helm-charts/gotenberg/values.yaml

# Scale the whole chart down without uninstalling it: scaleDown: true renders
# every Deployment/StatefulSet with replicas: 0 (and suspends CronJobs) and
# takes precedence over any per-workload replicas value. PVCs, Secrets and
# Services stay in place; scaleDown: false brings the workloads back up.
scaleDown: false

gotenberg:
  # Replica count for this workload; 0 is allowed and scales it down.
  # The chart-global scaleDown flag takes precedence.
  replicas: 1
  # The official image runs as the dedicated gotenberg user (uid 1001). /tmp
  # and /home/gotenberg are writable emptyDirs so Chromium/LibreOffice keep
  # working with a read-only root filesystem.
  securityContext:
    pod:
      runAsNonRoot: true
      runAsUser: 1001
      runAsGroup: 1001
      # RuntimeDefault applies the container runtime's default seccomp filter,
      # which blocks the syscalls a normal workload never makes. It sits in the
      # pod context on purpose: from here it covers every container in the pod
      # including init containers, while a container-level seccompProfile would
      # have to be repeated for each one (and silently missed on the next one
      # added). A container that genuinely needs a different filter can still
      # override it under securityContext.container, which wins over this value.
      #
      # Verified against both conversion engines, because a browser sandbox is
      # the classic case where a syscall filter bites: Chromium HTML->PDF and
      # LibreOffice document->PDF both still return real PDFs under the filter,
      # and /health reports chromium and libreoffice as "up".
      seccompProfile:
        type: RuntimeDefault
    container:
      allowPrivilegeEscalation: false
      readOnlyRootFilesystem: true
      runAsNonRoot: true
      capabilities:
        drop:
          - ALL
  # Gotenberg exposes a documented health endpoint at /health.
  livenessProbe:
    httpGet:
      path: /health
      port: gotenberg-port
    periodSeconds: 10
    timeoutSeconds: 5
    failureThreshold: 3
  readinessProbe:
    httpGet:
      path: /health
      port: gotenberg-port
    periodSeconds: 10
    timeoutSeconds: 5
    failureThreshold: 3
  # The startup probe gates liveness/readiness. Startup budget = 5s * 30 = 150s.
  startupProbe:
    httpGet:
      path: /health
      port: gotenberg-port
    periodSeconds: 5
    timeoutSeconds: 5
    failureThreshold: 30
  # Extra environment variables. Values are rendered through tpl; value,
  # secretKeyRef and configMapKeyRef forms are supported.
  env: []
  resources:
    # Limits are optional: memory and ephemeral-storage limits default to
    # limitFactor x the request, an explicitly set limit always wins, and a
    # CPU limit is only set when configured explicitly under "limits".
    limitFactor: 3
    # The requests stay small on purpose: gotenberg idles at a few dozen MB,
    # so reserving conversion-sized capacity on the node would waste it
    # around the clock. Conversions are short bursts, and the limits below
    # cover the burst instead (issue #106).
    requests:
      cpu: 0.1
      memory: 512Mi
      ephemeralStorage: 10Mi
    # Set explicitly rather than left to limitFactor x request, because the
    # computed limits (1536Mi / 30Mi) were too small for real documents.
    # Measured with the official image, HTML converted via Chromium:
    #   - 18 MB HTML: OOMKilled at 2Gi and 2560Mi, converts at 3Gi in ~22s
    #     (21 MB PDF). 12 MB HTML already OOM-kills at the old 1536Mi.
    #   - Raising memory alone only moves the failure: with 3Gi memory and
    #     the old 30Mi ephemeral limit, /tmp peaked at 40 MB on a single
    #     conversion and at ~125 MB over a short series, and the pod was
    #     evicted ("ephemeral local storage usage exceeds the total limit of
    #     containers 30Mi") instead of OOM-killed.
    # Memory beyond 3Gi buys nothing: gotenberg's own request timeout is 30s
    # and the chart passes no flags to change it, so a document that needs
    # more memory than this has already run out of time.
    limits:
      memory: 3Gi
      ephemeralStorage: 256Mi

