docs/node-mixin: Improve memory pressure rule

The `instance:node_memory_swap_io_pages:rate1m` rule was intended to
measure the amount of memory pressure a system is under, but its name is
a bit misleading (it specifically refers to swap), and the rate of
`node_vmstat_pgmajfault` is a better metric for memory pressure
(see #1524).

This commit renames `instance:node_memory_swap_io_pages:rate1m` to
`instance:node_vmstat_pgmajfault:rate1m`, and defines it as
`rate(node_vmstat_pgmajfault{%(nodeExporterSelector)s}[1m])`. The
dashboards are updated accordingly.

Signed-off-by: Benoît Knecht <benoit.knecht@fsfe.org>

2 files changed, 6 insertions, 10 deletions

diff --git a/docs/node-mixin/dashboards/use.libsonnet b/docs/node-mixin/dashboards/use.libsonnet
index 8463ab9..d2a568f 100644
--- a/docs/node-mixin/dashboards/use.libsonnet
+++ b/docs/node-mixin/dashboards/use.libsonnet
@@ -53,8 +53,8 @@ local g = import 'grafana-builder/grafana.libsonnet';
           { yaxes: g.yaxes({ format: 'percentunit', max: 1 }) },
         )
         .addPanel(
-          g.panel('Memory Saturation (Swapped Pages)') +
-          g.queryPanel('instance:node_memory_swap_io_pages:rate1m{%(nodeExporterSelector)s}' % $._config, '{{instance}}', legendLink) +
+          g.panel('Memory Saturation (Major Page Faults)') +
+          g.queryPanel('instance:node_vmstat_pgmajfault:rate1m{%(nodeExporterSelector)s}' % $._config, '{{instance}}', legendLink) +
           g.stack +
           { yaxes: g.yaxes('rps') },
         )
@@ -201,8 +201,8 @@ local g = import 'grafana-builder/grafana.libsonnet';
           { yaxes: g.yaxes('percentunit') },
         )
         .addPanel(
-          g.panel('Memory Saturation (pages swapped per second)') +
-          g.queryPanel('instance:node_memory_swap_io_pages:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Swap IO') +
+          g.panel('Memory Saturation (Major Page Faults)') +
+          g.queryPanel('instance:node_vmstat_pgmajfault:rate1m{%(nodeExporterSelector)s, instance="$instance"}' % $._config, 'Major page faults') +
           {
             yaxes: g.yaxes('short'),
             legend+: { show: false },
diff --git a/docs/node-mixin/rules/rules.libsonnet b/docs/node-mixin/rules/rules.libsonnet
index 85f7618..6b396e3 100644
--- a/docs/node-mixin/rules/rules.libsonnet
+++ b/docs/node-mixin/rules/rules.libsonnet
@@ -50,13 +50,9 @@
             ||| % $._config,
           },
           {
-            record: 'instance:node_memory_swap_io_pages:rate1m',
+            record: 'instance:node_vmstat_pgmajfault:rate1m',
             expr: |||
-              (
-                rate(node_vmstat_pgpgin{%(nodeExporterSelector)s}[1m])
-              +
-                rate(node_vmstat_pgpgout{%(nodeExporterSelector)s}[1m])
-              )
+              rate(node_vmstat_pgmajfault{%(nodeExporterSelector)s}[1m])
             ||| % $._config,
           },
           {