Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix metrics for k8s setup #2473

Merged
merged 4 commits into from
Aug 24, 2023
Merged

fix metrics for k8s setup #2473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8e598d1
fix metrics for k8s setup
jagadeeshi2i Jul 18, 2023
0967ccc
fix lint error
jagadeeshi2i Aug 4, 2023
72fc96f
Merge branch 'master' into fix/k8s-metrics
chauhang Aug 4, 2023
e333731
Merge branch 'master' into fix/k8s-metrics
chauhang Aug 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ repos:
- id: check-json
- id: check-toml
- id: check-yaml
args: [--allow-multiple-documents, --unsafe]
- id: end-of-file-fixer
- id: mixed-line-ending
- id: trailing-whitespace
Expand Down
2 changes: 2 additions & 0 deletions kubernetes/EKS/config.properties
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
inference_address=http://0.0.0.0:8080
management_address=http://0.0.0.0:8081
metrics_address=http://0.0.0.0:8082
enable_metrics_api=true
metrics_mode=prometheus
NUM_WORKERS=1
number_of_gpu=1
number_of_netty_threads=32
Expand Down
2 changes: 2 additions & 0 deletions kubernetes/GKE/config.properties
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
inference_address=http://0.0.0.0:8080
management_address=http://0.0.0.0:8081
metrics_address=http://0.0.0.0:8082
enable_metrics_api=true
metrics_mode=prometheus
NUM_WORKERS=1
number_of_gpu=1
number_of_netty_threads=32
Expand Down
5 changes: 3 additions & 2 deletions kubernetes/Helm/templates/torchserve.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,13 +6,14 @@ metadata:
labels:
app: torchserve
annotations:
prometheus.io/scrape: 'true'
prometheus.io/scrape: "true"
prometheus.io/path: /metrics
prometheus.io/port: '8082'
spec:
ports:
- name: preds
port: {{ .Values.torchserve.inference_port }}
targetPort: ts
targetPort: ts
- name: mdl
port: {{ .Values.torchserve.management_port }}
targetPort: ts-management
Expand Down
29 changes: 18 additions & 11 deletions kubernetes/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# Torchserve on Kubernetes

## Overview

This page demonstrates a Torchserve deployment in Kubernetes using Helm Charts. It uses the DockerHub Torchserve Image for the pods and a PersistentVolume for storing config / model files.
Expand Down Expand Up @@ -66,7 +66,7 @@ persitant_volume:
size: 1Gi
```

To install Torchserve run ```helm install ts .```
To install Torchserve run ```helm install ts .```

```bash
ubuntu@ip-172-31-50-36:~/serve/kubernetes/Helm$ helm install ts .
Expand Down Expand Up @@ -207,12 +207,6 @@ helm repo add grafana https://grafana.github.io/helm-charts
helm install grafana grafana/grafana
```

Get admin user password by running:

```bash
kubectl get secret --namespace default grafana -o jsonpath="{.data.admin-password}" | base64 --decode ; echo
```

## Add prometheus as data source in grafana

```bash
Expand All @@ -233,8 +227,6 @@ kubectl get pod prometheus-server-f8677599b-xmjbt -o jsonpath='{.status.podIPs[0
192.168.52.141
```

![Add data source](images/grafana_datasource.png)

## Expose grafana with loadbalancer

```bash
Expand All @@ -243,9 +235,24 @@ kubectl patch service grafana -p '{"spec": {"type": "LoadBalancer"}}'
kubectl get svc grafana -o jsonpath='{.status.loadBalancer.ingress[0].hostname}'
```

Get admin user password by running:

```bash
kubectl get secret --namespace default grafana -o jsonpath="{.data.admin-password}" | base64 --decode ; echo
```

## Login to grafana

`<http://your.grafana.loadbalancer.address:3000>`
<b>Username:</b> admin
<b>Password:</b> <--The password got from previous step-->

Open Grafana in browser with the url - `<http://your.grafana.loadbalancer.address:3000>`

Add Prometheus data source

![Add data source](images/grafana_datasource.png)

The TS metrics will be available in Prometheus for Grafana dashboards.

## Logging

Expand Down
Loading