# ---------------------------------------------------------------------------
# NetworkPolicy (Gitea #5). On by default. The reference implementation with
# the full reasoning is template-chart; the convention is in README, "Chart
# style guidelines", and the operator's view on this chart's wiki page.
# ---------------------------------------------------------------------------
networkPolicy:
  # WHAT THIS POLICY ALLOWS: inbound 3000 only and outbound nothing but DNS.
  #
  # THE EGRESS CAP IS THE POINT OF THIS ONE. Gotenberg drives a headless
  # Chromium, so allowing 80/443 outbound would let anything that can POST to
  # this service fetch arbitrary URLs through it - and 3000 is the probe port,
  # so the whole cluster can POST to it by default. The cost is the
  # remote-asset half of HTML conversion: a converted page keeps its inline
  # content and silently loses the images it would have FETCHED. That is a
  # degraded PDF, not a dead pod, which is exactly why it is written down here.
  # A deployment that needs those images sets egress.remoteAssets: true below -
  # a named switch, knowingly, rather than a port pair in extraPorts.
  #
  # And like every chart here: 3000 is not restricted by source in the default
  # (probe port), and a policy is only a boundary where the CNI enforces one.
  enabled: true
  # Namespaces whose pods may reach this workload, in addition to the release's
  # own namespace, which is always allowed. Empty means: own namespace only.
  #
  # Matched on the "kubernetes.io/metadata.name" label Kubernetes sets on every
  # namespace itself, so no labelling work is needed on a namespace this chart
  # does not own - and no typo protection either: a name that does not exist
  # matches nothing and is silently ineffective. Note the granularity: an entry
  # opens the port to EVERY pod in that namespace.
  allowedNamespaces: []
  # Source CIDRs allowed to reach port 3000, which is the port all three probes address.
  #
  # EMPTY MEANS OPEN, NOT BLOCKED. With no entry that rule is rendered WITHOUT a
  # "from" selector, so the port is reachable from anywhere the CNI routes to -
  # inside the cluster, since it carries no NodePort.
  #
  # That is the deliberate choice between two bad defaults. The kubelet's probes
  # originate from the IP of the WORKER NODE running the pod, an address this
  # chart cannot know and must not guess: a CIDR that excludes the real node
  # blocks every probe, the pod never becomes Ready, the rollout times out, and
  # the symptom reads as a broken application rather than as a policy.
  #
  # Narrow it by listing the worker node IPs (e.g. ["10.0.1.11/32"]) - and mind
  # the companion trap: once this list is non-empty the rule IS restricted, so
  # everything else that needs the port has to be in it. The chart adds the own
  # namespace and allowedNamespaces to the same rule for exactly that reason.
  probeSources: []

