RepoMirrors/node_exporter
1
0
Fork 0
mirror of https://github.com/prometheus/node_exporter synced 2024-12-17 20:05:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Replace load average with PSI metric

Browse Source 
The load average metric is misleading as a representation of CPU
saturation. Normal CPU utilization is a better real representation of
saturation.

On newer Linux, there is a new Pressure Stall Information[0] metric that
better represents CPU over saturation. This is also useful as it can
make single-core saturation more visible.

[0]: https://www.kernel.org/doc/html/latest/accounting/psi.html

Signed-off-by: Ben Kochie <superq@gmail.com>
This commit is contained in:
Ben Kochie 2021-08-19 12:19:26 +02:00
parent aea88e4dc5
commit d90b2d83d7
No known key found for this signature in database
GPG Key ID: C646B23C9E3245F1
1 changed files with 8 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docs/node-mixin/rules/rules.libsonnet
View File

@ -16,7 +16,7 @@
||| % $._config, ||| % $._config,
}, },
{ {
// CPU utilisation is % CPU is not idle. // CPU utilisation is % CPU is not idle. This represents CPU saturation.
record: 'instance:node_cpu_utilisation:rate%(rateInterval)s' % $._config, record: 'instance:node_cpu_utilisation:rate%(rateInterval)s' % $._config,
expr: ||| expr: |||
1 - avg without (cpu, mode) ( 1 - avg without (cpu, mode) (
@ -25,17 +25,14 @@
||| % $._config, ||| % $._config,
}, },
{ {
// This is CPU saturation: 1min avg run queue length / number of CPUs. // CPU pressure represents over-saturation. This is the amount of CPU seconds
// Can go over 1. // requested, but the kernel was not able to schedule.
// TODO: There are situation where a run queue >1/core is just normal and fine. // NOTE: This is only availalbe on Linux >= 4.19 and `CONFIG_PSI` is enabled.
// We need to clarify how to read this metric and if its usage is helpful at all. // See also:
record: 'instance:node_load1_per_cpu:ratio', // - https://www.kernel.org/doc/html/latest/accounting/psi.html
// - https://facebookmicrosites.github.io/psi/docs/overview
expr: ||| expr: |||
( rate(node_pressure_cpu_waiting_seconds_total{%(nodeExporterSelector)s}[%(rateInterval)s])
node_load1{%(nodeExporterSelector)s}
/
instance:node_num_cpu:sum{%(nodeExporterSelector)s}
)
||| % $._config, ||| % $._config,
}, },
{ {