Merge branch 'main' into mcmodel_crash

Author: ShashwathiNavada

.ci/metrics/metrics.py

@@ -24,6 +24,7 @@ class JobMetrics:
     status: int
     created_at_ns: int
     workflow_id: int
+    workflow_name: str
 
 
 @dataclass
@@ -43,40 +44,60 @@ def get_sampled_workflow_metrics(github_repo: github.Repository):
       Returns a list of GaugeMetric objects, containing the relevant metrics about
       the workflow
     """
+    queued_job_counts = {}
+    running_job_counts = {}
 
     # Other states are available (pending, waiting, etc), but the meaning
     # is not documented (See #70540).
     # "queued" seems to be the info we want.
-    queued_workflow_count = len(
-        [
-            x
-            for x in github_repo.get_workflow_runs(status="queued")
-            if x.name in WORKFLOWS_TO_TRACK
-        ]
-    )
-    running_workflow_count = len(
-        [
-            x
-            for x in github_repo.get_workflow_runs(status="in_progress")
-            if x.name in WORKFLOWS_TO_TRACK
-        ]
-    )
+    for queued_workflow in github_repo.get_workflow_runs(status="queued"):
+        if queued_workflow.name not in WORKFLOWS_TO_TRACK:
+            continue
+        for queued_workflow_job in queued_workflow.jobs():
+            job_name = queued_workflow_job.name
+            # Workflows marked as queued can potentially only have some jobs
+            # queued, so make sure to also count jobs currently in progress.
+            if queued_workflow_job.status == "queued":
+                if job_name not in queued_job_counts:
+                    queued_job_counts[job_name] = 1
+                else:
+                    queued_job_counts[job_name] += 1
+            elif queued_workflow_job.status == "in_progress":
+                if job_name not in running_job_counts:
+                    running_job_counts[job_name] = 1
+                else:
+                    running_job_counts[job_name] += 1
+
+    for running_workflow in github_repo.get_workflow_runs(status="in_progress"):
+        if running_workflow.name not in WORKFLOWS_TO_TRACK:
+            continue
+        for running_workflow_job in running_workflow.jobs():
+            job_name = running_workflow_job.name
+            if running_workflow_job.status != "in_progress":
+                continue
+
+            if job_name not in running_job_counts:
+                running_job_counts[job_name] = 1
+            else:
+                running_job_counts[job_name] += 1
 
     workflow_metrics = []
-    workflow_metrics.append(
-        GaugeMetric(
-            "workflow_queue_size",
-            queued_workflow_count,
-            time.time_ns(),
+    for queued_job in queued_job_counts:
+        workflow_metrics.append(
+            GaugeMetric(
+                f"workflow_queue_size_{queued_job}",
+                queued_job_counts[queued_job],
+                time.time_ns(),
+            )
         )
-    )
-    workflow_metrics.append(
-        GaugeMetric(
-            "running_workflow_count",
-            running_workflow_count,
-            time.time_ns(),
+    for running_job in running_job_counts:
+        workflow_metrics.append(
+            GaugeMetric(
+                f"running_workflow_count_{running_job}",
+                running_job_counts[running_job],
+                time.time_ns(),
+            )
         )
-    )
     # Always send a hearbeat metric so we can monitor is this container is still able to log to Grafana.
     workflow_metrics.append(
         GaugeMetric("metrics_container_heartbeat", 1, time.time_ns())
@@ -157,7 +178,7 @@ def get_per_workflow_metrics(
                 # longer in a testing state and we can directly assert the workflow
                 # result.
                 for step in workflow_job.steps:
-                    if step.conclusion != "success":
+                    if step.conclusion != "success" and step.conclusion != "skipped":
                         job_result = 0
                         break
 
@@ -179,6 +200,7 @@ def get_per_workflow_metrics(
                     job_result,
                     created_at_ns,
                     workflow_run.id,
+                    workflow_run.name,
                 )
             )
 
