master
md 131 lines 4.1 KB
Rendered Raw
1 <!--startmeta
2 custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/collectors/proc.plugin/integrations/system_load_average.md"
3 meta_yaml: "https://github.com/netdata/netdata/edit/master/src/collectors/proc.plugin/metadata.yaml"
4 sidebar_label: "System Load Average"
5 learn_status: "Published"
6 learn_rel_path: "Collecting Metrics/Collectors/Operating Systems"
7 keywords: ['load', 'load average']
8 message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE"
9 endmeta-->
10
11 # System Load Average
12
13
14 <img src="https://netdata.cloud/img/linuxserver.svg" width="150"/>
15
16
17 Plugin: proc.plugin
18 Module: /proc/loadavg
19
20 <img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" />
21
22 ## Overview
23
24 The `/proc/loadavg` file provides information about the system load average.
25
26 The load average is a measure of the amount of computational work that a system performs. It is a
27 representation of the average system load over a period of time.
28
29 This file contains three numbers representing the system load averages for the last 1, 5, and 15 minutes,
30 respectively. It also includes the currently running processes and the total number of processes.
31
32 Monitoring the load average can be used for:
33
34 - **System performance**: If the load average is too high, it may indicate that your system is overloaded.
35 On a system with a single CPU, if the load average is 1, it means the single CPU is fully utilized. If the
36 load averages are consistently higher than the number of CPUs/cores, it may indicate that your system is
37 overloaded and tasks are waiting for CPU time.
38
39 - **Troubleshooting**: If the load average is unexpectedly high, it can be a sign of a problem. This could be
40 due to a runaway process, a software bug, or a hardware issue.
41
42 - **Capacity planning**: By monitoring the load average over time, you can understand the trends in your
43 system's workload. This can help with capacity planning and scaling decisions.
44
45 Remember that load average not only considers CPU usage, but also includes processes waiting for disk I/O.
46 Therefore, high load averages could be due to I/O contention as well as CPU contention.
47
48
49
50
51 This collector is supported on all platforms.
52
53 This collector only supports collecting metrics from a single instance of this integration.
54
55
56 ### Default Behavior
57
58 #### Auto-Detection
59
60 This integration doesn't support auto-detection.
61
62 #### Limits
63
64 The default configuration for this integration does not impose any limits on data collection.
65
66 #### Performance Impact
67
68 The default configuration for this integration is not expected to impose a significant performance impact on the system.
69
70 ## Setup
71
72
73 ### Prerequisites
74
75 No action required.
76
77 ### Configuration
78
79 #### Options
80
81
82
83 There are no configuration options.
84
85
86
87 #### via File
88
89 There is no configuration file.
90
91 ##### Examples
92 There are no configuration examples.
93
94
95
96 ## Alerts
97
98
99 The following alerts are available:
100
101 | Alert name | On metric | Description |
102 |:------------|:----------|:------------|
103 | [ load_cpu_number ](https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf) | system.load | number of active CPU cores in the system |
104 | [ load_average_15 ](https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf) | system.load | system fifteen-minute load average |
105 | [ load_average_5 ](https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf) | system.load | system five-minute load average |
106 | [ load_average_1 ](https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf) | system.load | system one-minute load average |
107 | [ active_processes ](https://github.com/netdata/netdata/blob/master/src/health/health.d/processes.conf) | system.active_processes | system process IDs (PID) space utilization |
108
109
110 ## Metrics
111
112 Metrics grouped by *scope*.
113
114 The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels.
115
116
117
118 ### Per System Load Average instance
119
120
121
122 This scope has no labels.
123
124 Metrics:
125
126 | Metric | Dimensions | Unit |
127 |:------|:----------|:----|
128 | system.load | load1, load5, load15 | load |
129 | system.active_processes | active | processes |
130
131