  # The policy's INBOUND side. Mind the three names that overlap as substrings,
  # because a search for "ingress" matches all of them and they are different
  # things:
  #
  #   ingress                          (top level) the Ingress OBJECT this chart
  #                                    renders - host, TLS, className
  #   networkPolicy.ingress            this block: what the policy lets IN
  #   networkPolicy.ingressController  the SOURCE SELECTOR for the ingress
  #                                    controller's pods. A SIBLING of this block
  #                                    and NO PART OF IT, despite the name.
  ingress:
    # Opens the pod for Istio's ambient mesh (Gitea #143). OFF by default and
    # additive: while it is false this chart renders byte for byte as it did
    # before the value existed.
    #
    # IT RENDERS TWO THINGS, and that they come together is the point:
    #
    #   1. 15008/TCP inbound - ztunnel's HBONE tunnel. Every inbound mesh
    #      connection arrives on it, and ambient "does not and will never bypass
    #      Kubernetes NetworkPolicy enforcement", so without this port a pod
    #      whose namespace has joined the mesh is unreachable.
    #   2. 169.254.7.127/32 as an additional peer - but ONLY where the rule
    #      restricts sources at all, which here means probeSources is non-empty.
    #      Inside the mesh the kubelet's probes are redirected and no longer come
    #      from the worker node's address.
    #
    # WHY ONE SWITCH AND NOT TWO: point 2 is the one nobody thinks of. Whoever
    # adds "15008" to a port list by hand writes a policy that passes review, and
    # the first time probeSources is narrowed every probe is dropped - the pod
    # never becomes Ready and the symptom reads as a broken application rather
    # than as a policy. A switch whose halves can only be had together cannot be
    # set halfway, which is why this is a named intention and not a port list.
    #
    # TWO THINGS IT DOES NOT PROVE:
    #   - That 15008 alone is enough. That comes from Istio's documentation;
    #     measured on this cluster is only which listeners ztunnel opens.
    #     Provable at the first namespace to join the mesh - none carries
    #     istio.io/dataplane-mode yet.
    #   - That the probe-source half works. probeSources is empty in every chart
    #     here, so no release reaches that branch. CI proves its render, not its
    #     effect.
    #
    # Note where the port lands: it joins the rule that carries the probe port,
    # so once probeSources restricts that rule, 15008 is restricted with it.
    # Whether ztunnel needs a peer of its own is open - it runs with its own pod
    # IPs in istio-system (measured: no hostNetwork on the DaemonSet, Istio
    # 1.30.6), so if one proves necessary it is expressible as a
    # namespaceSelector plus podSelector and needs no unknowable node CIDR.
    # BOTH NUMBERS BELOW ARE ISTIO CONSTANTS, NOT STANDARDS, and they are values
    # rather than template literals for exactly that reason: a vendor constant
    # can change, and an operator should be able to correct it without waiting
    # for a chart release. Their provenance is written on each one.
    #
    # DELETING THIS OBJECT IS SAFE. Every read falls back to the defaults
    # declared here (#99), so "ambientMesh: null", or an object carrying only
    # "enabled: true", renders the documented defaults instead of failing.
    ambientMesh:
      # The switch. Everything else here is inert while it is false, and the
      # chart renders exactly as it did before the object existed.
      enabled: false

      # ISTIO'S HBONE PORT. A constant Istio chose, not a standard: not
      # registered with IANA for this, prescribed by no protocol, and unknown to
      # Kubernetes. Read for ztunnel 1.30.6 (measured on this cluster: ztunnel
      # opens [::]:15008 as its inbound listener).
      #
      # If Istio changes it, a pod in the mesh cannot be reached. Change it here
      # in all 30 charts AND in the pinned expectation inside
      # ci/run-networkpolicy-test.sh - the test is deliberately what forces
      # someone to look, because the exception it grants this port is pinned to
      # the number IT knows and not to whatever this value says. A value-driven
      # exception would let a mistyped port through, which is the hole design A
      # of #143 was rejected for.
      #
      # NOT MEASURED: that this port ALONE suffices comes from Istio's
      # documentation. Measured here is only which listeners ztunnel opens, and
      # no namespace carries istio.io/dataplane-mode yet.
      port: 15008

      # SOURCES THE KUBELET'S PROBES ARRIVE FROM ONCE ISTIO HAS REDIRECTED THEM.
      #
      # NOT THE SAME VALUE AS networkPolicy.probeSources one level up, and the
      # two are easy to confuse, so:
      #
      #   networkPolicy.probeSources
      #       YOUR worker node CIDRs. Empty by default, and empty means the
      #       probe rule is OPEN. The chart cannot know these addresses.
      #   networkPolicy.ingress.ambientMesh.redirectedProbeSources
      #       ISTIO's rewrite address. Shipped filled, because unlike the node
      #       IPs it is a constant the chart CAN know. Only rendered where the
      #       rule above is restricted, i.e. where probeSources is non-empty.
      #
      # WHERE 169.254.7.127 COMES FROM - vendor magic, not protocol:
      #
      #   - LINK-LOCAL, 169.254.0.0/16 (RFC 3927): a range reserved for
      #     node-local use that is never routed - exactly the range one picks a
      #     vendor's magic address out of.
      #   - Istio's IPv6 counterpart gives it away:
      #     fd16:9254:7127:1337:ffff:ffff:ffff:ffff carries the SAME DIGITS
      #     (9254:7127 is 169.254.7.127) plus 1337. Numbers built that way are
      #     vendor constants, not protocols.
      #   - KUBERNETES DOES NOT KNOW THIS ADDRESS. Neither the NetworkPolicy API
      #     nor the kubelet has any notion of it; only Istio's own data plane
      #     rewrites the probe source onto it.
      #
      # Read for ztunnel 1.30.6. IF ISTIO CHANGES IT, THE FAILURE IS SILENT:
      # probes would be dropped, and only where probeSources is non-empty - which
      # is nowhere in this repository today - so nothing here and nothing in
      # Kubernetes would report it. What to re-check then: the address Istio's
      # release notes name for probe redirection, this list in all 30 charts, and
      # the pinned expectation in ci/run-networkpolicy-test.sh.
      #
      # A LIST, not a string, and the one case where that does not contradict "a
      # constant, not a configuration": on a DUAL-STACK cluster BOTH entries are
      # needed at the same time, not one of two. This cluster is SingleStack
      # IPv4, so the IPv6 counterpart is left out - an ipBlock of the wrong
      # family is accepted by the API server and matches nothing. Add it
      # ALONGSIDE, never instead, if the cluster gains IPv6.
      #
      # Clearing this list restores the default rather than removing the ipBlock,
      # deliberately: the two halves of this switch are not separable. To not
      # open the port at all, set enabled: false.
      #
      # UNPROVEN IN OPERATION: probeSources is empty in every chart here, so no
      # release reaches this branch. CI proves the render, not the effect.
      redirectedProbeSources:
        - 169.254.7.127/32

