diff options
Diffstat (limited to '')
| -rw-r--r-- | collectors/proc.plugin/metadata.yaml (renamed from collectors/proc.plugin/multi_metadata.yaml) | 1965 |
1 files changed, 1283 insertions, 682 deletions
diff --git a/collectors/proc.plugin/multi_metadata.yaml b/collectors/proc.plugin/metadata.yaml index e78ec795c..81d83f50e 100644 --- a/collectors/proc.plugin/multi_metadata.yaml +++ b/collectors/proc.plugin/metadata.yaml @@ -1,54 +1,80 @@ -name: proc.plugin +plugin_name: proc.plugin modules: - meta: plugin_name: proc.plugin module_name: /proc/stat monitored_instance: - name: proc /proc/stat - link: '' - categories: [] - icon_filename: '' + name: System statistics + link: "" + categories: + - data-collection.linux-systems.system-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - cpu utilization + - process counts most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + CPU utilization, states and frequencies and key Linux system performance metrics. + + The `/proc/stat` file provides various types of system statistics: + + - The overall system CPU usage statistics + - Per CPU core statistics + - The total context switching of the system + - The total number of processes running + - The total CPU interrupts + - The total CPU softirqs + + The collector also reads: + + - `/proc/schedstat` for statistics about the process scheduler in the Linux kernel. + - `/sys/devices/system/cpu/[X]/thermal_throttle/core_throttle_count` to get the count of thermal throttling events for a specific CPU core on Linux systems. + - `/sys/devices/system/cpu/[X]/thermal_throttle/package_throttle_count` to get the count of thermal throttling events for a specific CPU package on a Linux system. + - `/sys/devices/system/cpu/[X]/cpufreq/scaling_cur_freq` to get the current operating frequency of a specific CPU core. + - `/sys/devices/system/cpu/[X]/cpufreq/stats/time_in_state` to get the amount of time the CPU has spent in each of its available frequency states. + - `/sys/devices/system/cpu/[X]/cpuidle/state[X]/name` to get the names of the idle states for each CPU core in a Linux system. + - `/sys/devices/system/cpu/[X]/cpuidle/state[X]/time` to get the total time each specific CPU core has spent in each idle state since the system was started. + method_description: "" supported_platforms: - include: [] + include: ["linux"] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: | + The collector auto-detects all metrics. No configuration is needed. limits: - description: '' + description: "" performance_impact: - description: '' + description: | + The collector disables cpu frequency and idle state monitoring when there are more than 128 CPU cores available. setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + section_name: "plugin:proc:/proc/stat" + name: "netdata.conf" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -69,11 +95,6 @@ modules: metric: system.cpu info: average CPU steal time over the last 20 minutes os: "linux" - - name: 10min_cpu_usage - link: https://github.com/netdata/netdata/blob/master/health/health.d/cpu.conf - metric: system.cpu - info: average CPU utilization over the last 10 minutes (excluding nice) - os: "freebsd" metrics: folding: title: Metrics @@ -174,51 +195,84 @@ modules: plugin_name: proc.plugin module_name: /proc/sys/kernel/random/entropy_avail monitored_instance: - name: proc /proc/sys/kernel/random/entropy_avail - link: '' - categories: [] - icon_filename: '' + name: Entropy + link: "" + categories: + - data-collection.linux-systems.system-metrics + icon_filename: "syslog.png" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - entropy most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + 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. + method_description: "" supported_platforms: - include: [] + include: ["linux"] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -227,8 +281,7 @@ modules: - name: lowest_entropy link: https://github.com/netdata/netdata/blob/master/health/health.d/entropy.conf metric: system.entropy - info: minimum number of entries in the random numbers pool in the last 5 minutes - os: "linux" + info: minimum number of bits of entropy available for the kernel’s random number generator metrics: folding: title: Metrics @@ -250,51 +303,64 @@ modules: plugin_name: proc.plugin module_name: /proc/uptime monitored_instance: - name: proc /proc/uptime - link: '' - categories: [] - icon_filename: '' + name: System Uptime + link: "" + categories: + - data-collection.linux-systems.system-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - uptime most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + The amount of time the system has been up (running). + + Uptime is a critical aspect of overall system performance: + + - **Availability**: Uptime monitoring can show whether a server is consistently available or experiences frequent downtimes. + - **Performance Monitoring**: While server uptime alone doesn't provide detailed performance data, analyzing the duration and frequency of downtimes can help identify patterns or trends. + - **Proactive problem detection**: If server uptime monitoring reveals unexpected downtimes or a decreasing uptime trend, it can serve as an early warning sign of potential problems. + - **Root cause analysis**: When investigating server downtime, the uptime metric alone may not provide enough information to pinpoint the exact cause. + - **Load balancing**: Uptime data can indirectly indicate load balancing issues if certain servers have significantly lower uptimes than others. + - **Optimize maintenance efforts**: Servers with consistently low uptimes or frequent downtimes may require more attention. + - **Compliance requirements**: Server uptime data can be used to demonstrate compliance with regulatory requirements or SLAs that mandate a minimum level of server availability. + method_description: "" supported_platforms: - include: [] + include: ["linux"] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -321,51 +387,77 @@ modules: plugin_name: proc.plugin module_name: /proc/vmstat monitored_instance: - name: proc /proc/vmstat - link: '' - categories: [] - icon_filename: '' + name: Memory Statistics + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - swap + - page faults + - oom + - numa most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + Linux Virtual memory subsystem. + + Information about memory management, indicating how effectively the kernel allocates and frees + memory resources in response to system demands. + + Monitors page faults, which occur when a process requests a portion of its memory that isn't + immediately available. Monitoring these events can help diagnose inefficiencies in memory management and + provide insights into application behavior. + + Tracks swapping activity — a vital aspect of memory management where the kernel moves data from RAM to + swap space, and vice versa, based on memory demand and usage. It also monitors the utilization of zswap, + a compressed cache for swap pages, and provides insights into its usage and performance implications. + + In the context of virtualized environments, it tracks the ballooning mechanism which is used to balance + memory resources between host and guest systems. + + For systems using NUMA architecture, it provides insights into the local and remote memory accesses, which + can impact the performance based on the memory access times. + + The collector also watches for 'Out of Memory' kills, a drastic measure taken by the system when it runs out + of memory resources. + method_description: "" supported_platforms: - include: [] + include: ["linux"] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -373,7 +465,7 @@ modules: alerts: - name: 30min_ram_swapped_out link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf - metric: system.swapio + metric: mem.swapio info: percentage of the system RAM swapped in the last 30 minutes os: "linux freebsd" - name: oom_kill @@ -392,7 +484,7 @@ modules: description: "" labels: [] metrics: - - name: system.swapio + - name: mem.swapio description: Swap I/O unit: "KiB/s" chart_type: area @@ -514,51 +606,83 @@ modules: plugin_name: proc.plugin module_name: /proc/interrupts monitored_instance: - name: proc /proc/interrupts - link: '' - categories: [] - icon_filename: '' + name: Interrupts + link: "" + categories: + - data-collection.linux-systems.cpu-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - interrupts most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + Monitors `/proc/interrupts`, a file organized by CPU and then by the type of interrupt. + The numbers reported are the counts of the interrupts that have occurred of each type. + + An interrupt is a signal to the processor emitted by hardware or software indicating an event that needs + immediate attention. The processor then interrupts its current activities and executes the interrupt handler + to deal with the event. This is part of the way a computer multitasks and handles concurrent processing. + + The types of interrupts include: + + - **I/O interrupts**: These are caused by I/O devices like the keyboard, mouse, printer, etc. For example, when + you type something on the keyboard, an interrupt is triggered so the processor can handle the new input. + + - **Timer interrupts**: These are generated at regular intervals by the system's timer circuit. It's primarily + used to switch the CPU among different tasks. + + - **Software interrupts**: These are generated by a program requiring disk I/O operations, or other system resources. + + - **Hardware interrupts**: These are caused by hardware conditions such as power failure, overheating, etc. + + Monitoring `/proc/interrupts` can be used for: + + - **Performance tuning**: If an interrupt is happening very frequently, it could be a sign that a device is not + configured correctly, or there is a software bug causing unnecessary interrupts. This could lead to system + performance degradation. + + - **System troubleshooting**: If you're seeing a lot of unexpected interrupts, it could be a sign of a hardware problem. + + - **Understanding system behavior**: More generally, keeping an eye on what interrupts are occurring can help you + understand what your system is doing. It can provide insights into the system's interaction with hardware, + drivers, and other parts of the kernel. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -597,51 +721,77 @@ modules: plugin_name: proc.plugin module_name: /proc/loadavg monitored_instance: - name: proc /proc/loadavg - link: '' - categories: [] - icon_filename: '' + name: System Load Average + link: "" + categories: + - data-collection.linux-systems.system-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - load + - load average most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + The `/proc/loadavg` file provides information about the system load average. + + The load average is a measure of the amount of computational work that a system performs. It is a + representation of the average system load over a period of time. + + This file contains three numbers representing the system load averages for the last 1, 5, and 15 minutes, + respectively. It also includes the currently running processes and the total number of processes. + + Monitoring the load average can be used for: + + - **System performance**: If the load average is too high, it may indicate that your system is overloaded. + On a system with a single CPU, if the load average is 1, it means the single CPU is fully utilized. If the + load averages are consistently higher than the number of CPUs/cores, it may indicate that your system is + overloaded and tasks are waiting for CPU time. + + - **Troubleshooting**: If the load average is unexpectedly high, it can be a sign of a problem. This could be + due to a runaway process, a software bug, or a hardware issue. + + - **Capacity planning**: By monitoring the load average over time, you can understand the trends in your + system's workload. This can help with capacity planning and scaling decisions. + + Remember that load average not only considers CPU usage, but also includes processes waiting for disk I/O. + Therefore, high load averages could be due to I/O contention as well as CPU contention. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -700,51 +850,76 @@ modules: plugin_name: proc.plugin module_name: /proc/pressure monitored_instance: - name: proc /proc/pressure - link: '' - categories: [] - icon_filename: '' + name: Pressure Stall Information + link: "" + categories: + - data-collection.linux-systems.pressure-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - pressure most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + Introduced in Linux kernel 4.20, `/proc/pressure` provides information about system pressure stall information + (PSI). PSI is a feature that allows the system to track the amount of time the system is stalled due to + resource contention, such as CPU, memory, or I/O. + + The collectors monitored 3 separate files for CPU, memory, and I/O: + + - **cpu**: Tracks the amount of time tasks are stalled due to CPU contention. + - **memory**: Tracks the amount of time tasks are stalled due to memory contention. + - **io**: Tracks the amount of time tasks are stalled due to I/O contention. + - **irq**: Tracks the amount of time tasks are stalled due to IRQ contention. + + Each of them provides metrics for stall time over the last 10 seconds, 1 minute, 5 minutes, and 15 minutes. + + Monitoring the /proc/pressure files can provide important insights into system performance and capacity planning: + + - **Identifying resource contention**: If these metrics are consistently high, it indicates that tasks are + frequently being stalled due to lack of resources, which can significantly degrade system performance. + + - **Troubleshooting performance issues**: If a system is experiencing performance issues, these metrics can + help identify whether resource contention is the cause. + + - **Capacity planning**: By monitoring these metrics over time, you can understand trends in resource + utilization and make informed decisions about when to add more resources to your system. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -849,51 +1024,76 @@ modules: plugin_name: proc.plugin module_name: /proc/softirqs monitored_instance: - name: proc /proc/softirqs - link: '' - categories: [] - icon_filename: '' + name: SoftIRQ statistics + link: "" + categories: + - data-collection.linux-systems.cpu-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - softirqs + - interrupts most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + In the Linux kernel, handling of hardware interrupts is split into two halves: the top half and the bottom half. + The top half is the routine that responds immediately to an interrupt, while the bottom half is deferred to be processed later. + + Softirqs are a mechanism in the Linux kernel used to handle the bottom halves of interrupts, which can be + deferred and processed later in a context where it's safe to enable interrupts. + + The actual work of handling the interrupt is offloaded to a softirq and executed later when the system + decides it's a good time to process them. This helps to keep the system responsive by not blocking the top + half for too long, which could lead to missed interrupts. + + Monitoring `/proc/softirqs` is useful for: + + - **Performance tuning**: A high rate of softirqs could indicate a performance issue. For instance, a high + rate of network softirqs (`NET_RX` and `NET_TX`) could indicate a network performance issue. + + - **Troubleshooting**: If a system is behaving unexpectedly, checking the softirqs could provide clues about + what is going on. For example, a sudden increase in block device softirqs (BLOCK) might indicate a problem + with a disk. + + - **Understanding system behavior**: Knowing what types of softirqs are happening can help you understand what + your system is doing, particularly in terms of how it's interacting with hardware and how it's handling + interrupts. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -932,51 +1132,75 @@ modules: plugin_name: proc.plugin module_name: /proc/net/softnet_stat monitored_instance: - name: proc /proc/net/softnet_stat - link: '' - categories: [] - icon_filename: '' + name: Softnet Statistics + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - softnet most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + `/proc/net/softnet_stat` provides statistics that relate to the handling of network packets by softirq. + + It provides information about: + + - Total number of processed packets (`processed`). + - Times ksoftirq ran out of quota (`dropped`). + - Times net_rx_action was rescheduled. + - Number of times processed all lists before quota. + - Number of times did not process all lists due to quota. + - Number of times net_rx_action was rescheduled for GRO (Generic Receive Offload) cells. + - Number of times GRO cells were processed. + + Monitoring the /proc/net/softnet_stat file can be useful for: + + - **Network performance monitoring**: By tracking the total number of processed packets and how many packets + were dropped, you can gain insights into your system's network performance. + + - **Troubleshooting**: If you're experiencing network-related issues, this collector can provide valuable clues. + For instance, a high number of dropped packets may indicate a network problem. + + - **Capacity planning**: If your system is consistently processing near its maximum capacity of network + packets, it might be time to consider upgrading your network infrastructure. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -990,13 +1214,10 @@ modules: - name: 1min_netdev_budget_ran_outs link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf metric: system.softnet_stat - info: average number of times ksoftirq ran out of sysctl net.core.netdev_budget or net.core.netdev_budget_usecs with work remaining over the last minute (this can be a cause for dropped packets) + info: + average number of times ksoftirq ran out of sysctl net.core.netdev_budget or net.core.netdev_budget_usecs with work remaining over the last + minute (this can be a cause for dropped packets) os: "linux" - - name: 10min_netisr_backlog_exceeded - link: https://github.com/netdata/netdata/blob/master/health/health.d/softnet.conf - metric: system.softnet_stat - info: average number of drops in the last minute due to exceeded sysctl net.route.netisr_maxqlen (this can be a cause for dropped packets) - os: "freebsd" metrics: folding: title: Metrics @@ -1036,51 +1257,72 @@ modules: plugin_name: proc.plugin module_name: /proc/meminfo monitored_instance: - name: proc /proc/meminfo - link: '' - categories: [] - icon_filename: '' + name: Memory Usage + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - memory + - ram + - available + - committed most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + `/proc/meminfo` provides detailed information about the system's current memory usage. It includes information + about different types of memory, RAM, Swap, ZSwap, HugePages, Transparent HugePages (THP), Kernel memory, + SLAB memory, memory mappings, and more. + + Monitoring /proc/meminfo can be useful for: + + - **Performance Tuning**: Understanding your system's memory usage can help you make decisions about system + tuning and optimization. For example, if your system is frequently low on free memory, it might benefit + from more RAM. + + - **Troubleshooting**: If your system is experiencing problems, `/proc/meminfo` can provide clues about + whether memory usage is a factor. For example, if your system is slow and cached swap is high, it could + mean that your system is swapping out a lot of memory to disk, which can degrade performance. + + - **Capacity Planning**: By monitoring memory usage over time, you can understand trends and make informed + decisions about future capacity needs. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1091,24 +1333,14 @@ modules: metric: system.ram info: system memory utilization os: "linux" - - name: ram_in_use - link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf - metric: system.ram - info: system memory utilization - os: "freebsd" - name: ram_available link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf metric: mem.available info: percentage of estimated amount of RAM available for userspace processes, without causing swapping os: "linux" - - name: ram_available - link: https://github.com/netdata/netdata/blob/master/health/health.d/ram.conf - metric: mem.available - info: percentage of estimated amount of RAM available for userspace processes, without causing swapping - os: "freebsd" - name: used_swap link: https://github.com/netdata/netdata/blob/master/health/health.d/swap.conf - metric: system.swap + metric: mem.swap info: swap memory utilization os: "linux freebsd" - name: 1hour_memory_hw_corrupted @@ -1142,13 +1374,26 @@ modules: chart_type: area dimensions: - name: avail - - name: system.swap + - name: mem.swap description: System Swap unit: "MiB" chart_type: stacked dimensions: - name: free - name: used + - name: mem.swap_cached + description: Swap Memory Cached in RAM + unit: "MiB" + chart_type: stacked + dimensions: + - name: cached + - name: mem.zswap + description: Zswap Usage + unit: "MiB" + chart_type: stacked + dimensions: + - name: in-ram + - name: on-disk - name: mem.hwcorrupt description: Corrupted Memory detected by ECC unit: "MiB" @@ -1188,7 +1433,7 @@ modules: dimensions: - name: reclaimable - name: unreclaimable - - name: mem.hugepage + - name: mem.hugepages description: Dedicated HugePages Memory unit: "MiB" chart_type: stacked @@ -1197,62 +1442,110 @@ modules: - name: used - name: surplus - name: reserved - - name: mem.transparent_hugepages + - name: mem.thp description: Transparent HugePages Memory unit: "MiB" chart_type: stacked dimensions: - name: anonymous - name: shmem + - name: mem.thp_details + description: Details of Transparent HugePages Usage + unit: "MiB" + chart_type: line + dimensions: + - name: ShmemPmdMapped + - name: FileHugePages + - name: FilePmdMapped + - name: mem.reclaiming + description: Memory Reclaiming + unit: "MiB" + chart_type: line + dimensions: + - name: Active + - name: Inactive + - name: Active(anon) + - name: Inactive(anon) + - name: Active(file) + - name: Inactive(file) + - name: Unevictable + - name: Mlocked + - name: mem.high_low + description: High and Low Used and Free Memory Areas + unit: "MiB" + chart_type: stacked + dimensions: + - name: high_used + - name: low_used + - name: high_free + - name: low_free + - name: mem.cma + description: Contiguous Memory Allocator (CMA) Memory + unit: "MiB" + chart_type: stacked + dimensions: + - name: used + - name: free + - name: mem.directmaps + description: Direct Memory Mappings + unit: "MiB" + chart_type: stacked + dimensions: + - name: 4k + - name: 2m + - name: 4m + - name: 1g - meta: plugin_name: proc.plugin module_name: /proc/pagetypeinfo monitored_instance: - name: proc /proc/pagetypeinfo - link: '' - categories: [] - icon_filename: '' + name: Page types + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "microchip.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - memory page types most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides metrics about the system's memory page types" + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1295,66 +1588,91 @@ modules: plugin_name: proc.plugin module_name: /sys/devices/system/edac/mc monitored_instance: - name: proc /sys/devices/system/edac/mc - link: '' - categories: [] - icon_filename: '' + name: Memory modules (DIMMs) + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "microchip.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - edac + - ecc + - dimm + - ram + - hardware most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + The Error Detection and Correction (EDAC) subsystem is detecting and reporting errors in the system's memory, + primarily ECC (Error-Correcting Code) memory errors. + + The collector provides data for: + + - Per memory controller (MC): correctable and uncorrectable errors. These can be of 2 kinds: + - errors related to a DIMM + - errors that cannot be associated with a DIMM + + - Per memory DIMM: correctable and uncorrectable errors. There are 2 kinds: + - memory controllers that can identify the physical DIMMS and report errors directly for them, + - memory controllers that report errors for memory address ranges that can be linked to dimms. + In this case the DIMMS reported may be more than the physical DIMMS installed. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: list: [] alerts: - - name: 1hour_ecc_memory_correctable + - name: ecc_memory_mc_noinfo_correctable + metric: mem.edac_mc + info: memory controller ${label:controller} ECC correctable errors (unknown DIMM slot) in the last 10 minutes link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf - metric: mem.ecc_ce - info: number of ECC correctable errors in the last 10 minutes - os: "linux" - - name: 1hour_ecc_memory_uncorrectable + - name: ecc_memory_mc_noinfo_uncorrectable + metric: mem.edac_mc + info: memory controller ${label:controller} ECC uncorrectable errors (unknown DIMM slot) in the last 10 minutes + link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf + - name: ecc_memory_dimm_correctable + metric: mem.edac_mc_dimm + info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors in the last 10 minutes + link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf + - name: ecc_memory_dimm_uncorrectable + metric: mem.edac_mc_dimm + info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors in the last 10 minutes link: https://github.com/netdata/netdata/blob/master/health/health.d/memory.conf - metric: mem.ecc_ue - info: number of ECC uncorrectable errors in the last 10 minutes - os: "linux" metrics: folding: title: Metrics @@ -1362,71 +1680,117 @@ modules: description: "" availability: [] scopes: - - name: global - description: "" - labels: [] + - name: memory controller + description: These metrics refer to the memory controller. + labels: + - name: controller + description: "[mcX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#mcx-directories) directory name of this memory controller." + - name: mc_name + description: Memory controller type. + - name: size_mb + description: The amount of memory in megabytes that this memory controller manages. + - name: max_location + description: Last available memory slot in this memory controller. metrics: - - name: mem.ecc_ce - description: ECC Memory Correctable Errors - unit: "errors" + - name: mem.edac_mc + description: Memory Controller (MC) Error Detection And Correction (EDAC) Errors + unit: errors/s chart_type: line dimensions: - - name: a dimension per mem controller - - name: mem.ecc_ue - description: ECC Memory Uncorrectable Errors - unit: "errors" + - name: correctable + - name: uncorrectable + - name: correctable_noinfo + - name: uncorrectable_noinfo + - name: memory module + description: These metrics refer to the memory module (or rank, [depends on the memory controller](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#f5)). + labels: + - name: controller + description: "[mcX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#mcx-directories) directory name of this memory controller." + - name: dimm + description: "[dimmX or rankX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#dimmx-or-rankx-directories) directory name of this memory module." + - name: dimm_dev_type + description: Type of DRAM device used in this memory module. For example, x1, x2, x4, x8. + - name: dimm_edac_mode + description: Used type of error detection and correction. For example, S4ECD4ED would mean a Chipkill with x4 DRAM. + - name: dimm_label + description: Label assigned to this memory module. + - name: dimm_location + description: Location of the memory module. + - name: dimm_mem_type + description: Type of the memory module. + - name: size + description: The amount of memory in megabytes that this memory module manages. + metrics: + - name: mem.edac_mc + description: DIMM Error Detection And Correction (EDAC) Errors + unit: errors/s chart_type: line dimensions: - - name: a dimension per mem controller + - name: correctable + - name: uncorrectable - meta: plugin_name: proc.plugin module_name: /sys/devices/system/node monitored_instance: - name: proc /sys/devices/system/node - link: '' - categories: [] - icon_filename: '' + name: Non-Uniform Memory Access + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "linuxserver.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - numa most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + Information about NUMA (Non-Uniform Memory Access) nodes on the system. + + NUMA is a method of configuring a cluster of microprocessor in a multiprocessing system so that they can + share memory locally, improving performance and the ability of the system to be expanded. NUMA is used in a + symmetric multiprocessing (SMP) system. + + In a NUMA system, processors, memory, and I/O devices are grouped together into cells, also known as nodes. + Each node has its own memory and set of I/O devices, and one or more processors. While a processor can access + memory in any of the nodes, it does so faster when accessing memory within its own node. + + The collector provides statistics on memory allocations for processes running on the NUMA nodes, revealing the + efficiency of memory allocations in multi-node systems. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1460,51 +1824,61 @@ modules: plugin_name: proc.plugin module_name: /sys/kernel/mm/ksm monitored_instance: - name: proc /sys/kernel/mm/ksm - link: '' - categories: [] - icon_filename: '' + name: Kernel Same-Page Merging + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "microchip.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - ksm + - samepage + - merging most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + Kernel Samepage Merging (KSM) is a memory-saving feature in Linux that enables the kernel to examine the + memory of different processes and identify identical pages. It then merges these identical pages into a + single page that the processes share. This is particularly useful for virtualization, where multiple virtual + machines might be running the same operating system or applications and have many identical pages. + + The collector provides information about the operation and effectiveness of KSM on your system. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1547,51 +1921,57 @@ modules: plugin_name: proc.plugin module_name: /sys/block/zram monitored_instance: - name: proc /sys/block/zram - link: '' - categories: [] - icon_filename: '' + name: ZRAM + link: "" + categories: + - data-collection.linux-systems.memory-metrics + icon_filename: "microchip.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - zram most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + zRAM, or compressed RAM, is a block device that uses a portion of your system's RAM as a block device. + The data written to this block device is compressed and stored in memory. + + The collectors provides information about the operation and the effectiveness of zRAM on your system. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1640,51 +2020,69 @@ modules: plugin_name: proc.plugin module_name: ipc monitored_instance: - name: proc ipc - link: '' - categories: [] - icon_filename: '' + name: Inter Process Communication + link: "" + categories: + - data-collection.linux-systems.ipc-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - ipc + - semaphores + - shared memory most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + IPC stands for Inter-Process Communication. It is a mechanism which allows processes to communicate with each + other and synchronize their actions. + + This collector exposes information about: + + - Message Queues: This allows messages to be exchanged between processes. It's a more flexible method that + allows messages to be placed onto a queue and read at a later time. + + - Shared Memory: This method allows for the fastest form of IPC because processes can exchange data by + reading/writing into shared memory segments. + + - Semaphores: They are used to synchronize the operations performed by independent processes. So, if multiple + processes are trying to access a single shared resource, semaphores can ensure that only one process + accesses the resource at a given time. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: false additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1751,51 +2149,61 @@ modules: plugin_name: proc.plugin module_name: /proc/diskstats monitored_instance: - name: proc /proc/diskstats - link: '' - categories: [] - icon_filename: '' + name: Disk Statistics + link: "" + categories: + - data-collection.linux-systems.disk-metrics + icon_filename: "hard-drive.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - disk + - disks + - io + - bcache + - block devices most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: | + 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. + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -1818,7 +2226,9 @@ modules: - name: bcache_cache_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/bcache.conf metric: disk.bcache_cache_read_races - info: 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) + info: + 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) metrics: folding: title: Metrics @@ -2023,51 +2433,56 @@ modules: plugin_name: proc.plugin module_name: /proc/mdstat monitored_instance: - name: proc /proc/mdstat - link: '' - categories: [] - icon_filename: '' + name: MD RAID + link: "" + categories: + - data-collection.linux-systems.disk-metrics + icon_filename: "hard-drive.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - raid + - mdadm + - mdstat + - raid most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors the status of MD RAID devices." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -2080,7 +2495,8 @@ modules: - name: mdstat_disks link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.disks - info: number of devices in the down state for the ${label:device} ${label:raid_level} array. Any number > 0 indicates that the array is degraded. + info: + number of devices in the down state for the ${label:device} ${label:raid_level} array. Any number > 0 indicates that the array is degraded. - name: mdstat_mismatch_cnt link: https://github.com/netdata/netdata/blob/master/health/health.d/mdstat.conf metric: md.mismatch_cnt @@ -2158,51 +2574,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/dev monitored_instance: - name: proc /proc/net/dev - link: '' - categories: [] - icon_filename: '' + name: Network interfaces + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - network interfaces most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "Monitor network interface metrics about bandwidth, state, errors and more." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -2251,18 +2669,10 @@ modules: - name: 10s_received_packets_storm link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.packets - info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute + info: + ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over + the last minute os: "linux freebsd" - - name: interface_inbound_errors - link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf - metric: net.errors - info: number of inbound errors for the network interface ${label:device} in the last 10 minutes - os: "freebsd" - - name: interface_outbound_errors - link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf - metric: net.errors - info: number of outbound errors for the network interface ${label:device} in the last 10 minutes - os: "freebsd" - name: inbound_packets_dropped link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf metric: net.drops @@ -2398,51 +2808,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/wireless monitored_instance: - name: proc /proc/net/wireless - link: '' - categories: [] - icon_filename: '' + name: Wireless network interfaces + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - wireless devices most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "Monitor wireless devices with metrics about status, link quality, signal level, noise level and more." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -2472,13 +2884,16 @@ modules: dimensions: - name: link_quality - name: wireless.signal_level - description: The signal level is the wireless signal power level received by the wireless client. The closer the value is to 0, the stronger the signal. + description: + The signal level is the wireless signal power level received by the wireless client. The closer the value is to 0, the stronger the + signal. unit: "dBm" chart_type: line dimensions: - name: signal_level - name: wireless.noise_level - description: The noise level indicates the amount of background noise in your environment. The closer the value to 0, the greater the noise level. + description: + The noise level indicates the amount of background noise in your environment. The closer the value to 0, the greater the noise level. unit: "dBm" chart_type: line dimensions: @@ -2503,51 +2918,54 @@ modules: plugin_name: proc.plugin module_name: /sys/class/infiniband monitored_instance: - name: proc /sys/class/infiniband - link: '' - categories: [] - icon_filename: '' + name: InfiniBand + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - infiniband + - rdma most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors InfiniBand network inteface statistics." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -2643,51 +3061,58 @@ modules: plugin_name: proc.plugin module_name: /proc/net/netstat monitored_instance: - name: proc /proc/net/netstat - link: '' - categories: [] - icon_filename: '' + name: Network statistics + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - ip + - udp + - udplite + - icmp + - netstat + - snmp most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides metrics from the `netstat`, `snmp` and `snmp6` modules." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -2726,7 +3151,9 @@ modules: - name: 10s_ipv4_tcp_resets_sent link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf metric: ipv4.tcphandshake - info: average number of sent TCP RESETS over the last 10 seconds. This can indicate a port scan, or that a service running on this host has crashed. Netdata will not send a clear notification for this alarm. + info: + average number of sent TCP RESETS over the last 10 seconds. This can indicate a port scan, or that a service running on this host has + crashed. Netdata will not send a clear notification for this alarm. os: "linux" - name: 1m_ipv4_tcp_resets_received link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf @@ -2736,7 +3163,9 @@ modules: - name: 10s_ipv4_tcp_resets_received link: https://github.com/netdata/netdata/blob/master/health/health.d/tcp_resets.conf metric: ipv4.tcphandshake - info: average number of received TCP RESETS over the last 10 seconds. This can be an indication that a service this host needs has crashed. Netdata will not send a clear notification for this alarm. + info: + average number of received TCP RESETS over the last 10 seconds. This can be an indication that a service this host needs has crashed. + Netdata will not send a clear notification for this alarm. os: "linux freebsd" - name: 1m_ipv4_udp_receive_buffer_errors link: https://github.com/netdata/netdata/blob/master/health/health.d/udp_errors.conf @@ -3232,51 +3661,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/sockstat monitored_instance: - name: proc /proc/net/sockstat - link: '' - categories: [] - icon_filename: '' + name: Socket statistics + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - sockets most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides socket statistics." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3364,51 +3795,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/sockstat6 monitored_instance: - name: proc /proc/net/sockstat6 - link: '' - categories: [] - icon_filename: '' + name: IPv6 Socket Statistics + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - ipv6 sockets most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides IPv6 socket statistics." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3459,51 +3892,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/ip_vs_stats monitored_instance: - name: proc /proc/net/ip_vs_stats - link: '' - categories: [] - icon_filename: '' + name: IP Virtual Server + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - ip virtual server most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors IP Virtual Server statistics" + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3544,51 +3979,54 @@ modules: plugin_name: proc.plugin module_name: /proc/net/rpc/nfs monitored_instance: - name: proc /proc/net/rpc/nfs - link: '' - categories: [] - icon_filename: '' + name: NFS Client + link: "" + categories: + - data-collection.linux-systems.filesystem-metrics.nfs + icon_filename: "nfs.png" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - nfs client + - filesystem most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides statistics from the Linux kernel's NFS Client." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3642,51 +4080,54 @@ modules: plugin_name: proc.plugin module_name: /proc/net/rpc/nfsd monitored_instance: - name: proc /proc/net/rpc/nfsd - link: '' - categories: [] - icon_filename: '' + name: NFS Server + link: "" + categories: + - data-collection.linux-systems.filesystem-metrics.nfs + icon_filename: "nfs.png" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - nfs server + - filesystem most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides statistics from the Linux kernel's NFS Server." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3773,51 +4214,54 @@ modules: plugin_name: proc.plugin module_name: /proc/net/sctp/snmp monitored_instance: - name: proc /proc/net/sctp/snmp - link: '' - categories: [] - icon_filename: '' + name: SCTP Statistics + link: "" + categories: + - data-collection.linux-systems.network-metrics + icon_filename: "network-wired.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - sctp + - stream control transmission protocol most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides statistics about the Stream Control Transmission Protocol (SCTP)." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3874,51 +4318,55 @@ modules: plugin_name: proc.plugin module_name: /proc/net/stat/nf_conntrack monitored_instance: - name: proc /proc/net/stat/nf_conntrack - link: '' - categories: [] - icon_filename: '' + name: Conntrack + link: "" + categories: + - data-collection.linux-systems.firewall-metrics + icon_filename: "firewall.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - connection tracking mechanism + - netfilter + - conntrack most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors the connection tracking mechanism of Netfilter in the Linux Kernel." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -3991,51 +4439,53 @@ modules: plugin_name: proc.plugin module_name: /proc/net/stat/synproxy monitored_instance: - name: proc /proc/net/stat/synproxy - link: '' - categories: [] - icon_filename: '' + name: Synproxy + link: "" + categories: + - data-collection.linux-systems.firewall-metrics + icon_filename: "firewall.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - synproxy most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides statistics about the Synproxy netfilter module." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -4076,51 +4526,56 @@ modules: plugin_name: proc.plugin module_name: /proc/spl/kstat/zfs monitored_instance: - name: proc /proc/spl/kstat/zfs - link: '' - categories: [] - icon_filename: '' + name: ZFS Pools + link: "" + categories: + - data-collection.linux-systems.filesystem-metrics.zfs + icon_filename: "filesystem.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - zfs pools + - pools + - zfs + - filesystem most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides metrics about the state of ZFS pools." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -4163,51 +4618,56 @@ modules: plugin_name: proc.plugin module_name: /proc/spl/kstat/zfs/arcstats monitored_instance: - name: proc /proc/spl/kstat/zfs/arcstats - link: '' - categories: [] - icon_filename: '' + name: ZFS Adaptive Replacement Cache + link: "" + categories: + - data-collection.linux-systems.filesystem-metrics.zfs + icon_filename: "filesystem.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - zfs arc + - arc + - zfs + - filesystem most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors ZFS Adadptive Replacement Cache (ARC) statistics." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -4424,51 +4884,54 @@ modules: plugin_name: proc.plugin module_name: /sys/fs/btrfs monitored_instance: - name: proc /sys/fs/btrfs - link: '' - categories: [] - icon_filename: '' + name: BTRFS + link: "" + categories: + - data-collection.linux-systems.filesystem-metrics.btrfs + icon_filename: "filesystem.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - btrfs + - filesystem most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration provides usage and error statistics from the BTRFS filesystem." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -4611,51 +5074,54 @@ modules: plugin_name: proc.plugin module_name: /sys/class/power_supply monitored_instance: - name: proc /sys/class/power_supply - link: '' - categories: [] - icon_filename: '' + name: Power Supply + link: "" + categories: + - data-collection.linux-systems.power-supply-metrics + icon_filename: "powersupply.svg" related_resources: integrations: list: [] info_provided_to_referring_integrations: - description: '' - keywords: [] + description: "" + keywords: + - psu + - power supply most_popular: false overview: data_collection: - metrics_description: '' - method_description: '' + metrics_description: "This integration monitors Power supply metrics, such as battery status, AC power status and more." + method_description: "" supported_platforms: include: [] exclude: [] - multi-instance: true + multi_instance: true additional_permissions: - description: '' + description: "" default_behavior: auto_detection: - description: '' + description: "" limits: - description: '' + description: "" performance_impact: - description: '' + description: "" setup: prerequisites: list: [] configuration: file: - name: '' - description: '' + name: "" + description: "" options: - description: '' + description: "" folding: - title: '' + title: "" enabled: true list: [] examples: folding: enabled: true - title: '' + title: "" list: [] troubleshooting: problems: @@ -4714,3 +5180,138 @@ modules: - name: now - name: max - name: max_design + - meta: + plugin_name: proc.plugin + module_name: /sys/class/drm + monitored_instance: + name: AMD GPU + link: "https://www.amd.com" + categories: + - data-collection.hardware-devices-and-sensors + icon_filename: amd.svg + related_resources: + integrations: + list: [] + info_provided_to_referring_integrations: + description: "" + keywords: + - amd + - gpu + - hardware + most_popular: false + overview: + data_collection: + metrics_description: "This integration monitors AMD GPU metrics, such as utilization, clock frequency and memory usage." + method_description: "It reads `/sys/class/drm` to collect metrics for every AMD GPU card instance it encounters." + supported_platforms: + include: + - Linux + exclude: [] + multi_instance: true + additional_permissions: + description: "" + default_behavior: + auto_detection: + description: "" + limits: + description: "" + performance_impact: + description: "" + setup: + prerequisites: + list: [] + configuration: + file: + name: "" + description: "" + options: + description: "" + folding: + title: "" + enabled: true + list: [] + examples: + folding: + enabled: true + title: "" + list: [] + troubleshooting: + problems: + list: [] + alerts: [] + metrics: + folding: + title: Metrics + enabled: false + description: "" + availability: [] + scopes: + - name: gpu + description: "These metrics refer to the GPU." + labels: + - name: product_name + description: GPU product name (e.g. AMD RX 6600) + metrics: + - name: amdgpu.gpu_utilization + description: GPU utilization + unit: "percentage" + chart_type: line + dimensions: + - name: utilization + - name: amdgpu.gpu_mem_utilization + description: GPU memory utilization + unit: "percentage" + chart_type: line + dimensions: + - name: utilization + - name: amdgpu.gpu_clk_frequency + description: GPU clock frequency + unit: "MHz" + chart_type: line + dimensions: + - name: frequency + - name: amdgpu.gpu_mem_clk_frequency + description: GPU memory clock frequency + unit: "MHz" + chart_type: line + dimensions: + - name: frequency + - name: amdgpu.gpu_mem_vram_usage_perc + description: VRAM memory usage percentage + unit: "percentage" + chart_type: line + dimensions: + - name: usage + - name: amdgpu.gpu_mem_vram_usage + description: VRAM memory usage + unit: "bytes" + chart_type: area + dimensions: + - name: free + - name: used + - name: amdgpu.gpu_mem_vis_vram_usage_perc + description: visible VRAM memory usage percentage + unit: "percentage" + chart_type: line + dimensions: + - name: usage + - name: amdgpu.gpu_mem_vis_vram_usage + description: visible VRAM memory usage + unit: "bytes" + chart_type: area + dimensions: + - name: free + - name: used + - name: amdgpu.gpu_mem_gtt_usage_perc + description: GTT memory usage percentage + unit: "percentage" + chart_type: line + dimensions: + - name: usage + - name: amdgpu.gpu_mem_gtt_usage + description: GTT memory usage + unit: "bytes" + chart_type: area + dimensions: + - name: free + - name: used |