diff --git a/packages/system/changelog.yml b/packages/system/changelog.yml index 6b58e294c6d..f3ce306c99d 100644 --- a/packages/system/changelog.yml +++ b/packages/system/changelog.yml @@ -1,4 +1,9 @@ # newer versions go on top +- version: "1.2.0" + changes: + - description: Update fields to include new cgroups fields + type: enhancement + link: https://github.com/elastic/integrations/pull/1539 - version: "1.1.5" changes: - description: Fix Windows links diff --git a/packages/system/data_stream/process/fields/fields.yml b/packages/system/data_stream/process/fields/fields.yml index 4dc7b1aab26..f211c8ff9d3 100644 --- a/packages/system/data_stream/process/fields/fields.yml +++ b/packages/system/data_stream/process/fields/fields.yml @@ -108,327 +108,551 @@ fields: - name: id type: keyword - description: | + description: > The ID common to all cgroups associated with this task. If there isn't a common ID used by all cgroups this field will be absent. + - name: path type: keyword - description: | + description: > The path to the cgroup relative to the cgroup subsystem's mountpoint. If there isn't a common path used by all cgroups this field will be absent. + + - name: cgroups_version + type: long + description: The version of cgroups reported for the process - name: cpu type: group + description: > + The cpu subsystem schedules CPU access for tasks in the cgroup. Access can be controlled by two separate schedulers, CFS and RT. CFS stands for completely fair scheduler which proportionally divides the CPU time between cgroups based on weight. RT stands for real time scheduler which sets a maximum amount of CPU time that processes in the cgroup can consume during a given period. In CPU under cgroups V2, the cgroup is merged with many of the metrics from cpuacct. In addition, per-scheduler metrics are gone in V2. + fields: - name: id type: keyword description: ID of the cgroup. - name: path type: keyword - description: | + description: > Path to the cgroup relative to the cgroup subsystem's mountpoint. + + - name: stats + type: group + description: cgroupv2 stats + fields: + - name: usage.ns + type: long + description: cgroups v2 usage in nanoseconds + - name: usage.pct + type: float + description: cgroups v2 usage + - name: usage.norm.pct + type: float + description: cgroups v2 normalized usage + - name: user.ns + type: long + description: cgroups v2 cpu user time in nanoseconds + - name: user.pct + type: float + description: cgroups v2 cpu user time + - name: user.norm.pct + type: float + description: cgroups v2 normalized cpu user time + - name: system.ns + type: long + description: cgroups v2 system time in nanoseconds + - name: system.pct + type: float + description: cgroups v2 system time + - name: system.norm.pct + type: float + description: cgroups v2 normalized system time - name: cfs.period.us type: long - unit: micros - description: | + description: > Period of time in microseconds for how regularly a cgroup's access to CPU resources should be reallocated. + - name: cfs.quota.us type: long - unit: micros - description: | + description: > Total amount of time in microseconds for which all tasks in a cgroup can run during one period (as defined by cfs.period.us). + - name: cfs.shares type: long - description: | + description: > An integer value that specifies a relative share of CPU time available to the tasks in a cgroup. The value specified in the cpu.shares file must be 2 or higher. + - name: rt.period.us type: long - unit: micros - description: | + description: > Period of time in microseconds for how regularly a cgroup's access to CPU resources is reallocated. + - name: rt.runtime.us type: long - unit: micros - description: | + description: > Period of time in microseconds for the longest continuous period in which the tasks in a cgroup have access to CPU resources. + - name: stats.periods type: long - metric_type: counter - description: | + description: > Number of period intervals (as specified in cpu.cfs.period.us) that have elapsed. + - name: stats.throttled.periods type: long - metric_type: counter - description: | + description: > Number of times tasks in a cgroup have been throttled (that is, not allowed to run because they have exhausted all of the available time as specified by their quota). + + - name: stats.throttled.us + type: long + description: > + The total time duration (in microseconds) for which tasks in a cgroup have been throttled, as reported by cgroupsv2 + - name: stats.throttled.ns type: long - metric_type: counter - unit: nanos - description: | + description: > The total time duration (in nanoseconds) for which tasks in a cgroup have been throttled. + + - name: pressure + type: group + description: Pressure (resource contention) stats. + fields: + - name: some + type: group + description: Share of time in which at least some tasks are stalled on a given resource + fields: + - name: 10.pct + type: float + format: percent + description: Pressure over 10 seconds + - name: 60.pct + type: float + format: percent + description: Pressure over 60 seconds + - name: 300.pct + type: float + format: percent + description: Pressure over 300 seconds + - name: total + type: long + format: percent + description: total Some pressure time + - name: full + type: group + description: Share of time in which all non-idle tasks are stalled on a given resource simultaneously + fields: + - name: 10.pct + type: float + format: percent + description: Pressure over 10 seconds + - name: 60.pct + type: float + format: percent + description: Pressure over 60 seconds + - name: 300.pct + type: float + format: percent + description: Pressure over 300 seconds + - name: total + type: long + description: total Full pressure time - name: cpuacct type: group + description: CPU accounting metrics. fields: - name: id type: keyword description: ID of the cgroup. - name: path type: keyword - description: | + description: > Path to the cgroup relative to the cgroup subsystem's mountpoint. + - name: total.ns type: long - metric_type: counter - unit: nanos - description: | + description: > Total CPU time in nanoseconds consumed by all tasks in the cgroup. + + - name: total.pct + type: scaled_float + description: > + CPU time of the cgroup as a percentage of overall CPU time. + + - name: total.norm.pct + type: scaled_float + description: > + CPU time of the cgroup as a percentage of overall CPU time, normalized by CPU count. This is functionally an average of time spent across individual CPUs. + - name: stats.user.ns type: long - metric_type: counter - unit: nanos description: CPU time consumed by tasks in user mode. + - name: stats.user.pct + type: scaled_float + description: time the cgroup spent in user space, as a percentage of total CPU time + - name: stats.user.norm.pct + type: scaled_float + description: time the cgroup spent in user space, as a percentage of total CPU time, normalized by CPU count. - name: stats.system.ns type: long - metric_type: counter - unit: nanos description: CPU time consumed by tasks in user (kernel) mode. + - name: stats.system.pct + type: scaled_float + description: Time the cgroup spent in kernel space, as a percentage of total CPU time + - name: stats.system.norm.pct + type: scaled_float + description: Time the cgroup spent in kernel space, as a percentage of total CPU time, normalized by CPU count. - name: percpu type: object - description: | + object_type: long + description: > CPU time (in nanoseconds) consumed on each CPU by all tasks in this cgroup. + - name: memory type: group + description: Memory limits and metrics. fields: - name: id type: keyword description: ID of the cgroup. - name: path type: keyword - description: | + description: > Path to the cgroup relative to the cgroup subsystem's mountpoint. + - name: mem.usage.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Total memory usage by processes in the cgroup (in bytes). + - name: mem.usage.max.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum memory used by processes in the cgroup (in bytes). + - name: mem.limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum amount of user memory in bytes (including file cache) that tasks in the cgroup are allowed to use. + - name: mem.failures type: long - description: | + description: > The number of times that the memory limit (mem.limit.bytes) was reached. + + - name: mem.low.bytes + type: long + format: bytes + description: memory low threshhold + - name: mem.high.bytes + type: long + format: bytes + description: memory high threshhold + - name: mem.max.bytes + type: long + format: bytes + description: memory max threshhold + - name: mem.events + type: group + description: number of times the controller tripped a given usage level + fields: + - name: low + type: long + description: low threshold + - name: high + type: long + description: high threshold + - name: max + type: long + description: max threshold + - name: oom + type: long + description: oom threshold + - name: oom_kill + type: long + description: oom killer threshold + - name: fail + type: long + description: failed threshold - name: memsw.usage.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The sum of current memory usage plus swap space used by processes in the cgroup (in bytes). + - name: memsw.usage.max.