This is an automated email from the ASF dual-hosted git repository.
hanahmily pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/skywalking-banyandb-helm.git
The following commit(s) were added to refs/heads/master by this push:
new 8f1b27f Enable FODC panic/crash diagnostics collection (#63)
8f1b27f is described below
commit 8f1b27f87edbf94b6dad9e787d07946bf8f1fa01
Author: mrproliu <[email protected]>
AuthorDate: Tue Jun 30 08:25:05 2026 +0800
Enable FODC panic/crash diagnostics collection (#63)
* Enable FODC panic/crash diagnostics collection
---
CHANGES.md | 2 +
chart/templates/cluster_data_statefulset.yaml | 39 +++++++++++++--
chart/templates/cluster_liaison_statefulset.yaml | 32 +++++++++++-
chart/templates/standalone_statefulset.yaml | 34 +++++++++++--
chart/values-lifecycle.yaml | 11 ++++
chart/values.yaml | 11 ++++
doc/parameters.md | 64 +++++++++++++-----------
7 files changed, 153 insertions(+), 40 deletions(-)
diff --git a/CHANGES.md b/CHANGES.md
index a3cfa38..9616a2a 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -10,6 +10,8 @@ Release Notes.
- Remove etcd support (breaking change).
If upgrading, remove `etcd-client.*` and `cluster.*.tls.etcdSecretName`
from your values overrides.
+- Enable FODC panic/crash diagnostics collection by default.
+ Configure via
`cluster.fodc.agent.config.crashCollection.{enabled,dir,maxArtifacts,diagnosisMemoryPercent}`.
0.6.0
-----------------
diff --git a/chart/templates/cluster_data_statefulset.yaml
b/chart/templates/cluster_data_statefulset.yaml
index d22e3e8..e4718a7 100644
--- a/chart/templates/cluster_data_statefulset.yaml
+++ b/chart/templates/cluster_data_statefulset.yaml
@@ -191,9 +191,21 @@ spec:
- name: {{ $env.name }}
value: {{ .value | toString | quote }}
{{- end }}
-
+ {{- if $.Values.cluster.fodc.enabled }}
+ - name: BYDB_PANIC_DIAGNOSTICS_ENABLED
+ value: {{
$.Values.cluster.fodc.agent.config.crashCollection.enabled | quote }}
+ {{- if $.Values.cluster.fodc.agent.config.crashCollection.enabled
}}
+ - name: BYDB_PANIC_DIAGNOSTICS_DIR
+ value: {{ $.Values.cluster.fodc.agent.config.crashCollection.dir
| quote }}
+ - name: BYDB_PANIC_DIAGNOSTICS_MAX_ARTIFACTS
+ value: {{
$.Values.cluster.fodc.agent.config.crashCollection.maxArtifacts | quote }}
+ - name: BYDB_MAX_DIAGNOSIS_MEMORY_USAGE_PERCENTAGE
+ value: {{
$.Values.cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent |
quote }}
+ {{- end }}
+ {{- end }}
+
args:
- - data
+ - data
ports:
- containerPort: 17912
name: grpc
@@ -253,7 +265,7 @@ spec:
{{- $schemaClientTls := $schemaProperty.tls | default dict }}
{{- $schemaServer := $schemaProperty.server | default dict }}
{{- $schemaServerTls := $schemaServer.tls | default dict }}
- {{- if or $.Values.storage.data.enabled $roleConfig.tls
$schemaClientTls.secretName $schemaServerTls.secretName $nodeDiscoveryFileMode
}}
+ {{- if or $.Values.storage.data.enabled $roleConfig.tls
$schemaClientTls.secretName $schemaServerTls.secretName $nodeDiscoveryFileMode
(and $.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumeMounts:
{{- if $.Values.storage.data.enabled }}
{{- range $claim := $.Values.storage.data.persistentVolumeClaims }}
@@ -294,6 +306,10 @@ spec:
name: node-discovery-file
readOnly: true
{{- end }}
+ {{- if and $.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ mountPath: {{
$.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
{{- if and $.Values.cluster.enabled $.Values.cluster.fodc.enabled }}
- name: fodc-agent
@@ -319,6 +335,9 @@ spec:
- --max-metrics-memory-usage-percentage={{
