path: root/collectors/cgroups.plugin/cgroup-internals.h

#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