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum amount of memory and swap space used by processes in the cgroup (in bytes). + - name: memsw.limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum amount for the sum of memory and swap usage that tasks in the cgroup are allowed to use. + + - name: memsw.low.bytes + type: long + format: bytes + description: memory low threshhold + - name: memsw.high.bytes + type: long + format: bytes + description: memory high threshhold + - name: memsw.max.bytes + type: long + format: bytes + description: memory max threshhold - name: memsw.failures type: long - unit: byte - metric_type: gauge - description: | + description: > The number of times that the memory plus swap space limit (memsw.limit.bytes) was reached. + + - name: memsw.events + type: group + description: number of times the controller tripped a given usage level + fields: + - name: low + type: long + description: low threshold + - name: high + type: long + description: high threshold + - name: max + type: long + description: max threshold + - name: oom + type: long + description: oom threshold + - name: oom_kill + type: long + description: oom killer threshold + - name: fail + type: long + description: failed threshold - name: kmem.usage.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Total kernel memory usage by processes in the cgroup (in bytes). + - name: kmem.usage.max.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum kernel memory used by processes in the cgroup (in bytes). + - name: kmem.limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum amount of kernel memory that tasks in the cgroup are allowed to use. + - name: kmem.failures type: long - metric_type: counter - description: | + description: > The number of times that the memory limit (kmem.limit.bytes) was reached. + - name: kmem_tcp.usage.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Total memory usage for TCP buffers in bytes. + - name: kmem_tcp.usage.max.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum memory used for TCP buffers by processes in the cgroup (in bytes). + - name: kmem_tcp.limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > The maximum amount of memory for TCP buffers that tasks in the cgroup are allowed to use. + - name: kmem_tcp.failures type: long - metric_type: counter - description: | + description: > The number of times that the memory limit (kmem_tcp.limit.bytes) was reached. + + - name: stats.* + type: object + description: detailed memory IO stats + - name: stats.*.bytes + type: object + description: detailed memory IO stats - name: stats.active_anon.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs (shmem), in bytes. + - name: stats.active_file.bytes type: long format: bytes - unit: byte - metric_type: gauge description: File-backed memory on active LRU list, in bytes. - name: stats.cache.bytes type: long format: bytes - unit: byte - metric_type: gauge description: Page cache, including tmpfs (shmem), in bytes. - name: stats.hierarchical_memory_limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Memory limit for the hierarchy that contains the memory cgroup, in bytes. + - name: stats.hierarchical_memsw_limit.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Memory plus swap limit for the hierarchy that contains the memory cgroup, in bytes. + - name: stats.inactive_anon.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Anonymous and swap cache on inactive LRU list, including tmpfs (shmem), in bytes + - name: stats.inactive_file.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > File-backed memory on inactive LRU list, in bytes. + - name: stats.mapped_file.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Size of memory-mapped mapped files, including tmpfs (shmem), in bytes. + - name: stats.page_faults type: long - metric_type: counter - description: | + description: > Number of times that a process in the cgroup triggered a page fault. + - name: stats.major_page_faults type: long - metric_type: counter - description: | + description: > Number of times that a process in the cgroup triggered a major fault. "Major" faults happen when the kernel actually has to read the data from disk. + - name: stats.pages_in type: long - metric_type: counter - description: | + description: > Number of pages paged into memory. This is a counter. + - name: stats.pages_out type: long - metric_type: counter - description: | + description: > Number of pages paged out of memory. This is a counter. + - name: stats.rss.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Anonymous and swap cache (includes transparent hugepages), not including tmpfs (shmem), in bytes. + - name: stats.rss_huge.