mirror of
https://github.com/NVIDIA/OpenShell.git
synced 2026-10-19 05:50:41 +08:00
krishicks
33a8eac196
Previously, Helm installations could not enable the gateway OCSF JSONL destination through chart values because generated `gateway.toml` omitted the `openshell.gateway.ocsf_log` table. Now, setting `server.ocsfLog.enabled` renders the path, optional schema version, rotation, retention, and queue limits into gateway configuration. Output is disabled by default. The default path, `/tmp/gateway-ocsf.jsonl`, is writable in the gateway container with either the StatefulSet or Deployment workload, so enabling output does not require persistent storage. Invalid schema versions, rotation values, non-positive limits, or an empty path while enabled fail chart rendering. Additionally, `server.extraVolumes` and `server.extraVolumeMounts` add operator-supplied volumes to the gateway pod, so operators who want records to survive restarts can place the OCSF path on persistent storage without replacing chart-generated configuration. The gateway pod's default termination grace period rises from 5 to 30 seconds. Gateway shutdown can spend up to 10 seconds on supervisor session cleanup before allowing 5 seconds to drain queued OCSF records, so the 5-second default risked a SIGKILL before the final records were written. The grace period is only an upper bound: the gateway exits as soon as its shutdown completes. Refs #2762 Signed-off-by: Kris Hicks <khicks@nvidia.com>
313 lines
12 KiB
Smarty
313 lines
12 KiB
Smarty
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
{{/*
|
|
Gateway pod template shared by the StatefulSet and Deployment workload shapes.
|
|
*/}}
|
|
{{- define "openshell.gatewayPodTemplate" -}}
|
|
metadata:
|
|
annotations:
|
|
# Roll the gateway workload when the rendered gateway TOML changes - the
|
|
# gateway only reads /etc/openshell/gateway.toml at startup, so without
|
|
# this annotation a `helm upgrade` that only mutates the ConfigMap would
|
|
# leave pods running with stale config.
|
|
checksum/gateway-config: {{ include (print $.Template.BasePath "/gateway-config.yaml") . | sha256sum }}
|
|
{{- with .Values.podAnnotations }}
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
labels:
|
|
{{- include "openshell.labels" . | nindent 4 }}
|
|
{{- with .Values.podLabels }}
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
spec:
|
|
terminationGracePeriodSeconds: {{ .Values.podLifecycle.terminationGracePeriodSeconds }}
|
|
{{- with .Values.imagePullSecrets }}
|
|
imagePullSecrets:
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
serviceAccountName: {{ include "openshell.serviceAccountName" . }}
|
|
{{- if .Values.server.hostGatewayIP }}
|
|
hostAliases:
|
|
- ip: {{ .Values.server.hostGatewayIP | quote }}
|
|
hostnames:
|
|
- host.docker.internal
|
|
- host.openshell.internal
|
|
{{- end }}
|
|
{{- with .Values.podSecurityContext }}
|
|
securityContext:
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
containers:
|
|
- name: openshell-gateway
|
|
securityContext:
|
|
{{- toYaml .Values.securityContext | nindent 8 }}
|
|
image: {{ include "openshell.image" . | quote }}
|
|
imagePullPolicy: {{ .Values.gateway.image.pullPolicy | default .Values.global.image.pullPolicy }}
|
|
args:
|
|
- --config
|
|
- /etc/openshell/gateway.toml
|
|
{{- if not .Values.server.externalDbSecret }}
|
|
- --db-url
|
|
- {{ .Values.server.dbUrl | quote }}
|
|
{{- end }}
|
|
env:
|
|
- name: OPENSHELL_REPLICA_ID
