diff options
Diffstat (limited to 'collectors/proc.plugin')
35 files changed, 4040 insertions, 0 deletions
diff --git a/collectors/proc.plugin/integrations/amd_gpu.md b/collectors/proc.plugin/integrations/amd_gpu.md new file mode 100644 index 0000000000..2b83867ee3 --- /dev/null +++ b/collectors/proc.plugin/integrations/amd_gpu.md @@ -0,0 +1,105 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/amd_gpu.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "AMD GPU" +learn_status: "Published" +learn_rel_path: "Data Collection/Hardware Devices and Sensors" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# AMD GPU + +Plugin: proc.plugin +Module: /sys/class/drm + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This integration monitors AMD GPU metrics, such as utilization, clock frequency and memory usage. + +It reads `/sys/class/drm` to collect metrics for every AMD GPU card instance it encounters. + +This collector is only supported on the following platforms: + +- Linux + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per gpu + +These metrics refer to the GPU. + +Labels: + +| Label | Description | +|:-----------|:----------------| +| product_name | GPU product name (e.g. AMD RX 6600) | + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| amdgpu.gpu_utilization | utilization | percentage | +| amdgpu.gpu_mem_utilization | utilization | percentage | +| amdgpu.gpu_clk_frequency | frequency | MHz | +| amdgpu.gpu_mem_clk_frequency | frequency | MHz | +| amdgpu.gpu_mem_vram_usage_perc | usage | percentage | +| amdgpu.gpu_mem_vram_usage | free, used | bytes | +| amdgpu.gpu_mem_vis_vram_usage_perc | usage | percentage | +| amdgpu.gpu_mem_vis_vram_usage | free, used | bytes | +| amdgpu.gpu_mem_gtt_usage_perc | usage | percentage | +| amdgpu.gpu_mem_gtt_usage | free, used | bytes | + + + +## Alerts + +There are no alerts configured by default for this integration. + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/btrfs.md b/collectors/proc.plugin/integrations/btrfs.md new file mode 100644 index 0000000000..1568d8dc02 --- /dev/null +++ b/collectors/proc.plugin/integrations/btrfs.md @@ -0,0 +1,132 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/btrfs.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "BTRFS" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/Filesystem/BTRFS" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# BTRFS + +Plugin: proc.plugin +Module: /sys/fs/btrfs + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This integration provides usage and error statistics from the BTRFS filesystem. + + + +This collector is supported on all platforms. + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per btrfs filesystem + + + +Labels: + +| Label | Description | +|:-----------|:----------------| +| filesystem_uuid | TBD | +| filesystem_label | TBD | + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| btrfs.disk | unallocated, data_free, data_used, meta_free, meta_used, sys_free, sys_used | MiB | +| btrfs.data | free, used | MiB | +| btrfs.metadata | free, used, reserved | MiB | +| btrfs.system | free, used | MiB | +| btrfs.commits | commits | commits | +| btrfs.commits_perc_time | commits | percentage | +| btrfs.commit_timings | last, max | ms | + +### Per btrfs device + + + +Labels: + +| Label | Description | +|:-----------|:----------------| +| device_id | TBD | +| filesystem_uuid | TBD | +| filesystem_label | TBD | + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| btrfs.device_errors | write_errs, read_errs, flush_errs, corruption_errs, generation_errs | errors | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ btrfs_allocated ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.disk | percentage of allocated BTRFS physical disk space | +| [ btrfs_data ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.data | utilization of BTRFS data space | +| [ btrfs_metadata ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.metadata | utilization of BTRFS metadata space | +| [ btrfs_system ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.system | utilization of BTRFS system space | +| [ btrfs_device_read_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.device_errors | number of encountered BTRFS read errors | +| [ btrfs_device_write_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.device_errors | number of encountered BTRFS write errors | +| [ btrfs_device_flush_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.device_errors | number of encountered BTRFS flush errors | +| [ btrfs_device_corruption_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.device_errors | number of encountered BTRFS corruption errors | +| [ btrfs_device_generation_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/btrfs.conf) | btrfs.device_errors | number of encountered BTRFS generation errors | + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/conntrack.md b/collectors/proc.plugin/integrations/conntrack.md new file mode 100644 index 0000000000..5cd806c8bd --- /dev/null +++ b/collectors/proc.plugin/integrations/conntrack.md @@ -0,0 +1,100 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/conntrack.