From 9585870156cbf001b9bfbe601ddbadcd92f2f245 Mon Sep 17 00:00:00 2001
From: Baptiste <collebaptiste@gmail.com>
Date: Mon, 6 Jan 2025 11:21:03 +0000
Subject: [PATCH] debug dind

---
 .github/workflows/debug-dind.yml | 54 +++++++++++++++++---------------
 1 file changed, 28 insertions(+), 26 deletions(-)

diff --git a/.github/workflows/debug-dind.yml b/.github/workflows/debug-dind.yml
index dc339ec1..b282d24f 100644
--- a/.github/workflows/debug-dind.yml
+++ b/.github/workflows/debug-dind.yml
@@ -21,15 +21,40 @@ jobs:
           apt-get update -y
           apt-get install -y docker.io
 
+      # @pauline, everything below are alternative tests that show the same behavior (bug)
+      # this is the most concise test that shows the behavior and i think it is the most straightforward to understand
+      # More or less when doing DIND, i cannot get the container to be reachable from the runner
+      # test-pytorch-xla-tpu-tgi-integration.yml is my full workflow when i first notice this behavior
+      # test-pytorch-xla-tpu-tgi-integration.yml starts a TGI webserver and then do requests to it to check that it's working, this is my end goal
+      # this is a minimal test to see if i can get the container to be reachable from the runner and it does not work
+      # i'm trying to find out why the container is not reachable from the runner, do you have any idea why?
+
+      - name: Test HTTP request
+        run: |
+          # Run the whoami container with environment variables
+          # @pauline adding --ipc host, --privileged and/or --network host did not help me. I also tried to use different ports 80, 8080, 5001
+          docker run ${{ vars.V5_LITEPOD_8_ENV}} -d --name network-test -p 5001:80 traefik/whoami
+
+          # Wait for container to be ready
+          sleep 5
+
+          # Show container status and logs
+          docker ps
+          docker logs network-test
+
+          # Test with multiple endpoints to verify connectivity
+          echo "Testing basic endpoint..."
+          curl --max-time 30 -v localhost:5001
 
+    # OPTION 1: altnerative test 1 that shows the same behavior
     # the run test step is similar to "Create test server Dockerfile", "Create minimal test server", "Build and run test container"
-    # but it's not in a single step inside a python script so it can be run locally
-    # this scripts work on the local machine, not in the github actions environment
-    # i left commented out for now, as "Create test server Dockerfile", "Create minimal test server", "Build and run test container" maybe be easier to debug in a ci environment
+    # but it's in a single step inside a python script so it can be run locally
+    # this scripts work on the local machine but not in the github actions environment and this is not expected, the behavior should be the same
       # - name: Run test
       #   run: |
       #     python debug-dind-locally/test.py
 
+    # OPTION 2: altnerative test 2 that shows the same behavior (until end of the file)
       # - name: Create test server Dockerfile
       #   run: |
       #     cat << EOF > Dockerfile
@@ -83,26 +108,3 @@ jobs:
       #     # Clean up
       #     docker stop test-server
 
-      # @pauline, everything above is alternative tests that show the same behavior (bug)
-      # More or less when doing DIND, i cannot get the container to be reachable from the runner
-      # test-pytorch-xla-tpu-tgi-integration.yml is my full workflow when i first notice this behavior
-      # test-pytorch-xla-tpu-tgi-integration.yml starts a TGI webserver and then do requests to it to check that it's working, this is my end goal
-      # this is a minimal test to see if i can get the container to be reachable from the runner and it does not work
-      # i'm trying to find out why the container is not reachable from the runner, do you have any idea why?
-
-      - name: Test HTTP request
-        run: |
-          # Run the whoami container with environment variables
-          # @pauline adding --ipc host, --privileged and/or --network host did not help me. I also tried to use different ports 80, 8080, 5001
-          docker run ${{ vars.V5_LITEPOD_8_ENV}} -d --name network-test -p 5001:80 traefik/whoami
-
-          # Wait for container to be ready
-          sleep 5
-
-          # Show container status and logs
-          docker ps
-          docker logs network-test
-
-          # Test with multiple endpoints to verify connectivity
-          echo "Testing basic endpoint..."
-          curl --max-time 30 -v localhost:5001
\ No newline at end of file