jcoffey-dev
1de77b969f
ingest tags every record with a tenant_id Kafka header (built previously), but nothing consumed it to actually route the write. This closes that for ClickHouse: enterprise/cmd/enterprise-ingest (a second binary, mirroring enterprise-api) reuses ingest/consumer's own flush loop unchanged, with enterprise/internal/chwriter.Registry -- a per-tenant clickhousewriter.Writer registry -- swapped in as the writer. A batch pulled from the single shared Redpanda topic can mix records from many tenants, so WriteBatch groups by TenantID and dispatches each group to its own tenant's connection, fail- closed on an empty or unrecognized tenant_id. ingest/consumer and ingest/clickhousewriter move out of internal/ (same reason api/internal/* moved earlier this phase: enterprise/ can't import anything under another module's internal/). Their New() constructors now take small local Config structs instead of ingest/internal/config types, so enterprise/ doesn't need that import either. Building this surfaced a real bug: tenantprovision.ProvisionClickHouse only granted SELECT on a tenant's ClickHouse user, correct for chrunner's read-only use but not enough for chwriter reusing the same credential to write -- every real per-tenant write would have failed closed with a permission error. Fixed by widening the grant to SELECT, INSERT; no cross-tenant boundary is crossed by also allowing INSERT within a tenant's own database. Helm gates enterprise-ingest's Deployment on the same ingest.requireTenantCredential flag that already gates tag validation -- write-routing is meaningless without tagging already being required, so they're one decision, not two. docker-compose.yml's version is a disclosed, weaker approximation: it can't achieve Helm's genuine -mode=server/-mode=consumer split, so with the enterprise profile active both ingest and enterprise-ingest independently consume every message via different consumer groups -- harmless duplication for local verification only. Not built: Tantivy's independent Redpanda consumer (search/src/consumer.rs) still doesn't read the tenant_id header at all -- every record still lands in the one shared index regardless of tenant. Not run: the live-ClickHouse- gated tests (chwriter's cross-tenant routing test, tenantprovision's INSERT regression test) -- no Docker/database access in this environment; they're correct Go that has never executed, disclosed as such in docs/security/ threat-model.md and docs/phase-4-runbook.md §14.
219 lines
8.2 KiB
YAML
219 lines
8.2 KiB
YAML
# Default values for the sentry chart. See deploy/helm/sentry/README.md
|
|
# for the multi-tenant-specific values (enterprise.*, tenants) and what
|
|
# "multi-tenant-aware" does and doesn't mean at this layer.
|
|
#
|
|
# Image repositories default to locally-built tags matching each
|
|
# service's docker-compose.yml container_name, minus the "sentry-"
|
|
# container_name prefix duplication -- push these to a registry this
|
|
# cluster can actually pull from before installing; this chart never
|
|
# builds images itself (same division of labor as docker-compose.yml:
|
|
# `docker compose build` vs. `docker compose up`).
|
|
|
|
global:
|
|
imagePullPolicy: IfNotPresent
|
|
|
|
redpanda:
|
|
image:
|
|
repository: docker.redpanda.com/redpandadata/redpanda
|
|
tag: v24.2.7
|
|
persistence:
|
|
size: 10Gi
|
|
resources: {}
|
|
# Built from ./transport (docker-compose.yml's redpanda-provision
|
|
# service) -- the one-shot topic-creation Job below.
|
|
provisionImage:
|
|
repository: sentry-redpanda-provision
|
|
tag: latest
|
|
|
|
clickhouse:
|
|
image:
|
|
repository: clickhouse/clickhouse-server
|
|
tag: "24.8"
|
|
persistence:
|
|
size: 20Gi
|
|
resources: {}
|
|
# Leave empty to auto-generate and persist across upgrades -- see
|
|
# templates/secrets.yaml's stableSecretValue helper.
|
|
password: ""
|
|
# Built from ./storage (docker-compose.yml's clickhouse-migrate
|
|
# service) -- the one-shot schema-migration Job.
|
|
migrateImage:
|
|
repository: sentry-clickhouse-migrate
|
|
tag: latest
|
|
|
|
postgres:
|
|
image:
|
|
repository: postgres
|
|
tag: 16-alpine
|
|
persistence:
|
|
size: 10Gi
|
|
resources: {}
|
|
password: ""
|
|
auditWriterPassword: ""