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "Conntrack" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/Firewall" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# Conntrack + +Plugin: proc.plugin +Module: /proc/net/stat/nf_conntrack + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This integration monitors the connection tracking mechanism of Netfilter in the Linux Kernel. + + + +This collector is supported on all platforms. + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per Conntrack instance + + + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| netfilter.conntrack_sockets | connections | active connections | +| netfilter.conntrack_new | new, ignore, invalid | connections/s | +| netfilter.conntrack_changes | inserted, deleted, delete_list | changes/s | +| netfilter.conntrack_expect | created, deleted, new | expectations/s | +| netfilter.conntrack_search | searched, restarted, found | searches/s | +| netfilter.conntrack_errors | icmp_error, error_failed, drop, early_drop | events/s | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ netfilter_conntrack_full ](https://github.com/netdata/netdata/blob/master/health/health.d/netfilter.conf) | netfilter.conntrack_sockets | netfilter connection tracker table size utilization | + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/disk_statistics.md b/collectors/proc.plugin/integrations/disk_statistics.md new file mode 100644 index 0000000000..f1499fddbd --- /dev/null +++ b/collectors/proc.plugin/integrations/disk_statistics.md @@ -0,0 +1,144 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/disk_statistics.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "Disk Statistics" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/Disk" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# Disk Statistics + +Plugin: proc.plugin +Module: /proc/diskstats + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +Detailed statistics for each of your system's disk devices and partitions. +The data is reported by the kernel and can be used to monitor disk activity on a Linux system. + +Get valuable insight into how your disks are performing and where potential bottlenecks might be. + + + + +This collector is supported on all platforms. + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per Disk Statistics instance + + + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| system.io | in, out | KiB/s | + +### Per disk + + + +Labels: + +| Label | Description | +|:-----------|:----------------| +| device | TBD | +| mount_point | TBD | +| device_type | TBD | + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| disk.io | reads, writes | KiB/s | +| disk_ext.io | discards | KiB/s | +| disk.ops | reads, writes | operations/s | +| disk_ext.ops | discards, flushes | operations/s | +| disk.qops | operations | operations | +| disk.backlog | backlog | milliseconds | +| disk.busy | busy | milliseconds | +| disk.util | utilization | % of time working | +| disk.mops | reads, writes | merged operations/s | +| disk_ext.mops | discards | merged operations/s | +| disk.iotime | reads, writes | milliseconds/s | +| disk_ext.iotime | discards, flushes | milliseconds/s | +| disk.await | reads, writes | milliseconds/operation | +| disk_ext.await | discards, flushes | milliseconds/operation | +| disk.avgsz | reads, writes | KiB/operation | +| disk_ext.avgsz | discards | KiB/operation | +| disk.svctm | svctm | milliseconds/operation | +| disk.bcache_cache_alloc | ununsed, dirty, clean, metadata, undefined | percentage | +| disk.bcache_hit_ratio | 5min, 1hour, 1day, ever | percentage | +| disk.bcache_rates | congested, writeback | KiB/s | +| disk.bcache_size | dirty | MiB | +| disk.bcache_usage | avail | percentage | +| disk.bcache_cache_read_races | races, errors | operations/s | +| disk.bcache | hits, misses, collisions, readaheads | operations/s | +| disk.bcache_bypass | hits, misses | operations/s | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ 10min_disk_backlog ](https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf) | disk.backlog | average backlog size of the ${label:device} disk over the last 10 minutes | +| [ 10min_disk_utilization ](https://github.com/netdata/netdata/blob/master/health/health.d/disks.conf) | disk.util | average percentage of time ${label:device} disk was busy over the last 10 minutes | +| [ bcache_cache_dirty ](https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf) | disk.bcache_cache_alloc | percentage of cache space used for dirty data and metadata (this usually means your SSD cache is too small) | +| [ bcache_cache_errors ](https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf) | disk.bcache_cache_read_races | number of times data was read from the cache, the bucket was reused and invalidated in the last 10 minutes (when this occurs the data is reread from the backing device) | + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/entropy.md b/collectors/proc.plugin/integrations/entropy.md new file mode 100644 index 0000000000..215a2d34ae --- /dev/null +++ b/collectors/proc.plugin/integrations/entropy.md @@ -0,0 +1,128 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/entropy.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "Entropy" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/System" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# Entropy + +Plugin: proc.plugin +Module: /proc/sys/kernel/random/entropy_avail + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +Entropy, a measure of the randomness or unpredictability of data. + +In the context of cryptography, entropy is used to generate random numbers or keys that are essential for +secure communication and encryption. Without a good source of entropy, cryptographic protocols can become +vulnerable to attacks that exploit the predictability of the generated keys. + +In most operating systems, entropy is generated by collecting random events from various sources, such as +hardware interrupts, mouse movements, keyboard presses, and disk activity. These events are fed into a pool +of entropy, which is then used to generate random numbers when needed. + +The `/dev/random` device in Linux is one such source of entropy, and it provides an interface for programs +to access the pool of entropy. When a program requests random numbers, it reads from the `/dev/random` device, +which blocks until enough entropy is available to generate the requested numbers. This ensures that the +generated