$.Values.cluster.fodc.agent.config.ktmEnabled | ternary 20 10 }}
- --heartbeat-interval={{
$.Values.cluster.fodc.agent.config.heartbeatInterval }}
- --reconnect-interval={{
$.Values.cluster.fodc.agent.config.reconnectInterval }}
+ {{- if $.Values.cluster.fodc.agent.config.crashCollection.enabled
}}
+ - --crash-source-dir={{
$.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
env:
- name: POD_NAME
valueFrom:
@@ -350,10 +369,16 @@ spec:
{{- end }}
{{- end }}
{{- end }}
- {{- if $roleConfig.lifecycleSidecar.enabled }}
+ {{- if or $roleConfig.lifecycleSidecar.enabled (and
$.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumeMounts:
+ {{- if $roleConfig.lifecycleSidecar.enabled }}
- name: lifecycle-report-shared
mountPath: {{ default "/tmp/lifecycle-reports"
$roleConfig.lifecycleSidecar.reportDir }}
+ {{- end }}
+ {{- if and $.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ mountPath: {{
$.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
{{- end }}
{{- if $roleConfig.backupSidecar.enabled }}
@@ -508,7 +533,7 @@ spec:
{{- end }}
{{- end }}
- {{- if or $roleConfig.tls $schemaClientTls.secretName
$schemaServerTls.secretName $nodeDiscoveryFileMode (and
$roleConfig.lifecycleSidecar.enabled $.Values.cluster.fodc.enabled) }}
+ {{- if or $roleConfig.tls $schemaClientTls.secretName
$schemaServerTls.secretName $nodeDiscoveryFileMode (and
$roleConfig.lifecycleSidecar.enabled $.Values.cluster.fodc.enabled) (and
$.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumes:
{{- if $roleConfig.tls }}
{{- if $roleConfig.tls.grpcSecretName }}
@@ -539,6 +564,10 @@ spec:
- name: lifecycle-report-shared
emptyDir: {}
{{- end }}
+ {{- if and $.Values.cluster.fodc.enabled
$.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ emptyDir: {}
+ {{- end }}
{{- end }}
{{- if $roleConfig.tolerations }}
diff --git a/chart/templates/cluster_liaison_statefulset.yaml
b/chart/templates/cluster_liaison_statefulset.yaml
index 7182256..f0efebf 100644
--- a/chart/templates/cluster_liaison_statefulset.yaml
+++ b/chart/templates/cluster_liaison_statefulset.yaml
@@ -157,6 +157,18 @@ spec:
- name: {{ $env.name }}
value: {{ $env.value }}
{{- end }}
+ {{- if .Values.cluster.fodc.enabled }}
+ - name: BYDB_PANIC_DIAGNOSTICS_ENABLED
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.enabled | quote }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: BYDB_PANIC_DIAGNOSTICS_DIR
+ value: {{ .Values.cluster.fodc.agent.config.crashCollection.dir
| quote }}
+ - name: BYDB_PANIC_DIAGNOSTICS_MAX_ARTIFACTS
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.maxArtifacts | quote }}
+ - name: BYDB_MAX_DIAGNOSIS_MEMORY_USAGE_PERCENTAGE
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent |
quote }}
+ {{- end }}
+ {{- end }}
args:
- liaison
{{- if .Values.auth.enabled }}
@@ -233,7 +245,7 @@ spec:
{{- $schemaProperty := (.Values.cluster.schemaStorage).property |
default dict }}
{{- $schemaClientTls := $schemaProperty.tls | default dict }}
- {{- if or .Values.storage.liaison.enabled
.Values.cluster.liaison.tls $schemaClientTls.secretName .Values.auth.enabled
$nodeDiscoveryFileMode }}
+ {{- if or .Values.storage.liaison.enabled
.Values.cluster.liaison.tls $schemaClientTls.secretName .Values.auth.enabled
$nodeDiscoveryFileMode (and .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumeMounts:
{{- if .Values.storage.liaison.enabled }}
{{- range $claim := .Values.storage.liaison.persistentVolumeClaims
}}
@@ -267,6 +279,10 @@ spec:
name: node-discovery-file
readOnly: true
