diff --git a/backend/probes/default.json b/backend/probes/default.json index 85f8274..1d1c6ee 100644 --- a/backend/probes/default.json +++ b/backend/probes/default.json @@ -283,7 +283,7 @@ } }, "k8s Pods": { - "command" : "kubectl get pods -A 2>/dev/null | egrep -i 'Err|Failed|ImagePull|Pending|Creating'", + "command" : "(kubectl get pods -A 2>/dev/null || kubectl get pods 2>/dev/null) | egrep -i 'Err|Failed|ImagePull|Pending|Creating'", "local" : "True", "localOnly" : "True", "initial": "True", @@ -298,7 +298,7 @@ } }, "k8s PVCs": { - "command": "kubectl get pvc -A 2>/dev/null | egrep -i 'Failed|Pending'", + "command": "(kubectl get pvc -A 2>/dev/null || kubectl get pvc 2>/dev/null) | egrep -i 'Failed|Pending'", "local" : "True", "localOnly" : "True", "initial": "True", diff --git a/frontend/notebooks/systemd.md b/frontend/notebooks/systemd.md index c2a93a7..8575038 100644 --- a/frontend/notebooks/systemd.md +++ b/frontend/notebooks/systemd.md @@ -1,12 +1,43 @@ # %% [markdown] ## Debugging Systemd Problems +# %% [markdown] +Status for a specific unit +# %% [shell] +systemctl status dbus # %% [markdown] Failed systemd units # %% [shell] systemctl --failed # %% [markdown] -Status for a specific unit +Reset a failed unit. This is useful if the restart of a unit runs into a rate limit and you cannot restart it anymore. +# %% [shell] +systemctl reset-failed +# %% [markdown] +### Modifying Units +# %% [shell] +systemctl edit +systemctl daemon-reload +# %% [markdown] +### Performance Debugging +# %% [shell] +systemd-analyze blame +# %% [markdown] +### Logging Disk Space + +Show used disk space +# %% [shell] +journalctl --disk-usage +# %% [markdown] +Force a log rotation +# %% [shell] +journalctl --rotate +# %% [markdown] +Drop all logs older 2 days +# %% [shell] +journalctl --vacuum-time=2d +# %% [markdown] +Free everything until only 100MB used # %% [shell] -systemctl status dbus \ No newline at end of file +journalctl --vacuum-size=100M \ No newline at end of file