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.name
|
|
- name: OPENSHELL_POD_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.name
|
|
- name: OPENSHELL_POD_NAMESPACE
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.namespace
|
|
{{- if eq (include "openshell.workloadKind" .) "deployment" }}
|
|
- name: OPENSHELL_POD_IP
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: status.podIP
|
|
- name: OPENSHELL_PEER_ENDPOINT
|
|
value: {{ printf "%s://$(OPENSHELL_POD_IP):%d" (ternary "http" "https" (default false .Values.server.disableTls)) (int .Values.service.port) | quote }}
|
|
{{- end }}
|
|
- name: OPENSHELL_SERVICE_ACCOUNT_NAME
|
|
value: {{ include "openshell.serviceAccountName" . | quote }}
|
|
- name: OPENSHELL_PEER_SERVICE_NAME
|
|
value: {{ include "openshell.peerServiceName" . | quote }}
|
|
- name: OPENSHELL_PEER_TOKEN_AUDIENCE
|
|
value: "openshell-gateway-peer"
|
|
- name: OPENSHELL_PEER_SERVICE_ACCOUNT_TOKEN_FILE
|
|
value: /var/run/secrets/openshell-peer/token
|
|
- name: OPENSHELL_PEER_POD_LABELS
|
|
value: {{ printf "app.kubernetes.io/name=%s,app.kubernetes.io/instance=%s" (include "openshell.name" .) .Release.Name | quote }}
|
|
{{- if not .Values.server.disableTls }}
|
|
- name: OPENSHELL_PEER_TLS_SERVER_NAME
|
|
value: {{ printf "%s.%s.svc.cluster.local" (include "openshell.fullname" .) .Release.Namespace | quote }}
|
|
{{- if or .Values.pkiInitJob.enabled .Values.certManager.enabled }}
|
|
- name: OPENSHELL_PEER_TLS_CA_FILE
|
|
value: /etc/openshell-tls/server/ca.crt
|
|
{{- end }}
|
|
{{- if eq (include "openshell.gatewayClientCaEnabled" .) "true" }}
|
|
- name: OPENSHELL_PEER_TLS_CERT_FILE
|
|
value: /etc/openshell-tls/peer-client/tls.crt
|
|
- name: OPENSHELL_PEER_TLS_KEY_FILE
|
|
value: /etc/openshell-tls/peer-client/tls.key
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (or .Values.server.credentialDrivers.kubernetesSecrets.enabled .Values.server.credentialDrivers.vault.enabled) }}
|
|
- name: {{ include "openshell.credentialStorageKeyEncryptionKeyEnvName" . }}
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: {{ include "openshell.credentialStorageKeyEncryptionKeySecretName" . }}
|
|
key: {{ include "openshell.credentialStorageKeyEncryptionKeySecretKey" . }}
|
|
{{- end }}
|
|
{{- if .Values.server.externalDbSecret }}
|
|
- name: OPENSHELL_DB_URL
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: {{ .Values.server.externalDbSecret }}
|
|
key: uri
|
|
{{- end }}
|
|
# Most gateway settings live in the ConfigMap-backed TOML file
|
|
# mounted at /etc/openshell/gateway.toml. Secret-bearing settings use
|
|
# env vars that the TOML references by name. Some process-level
|
|
# settings consumed by libraries outside gateway code also remain here.
|
|
{{- if and .Values.server.oidc.issuer .Values.server.oidc.caConfigMapName }}
|
|
# OIDC issuer custom-CA: rustls/reqwest read SSL_CERT_FILE for
|
|
# outbound TLS verification. This is a process-level env var
|
|
# consumed by the TLS stack itself, not by gateway code, so it
|
|
# cannot be represented in the gateway TOML schema.
|
|
- name: SSL_CERT_FILE
|
|
value: /etc/openshell-tls/oidc-ca/ca.crt
|
|
{{- end }}
|
|
- name: OPENSHELL_TELEMETRY_ENABLED
|
|
value: {{ .Values.server.telemetryEnabled | quote }}
|
|
{{- if .Values.server.providerTokenGrants.spiffe.enabled }}
|
|
- name: OPENSHELL_GATEWAY_SPIFFE_WORKLOAD_API_SOCKET
|
|
value: {{ .Values.server.providerTokenGrants.spiffe.workloadApiSocketPath | quote }}
|
|
{{- end }}
|
|
volumeMounts:
|
|
{{- if eq (include "openshell.workloadKind" .) "statefulset" }}
|
|
- name: openshell-data
|
|
mountPath: /var/openshell
|
|
{{- end }}
|
|
# ConfigMap directory mounts expose keys through atomic-writer symlinks,
|
|
# while the gateway intentionally rejects symlinked configuration.
|
|
# The checksum annotation above rolls pods when this subPath changes.
|
|
- name: gateway-config
|
|
mountPath: /etc/openshell/gateway.toml
|
|
subPath: gateway.toml
|
|
readOnly: true
|
|
- name: sandbox-jwt
|
|
mountPath: /etc/openshell-jwt
|
|
readOnly: true
|
|
- name: gateway-peer-token
|
|
mountPath: /var/run/secrets/openshell-peer
|
|
readOnly: true
|
|
{{- if not .Values.server.disableTls }}
|
|
- name: tls-cert
|
|
mountPath: /etc/openshell-tls/server
|
|
readOnly: true
|
|
{{- if .Values.certManager.serverIssuerRef.name }}
|
|
- name: tls-external-cert
|
|
mountPath: /etc/openshell-tls/server-external
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- if eq (include "openshell.gatewayClientCaEnabled" .) "true" }}
|
|
- name: peer-client-tls
|
|
mountPath: /etc/openshell-tls/peer-client
|
|
readOnly: true
|
|
- name: tls-client-ca
|
|
mountPath: /etc/openshell-tls/client-ca
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if and .Values.server.oidc.issuer .Values.server.oidc.caConfigMapName }}
|
|
- name: oidc-ca
|
|
mountPath: /etc/openshell-tls/oidc-ca
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- if and .Values.server.credentialDrivers.vault.enabled .Values.server.credentialDrivers.vault.caConfigMapName }}
|
|
- name: vault-ca
|
|
mountPath: /etc/openshell-tls/vault-ca
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- if .Values.upstreamProxy.caBundle.configMapName }}
|
|
- name: upstream-proxy-ca
|
|
mountPath: /etc/openshell-tls/proxy-ca
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- if .Values.server.providerTokenGrants.spiffe.enabled }}
|
|
- name: spiffe-workload-api
|
|
mountPath: {{ dir .Values.server.providerTokenGrants.spiffe.workloadApiSocketPath | quote }}
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- with .Values.server.extraVolumeMounts }}
|
|
{{- toYaml . | nindent 8 }}
|
|
{{- end }}
|
|
ports:
|
|
- name: grpc
|
|
containerPort: {{ .Values.service.port }}
|
|
protocol: TCP
|
|
- name: health
|
|
containerPort: {{ .Values.service.healthPort }}
|
|
protocol: TCP
|
|
{{- if .Values.service.metricsPort }}
|
|
- name: metrics
|
|
containerPort: {{ .Values.service.metricsPort }}
|
|
protocol: TCP
|
|
{{- end }}
|
|
startupProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: health
|
|
periodSeconds: {{ .Values.probes.startup.periodSeconds }}
|
|
timeoutSeconds: {{ .Values.probes.startup.timeoutSeconds }}
|
|
failureThreshold: {{ .Values.probes.startup.failureThreshold }}
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: health
|
|
initialDelaySeconds: {{ .Values.probes.liveness.initialDelaySeconds }}
|
|
periodSeconds: {{ .Values.probes.liveness.periodSeconds }}
|
|
timeoutSeconds: {{ .Values.probes.liveness.timeoutSeconds }}
|
|
failureThreshold: {{ .Values.probes.liveness.failureThreshold }}
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /readyz
|
|
port: health
|
|