{{- end }}
+ {{- if and .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ mountPath: {{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
{{- if and .Values.cluster.enabled .Values.cluster.fodc.enabled }}
@@ -290,6 +306,9 @@ spec:
- --max-metrics-memory-usage-percentage={{
.Values.cluster.fodc.agent.config.ktmEnabled | ternary 20 10 }}
- --heartbeat-interval={{
.Values.cluster.fodc.agent.config.heartbeatInterval }}
- --reconnect-interval={{
.Values.cluster.fodc.agent.config.reconnectInterval }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - --crash-source-dir={{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
env:
- name: POD_NAME
valueFrom:
@@ -321,9 +340,14 @@ spec:
{{- end }}
{{- end }}
{{- end }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ volumeMounts:
+ - name: crash-shared
+ mountPath: {{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
- {{- if or .Values.cluster.liaison.tls $schemaClientTls.secretName
.Values.auth.enabled $nodeDiscoveryFileMode }}
+ {{- if or .Values.cluster.liaison.tls $schemaClientTls.secretName
.Values.auth.enabled $nodeDiscoveryFileMode (and .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumes:
{{- if .Values.cluster.liaison.tls }}
{{- if .Values.cluster.liaison.tls.grpcSecretName }}
@@ -364,6 +388,10 @@ spec:
- name: banyandb-auth-writable
emptyDir: {}
{{- end }}
+ {{- if and .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ emptyDir: {}
+ {{- end }}
{{- end }}
{{- if .Values.cluster.liaison.tolerations }}
diff --git a/chart/templates/standalone_statefulset.yaml
b/chart/templates/standalone_statefulset.yaml
index 231c0b3..866548a 100644
--- a/chart/templates/standalone_statefulset.yaml
+++ b/chart/templates/standalone_statefulset.yaml
@@ -128,6 +128,18 @@ spec:
- name: {{ $env.name }}
value: {{ $env.value }}
{{- end }}
+ {{- if and .Values.cluster.enabled .Values.cluster.fodc.enabled }}
+ - name: BYDB_PANIC_DIAGNOSTICS_ENABLED
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.enabled | quote }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: BYDB_PANIC_DIAGNOSTICS_DIR
+ value: {{ .Values.cluster.fodc.agent.config.crashCollection.dir
| quote }}
+ - name: BYDB_PANIC_DIAGNOSTICS_MAX_ARTIFACTS
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.maxArtifacts | quote }}
+ - name: BYDB_MAX_DIAGNOSIS_MEMORY_USAGE_PERCENTAGE
+ value: {{
.Values.cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent |
quote }}
+ {{- end }}
+ {{- end }}
args:
- standalone
{{- if .Values.auth.enabled }}
@@ -200,7 +212,7 @@ spec:
{{- end }}
{{- end }}
- {{- if or .Values.storage.standalone.enabled .Values.standalone.tls
.Values.auth.enabled }}
+ {{- if or .Values.storage.standalone.enabled .Values.standalone.tls
.Values.auth.enabled (and .Values.cluster.enabled .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumeMounts:
{{- if .Values.storage.standalone.enabled }}
{{- range $claim :=
.Values.storage.standalone.persistentVolumeClaims }}
@@ -234,6 +246,10 @@ spec:
- mountPath: /etc/banyandb
name: banyandb-auth-writable
{{- end }}
+ {{- if and .Values.cluster.enabled .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ mountPath: {{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
{{- if and .Values.cluster.enabled .Values.cluster.fodc.enabled }}
@@ -245,7 +261,7 @@ spec:
{{- toYaml . | nindent 12 }}
{{- end }}
args:
- - --proxy-addr={{ template "banyandb.fullname" .
}}-fodc-proxy-grpc:{{ .Values.cluster.fodc.proxy.grpcSvc.port }} \
+ - --proxy-addr={{ template "banyandb.fullname" .