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Number of bytes of anonymous transparent hugepages. + - name: stats.swap.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Swap usage, in bytes. + - name: stats.unevictable.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Memory that cannot be reclaimed, in bytes. + - name: blkio type: group + description: Block IO metrics. fields: - name: id type: keyword description: ID of the cgroup. - name: path type: keyword - description: | + description: > Path to the cgroup relative to the cgroup subsystems mountpoint. + - name: total.bytes type: long format: bytes - unit: byte - metric_type: gauge - description: | + description: > Total number of bytes transferred to and from all block devices by processes in the cgroup. + - name: total.ios type: long - metric_type: counter - description: | + description: > Total number of I/O operations performed on all devices by processes in the cgroup as seen by the throttling policy. + + - name: io + type: group + description: cgroup V2 IO Metrics, replacing blkio. + fields: + - name: id + type: keyword + description: ID of the cgroup. + - name: path + type: keyword + description: > + Path to the cgroup relative to the cgroup subsystems mountpoint. + + - name: stats.* + type: object + description: per-device IO usage stats + - name: stats.*.* + type: object + - name: stats.*.*.bytes + type: object + description: per-device IO usage stats + - name: stats.*.*.ios + type: object + description: per-device IO usage stats + - name: pressure + type: group + description: Pressure (resource contention) stats. + fields: + - name: full + type: group + description: Share of time in which at least some tasks are stalled on a given resource + fields: + - name: 10.pct + type: float + format: percent + description: Pressure over 10 seconds + - name: 60.pct + type: float + format: percent + description: Pressure over 60 seconds + - name: 300.pct + type: float + format: percent + description: Pressure over 300 seconds + - name: total + type: long + description: total Some pressure time + - name: some + type: group + description: Share of time in which all tasks are stalled on a given resource + fields: + - name: 10.pct + type: float + format: percent + description: Pressure over 10 seconds + - name: 60.pct + type: float + format: percent + description: Pressure over 60 seconds + - name: 300.pct + type: float + description: Pressure over 300 seconds + - name: total + type: long + description: total Some pressure time diff --git a/packages/system/docs/README.md b/packages/system/docs/README.md index 05145f9bd30..856492215ec 100644 --- a/packages/system/docs/README.md +++ b/packages/system/docs/README.md @@ -1613,59 +1613,118 @@ This dataset is available on: | process.working_directory | The working directory of the process. | keyword | | | | system.process.cgroup.blkio.id | ID of the cgroup. | keyword | | | | system.process.cgroup.blkio.path | Path to the cgroup relative to the cgroup subsystems mountpoint. | keyword | | | -| system.process.cgroup.blkio.total.bytes | Total number of bytes transferred to and from all block devices by processes in the cgroup. | long | byte | gauge | -| system.process.cgroup.blkio.total.ios | Total number of I/O operations performed on all devices by processes in the cgroup as seen by the throttling policy. | long | | counter | -| system.process.cgroup.cpu.cfs.period.us | Period of time in microseconds for how regularly a cgroup's access to CPU resources should be reallocated. | long | micros | | -| system.process.cgroup.cpu.cfs.quota.us | Total amount of time in microseconds for which all tasks in a cgroup can run during one period (as defined by cfs.period.us). | long | micros | | +| system.process.cgroup.blkio.total.bytes | Total number of bytes transferred to and from all block devices by processes in the cgroup. | long | | | +| system.process.cgroup.blkio.total.ios | Total number of I/O operations performed on all devices by processes in the cgroup as seen by the throttling policy. | long | | | +| system.process.cgroup.cgroups_version | The version of cgroups reported for the process | long | | | +| system.process.cgroup.cpu.cfs.period.us | Period of time in microseconds for how regularly a cgroup's access to CPU resources should be reallocated. | long | | | +| system.process.cgroup.cpu.cfs.quota.us | Total amount of time in microseconds for which all tasks in a cgroup can run during one period (as defined by cfs.period.us). | long | | | | system.process.cgroup.cpu.cfs.shares | An integer value that specifies a relative share of CPU time available to the tasks in a cgroup. The value specified in the cpu.shares file must be 