initialDelaySeconds: {{ .Values.probes.readiness.initialDelaySeconds }}
|
|
periodSeconds: {{ .Values.probes.readiness.periodSeconds }}
|
|
timeoutSeconds: {{ .Values.probes.readiness.timeoutSeconds }}
|
|
failureThreshold: {{ .Values.probes.readiness.failureThreshold }}
|
|
resources:
|
|
{{- toYaml .Values.resources | nindent 8 }}
|
|
volumes:
|
|
- name: gateway-config
|
|
configMap:
|
|
name: {{ include "openshell.fullname" . }}-config
|
|
- name: sandbox-jwt
|
|
secret:
|
|
secretName: {{ include "openshell.sandboxJwtSecretName" . }}
|
|
defaultMode: {{ .Values.server.sandboxJwt.secretDefaultMode | default 0400 }}
|
|
- name: gateway-peer-token
|
|
projected:
|
|
defaultMode: 0400
|
|
sources:
|
|
- serviceAccountToken:
|
|
path: token
|
|
audience: openshell-gateway-peer
|
|
expirationSeconds: 3600
|
|
{{- if not .Values.server.disableTls }}
|
|
- name: tls-cert
|
|
secret:
|
|
secretName: {{ .Values.server.tls.certSecretName }}
|
|
{{- if .Values.certManager.serverIssuerRef.name }}
|
|
- name: tls-external-cert
|
|
secret:
|
|
secretName: {{ include "openshell.fullname" . }}-server-external-tls
|
|
{{- end }}
|
|
{{- if eq (include "openshell.gatewayClientCaEnabled" .) "true" }}
|
|
- name: peer-client-tls
|
|
secret:
|
|
secretName: {{ .Values.server.tls.clientTlsSecretName }}
|
|
- name: tls-client-ca
|
|
secret:
|
|
{{- if or (and .Values.pkiInitJob.enabled (not .Values.certManager.enabled)) (and .Values.certManager.enabled .Values.certManager.clientCaFromServerTlsSecret) }}
|
|
secretName: {{ .Values.server.tls.certSecretName }}
|
|
items:
|
|
- key: ca.crt
|
|
path: ca.crt
|
|
{{- else }}
|
|
secretName: {{ .Values.server.tls.clientCaSecretName }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if and .Values.server.oidc.issuer .Values.server.oidc.caConfigMapName }}
|
|
- name: oidc-ca
|
|
configMap:
|
|
name: {{ .Values.server.oidc.caConfigMapName }}
|
|
{{- end }}
|
|
{{- if and .Values.server.credentialDrivers.vault.enabled .Values.server.credentialDrivers.vault.caConfigMapName }}
|
|
- name: vault-ca
|
|
configMap:
|
|
name: {{ .Values.server.credentialDrivers.vault.caConfigMapName }}
|
|
items:
|
|
- key: ca.crt
|
|
path: ca.crt
|
|
{{- end }}
|
|
{{- if .Values.upstreamProxy.caBundle.configMapName }}
|
|
- name: upstream-proxy-ca
|
|
configMap:
|
|
name: {{ .Values.upstreamProxy.caBundle.configMapName | quote }}
|
|
items:
|
|
# The mounted filename stays fixed so the rendered proxy_ca_bundle
|
|
# path does not depend on the operator's ConfigMap key.
|
|
- key: {{ .Values.upstreamProxy.caBundle.key | default "ca.crt" | quote }}
|
|
path: ca.crt
|
|
{{- end }}
|
|
{{- if .Values.server.providerTokenGrants.spiffe.enabled }}
|
|
- name: spiffe-workload-api
|
|
csi:
|
|
driver: csi.spiffe.io
|
|
readOnly: true
|
|
{{- end }}
|
|
{{- with .Values.server.extraVolumes }}
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
{{- with .Values.nodeSelector }}
|
|
nodeSelector:
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
{{- with .Values.affinity }}
|
|
affinity:
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
{{- with .Values.tolerations }}
|
|
tolerations:
|
|
{{- toYaml . | nindent 4 }}
|
|
{{- end }}
|
|
{{- end }}
|