}}-fodc-proxy-grpc:{{ .Values.cluster.fodc.proxy.grpcSvc.port }}
- --pod-name=$(POD_NAME)
- --container-names=standalone
- --poll-metrics-ports=2121
@@ -257,6 +273,9 @@ spec:
- --max-metrics-memory-usage-percentage={{
.Values.cluster.fodc.agent.config.ktmEnabled | ternary 20 10 }}
- --heartbeat-interval={{
.Values.cluster.fodc.agent.config.heartbeatInterval }}
- --reconnect-interval={{
.Values.cluster.fodc.agent.config.reconnectInterval }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - --crash-source-dir={{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
env:
- name: POD_NAME
valueFrom:
@@ -288,9 +307,14 @@ spec:
{{- end }}
{{- end }}
{{- end }}
+ {{- if .Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ volumeMounts:
+ - name: crash-shared
+ mountPath: {{
.Values.cluster.fodc.agent.config.crashCollection.dir }}
+ {{- end }}
{{- end }}
- {{- if or .Values.standalone.tls .Values.auth.enabled }}
+ {{- if or .Values.standalone.tls .Values.auth.enabled (and
.Values.cluster.enabled .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled) }}
volumes:
{{- if .Values.standalone.tls }}
{{- if .Values.standalone.tls.grpcSecretName }}
@@ -318,6 +342,10 @@ spec:
- name: banyandb-auth-writable
emptyDir: {}
{{- end }}
+ {{- if and .Values.cluster.enabled .Values.cluster.fodc.enabled
.Values.cluster.fodc.agent.config.crashCollection.enabled }}
+ - name: crash-shared
+ emptyDir: {}
+ {{- end }}
{{- end }}
{{- if .Values.standalone.tolerations }}
diff --git a/chart/values-lifecycle.yaml b/chart/values-lifecycle.yaml
index 69a5a38..a71bb51 100644
--- a/chart/values-lifecycle.yaml
+++ b/chart/values-lifecycle.yaml
@@ -1035,6 +1035,17 @@ cluster:
reconnectInterval: 10s
## @param cluster.fodc.agent.config.ktmEnabled Enable Kernel Telemetry
Module (affects max-metrics-memory-usage-percentage)
ktmEnabled: true
+ ## Panic/crash diagnostics collection. Shares an emptyDir between the
banyand
+ ## container (writes panic.json) and the fodc-agent (reads & reports
it).
+ crashCollection:
+ ## @param cluster.fodc.agent.config.crashCollection.enabled Enable
panic/crash diagnostics collection
+ enabled: true
+ ## @param cluster.fodc.agent.config.crashCollection.dir Shared path
where banyand writes panic.json and fodc-agent reads it
+ dir: /tmp/crash
+ ## @param cluster.fodc.agent.config.crashCollection.maxArtifacts Max
crash artifact directories banyand retains (oldest removed first; 0 disables
pruning)
+ maxArtifacts: 10
+ ## @param
cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent Set banyand
GOMEMLIMIT to this percent of the cgroup memory limit, reserving headroom for
post-panic diagnostics (0 disables)
+ diagnosisMemoryPercent: 50
## Liveness probe for Agent
livenessProbe:
## @param cluster.fodc.agent.livenessProbe.initialDelaySeconds Initial
delay for Agent liveness probe
diff --git a/chart/values.yaml b/chart/values.yaml
index 051f779..694fffc 100644
--- a/chart/values.yaml
+++ b/chart/values.yaml
@@ -1056,6 +1056,17 @@ cluster:
ktmEnabled: true
## @param cluster.fodc.agent.config.pollClusterStateInterval Interval
for polling cluster state from Proxy (poll-cluster-state-interval flag)
pollClusterStateInterval: 30s
+ ## Panic/crash diagnostics collection. Shares an emptyDir between the
banyand
+ ## container (writes panic.json) and the fodc-agent (reads & reports
it).
