Architecture

The chart installs a controller (the operator) that reconciles LMCacheEngine custom resources into a DaemonSet of LMCache cache servers, and — when observability is enabled — wires those engines to an OpenTelemetry Collector that fans metrics and traces out to Prometheus and Tempo.

What gets created, and by whom

Every piece follows the same pattern: the chart writes a declaration (a CR); a controller reconciles it into a running thing. The chart runs exactly one controller itself — the Tensormesh Operator. The Collector and Tempo are reconciled by operators you pre-install; the chart only submits their CRs. This table is the precise “which thing belongs where”:

Declaration (the chart creates this)	Reconciled by	Becomes	Scope
`LMCacheEngine` CR	Tensormesh Operator (this chart)	engine DaemonSet — 1 pod per GPU node	Namespaced
`OpenTelemetryCollector` CR	OpenTelemetry Operator (prerequisite)	OTel Collector pod	Namespaced
`TempoMonolithic` CR	Tempo Operator (prerequisite)	Tempo instance	Namespaced
`ServiceMonitor`	Prometheus Operator (prerequisite)	a scrape target (no new pod)	Namespaced
CRD `lmcacheengines.lmcache.lmcache.ai`	— (registered with the API server)	defines the `LMCacheEngine` kind	Cluster

The Tensormesh Operator itself runs as a plain Deployment (no CR needed) and owns the engine DaemonSet’s lifecycle.

Data flow

vLLM pod  ──hostIPC / MP connector──▶  LMCache engine
LMCache engine  ──OTLP gRPC───────────▶  OTel Collector
OTel Collector  ──Prometheus scrape───▶  Prometheus   (via ServiceMonitor)
OTel Collector  ──OTLP traces─────────▶  Tempo / external backend

Hop	Transport	Port
vLLM → engine	shared-memory IPC (`hostIPC`)	— (same node)
engine → Collector	OTLP gRPC	`4317`
Collector → Prometheus	scrape of the Collector’s exporter	`8889`
Collector → itself	`otelcol_*` internal metrics	`8888`
Collector → Tempo / external	OTLP	per backend

See Observability for enabling and verifying this path.

Resources the chart creates

Everything the chart can render, with its scope — this is the table to consult before a cleanup, because cluster-scoped resources survive a namespace delete and must be removed explicitly.

Resource	API group	Scope	Created when	Cleanup notes
CustomResourceDefinition `lmcacheengines.lmcache.lmcache.ai`	`apiextensions.k8s.io`	Cluster	`crds.enabled` (default `true`)	⚠️ Kept on `helm uninstall` (`resource-policy: keep`). Survives namespace delete. Remove with `kubectl delete crd …`.
ClusterRole (operator)	`rbac.authorization.k8s.io`	Cluster	`operator.rbac.create`	⚠️ Survives namespace delete — sweep manually.
ClusterRoleBinding (operator)	`rbac.authorization.k8s.io`	Cluster	`operator.rbac.create`	⚠️ Survives namespace delete — sweep manually.
ClusterRole / ClusterRoleBinding (pre-delete hook)	`rbac.authorization.k8s.io`	Cluster	`helm uninstall` hook	Created and removed by the hook; can orphan if uninstall fails mid-way.
`LMCacheEngine` (CR)	`lmcache.lmcache.ai/v1alpha1`	Namespaced	`engine.enabled` (default `true`)	Has a `lmcache.ai/cleanup` finalizer — if the operator is gone, it blocks namespace deletion. See troubleshooting.
`OpenTelemetryCollector` (CR)	`opentelemetry.io`	Namespaced	`observability.enabled`	Goes with the namespace.
`TempoMonolithic` (CR)	`tempo.grafana.com`	Namespaced	`observability.traces.tempoCR.enabled`	Goes with the namespace.
`ServiceMonitor` (CR)	`monitoring.coreos.com`	Namespaced	`operator.serviceMonitor.enabled` and/or `observability.prometheus.serviceMonitor.enabled`	Goes with the namespace.
Deployment (controller-manager)	`apps`	Namespaced	`operator.enabled`	Goes with the namespace.
DaemonSet (engine)	`apps`	Namespaced	created by the operator from the CR	Removed when the CR/namespace is.
Service (metrics)	core	Namespaced	`operator.enabled`	Goes with the namespace.
ServiceAccount (operator)	core	Namespaced	`operator.serviceAccount.create`	Goes with the namespace.
Role / RoleBinding (operator)	`rbac.authorization.k8s.io`	Namespaced	`operator.rbac.create`	Goes with the namespace.
ServiceAccount + RoleBinding (privileged SCC)	core / `rbac…`	Namespaced	`openshift.enabled`	Goes with the namespace. Binds to the built-in `system:openshift:scc:privileged` ClusterRole — do not delete that.
NetworkPolicy	`networking.k8s.io`	Namespaced	`operator.networkPolicy.enabled`	Goes with the namespace.
Job + ServiceAccount + Role + RoleBinding (pre-delete hook)	batch / core / `rbac…`	Namespaced	`helm uninstall` hook	Transient; removed after the hook runs.

The three things a namespace delete leaves behind

If you kubectl delete namespace instead of helm uninstall, these cluster-scoped resources orphan and need explicit cleanup:

CRD lmcacheengines.lmcache.lmcache.ai
ClusterRole for the operator
ClusterRoleBinding for the operator

kubectl delete crd lmcacheengines.lmcache.lmcache.ai
kubectl get clusterrole,clusterrolebinding | grep -i tensormesh   # delete what it lists

See Troubleshooting → Cleaning up an inconsistent or orphaned install for the full recipe (including clearing the LMCacheEngine finalizer first).

Next steps

Configuration

Every values.yaml key and example overlays.

Observability

The OTel Collector / Tempo / Prometheus wiring in detail.

Installation

Feature List

Integrations

Management

Operator UI

Reference

What gets created, and by whom

Data flow

Resources the chart creates

The three things a namespace delete leaves behind

Next steps

Configuration

Observability

​What gets created, and by whom

​Data flow

​Resources the chart creates

​The three things a namespace delete leaves behind

​Next steps

Configuration

Observability

What gets created, and by whom

Data flow

Resources the chart creates

The three things a namespace delete leaves behind

Next steps