2 or higher. | long | | | | system.process.cgroup.cpu.id | ID of the cgroup. | keyword | | | | system.process.cgroup.cpu.path | Path to the cgroup relative to the cgroup subsystem's mountpoint. | keyword | | | -| system.process.cgroup.cpu.rt.period.us | Period of time in microseconds for how regularly a cgroup's access to CPU resources is reallocated. | long | micros | | -| system.process.cgroup.cpu.rt.runtime.us | Period of time in microseconds for the longest continuous period in which the tasks in a cgroup have access to CPU resources. | long | micros | | -| system.process.cgroup.cpu.stats.periods | Number of period intervals (as specified in cpu.cfs.period.us) that have elapsed. | long | | counter | -| system.process.cgroup.cpu.stats.throttled.ns | The total time duration (in nanoseconds) for which tasks in a cgroup have been throttled. | long | nanos | counter | -| system.process.cgroup.cpu.stats.throttled.periods | Number of times tasks in a cgroup have been throttled (that is, not allowed to run because they have exhausted all of the available time as specified by their quota). | long | | counter | +| system.process.cgroup.cpu.pressure.full.10.pct | Pressure over 10 seconds | float | | | +| system.process.cgroup.cpu.pressure.full.300.pct | Pressure over 300 seconds | float | | | +| system.process.cgroup.cpu.pressure.full.60.pct | Pressure over 60 seconds | float | | | +| system.process.cgroup.cpu.pressure.full.total | total Full pressure time | long | | | +| system.process.cgroup.cpu.pressure.some.10.pct | Pressure over 10 seconds | float | | | +| system.process.cgroup.cpu.pressure.some.300.pct | Pressure over 300 seconds | float | | | +| system.process.cgroup.cpu.pressure.some.60.pct | Pressure over 60 seconds | float | | | +| system.process.cgroup.cpu.pressure.some.total | total Some pressure time | long | | | +| system.process.cgroup.cpu.rt.period.us | Period of time in microseconds for how regularly a cgroup's access to CPU resources is reallocated. | long | | | +| system.process.cgroup.cpu.rt.runtime.us | Period of time in microseconds for the longest continuous period in which the tasks in a cgroup have access to CPU resources. | long | | | +| system.process.cgroup.cpu.stats.periods | Number of period intervals (as specified in cpu.cfs.period.us) that have elapsed. | long | | | +| system.process.cgroup.cpu.stats.system.norm.pct | cgroups v2 normalized system time | float | | | +| system.process.cgroup.cpu.stats.system.ns | cgroups v2 system time in nanoseconds | long | | | +| system.process.cgroup.cpu.stats.system.pct | cgroups v2 system time | float | | | +| system.process.cgroup.cpu.stats.throttled.ns | The total time duration (in nanoseconds) for which tasks in a cgroup have been throttled. | long | | | +| system.process.cgroup.cpu.stats.throttled.periods | Number of times tasks in a cgroup have been throttled (that is, not allowed to run because they have exhausted all of the available time as specified by their quota). | long | | | +| system.process.cgroup.cpu.stats.throttled.us | The total time duration (in microseconds) for which tasks in a cgroup have been throttled, as reported by cgroupsv2 | long | | | +| system.process.cgroup.cpu.stats.usage.norm.pct | cgroups v2 normalized usage | float | | | +| system.process.cgroup.cpu.stats.usage.ns | cgroups v2 usage in nanoseconds | long | | | +| system.process.cgroup.cpu.stats.usage.pct | cgroups v2 usage | float | | | +| system.process.cgroup.cpu.stats.user.norm.pct | cgroups v2 normalized cpu user time | float | | | +| system.process.cgroup.cpu.stats.user.ns | cgroups v2 cpu user time in nanoseconds | long | | | +| system.process.cgroup.cpu.stats.user.pct | cgroups v2 cpu user time | float | | | | system.process.cgroup.cpuacct.id | ID of the cgroup. | keyword | | | | system.process.cgroup.cpuacct.path | Path to the cgroup relative to the cgroup subsystem's mountpoint. | keyword | | | | system.process.cgroup.cpuacct.percpu | CPU time (in nanoseconds) consumed on each CPU by all tasks in this cgroup. | object | | | -| system.process.cgroup.cpuacct.stats.system.ns | CPU time consumed by tasks in user (kernel) mode. | long | nanos | counter | -| system.process.cgroup.cpuacct.stats.user.ns | CPU time consumed by tasks in user mode. | long | nanos | counter | -| system.process.cgroup.cpuacct.total.ns | Total CPU time in nanoseconds consumed by all tasks in the cgroup. | long | nanos | counter | +| system.process.cgroup.cpuacct.stats.system.norm.pct | Time the cgroup spent in kernel space, as a percentage of total CPU time, normalized by CPU count. | scaled_float | | | +| system.process.cgroup.cpuacct.stats.system.ns | CPU time