|
|
# Built from ./metadata (docker-compose.yml's metadata-migrate
|
|
# service) -- the one-shot schema-migration Job.
|
|
migrateImage:
|
|
repository: sentry-metadata-migrate
|
|
tag: latest
|
|
|
|
ingest:
|
|
image:
|
|
repository: sentry-ingest
|
|
tag: latest
|
|
replicas: 1
|
|
resources: {}
|
|
# mTLS server cert/key/CA -- see hack/dev-certs/generate.sh for the
|
|
# dev equivalent of what this Secret must contain
|
|
# (server.pem/server-key.pem/ca.pem) in a real deployment. Unlike
|
|
# docker-compose.yml's bind-mounted ./hack/dev-certs/out, a cluster
|
|
# deployment supplies this as a real Secret -- named here, not
|
|
# generated by this chart (cert issuance is out of scope, same
|
|
# "boring, well-understood" preference as everywhere else in this
|
|
# repo -- use cert-manager or an equivalent, don't hand-roll it here).
|
|
tlsSecretName: ""
|
|
# Only meaningful when enterprise.enabled is also true -- see
|
|
# templates/ingest.yaml's ENTERPRISE_AUTH_URL comment for why this is
|
|
# its own deliberate opt-in, not folded into enterprise.enabled
|
|
# directly: turning it on requires every agent to already present a
|
|
# valid ingest credential (`enterprise-auth
|
|
# -create-ingest-credential-tenant=<id>`) or be refused outright. Also
|
|
# controls per-tenant write-routing: true switches ingest.yaml's
|
|
# Deployment to -mode=server only and renders enterprise-ingest.yaml
|
|
# to take over consuming sentry.logs.raw, writing each tenant's
|
|
# records into their own ClickHouse database instead of the one
|
|
# shared table -- both flags gate together since write-routing is only
|
|
# meaningful once records actually carry a tenant_id to route on.
|
|
requireTenantCredential: false
|
|
|
|
search:
|
|
image:
|
|
repository: sentry-search
|
|
tag: latest
|
|
# Pinned to 1: search consumes the same Redpanda topic ingest's
|
|
# consumer does with its own offset tracking (see search/README.md).
|
|
# A second replica would form a second, independent consumer instance
|
|
# against the same partitions with no coordination -- correctness,
|
|
# not just resource waste, is the reason this isn't a `replicas` knob
|
|
# yet. Matches CLAUDE.md's Phase 4 non-goal: "no general multi-cluster
|
|
# orchestration."
|
|
replicas: 1
|
|
resources: {}
|
|
persistence:
|
|
size: 20Gi
|
|
|
|
api:
|
|
image:
|
|
repository: sentry-api
|
|
tag: latest
|
|
replicas: 2
|
|
resources: {}
|
|
|
|
alerting:
|
|
image:
|
|
repository: sentry-alerting
|
|
tag: latest
|
|
# Pinned to 1 for the same reason as search: rulestore.ClaimDueRules
|
|
# has no leader-election/partitioning story for multiple evaluator
|
|
# replicas yet -- two would both try to claim and evaluate the same
|
|
# due rules. Named explicitly rather than silently defaulted, since
|
|
# it's the kind of knob someone reasonably expects to just work.
|
|
replicas: 1
|
|
resources: {}
|
|
# See templates/alerting.yaml's comment -- only meaningful when
|
|
# enterprise.enabled is true. Empty by default.
|
|
apiServiceToken: ""
|
|
|
|
web:
|
|
image:
|
|
repository: sentry-web
|
|
tag: latest
|
|
replicas: 2
|
|
resources: {}
|
|
# NOT wired to any Deployment env var -- web is a static SvelteKit
|
|
# build (adapter-static, see web/package.json), and VITE_API_BASE_URL/
|
|
# VITE_ALERTING_API_BASE_URL/VITE_ENTERPRISE_AUTH_BASE_URL are baked in
|
|
# at *image build time* (docker-compose.yml's web.build.args), not
|
|
# read at container runtime. Deploying this chart into a real cluster
|
|
# means rebuilding the web image with these three build args pointed
|
|
# at wherever api/alerting/enterprise-auth are actually reachable from
|
|
# a browser (an Ingress host, a LoadBalancer IP, etc.) -- this section
|
|
# exists to document that requirement, not because the chart can act
|
|
# on it.
|
|
builtWithApiBaseURL: "http://localhost:8080"
|
|
builtWithAlertingApiBaseURL: "http://localhost:8081"
|
|
builtWithEnterpriseAuthBaseURL: "http://localhost:8082"
|
|
|
|
# enterprise-auth (commercial license) + the tenant-operator that
|
|
# reconciles the Tenant CRD -- both off by default, matching
|
|
# docker-compose.yml's own "included, not wired into enforcement by
|
|
# default" stance (see its enterprise-auth service comment) and
|
|
# enterprise/README.md's "Status" section on what's built vs. deferred.
|
|
enterprise:
|
|
enabled: false
|
|
image:
|
|
repository: sentry-enterprise-auth
|
|
tag: latest
|
|
# enterprise-api (templates/enterprise-api.yaml) -- swaps in for
|
|
# api.yaml's plain api Deployment when enterprise.enabled is true, on
|
|
# the same Service/port every consumer already expects. Built from the
|
|
# repo root (needs api/ and proto/, not just enterprise/), unlike
|
|
# enterprise-auth's image above -- see
|
|
# enterprise/cmd/enterprise-api/Dockerfile.
|
|
apiImage:
|
|
repository: sentry-enterprise-api
|
|
tag: latest
|
|
# enterprise-ingest (templates/enterprise-ingest.yaml) -- only
|
|
# rendered when ingest.requireTenantCredential is also true (see that
|
|
# value's comment); takes over consuming sentry.logs.raw from
|
|
# ingest.yaml's own consumer once per-tenant write-routing is on. Same
|
|
# "repo root build context" reasoning as apiImage above -- see
|
|
# enterprise/cmd/enterprise-ingest/Dockerfile.
|
|
ingestImage:
|
|
repository: sentry-enterprise-ingest
|
|
tag: latest
|
|
replicas: 1
|
|
resources: {}
|
|
# Leave empty to auto-generate (>= 32 bytes) and persist across
|
|
# upgrades -- see templates/secrets.yaml.
|
|
sessionSigningKey: ""
|
|
oidc:
|
|
issuerURL: ""
|
|
clientID: ""
|
|
clientSecret: ""
|
|
redirectURL: ""
|
|
saml:
|
|
entityID: ""
|
|
acsURL: ""
|
|
idpMetadataURL: ""
|
|
|
|
# Installs deploy/operator (the Tenant CRD controller) alongside this
|
|
# chart. Only meaningful when enterprise.enabled is also true -- gated
|
|
# on that, not a separate flag, since a Tenant CR with nothing to
|
|
# reflect (see below) has nothing to do. Also turns on enterprise-api's
|
|
# own Tenant-CRD-syncing permissions (a ServiceAccount/Role, and the
|
|
# TENANT_CRD_NAMESPACE env var) -- see templates/enterprise-api.yaml.
|
|
tenantOperator:
|
|
enabled: false
|
|
image:
|
|
repository: sentry-tenant-operator
|
|
tag: latest
|
|
resources: {}
|
|
|
|
# One entry per tenant to provision -- rendered as Tenant CRs
|
|
# (templates/tenants.yaml), a declarative request an admin/GitOps
|
|
# process makes. The operator (tenant-operator, above) only ever
|
|
# *reflects* real state onto these objects (Phase/Conditions, derived
|
|
# from what enterprise-api's `-provision-tenant` has reported) -- it's
|
|
# `-provision-tenant` (run via `kubectl exec` into the enterprise-api
|
|
# Pod), not the operator, that actually calls ClickHouse and writes the
|
|
# credential Secret. See deploy/operator/internal/controller/
|
|
# tenant_controller.go's and enterprise/internal/tenantcrd's doc
|
|
# comments for the full split. Empty by default; a real two-tenant
|
|
# deployment (Phase 4's exit criteria) sets e.g.:
|
|
# tenants:
|
|
# - name: acme
|
|
# displayName: "Acme Corp"
|
|
# - name: globex
|
|
# displayName: "Globex Corporation"
|
|
tenants: []
|