Skip to main content

​
Supported Metrics

The Simplismart metrics endpoint exposes metrics in Prometheus format covering Kubernetes infrastructure health, GPU utilization, inference engine performance, and request lifecycle.
For each metric, you only need to provide one of the listed parameters.
Deployment namespace and deployment slug refer to the same value. Learn how to find it here.

​
Kubernetes Deployment Metrics

Track deployment health and replica status.

​
kube_deployment_spec_replicas

The number of desired replicas for a deployment, as specified in the deployment spec. Type: gauge Labels:
​
label
Deployment namespace (deployment slug).
​
label
Deployment name.

​
kube_deployment_status_replicas

The number of observed replicas for a deployment. Type: gauge Labels:
​
label
Deployment namespace.
​
label
Deployment name.

​
kube_deployment_status_replicas_available

Number of replicas that are available (ready for at least minReadySeconds). Type: gauge Labels:
​
label
Deployment namespace.
​
label
Deployment name.

​
kube_deployment_status_replicas_ready

Number of replicas that have passed their readiness probes. Type: gauge Labels:
​
label
Deployment namespace.
​
label
Deployment name.
For inference servers, readiness means “model is loaded and accepting requests.” A container running but not ready consumes resources without serving traffic.

​
kube_deployment_status_replicas_unavailable

Number of replicas that are not yet available. Type: gauge Labels:
​
label
Deployment namespace.
​
label
Deployment name.
A non-zero value means capacity is degraded: pods may be crashing, stuck in image pull, or failing health checks.

​
Kubernetes Pod Metrics

Pod-level visibility into lifecycle and health.

​
kube_pod_info

Pod metadata information including node, IP, and phase. Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Node name where the pod is scheduled.
​
label
Pod IP address.

​
kube_pod_status_phase

Current phase of the pod (Pending, Running, Succeeded, Failed, Unknown). Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Pod phase (Pending, Running, Succeeded, Failed, Unknown).

​
kube_pod_container_status_ready

Whether the container is ready (1) or not (0). Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.

​
kube_pod_container_status_running

Whether the container is running (1) or not (0). Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.

​
kube_pod_container_status_restarts_total

Cumulative count of container restarts. Type: counter Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.
Frequent restarts indicate OOM kills, crash loops, or probe failures. For GPU inference pods, restarts are expensive because model loading can take minutes.

​
kube_pod_container_status_waiting_reason

The reason the container is in waiting state (e.g., ContainerCreating, CrashLoopBackOff, ErrImagePull). Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.
​
label
Reason for waiting state.

​
Container Resource Metrics

Track actual resource consumption.

​
container_cpu_usage_seconds_total

Cumulative CPU time consumed by the container, in core-seconds. Type: counter Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.

​
container_memory_working_set_bytes

Current working set memory of the container in bytes. This is what the OOM killer uses for eviction decisions. Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.
When this approaches the container’s memory limit, OOM kills become imminent.

​
kube_pod_container_resource_requests

Resource requests configured for the container. Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.
​
label
Resource type (cpu, memory, nvidia_com_gpu).
​
label
Unit of measurement (core, byte, etc.).

​
kube_pod_container_resource_limits

Resource limits configured for the container. Type: gauge Labels:
​
label
Pod namespace.
​
label
Pod name.
​
label
Container name.
​
label
Resource type (cpu, memory, nvidia_com_gpu).
​
label
Unit of measurement (core, byte, etc.).

​
GPU Metrics

GPU metrics for Simplismart’s GPU-accelerated inference workloads.

​
DCGM_FI_DEV_GPU_UTIL

GPU utilization as a percentage (0–100). Measures what fraction of time the GPU’s streaming multiprocessors are active. Type: gauge Labels:
​
label
GPU index.
​
label
GPU UUID.
​
label
Device identifier.
​
label
GPU model name (e.g., “NVIDIA H100”).
​
label
Host name.
​
label
Deployment namespace.
​
label
Pod name.
Example:
Low utilization means inefficient batching; high sustained utilization (>90%) indicates the GPU is at capacity.

​
DCGM_FI_DEV_FB_USED

Frame buffer (GPU VRAM) memory used, in MiB. Type: gauge Labels:
​
label
GPU index.
​
label
Host name.
​
label
Deployment namespace.
​
label
Pod name.
Example:
GPU memory is the primary constraint for model serving. When VRAM is exhausted, inference requests fail with OOM errors.

​
DCGM_FI_DEV_FB_FREE

Frame buffer (GPU VRAM) memory free, in MiB. Type: gauge Labels:
​
label
Host name.
​
label
Deployment namespace.
​
label
Pod name.
Example:

​
Ingress Metrics

External traffic entering the Simplismart platform.

​
nginx_ingress_controller_requests

Total number of requests handled by the NGINX ingress controller. Type: counter Labels:
​
label
Ingress name.
​
label
Namespace.
​
label
Service name.
​
label
HTTP status code.
​
label
HTTP method (GET, POST, etc.).
​
label
Request path.
Available metrics:
  • nginx_ingress_controller_requests - Total request count
  • nginx_ingress_controller_request_duration_seconds_bucket - Request duration histogram buckets
  • nginx_ingress_controller_request_duration_seconds_sum - Total request duration sum
  • nginx_ingress_controller_request_duration_seconds_count - Total request count for duration

​
nginx_ingress_controller_request_duration_seconds

End-to-end request duration as observed by the ingress controller. Type: histogram (exposes _bucket, _sum, and _count time series) Labels:
​
label
Ingress name.
​
label
Namespace.
​
label
Service name.
​
label
HTTP status code.
​
label
HTTP method (GET, POST, etc.).
​
label
Request path.
Example query (p99):