consumed by tasks in user (kernel) mode. | long | | | +| system.process.cgroup.cpuacct.stats.system.pct | Time the cgroup spent in kernel space, as a percentage of total CPU time | scaled_float | | | +| system.process.cgroup.cpuacct.stats.user.norm.pct | time the cgroup spent in user space, as a percentage of total CPU time, normalized by CPU count. | scaled_float | | | +| system.process.cgroup.cpuacct.stats.user.ns | CPU time consumed by tasks in user mode. | long | | | +| system.process.cgroup.cpuacct.stats.user.pct | time the cgroup spent in user space, as a percentage of total CPU time | scaled_float | | | +| system.process.cgroup.cpuacct.total.norm.pct | CPU time of the cgroup as a percentage of overall CPU time, normalized by CPU count. This is functionally an average of time spent across individual CPUs. | scaled_float | | | +| system.process.cgroup.cpuacct.total.ns | Total CPU time in nanoseconds consumed by all tasks in the cgroup. | long | | | +| system.process.cgroup.cpuacct.total.pct | CPU time of the cgroup as a percentage of overall CPU time. | scaled_float | | | | system.process.cgroup.id | The ID common to all cgroups associated with this task. If there isn't a common ID used by all cgroups this field will be absent. | keyword | | | +| system.process.cgroup.io.id | ID of the cgroup. | keyword | | | +| system.process.cgroup.io.path | Path to the cgroup relative to the cgroup subsystems mountpoint. | keyword | | | +| system.process.cgroup.io.pressure.full.10.pct | Pressure over 10 seconds | float | | | +| system.process.cgroup.io.pressure.full.300.pct | Pressure over 300 seconds | float | | | +| system.process.cgroup.io.pressure.full.60.pct | Pressure over 60 seconds | float | | | +| system.process.cgroup.io.pressure.full.total | total Some pressure time | long | | | +| system.process.cgroup.io.pressure.some.10.pct | Pressure over 10 seconds | float | | | +| system.process.cgroup.io.pressure.some.300.pct | Pressure over 300 seconds | float | | | +| system.process.cgroup.io.pressure.some.60.pct | Pressure over 60 seconds | float | | | +| system.process.cgroup.io.pressure.some.total | total Some pressure time | long | | | +| system.process.cgroup.io.stats.\* | per-device IO usage stats | object | | | +| system.process.cgroup.io.stats.\*.\* | | object | | | +| system.process.cgroup.io.stats.\*.\*.bytes | per-device IO usage stats | object | | | +| system.process.cgroup.io.stats.\*.\*.ios | per-device IO usage stats | object | | | | system.process.cgroup.memory.id | ID of the cgroup. | keyword | | | -| system.process.cgroup.memory.kmem.failures | The number of times that the memory limit (kmem.limit.bytes) was reached. | long | | counter | -| system.process.cgroup.memory.kmem.limit.bytes | The maximum amount of kernel memory that tasks in the cgroup are allowed to use. | long | byte | gauge | -| system.process.cgroup.memory.kmem.usage.bytes | Total kernel memory usage by processes in the cgroup (in bytes). | long | byte | gauge | -| system.process.cgroup.memory.kmem.usage.max.bytes | The maximum kernel memory used by processes in the cgroup (in bytes). | long | byte | gauge | -| system.process.cgroup.memory.kmem_tcp.failures | The number of times that the memory limit (kmem_tcp.limit.bytes) was reached. | long | | counter | -| system.process.cgroup.memory.kmem_tcp.limit.bytes | The maximum amount of memory for TCP buffers that tasks in the cgroup are allowed to use. | long | byte | gauge | -| system.process.cgroup.memory.kmem_tcp.usage.bytes | Total memory usage for TCP buffers in bytes. | long | byte | gauge | -| system.process.cgroup.memory.kmem_tcp.usage.max.bytes | The maximum memory used for TCP buffers by processes in the cgroup (in bytes). | long | byte | gauge | +| system.process.cgroup.memory.kmem.failures | The number of times that the memory limit (kmem.limit.bytes) was reached. | long | | | +| system.process.cgroup.memory.kmem.limit.bytes | The maximum amount of kernel memory that tasks in the cgroup are allowed to use. | long | | | +| system.process.cgroup.memory.kmem.usage.bytes | Total kernel memory usage by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.kmem.usage.max.bytes | The maximum kernel memory used by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.kmem_tcp.failures | The number of times that the memory limit (kmem_tcp.limit.bytes) was reached. | long | | | +| system.process.cgroup.memory.kmem_tcp.limit.bytes | The maximum amount of memory for TCP buffers that tasks in the cgroup are allowed to use. | long | | | +| system.process.cgroup.memory.kmem_tcp.usage.bytes | Total memory usage for TCP buffers in bytes. | long | | | +| system.process.cgroup.memory.kmem_tcp.usage.max.bytes | The maximum memory used for TCP buffers by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.mem.events.fail | failed threshold | long | | | +| system.process.cgroup.memory.mem.events.high | high threshold | long | | | +| system.process.cgroup.memory.mem.events.low | low threshold | long | | | +| system.process.cgroup.memory.mem.events.max | max threshold | long | | | +| system.process.cgroup.memory.mem.events.oom | oom threshold | long | | | +| system.process.cgroup.memory.mem.events.oom_kill | oom killer threshold | long | | | | system.process.cgroup.memory.mem.failures | The number of times that the memory limit (mem.limit.bytes) was reached. | long | | | -| system.process.cgroup.memory.mem.limit.bytes | The maximum amount of user memory in bytes (including file cache) that tasks in the cgroup are allowed to use. | long | byte | gauge | -| system.process.cgroup.memory.mem.usage.bytes | Total memory usage by processes in the cgroup (in bytes). | long | byte | gauge | -| system.process.cgroup.memory.mem.usage.max.bytes | The maximum memory used by processes in the cgroup (in bytes). | long | byte | gauge | -| system.process.cgroup.memory.memsw.failures | The number of times that the memory plus swap space limit (memsw.limit.bytes) was reached. | long | byte | gauge | -| system.process.cgroup.memory.memsw.limit.bytes | The maximum amount for the sum of memory and swap usage that tasks in the cgroup are allowed to use. | long | byte | gauge | -| system.process.cgroup.memory.memsw.usage.bytes | The sum of current memory usage plus swap space used by processes in the cgroup (in bytes). | long | byte | gauge | -| system.process.cgroup.memory.memsw.usage.max.bytes | The maximum amount of memory and swap space used by processes in the cgroup (in bytes). | long | byte | gauge | +| system.process.cgroup.memory.mem.high.bytes | memory high threshhold | long | | | +| system.process.cgroup.memory.mem.limit.bytes | The maximum amount of user memory in bytes (including file cache) that tasks in the cgroup are allowed to use. | long | | | +| system.process.cgroup.memory.mem.low.bytes | memory low threshhold | long | | | +| system.process.cgroup.memory.mem.max.bytes | memory max threshhold | long | | | +| system.process.cgroup.memory.mem.usage.bytes | Total memory usage by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.mem.usage.max.bytes | The maximum memory used by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.memsw.events.fail | failed threshold | long | | | +| system.process.cgroup.memory.memsw.events.high | high threshold | long | | | +| system.process.cgroup.memory.memsw.events.low | low threshold | long | | | +| system.process.cgroup.memory.memsw.events.max | max threshold | long | | | +| system.process.cgroup.memory.memsw.events.oom | oom threshold | long | | | +| system.process.cgroup.memory.memsw.events.oom_kill | oom killer threshold | long | | | +| system.process.cgroup.memory.memsw.failures | The number of times that the memory plus swap space limit (memsw.limit.bytes) was reached. | long | | | +| system.process.cgroup.memory.memsw.high.bytes | memory high threshhold | long | | | +| system.process.cgroup.memory.memsw.limit.bytes | The maximum amount for the sum of memory and swap usage that tasks in the cgroup are allowed to use. | long | | | +| system.process.cgroup.memory.memsw.low.bytes | memory low threshhold | long | | | +| system.process.cgroup.memory.memsw.max.bytes | memory max threshhold | long | | | +| system.process.cgroup.memory.memsw.usage.bytes | The sum of current memory usage plus swap space used by processes in the cgroup (in bytes). | long | | | +| system.process.cgroup.memory.memsw.usage.max.bytes | The maximum amount of memory and swap space used by processes in the cgroup (in bytes). | long | | | | system.process.cgroup.memory.path | Path to the cgroup relative to the cgroup subsystem's mountpoint. | keyword | | | -| system.process.cgroup.memory.stats.active_anon.bytes | Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs (shmem), in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.active_file.bytes | File-backed memory on active LRU list, in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.cache.bytes | Page cache, including tmpfs (shmem), in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.hierarchical_memory_limit.bytes | Memory limit for the hierarchy that contains the memory cgroup, in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.hierarchical_memsw_limit.bytes | Memory plus swap limit for the hierarchy that contains the memory cgroup, in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.inactive_anon.bytes | Anonymous and swap cache on inactive LRU list, including tmpfs (shmem), in bytes | long | byte | gauge | -| system.process.cgroup.memory.stats.inactive_file.bytes | File-backed memory on inactive LRU list, in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.major_page_faults | Number of times that a process in the cgroup triggered a major fault. "Major" faults happen when the kernel actually has to read the data from disk. | long | | counter | -| system.process.cgroup.memory.stats.mapped_file.bytes | Size of memory-mapped mapped files, including tmpfs (shmem), in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.page_faults | Number of times that a process in the cgroup triggered a page fault. | long | | counter | -| system.process.cgroup.memory.stats.pages_in | Number of pages paged into memory. This is a counter. | long | | counter | -| system.process.cgroup.memory.stats.pages_out | Number of pages paged out of memory. This is a counter. | long | | counter | -| system.process.cgroup.memory.stats.rss.bytes | Anonymous and swap cache (includes transparent hugepages), not including tmpfs (shmem), in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.rss_huge.bytes | Number of bytes of anonymous transparent hugepages. | long | byte | gauge | -| system.process.cgroup.memory.stats.swap.bytes | Swap usage, in bytes. | long | byte | gauge | -| system.process.cgroup.memory.stats.unevictable.bytes | Memory that cannot be reclaimed, in bytes. | long | byte | gauge | +| system.process.cgroup.memory.stats.\* | detailed memory IO stats | object | | | +| system.process.cgroup.memory.stats.\*.bytes | detailed memory IO stats | object | | | +| system.process.cgroup.memory.stats.active_anon.bytes | Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs (shmem), in bytes. | long | | | +| system.process.cgroup.memory.stats.active_file.bytes | File-backed memory on active LRU list, in bytes. | long | | | +| system.process.cgroup.memory.stats.cache.bytes | Page cache, including tmpfs (shmem), in bytes. | long | | | +| system.process.cgroup.memory.stats.hierarchical_memory_limit.bytes | Memory limit for the hierarchy that contains the memory cgroup, in bytes. | long | | | +| system.process.cgroup.memory.stats.hierarchical_memsw_limit.bytes | Memory plus swap limit for the hierarchy that contains the memory cgroup, in bytes. | long | | | +| system.process.cgroup.memory.stats.inactive_anon.bytes | Anonymous and swap cache on inactive LRU list, including tmpfs (shmem), in bytes | long | | | +| system.process.cgroup.memory.stats.inactive_file.bytes | File-backed memory on inactive LRU list, in bytes. | long | | | +| system.process.cgroup.memory.stats.major_page_faults | Number of times that a process in the cgroup triggered a major fault. "Major" faults happen when the kernel actually has to read the data from disk. | long | | | +| system.process.cgroup.memory.stats.mapped_file.bytes | Size of memory-mapped mapped files, including tmpfs (shmem), in bytes. | long | | | +| system.process.cgroup.memory.stats.page_faults | Number of times that a process in the cgroup triggered a page fault. | long | | | +| system.process.cgroup.memory.stats.pages_in | Number of pages paged into memory. This is a counter. | long | | | +| system.process.cgroup.memory.stats.pages_out | Number of pages paged out of memory. This is a counter. | long | | | +| system.process.cgroup.memory.stats.rss.bytes | Anonymous and swap cache (includes transparent hugepages), not including tmpfs (shmem), in bytes. | long | | | +| system.process.cgroup.memory.stats.rss_huge.bytes | Number of bytes of anonymous transparent hugepages. | long | | | +| system.process.cgroup.memory.stats.swap.bytes | Swap usage, in bytes. | long | | | +| system.process.cgroup.memory.stats.unevictable.bytes | Memory that cannot be reclaimed, in bytes. | long | | | | system.process.cgroup.path | The path to the cgroup relative to the cgroup subsystem's mountpoint. If there isn't a common path used by all cgroups this field will be absent. | keyword | | | | system.process.cmdline | The full command-line used to start the process, including the arguments separated by space. | keyword | | | | system.process.cpu.start_time | The time when the process was started. | date | | | diff --git a/packages/system/manifest.yml b/packages/system/manifest.yml index c5865662b46..a3a8418347c 100644 --- a/packages/system/manifest.yml +++ b/packages/system/manifest.yml @@ -1,7 +1,7 @@ format_version: 1.0.0 name: system title: System -version: 1.1.5 +version: 1.2.0 license: basic description: This Elastic integration collects logs and metrics from your servers type: integration