  egress:
    # REMOTE ASSETS: lets Chromium fetch over TCP 80 and 443, to any
    # destination. OFF by default, and both halves of that are deliberate.
    #
    # WHAT IT BUYS, measured rather than assumed. paperless-ngx splits a mail
    # into two steps with two separate cluster-internal endpoints: the .eml goes
    # to TIKA for parsing (PAPERLESS_TIKA_ENDPOINT) and the resulting HTML comes
    # here for rendering (PAPERLESS_TIKA_GOTENBERG_ENDPOINT). Of the images in
    # that HTML:
    #   - EMBEDDED images are MIME parts INSIDE the file. Neither Tika nor
    #     Gotenberg needs the network for them - which is why apache-tika stays
    #     DNS-only, and why a mail that carries its pictures with it needs
    #     nothing from this switch.
    #   - REMOTE images (<img src="https://..."> in the body) are fetched by
    #     CHROMIUM, here, at render time. With this off they are SILENTLY
    #     DROPPED: the PDF is produced and is simply missing them. Nothing
    #     fails, nothing is logged by this chart, no probe notices.
    #
    # NOT CHECKED, and deliberately not claimed: whether paperless-ngx re-embeds
    # the images Tika extracted before handing the HTML over. If it does not,
    # embedded images would be lost as well - but that would be pre-existing
    # paperless behaviour and not this policy. Do not read this switch as a fix
    # for it.
    #
    # WHY IT IS OFF BY DEFAULT. Gotenberg drives a headless Chromium and 3000 is
    # its probe port, so the service is reachable from the whole cluster by
    # default. Allowing 80/443 outbound therefore turns anything that can POST
    # here into a way of fetching arbitrary URLs - an SSRF pivot with the
    # cluster's internal address space behind it. Switching this on is a trade,
    # and it should be one somebody made on purpose.
    remoteAssets: false
    # Additional outbound TCP ports. DNS (UDP and TCP 53) is always allowed and
    # has no switch - a knob whose only other setting breaks every name lookup
    # in the pod is a trap, not a feature.
    #
    # Use remoteAssets above rather than putting 80 and 443 here: the named
    # value says WHY the ports are open, and this list cannot.
    #
    # PORTS, NOT DESTINATIONS, and that is a limit of the object rather than
    # laziness: a NetworkPolicy matches CIDRs and selectors and never hostnames,
    # so "only to the database host" cannot be written at all. Each entry
    # permits its port to ANY destination. What the cap still buys is real: a
    # compromised pod cannot open arbitrary outbound connections.
    #
    # Normally empty. Remote assets have their own switch above
    # (egress.remoteAssets) and do NOT belong here, because a bare 80/443 in
    # this list records no reason. Add a port here only for something neither
    # the switch nor the chart covers.
    extraPorts: []