Refactor launch without cached state into a single job

.github/workflows/deploy-gcp-tests.yml

@@ -104,11 +104,15 @@ env:
   CACHED_STATE_UPDATE_LIMIT: 576
 
 jobs:
-  # set up and launch the test, if it doesn't use any cached state
+  # set up and run the test, if it doesn't use any cached state
   # each test runs one of the *-with/without-cached-state job series, and skips the other
-  launch-without-cached-state:
-    name: Launch ${{ inputs.test_id }} test
-    if: ${{ !inputs.needs_zebra_state }}
+  #
+  # Launches the test and checks the results of the test.
+  #
+  run-without-cached-state:
+    name: Run ${{ inputs.test_id }} test
+    # If `inputs.is_long_test` is `true`, the timeout is 5 days, otherwise it's 3 hours.
+    timeout-minutes: ${{ inputs.is_long_test && 7200 || 180 }}
     runs-on: zfnd-runners
     permissions:
       contents: 'read'
@@ -136,19 +140,6 @@ jobs:
           NETWORK_CAPS="${{ inputs.network }}"
           echo "NETWORK=${NETWORK_CAPS,,}" >> "$GITHUB_ENV"
 
-      # Install our SSH secret
-      - name: Install private SSH key
-        uses: shimataro/ssh-key-action@v2.5.1
-        with:
-          key: ${{ secrets.GCP_SSH_PRIVATE_KEY }}
-          name: google_compute_engine
-          known_hosts: unnecessary
-
-      - name: Generate public SSH key
-        run: |
-          sudo apt-get update && sudo apt-get -qq install -y --no-install-recommends openssh-client
-          ssh-keygen -y -f ~/.ssh/google_compute_engine > ~/.ssh/google_compute_engine.pub
-
       # Setup gcloud CLI
       - name: Authenticate to Google Cloud
         id: auth
@@ -161,17 +152,20 @@ jobs:
       - name: Set up Cloud SDK
         uses: google-github-actions/setup-gcloud@v1.1.1
 
-      # Create a Compute Engine virtual machine
-      - name: Create ${{ inputs.test_id }} GCP compute instance
-        id: create-instance
+      # Create a Compute Engine virtual machine and run the tests
+      # Show all the test logs, then follow the logs of the test we just launched, until it finishes.
+      #
+      # TODO: fail if the "Zcash network" regex isn't found in the first 700 lines of output
+      - name: Run ${{ inputs.test_id }} test
+        id: test-result
         run: |
           gcloud compute instances create-with-container "${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}" \
-          --boot-disk-size 300GB \
+          --boot-disk-size 350GB \
           --boot-disk-type pd-ssd \
-          --image-project=cos-cloud \
-          --image-family=cos-stable \
-          --create-disk=name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",device-name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",size=300GB,type=pd-ssd \
-          --container-image=gcr.io/google-containers/busybox \
+          --container-image="${{ vars.GAR_BASE }}/${{ vars.CI_IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }}" \
+          --container-env="${{ inputs.test_variables }}" \
+          --container-mount-host-path=name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",host-path=mount-path=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }},mount-path=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} \
+          --container-tty \
           --machine-type ${{ vars.GCP_LARGE_MACHINE }} \
           --network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
           --scopes cloud-platform \
@@ -179,45 +173,12 @@ jobs:
           --metadata-from-file=startup-script=.github/workflows/scripts/gcp-vm-startup-script.sh \
           --labels=app=${{ inputs.app_name }},environment=test,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }},test=${{ inputs.test_id }} \
           --tags ${{ inputs.app_name }} \
-          --zone ${{ vars.GCP_ZONE }}
-          sleep 60
-
-      # Create a docker volume with the new disk we just created.
-      #
-      # SSH into the just created VM, and create a docker volume with the newly created disk.
-      - name: Create ${{ inputs.test_id }} Docker volume
-        run: |
-          gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
-          --zone ${{ vars.GCP_ZONE }} \
-          --ssh-flag="-o ServerAliveInterval=5" \
-          --ssh-flag="-o ConnectionAttempts=20" \
-          --ssh-flag="-o ConnectTimeout=5" \
-          --command \
-          "\
-          sudo mkfs.ext4 -v /dev/sdb \
-          && \
-          sudo docker volume create --driver local --opt type=ext4 --opt device=/dev/sdb \
-          ${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
-          "
-
-      # Launch the test without any cached state
-      - name: Launch ${{ inputs.test_id }} test
-        run: |
-          gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
-          --zone ${{ vars.GCP_ZONE }} \
-          --ssh-flag="-o ServerAliveInterval=5" \
-          --ssh-flag="-o ConnectionAttempts=20" \
-          --ssh-flag="-o ConnectTimeout=5" \
-          --command \
-          "\
-          sudo docker run \
-          --name ${{ inputs.test_id }} \
-          --tty \
-          --detach \
-          ${{ inputs.test_variables }} \
-          --mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} \
-          ${{ vars.GAR_BASE }}/${{ vars.CI_IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
-          "
+          --zone ${{ vars.GCP_ZONE }} | \
+          tee --output-error=exit /dev/stderr | \
+          grep --extended-regexp \
+          -e 'Zcash network: ${{ inputs.network }}' | \
+          grep --max-count=1 --extended-regexp --color=always \
+          "test result: .*ok.* [1-9][0-9]* passed.*finished in"; \
 
   # set up and launch the test, if it uses cached state
   # each test runs one of the *-with/without-cached-state job series, and skips the other
@@ -501,7 +462,7 @@ jobs:
   test-result:
     name: Run ${{ inputs.test_id }} test
     # We run exactly one of without-cached-state or with-cached-state, and we always skip the other one.
-    needs: [ launch-with-cached-state, launch-without-cached-state ]
+    needs: [ launch-with-cached-state ]
     # If the previous job fails, we also want to run and fail this job,
     # so that the branch protection rule fails in Mergify and GitHub.
     if: ${{ !cancelled() }}
@@ -621,7 +582,7 @@ jobs:
   create-state-image:
     name: Create ${{ inputs.test_id }} cached state image
     runs-on: ubuntu-latest
-    needs: [ test-result, launch-with-cached-state ]
+    needs: [ test-result, launch-with-cached-state, run-without-cached-state ]
     # We run exactly one of without-cached-state or with-cached-state, and we always skip the other one.
     # Normally, if a job is skipped, all the jobs that depend on it are also skipped.
     # So we need to override the default success() check to make this job run.