You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|`system.linux.psi.total_time`| Counter |`us`| Linux Pressure Stall Information (PSI) total cumulative stall time. [1]||[`host`](/docs/registry/entities/host.md#host)|
1395
+
|`system.linux.psi.total_time`| Counter |`s`| Linux Pressure Stall Information (PSI) total cumulative stall time. [1]||[`host`](/docs/registry/entities/host.md#host)|
1398
1396
1399
-
**[1]:** This metric tracks the total absolute stall time in microseconds since system boot.
1397
+
**[1]:** This metric tracks the total absolute stall time since system boot.
1400
1398
Unlike the percentage-based `system.linux.psi.pressure` metric, this allows detection
1401
1399
of latency spikes that wouldn't necessarily make a noticeable impact on time averages.
1402
1400
It also enables calculating average trends over custom time frames.
@@ -1406,6 +1404,9 @@ CPU "full" stall is reported as zero at the system level for backward compatibil
1406
1404
1407
1405
This is a monotonically increasing counter that resets on system reboot.
1408
1406
1407
+
Linux exposes this metric in microseconds. Following OpenTelemetry guidelines for measuring durations,
1408
+
this metric uses seconds.
1409
+
1409
1410
See [Linux kernel PSI documentation](https://docs.kernel.org/accounting/psi.html)
0 commit comments