feat(container): update image ghcr.io/home-operations/charts-mirror/dcgm-exporter ( 4.7.1 ➔ 4.8.1 )

[not-hydaz]

This PR contains the following updates:

Package	Update	Change
ghcr.io/home-operations/charts-mirror/dcgm-exporter	minor	4.7.1 → 4.8.1

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR has been generated by Renovate Bot.

[not-hydaz]

--- kubernetes/apps/observability/dcgm-exporter/app Kustomization: observability/dcgm-exporter OCIRepository: observability/dcgm-exporter

+++ kubernetes/apps/observability/dcgm-exporter/app Kustomization: observability/dcgm-exporter OCIRepository: observability/dcgm-exporter

@@ -10,9 +10,9 @@

 spec:
   interval: 15m
   layerSelector:
     mediaType: application/vnd.cncf.helm.chart.content.v1.tar+gzip
     operation: copy
   ref:
-    tag: 4.7.1
+    tag: 4.8.1
   url: oci://ghcr.io/home-operations/charts-mirror/dcgm-exporter
 

[not-hydaz]

--- HelmRelease: observability/dcgm-exporter ConfigMap: observability/exporter-metrics-config-map

+++ HelmRelease: observability/dcgm-exporter ConfigMap: observability/exporter-metrics-config-map

@@ -47,12 +47,13 @@

     # DCGM_FI_DEV_LOW_UTIL_VIOLATION,    counter, Throttling duration due to low utilization (in ns).
     # DCGM_FI_DEV_RELIABILITY_VIOLATION, counter, Throttling duration due to reliability constraints (in ns).
 
     # Memory usage
     DCGM_FI_DEV_FB_FREE, gauge, Framebuffer memory free (in MiB).
     DCGM_FI_DEV_FB_USED, gauge, Framebuffer memory used (in MiB).
+    DCGM_FI_DEV_FB_RESERVED, gauge, Framebuffer memory reserved (in MiB).
 
     # ECC
     # DCGM_FI_DEV_ECC_SBE_VOL_TOTAL, counter, Total number of single-bit volatile ECC errors.
     # DCGM_FI_DEV_ECC_DBE_VOL_TOTAL, counter, Total number of double-bit volatile ECC errors.
     # DCGM_FI_DEV_ECC_SBE_AGG_TOTAL, counter, Total number of single-bit persistent ECC errors.
     # DCGM_FI_DEV_ECC_DBE_AGG_TOTAL, counter, Total number of double-bit persistent ECC errors.
@@ -75,18 +76,21 @@

 
     # Remapped rows
     DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for uncorrectable errors
     DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS,   counter, Number of remapped rows for correctable errors
     DCGM_FI_DEV_ROW_REMAP_FAILURE,           gauge,   Whether remapping of rows has failed
 
+    # Static configuration information. These appear as labels on the other metrics
+    DCGM_FI_DRIVER_VERSION,        label, Driver Version
+
     # DCP metrics
     DCGM_FI_PROF_GR_ENGINE_ACTIVE,   gauge, Ratio of time the graphics engine is active.
     # DCGM_FI_PROF_SM_ACTIVE,          gauge, The ratio of cycles an SM has at least 1 warp assigned.
     # DCGM_FI_PROF_SM_OCCUPANCY,       gauge, The ratio of number of warps resident on an SM.
     DCGM_FI_PROF_PIPE_TENSOR_ACTIVE, gauge, Ratio of cycles the tensor (HMMA) pipe is active.
     DCGM_FI_PROF_DRAM_ACTIVE,        gauge, Ratio of cycles the device memory interface is active sending or receiving data.
     # DCGM_FI_PROF_PIPE_FP64_ACTIVE,   gauge, Ratio of cycles the fp64 pipes are active.
     # DCGM_FI_PROF_PIPE_FP32_ACTIVE,   gauge, Ratio of cycles the fp32 pipes are active.
     # DCGM_FI_PROF_PIPE_FP16_ACTIVE,   gauge, Ratio of cycles the fp16 pipes are active.
-    DCGM_FI_PROF_PCIE_TX_BYTES,      counter, The number of bytes of active pcie tx data including both header and payload.
-    DCGM_FI_PROF_PCIE_RX_BYTES,      counter, The number of bytes of active pcie rx data including both header and payload.
+    DCGM_FI_PROF_PCIE_TX_BYTES,      gauge, The rate of data transmitted over the PCIe bus - including both protocol headers and data payloads - in bytes per second.
+    DCGM_FI_PROF_PCIE_RX_BYTES,      gauge, The rate of data received over the PCIe bus - including both protocol headers and data payloads - in bytes per second.
 
--- HelmRelease: observability/dcgm-exporter DaemonSet: observability/dcgm-exporter

+++ HelmRelease: observability/dcgm-exporter DaemonSet: observability/dcgm-exporter

@@ -61,13 +61,13 @@

             add:
             - SYS_ADMIN
             drop:
             - ALL
           runAsNonRoot: false
           runAsUser: 0
-        image: nvcr.io/nvidia/k8s/dcgm-exporter:4.4.2-4.7.1-ubuntu22.04
+        image: nvcr.io/nvidia/k8s/dcgm-exporter:4.5.2-4.8.1-distroless
         imagePullPolicy: IfNotPresent
         args:
         - -f
         - /etc/dcgm-exporter/default-counters.csv
         env:
         - name: DCGM_EXPORTER_KUBERNETES
--- HelmRelease: observability/dcgm-exporter ServiceMonitor: observability/dcgm-exporter

+++ HelmRelease: observability/dcgm-exporter ServiceMonitor: observability/dcgm-exporter

@@ -19,10 +19,11 @@

     matchNames:
     - observability
   endpoints:
   - port: metrics
     path: /metrics
     interval: 15s
+    scrapeTimeout: 10s
     honorLabels: false
     relabelings: []
     metricRelabelings: []