commit 12138dfea0d2a021b49635380b7e12a1f67df794 parent 9b242ee4173470af9c360f612a19a6eb841bfe83 Author: MTRNord <MTRNord@users.noreply.github.com> Date: Fri, 27 Mar 2026 10:59:28 +0100 further backup fixes Signed-off-by: MTRNord <MTRNord@users.noreply.github.com> Diffstat:
| M | infrastructure_talos/configs/velero-alerts.yaml | | | 8 | +++++--- |
| M | infrastructure_talos/controllers/descheduler.yaml | | | 1 | + |
| M | infrastructure_talos/controllers/velero/release.yaml | | | 8 | +++++--- |
3 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/infrastructure_talos/configs/velero-alerts.yaml b/infrastructure_talos/configs/velero-alerts.yaml @@ -11,13 +11,15 @@ spec: rules: - alert: VeleroBackupPartialFailure expr: | - increase(velero_backup_partial_failure_total{schedule!=""}[1h]) > 0 + increase(velero_backup_partial_failure_total{schedule!=""}[6h]) > 0 + and on(schedule) + (time() - velero_backup_last_successful_timestamp{schedule!=""}) > 21600 for: 15m labels: severity: warning annotations: - summary: "Velero backup partially failed" - description: "Schedule {{ $labels.schedule }} has partial failures in the last hour." + summary: "Velero backup partially failed and no recent success" + description: "Schedule {{ $labels.schedule }} has partial failures and no successful backup in the last 6 hours." - alert: VeleroBackupFailure expr: | diff --git a/infrastructure_talos/controllers/descheduler.yaml b/infrastructure_talos/controllers/descheduler.yaml @@ -29,6 +29,7 @@ spec: namespace: descheduler interval: 12h values: + schedule: "*/30 * * * *" tolerations: - key: "arch" operator: "Equal" diff --git a/infrastructure_talos/controllers/velero/release.yaml b/infrastructure_talos/controllers/velero/release.yaml @@ -28,13 +28,15 @@ spec: deployNodeAgent: true nodeAgent: + extraArgs: + - --uploader-concurrency=4 resources: requests: cpu: 100m - memory: 128Mi + memory: 256Mi limits: - cpu: "1" - memory: 1Gi + cpu: "2" + memory: 2Gi metrics: enabled: true