+ crashCollection:
+ ## @param cluster.fodc.agent.config.crashCollection.enabled Enable
panic/crash diagnostics collection
+ enabled: true
+ ## @param cluster.fodc.agent.config.crashCollection.dir Shared path
where banyand writes panic.json and fodc-agent reads it
+ dir: /tmp/crash
+ ## @param cluster.fodc.agent.config.crashCollection.maxArtifacts Max
crash artifact directories banyand retains (oldest removed first; 0 disables
pruning)
+ maxArtifacts: 10
+ ## @param
cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent Set banyand
GOMEMLIMIT to this percent of the cgroup memory limit, reserving headroom for
post-panic diagnostics (0 disables)
+ diagnosisMemoryPercent: 50
## Liveness probe for Agent
livenessProbe:
## @param cluster.fodc.agent.livenessProbe.initialDelaySeconds Initial
delay for Agent liveness probe
diff --git a/doc/parameters.md b/doc/parameters.md
index 246e608..d52581d 100644
--- a/doc/parameters.md
+++ b/doc/parameters.md
@@ -377,36 +377,40 @@ The content of this document describes the parameters
that can be configured in
### FODC Agent sidecar
-| Name | Description
| Value
|
-| ------------------------------------------------------ |
---------------------------------------------------------------------------- |
------------------------------------------------- |
-| `cluster.fodc.agent.image.repository` | Docker repository
for FODC Agent |
`ghcr.io/apache/skywalking-banyandb-fodc-agent` |
-| `cluster.fodc.agent.image.tag` | Image tag/version
for FODC Agent (defaults to same as main image) | `""`
|
-| `cluster.fodc.agent.image.pullPolicy` | Image pull policy
for FODC Agent | `IfNotPresent`
|
-| `cluster.fodc.agent.env` | Environment
variables for Agent sidecar | `[]`
|
-| `cluster.fodc.agent.containerSecurityContext` | Container-level
security context for Agent | `{}`
|
-| `cluster.fodc.agent.resources.requests` | Resource requests
for Agent | `{"memory":
"256Mi"}` |
-| `cluster.fodc.agent.resources.limits` | Resource limits
for Agent | `{"memory":
"256Mi"}` |
-| `cluster.fodc.agent.metricsPort` | Metrics port for
Agent sidecar (prometheus-listen-addr flag) | `9090`
|
-| `cluster.fodc.agent.config.pollMetricsInterval` | Interval for
polling BanyanDB metrics (poll-metrics-interval flag) | `15s`
|
-| `cluster.fodc.agent.config.heartbeatInterval` | Heartbeat interval
to Proxy (heartbeat-interval flag) | `10s`
|
-| `cluster.fodc.agent.config.reconnectInterval` | Reconnect interval
when connection to Proxy is lost (reconnect-interval flag) | `10s`
|
-| `cluster.fodc.agent.config.ktmEnabled` | Enable Kernel
Telemetry Module (affects max-metrics-memory-usage-percentage) | `true`
|
-| `cluster.fodc.agent.config.pollClusterStateInterval` | Interval for
polling cluster state from Proxy (poll-cluster-state-interval flag) | `30s`
|
-| `cluster.fodc.agent.livenessProbe.initialDelaySeconds` | Initial delay for
Agent liveness probe | `90`
|
-| `cluster.fodc.agent.livenessProbe.periodSeconds` | Probe period for
Agent liveness probe | `30`
|
-| `cluster.fodc.agent.livenessProbe.timeoutSeconds` | Timeout in seconds
for Agent liveness probe | `5`
|
-| `cluster.fodc.agent.livenessProbe.successThreshold` | Success threshold
for Agent liveness probe | `1`
|
-| `cluster.fodc.agent.livenessProbe.failureThreshold` | Failure threshold
for Agent liveness probe | `5`
|
-| `cluster.fodc.agent.readinessProbe.initialDelaySeconds` | Initial delay for
Agent readiness probe | `60`
|
-| `cluster.fodc.agent.readinessProbe.periodSeconds` | Probe period for
Agent readiness probe | `10`
|
-| `cluster.fodc.agent.readinessProbe.timeoutSeconds` | Timeout in seconds
for Agent readiness probe | `5`
|
-| `cluster.fodc.agent.readinessProbe.successThreshold` | Success threshold
for Agent readiness probe | `1`
|
-| `cluster.fodc.agent.readinessProbe.failureThreshold` | Failure threshold
for Agent readiness probe | `12`
|
-| `cluster.fodc.agent.startupProbe.initialDelaySeconds` | Initial delay for
Agent startup probe | `30`
|
-| `cluster.fodc.agent.startupProbe.periodSeconds` | Probe period for
Agent startup probe | `5`
|
-| `cluster.fodc.agent.startupProbe.timeoutSeconds` | Timeout in seconds