numbers are truly random and not predictable. + +However, if the pool of entropy gets depleted, the `/dev/random` device may block indefinitely, causing +programs that rely on random numbers to slow down or even freeze. This is especially problematic for +cryptographic protocols that require a continuous stream of random numbers, such as SSL/TLS and SSH. + +To avoid this issue, some systems use a hardware random number generator (RNG) to generate high-quality +entropy. A hardware RNG generates random numbers by measuring physical phenomena, such as thermal noise or +radioactive decay. These sources of randomness are considered to be more reliable and unpredictable than +software-based sources. + +One such hardware RNG is the Trusted Platform Module (TPM), which is a dedicated hardware chip that is used +for cryptographic operations and secure boot. The TPM contains a built-in hardware RNG that generates +high-quality entropy, which can be used to seed the pool of entropy in the operating system. + +Alternatively, software-based solutions such as `Haveged` can be used to generate additional entropy by +exploiting sources of randomness in the system, such as CPU utilization and network traffic. These solutions +can help to mitigate the risk of entropy depletion, but they may not be as reliable as hardware-based solutions. + + + + +This collector is only supported on the following platforms: + +- linux + +This collector only supports collecting metrics from a single instance of this integration. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per Entropy instance + + + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| system.entropy | entropy | entropy | + + + +## Alerts + + +The following alerts are available: + +| Alert name | On metric | Description | +|:------------|:----------|:------------| +| [ lowest_entropy ](https://github.com/netdata/netdata/blob/master/health/health.d/entropy.conf) | system.entropy | minimum number of bits of entropy available for the kernel’s random number generator | + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/infiniband.md b/collectors/proc.plugin/integrations/infiniband.md new file mode 100644 index 0000000000..a940fd5423 --- /dev/null +++ b/collectors/proc.plugin/integrations/infiniband.md @@ -0,0 +1,94 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/infiniband.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "InfiniBand" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/Network" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# InfiniBand + +Plugin: proc.plugin +Module: /sys/class/infiniband + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +This integration monitors InfiniBand network inteface statistics. + + + +This collector is supported on all platforms. + +This collector supports collecting metrics from multiple instances of this integration, including remote instances. + + +### Default Behavior + +#### Auto-Detection + +This integration doesn't support auto-detection. + +#### Limits + +The default configuration for this integration does not impose any limits on data collection. + +#### Performance Impact + +The default configuration for this integration is not expected to impose a significant performance impact on the system. + + +## Metrics + +Metrics grouped by *scope*. + +The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels. + + + +### Per infiniband port + + + +This scope has no labels. + +Metrics: + +| Metric | Dimensions | Unit | +|:------|:----------|:----| +| ib.bytes | Received, Sent | kilobits/s | +| ib.packets | Received, Sent, Mcast_rcvd, Mcast_sent, Ucast_rcvd, Ucast_sent | packets/s | +| ib.errors | Pkts_malformated, Pkts_rcvd_discarded, Pkts_sent_discarded, Tick_Wait_to_send, Pkts_missed_resource, Buffer_overrun, Link_Downed, Link_recovered, Link_integrity_err, Link_minor_errors, Pkts_rcvd_with_EBP, Pkts_rcvd_discarded_by_switch, Pkts_sent_discarded_by_switch | errors/s | +| ib.hwerrors | Duplicated_packets, Pkt_Seq_Num_gap, Ack_timer_expired, Drop_missing_buffer, Drop_out_of_sequence, NAK_sequence_rcvd, CQE_err_Req, CQE_err_Resp, CQE_Flushed_err_Req, CQE_Flushed_err_Resp, Remote_access_err_Req, Remote_access_err_Resp, Remote_invalid_req, Local_length_err_Resp, RNR_NAK_Packets, CNP_Pkts_ignored, RoCE_ICRC_Errors | errors/s | +| ib.hwpackets | RoCEv2_Congestion_sent, RoCEv2_Congestion_rcvd, IB_Congestion_handled, ATOMIC_req_rcvd, Connection_req_rcvd, Read_req_rcvd, Write_req_rcvd, RoCE_retrans_adaptive, RoCE_retrans_timeout, RoCE_slow_restart, RoCE_slow_restart_congestion, RoCE_slow_restart_count | packets/s | + + + +## Alerts + +There are no alerts configured by default for this integration. + + +## Setup + +### Prerequisites + +No action required. + +### Configuration + +#### File + +There is no configuration file. +#### Options + + + +There are no configuration options. + +#### Examples +There are no configuration examples. + + diff --git a/collectors/proc.plugin/integrations/inter_process_communication.md b/collectors/proc.plugin/integrations/inter_process_communication.md new file mode 100644 index 0000000000..14f2114371 --- /dev/null +++ b/collectors/proc.plugin/integrations/inter_process_communication.md @@ -0,0 +1,115 @@ +<!--startmeta +custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/integrations/inter_process_communication.md" +meta_yaml: "https://github.com/netdata/netdata/edit/master/collectors/proc.plugin/metadata.yaml" +sidebar_label: "Inter Process Communication" +learn_status: "Published" +learn_rel_path: "Data Collection/Linux Systems/IPC" +message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE" +endmeta--> + +# Inter Process Communication + +Plugin: proc.plugin +Module: ipc + +<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" /> + +## Overview + +IPC stands for Inter- |