 1, RRD_ALGORITHM_ABSOLUTE); - rrddim_add(cg->st_queued_ops, "write", NULL, -1, 1, RRD_ALGORITHM_ABSOLUTE); - } - - rrddim_set(cg->st_queued_ops, "read", cg->io_queued.Read); - rrddim_set(cg->st_queued_ops, "write", cg->io_queued.Write); - rrdset_done(cg->st_queued_ops); + if (likely(cg->io_queued.updated && cg->io_queued.enabled == CONFIG_BOOLEAN_YES)) { + update_io_queued_ops_chart(cg); } - if(likely(cg->io_merged.updated && cg->io_merged.enabled == CONFIG_BOOLEAN_YES)) { - if(unlikely(!cg->st_merged_ops)) { - snprintfz(title, CHART_TITLE_MAX, "Merged I/O Operations (all disks)"); - - cg->st_merged_ops = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "merged_ops" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.merged_ops" : "cgroup.merged_ops" - , title - , "operations/s" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2100 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(cg->st_merged_ops, cg->chart_labels); - - rrddim_add(cg->st_merged_ops, "read", NULL, 1, 1024, RRD_ALGORITHM_INCREMENTAL); - rrddim_add(cg->st_merged_ops, "write", NULL, -1, 1024, RRD_ALGORITHM_INCREMENTAL); - } + if (likely(cg->io_merged.updated && cg->io_merged.enabled == CONFIG_BOOLEAN_YES)) { + update_io_merged_ops_chart(cg); + } - rrddim_set(cg->st_merged_ops, "read", cg->io_merged.Read); - rrddim_set(cg->st_merged_ops, "write", cg->io_merged.Write); - rrdset_done(cg->st_merged_ops); + if (likely(cg->pids.pids_current_updated)) { + update_pids_current_chart(cg); } if (cg->options & CGROUP_OPTIONS_IS_UNIFIED) { - struct pressure *res = &cg->cpu_pressure; - - if (likely(res->updated && res->some.enabled)) { - struct pressure_charts *pcs; - pcs = &res->some; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "CPU some pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_some_pressure" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_some_pressure" : "cgroup.cpu_some_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2200 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "CPU some pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_some_pressure_stall_time" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_some_pressure_stall_time" : "cgroup.cpu_some_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2220 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - update_pressure_charts(pcs); - } - if (likely(res->updated && res->full.enabled)) { - struct pressure_charts *pcs; - pcs = &res->full; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "CPU full pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_full_pressure" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_full_pressure" : "cgroup.cpu_full_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2240 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "CPU full pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "cpu_full_pressure_stall_time" - , NULL - , "cpu" - , k8s_is_kubepod(cg) ? "k8s.cgroup.cpu_full_pressure_stall_time" : "cgroup.cpu_full_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2260 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - update_pressure_charts(pcs); - } - - res = &cg->memory_pressure; - - if (likely(res->updated && res->some.enabled)) { - struct pressure_charts *pcs; - pcs = &res->some; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "Memory some pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_some_pressure" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.memory_some_pressure" : "cgroup.memory_some_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2300 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "Memory some pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "memory_some_pressure_stall_time" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.memory_some_pressure_stall_time" : "cgroup.memory_some_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2320 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - update_pressure_charts(pcs); - } - - if (likely(res->updated && res->full.enabled)) { - struct pressure_charts *pcs; - pcs = &res->full; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "Memory full pressure"); - - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "mem_full_pressure" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.memory_full_pressure" : "cgroup.memory_full_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2340 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "Memory full pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "memory_full_pressure_stall_time" - , NULL - , "mem" - , k8s_is_kubepod(cg) ? "k8s.cgroup.memory_full_pressure_stall_time" : "cgroup.memory_full_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2360 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - update_pressure_charts(pcs); - } - - res = &cg->irq_pressure; - - if (likely(res->updated && res->some.enabled)) { - struct pressure_charts *pcs; - pcs = &res->some; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "IRQ some pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "irq_some_pressure" - , NULL - , "interrupts" - , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure" : "cgroup.irq_some_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2310 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "IRQ some pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "irq_some_pressure_stall_time" - , NULL - , "interrupts" - , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_some_pressure_stall_time" : "cgroup.irq_some_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2330 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); - } - - update_pressure_charts(pcs); + if (likely(cg->cpu_pressure.updated)) { + if (cg->cpu_pressure.some.enabled) { + update_cpu_some_pressure_chart(cg); + update_cpu_some_pressure_stall_time_chart(cg); + } + if (cg->cpu_pressure.full.enabled) { + update_cpu_full_pressure_chart(cg); + update_cpu_full_pressure_stall_time_chart(cg); + } } - if (likely(res->updated && res->full.enabled)) { - struct pressure_charts *pcs; - pcs = &res->full; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "IRQ full pressure"); - - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "irq_full_pressure" - , NULL - , "interrupts" - , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure" : "cgroup.irq_full_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2350 - , update_every - , RRDSET_TYPE_LINE - ); - - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + if (likely(cg->memory_pressure.updated)) { + if (cg->memory_pressure.some.enabled) { + update_mem_some_pressure_chart(cg); + update_mem_some_pressure_stall_time_chart(cg); } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "IRQ full pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "irq_full_pressure_stall_time" - , NULL - , "interrupts" - , k8s_is_kubepod(cg) ? "k8s.cgroup.irq_full_pressure_stall_time" : "cgroup.irq_full_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2370 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + if (cg->memory_pressure.full.enabled) { + update_mem_full_pressure_chart(cg); + update_mem_full_pressure_stall_time_chart(cg); } - - update_pressure_charts(pcs); } - res = &cg->io_pressure; - - if (likely(res->updated && res->some.enabled)) { - struct pressure_charts *pcs; - pcs = &res->some; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "I/O some pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "io_some_pressure" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.io_some_pressure" : "cgroup.io_some_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2400 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "some 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "some 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "some 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + if (likely(cg->irq_pressure.updated)) { + if (cg->irq_pressure.some.enabled) { + update_irq_some_pressure_chart(cg); + update_irq_some_pressure_stall_time_chart(cg); } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "I/O some pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "io_some_pressure_stall_time" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.io_some_pressure_stall_time" : "cgroup.io_some_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2420 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + if (cg->irq_pressure.full.enabled) { + update_irq_full_pressure_chart(cg); + update_irq_full_pressure_stall_time_chart(cg); } - - update_pressure_charts(pcs); } - if (likely(res->updated && res->full.enabled)) { - struct pressure_charts *pcs; - pcs = &res->full; - - if (unlikely(!pcs->share_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "I/O full pressure"); - chart = pcs->share_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "io_full_pressure" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.io_full_pressure" : "cgroup.io_full_pressure" - , title - , "percentage" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2440 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->share_time.st, cg->chart_labels); - pcs->share_time.rd10 = rrddim_add(chart, "full 10", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd60 = rrddim_add(chart, "full 60", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); - pcs->share_time.rd300 = rrddim_add(chart, "full 300", NULL, 1, 100, RRD_ALGORITHM_ABSOLUTE); + if (likely(cg->io_pressure.updated)) { + if (cg->io_pressure.some.enabled) { + update_io_some_pressure_chart(cg); + update_io_some_pressure_stall_time_chart(cg); } - - if (unlikely(!pcs->total_time.st)) { - RRDSET *chart; - snprintfz(title, CHART_TITLE_MAX, "I/O full pressure stall time"); - chart = pcs->total_time.st = rrdset_create_localhost( - cgroup_chart_type(type, cg) - , "io_full_pressure_stall_time" - , NULL - , "disk" - , k8s_is_kubepod(cg) ? "k8s.cgroup.io_full_pressure_stall_time" : "cgroup.io_full_pressure_stall_time" - , title - , "ms" - , PLUGIN_CGROUPS_NAME - , PLUGIN_CGROUPS_MODULE_CGROUPS_NAME - , cgroup_containers_chart_priority + 2460 - , update_every - , RRDSET_TYPE_LINE - ); - rrdset_update_rrdlabels(chart = pcs->total_time.st, cg->chart_labels); - pcs->total_time.rdtotal = rrddim_add(chart, "time", NULL, 1, 1, RRD_ALGORITHM_INCREMENTAL); + if (cg->io_pressure.full.enabled) { + update_io_full_pressure_chart(cg); + update_io_full_pressure_stall_time_chart(cg); } - - update_pressure_charts(pcs); } } - } - - if(likely(cgroup_enable_systemd_services)) - update_systemd_services_charts(update_every, services_do_cpu, services_do_mem_usage, services_do_mem_detailed - , services_do_mem_failcnt, services_do_swap_usage, services_do_io - , services_do_io_ops, services_do_throttle_io, services_do_throttle_ops - , services_do_queued_ops, services_do_merged_ops - ); - netdata_log_debug(D_CGROUP, "done updating cgroups charts"); + cg->function_ready = true; + } } // ---------------------------------------------------------------------------- @@ -4587,6 +1608,22 @@ static void cgroup_main_cleanup(void *ptr) { static_thread->enabled = NETDATA_MAIN_THREAD_EXITED; } +void cgroup_read_host_total_ram() { + procfile *ff = NULL; + char filename[FILENAME_MAX + 1]; + snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/proc/meminfo"); + + ff = procfile_open( + config_get("plugin:cgroups", "meminfo filename to monitor", filename), " \t:", PROCFILE_FLAG_DEFAULT); + + if (likely((ff = procfile_readall(ff)) && procfile_lines(ff) && !strncmp(procfile_word(ff, 0), "MemTotal", 8))) + host_ram_total = str2ull(procfile_word(ff, 1), NULL) * 1024; + else + collector_error("Cannot read file %s. Will not create RAM limit charts.", filename); + + procfile_close(ff); +} + void *cgroups_main(void *ptr) { worker_register("CGROUPS"); worker_register_job_name(WORKER_CGROUPS_LOCK, "lock"); @@ -4601,6 +1638,9 @@ void *cgroups_main(void *ptr) { } read_cgroup_plugin_configuration(); + + cgroup_read_host_total_ram(); + netdata_cgroup_ebpf_initialize_shm(); if (uv_mutex_init(&cgroup_root_mutex)) { @@ -4624,7 +1664,15 @@ void *cgroups_main(void *ptr) { collector_error("CGROUP: cannot create thread worker. uv_thread_create(): %s", uv_strerror(error)); goto exit; } - uv_thread_set_name_np(discovery_thread.thread, "PLUGIN[cgroups]"); + + uv_thread_set_name_np(discovery_thread.thread, "P[cgroups]"); + + // we register this only on localhost + // for the other nodes, the origin server should register it + rrd_collector_started(); // this creates a collector that runs for as long as netdata runs + cgroup_netdev_link_init(); + rrd_function_add(localhost, NULL, "containers-vms", 10, RRDFUNCTIONS_CGTOP_HELP, true, cgroup_function_cgroup_top, NULL); + rrd_function_add(localhost, NULL, "systemd-services", 10, RRDFUNCTIONS_CGTOP_HELP, true, cgroup_function_systemd_top, NULL); heartbeat_t hb; heartbeat_init(&hb); @@ -4632,11 +1680,13 @@ void *cgroups_main(void *ptr) { usec_t find_every = cgroup_check_for_new_every * USEC_PER_SEC, find_dt = 0; netdata_thread_disable_cancelability(); + while(service_running(SERVICE_COLLECTORS)) { worker_is_idle(); usec_t hb_dt = heartbeat_next(&hb, step); - if(unlikely(!service_running(SERVICE_COLLECTORS))) break; + if (unlikely(!service_running(SERVICE_COLLECTORS))) + break; find_dt += hb_dt; if (unlikely(find_dt >= find_every || (!is_inside_k8s && cgroups_check))) { @@ -4652,12 +1702,18 @@ void *cgroups_main(void *ptr) { worker_is_busy(WORKER_CGROUPS_READ); read_all_discovered_cgroups(cgroup_root); + if (unlikely(!service_running(SERVICE_COLLECTORS))) { uv_mutex_unlock(&cgroup_root_mutex); break; } + worker_is_busy(WORKER_CGROUPS_CHART); - update_cgroup_charts(cgroup_update_every); + + update_cgroup_charts(); + if (cgroup_enable_systemd_services) + update_cgroup_systemd_services_charts(); + if (unlikely(!service_running(SERVICE_COLLECTORS))) { uv_mutex_unlock(&cgroup_root_mutex); break; diff --git a/collectors/cgroups.plugin/sys_fs_cgroup.h b/collectors/cgroups.plugin/sys_fs_cgroup.h index 625be755d..e8cfcf5f6 100644 --- a/collectors/cgroups.plugin/sys_fs_cgroup.h +++ b/collectors/cgroups.plugin/sys_fs_cgroup.h @@ -5,6 +5,10 @@ #include "daemon/common.h" +#define PLUGIN_CGROUPS_NAME "cgroups.plugin" +#define PLUGIN_CGROUPS_MODULE_SYSTEMD_NAME "systemd" +#define PLUGIN_CGROUPS_MODULE_CGROUPS_NAME "/sys/fs/cgroup" + #define CGROUP_OPTIONS_DISABLED_DUPLICATE 0x00000001 #define CGROUP_OPTIONS_SYSTEM_SLICE_SERVICE 0x00000002 #define CGROUP_OPTIONS_IS_UNIFIED 0x00000004 diff --git a/collectors/cgroups.plugin/tests/test_doubles.c b/collectors/cgroups.plugin/tests/test_doubles.c index 498f649f5..b13d4b19c 100644 --- a/collectors/cgroups.plugin/tests/test_doubles.c +++ b/collectors/cgroups.plugin/tests/test_doubles.c @@ -2,12 +2,12 @@ #include "test_cgroups_plugin.h" -void rrdset_is_obsolete(RRDSET *st) +void rrdset_is_obsolete___safe_from_collector_thread(RRDSET *st) { UNUSED(st); } -void rrdset_isnot_obsolete(RRDSET *st) +void rrdset_isnot_obsolete___safe_from_collector_thread(RRDSET *st) { UNUSED(st); } |