for Agent startup probe | `3`
|
-| `cluster.fodc.agent.startupProbe.successThreshold` | Success threshold
for Agent startup probe | `1`
|
-| `cluster.fodc.agent.startupProbe.failureThreshold` | Failure threshold
for Agent startup probe | `60`
|
+| Name |
Description
| Value
|
+|--------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------|
+| `cluster.fodc.agent.image.repository` | Docker
repository for FODC Agent
|
`ghcr.io/apache/skywalking-banyandb-fodc-agent` |
+| `cluster.fodc.agent.image.tag` | Image
tag/version for FODC Agent (defaults to same as main image)
| `""`
|
+| `cluster.fodc.agent.image.pullPolicy` | Image
pull policy for FODC Agent
| `IfNotPresent`
|
+| `cluster.fodc.agent.env` |
Environment variables for Agent sidecar
| `[]`
|
+| `cluster.fodc.agent.containerSecurityContext` |
Container-level security context for Agent
| `{}`
|
+| `cluster.fodc.agent.resources.requests` |
Resource requests for Agent
| `{"memory": "256Mi"}`
|
+| `cluster.fodc.agent.resources.limits` |
Resource limits for Agent
| `{"memory": "256Mi"}`
|
+| `cluster.fodc.agent.metricsPort` | Metrics
port for Agent sidecar (prometheus-listen-addr flag)
| `9090`
|
+| `cluster.fodc.agent.config.pollMetricsInterval` |
Interval for polling BanyanDB metrics (poll-metrics-interval flag)
| `15s`
|
+| `cluster.fodc.agent.config.heartbeatInterval` |
Heartbeat interval to Proxy (heartbeat-interval flag)
| `10s`
|
+| `cluster.fodc.agent.config.reconnectInterval` |
Reconnect interval when connection to Proxy is lost (reconnect-interval flag)
| `10s`
|
+| `cluster.fodc.agent.config.ktmEnabled` | Enable
Kernel Telemetry Module (affects max-metrics-memory-usage-percentage)
| `true`
|
+| `cluster.fodc.agent.config.pollClusterStateInterval` |
Interval for polling cluster state from Proxy (poll-cluster-state-interval
flag) | `30s`
|
+| `cluster.fodc.agent.config.crashCollection.enabled` | Enable
panic/crash diagnostics collection
| `true`
|
+| `cluster.fodc.agent.config.crashCollection.dir` | Shared
path where banyand writes panic.json and fodc-agent reads it
| `/tmp/crash`
|
+| `cluster.fodc.agent.config.crashCollection.maxArtifacts` | Max
crash artifact directories banyand retains (oldest removed first; 0 disables
pruning) | `10`
|
+| `cluster.fodc.agent.config.crashCollection.diagnosisMemoryPercent` | Set
banyand GOMEMLIMIT to this percent of the cgroup memory limit, reserving
headroom for post-panic diagnostics (0 disables) | `50`
|
+| `cluster.fodc.agent.livenessProbe.initialDelaySeconds` | Initial
delay for Agent liveness probe
| `90`
|
+| `cluster.fodc.agent.livenessProbe.periodSeconds` | Probe
period for Agent liveness probe
| `30`
|
+| `cluster.fodc.agent.livenessProbe.timeoutSeconds` | Timeout
in seconds for Agent liveness probe
| `5`
|
+| `cluster.fodc.agent.livenessProbe.successThreshold` | Success
threshold for Agent liveness probe
| `1`
|
+| `cluster.fodc.agent.livenessProbe.failureThreshold` | Failure
threshold for Agent liveness probe
| `5`
|
+| `cluster.fodc.agent.readinessProbe.initialDelaySeconds` | Initial
delay for Agent readiness probe
| `60`
|
+| `cluster.fodc.agent.readinessProbe.periodSeconds` | Probe
period for Agent readiness probe
| `10`
|
+| `cluster.fodc.agent.readinessProbe.timeoutSeconds` | Timeout
in seconds for Agent readiness probe
| `5`
|
+| `cluster.fodc.agent.readinessProbe.successThreshold` | Success
threshold for Agent readiness probe
| `1`
|
+| `cluster.fodc.agent.readinessProbe.failureThreshold` | Failure
threshold for Agent readiness probe
| `12`
|
+| `cluster.fodc.agent.startupProbe.initialDelaySeconds` | Initial
delay for Agent startup probe
| `30`
|
+| `cluster.fodc.agent.startupProbe.periodSeconds` | Probe
period for Agent startup probe
| `5`
|
+| `cluster.fodc.agent.startupProbe.timeoutSeconds` | Timeout
in seconds for Agent startup probe
| `3`
|
+| `cluster.fodc.agent.startupProbe.successThreshold` | Success
threshold for Agent startup probe
| `1`
|
+| `cluster.fodc.agent.startupProbe.failureThreshold` | Failure
threshold for Agent startup probe
| `60`
|
### Storage configuration for persistent volumes