@@ -235,8 +257,6 @@ def upload_metrics(workflow_metrics, metrics_userid, api_key):
 def main():
     # Authenticate with Github
     auth = Auth.Token(os.environ["GITHUB_TOKEN"])
-    github_object = Github(auth=auth)
-    github_repo = github_object.get_repo("llvm/llvm-project")
 
     grafana_api_key = os.environ["GRAFANA_API_KEY"]
     grafana_metrics_userid = os.environ["GRAFANA_METRICS_USERID"]
@@ -248,20 +268,19 @@ def main():
     # Enter the main loop. Every five minutes we wake up and dump metrics for
     # the relevant jobs.
     while True:
+        github_object = Github(auth=auth)
+        github_repo = github_object.get_repo("llvm/llvm-project")
+
         current_metrics = get_per_workflow_metrics(github_repo, workflows_to_track)
         current_metrics += get_sampled_workflow_metrics(github_repo)
-        # Always send a hearbeat metric so we can monitor is this container is still able to log to Grafana.
-        current_metrics.append(
-            GaugeMetric("metrics_container_heartbeat", 1, time.time_ns())
-        )
 
         upload_metrics(current_metrics, grafana_metrics_userid, grafana_api_key)
         print(f"Uploaded {len(current_metrics)} metrics", file=sys.stderr)
 
         for workflow_metric in reversed(current_metrics):
             if isinstance(workflow_metric, JobMetrics):
                 workflows_to_track[
-                    workflow_metric.job_name
+                    workflow_metric.workflow_name
                 ] = workflow_metric.workflow_id
 
         time.sleep(SCRAPE_INTERVAL_SECONDS)

.github/CODEOWNERS

@@ -131,7 +131,7 @@
 /bolt/ @aaupov @maksfb @rafaelauler @ayermolo @dcci @yota9
 
 # Bazel build system.
-/utils/bazel/ @rupprecht @keith
+/utils/bazel/ @rupprecht @keith @aaronmondal
 
 # InstallAPI and TextAPI
 /llvm/**/TextAPI/ @cyndyishida

.github/workflows/build-ci-container-windows.yml

@@ -27,7 +27,7 @@ jobs:
       container-filename: ${{ steps.vars.outputs.container-filename }}
     steps:
       - name: Checkout LLVM
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           sparse-checkout: .github/workflows/containers/github-action-ci-windows
       - name: Write Variables
@@ -46,7 +46,7 @@ jobs:
         run: |
           docker save  ${{ steps.vars.outputs.container-name-tag }} >  ${{ steps.vars.outputs.container-filename }}
       - name: Upload container image
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
         with:
           name: container
           path: ${{ steps.vars.outputs.container-filename }}
@@ -63,7 +63,7 @@ jobs:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
       - name: Download container
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
         with:
           name: container
       - name: Push Container

.github/workflows/build-ci-container.yml

@@ -32,7 +32,7 @@ jobs:
             runs-on: depot-ubuntu-22.04-arm-16
     steps:
       - name: Checkout LLVM
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           sparse-checkout: .github/workflows/containers/github-action-ci/
       # podman is not installed by default on the ARM64 images.
@@ -66,7 +66,7 @@ jobs:
           podman save ${{ steps.vars.outputs.container-name-agent-tag }} > ${{ steps.vars.outputs.container-agent-filename }}
 
       - name: Upload container image
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
         with:
           name: container-${{ matrix.arch }}
           path: "*.tar"
@@ -90,7 +90,7 @@ jobs:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
       - name: Download container
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
 
       - name: Push Container
         run: |

.github/workflows/libcxx-build-and-test.yaml

@@ -37,7 +37,7 @@ jobs:
   stage1:
     if: github.repository_owner == 'llvm'
     runs-on: libcxx-self-hosted-linux
-    container: ghcr.io/llvm/libcxx-linux-builder:d8a0709b1090350a7fe3604d8ab78c7d62f10698
+    container: ghcr.io/llvm/libcxx-linux-builder:b319dfef21f6c7b0bc6a356d6b9f41a3b3b98ae9
     continue-on-error: false
     strategy:
       fail-fast: false
@@ -48,8 +48,8 @@ jobs:
           'generic-cxx26',
           'generic-modules'
         ]
-        cc: [  'clang-20' ]
-        cxx: [ 'clang++-20' ]
+        cc: [  'clang-21' ]
+        cxx: [ 'clang++-21' ]
         include:
           - config: 'generic-gcc'
             cc: 'gcc-14'
@@ -75,7 +75,7 @@ jobs:
   stage2:
     if: github.repository_owner == 'llvm'
     runs-on: libcxx-self-hosted-linux
-    container: ghcr.io/llvm/libcxx-linux-builder:d8a0709b1090350a7fe3604d8ab78c7d62f10698
+    container: ghcr.io/llvm/libcxx-linux-builder:b319dfef21f6c7b0bc6a356d6b9f41a3b3b98ae9
     needs: [ stage1 ]
     continue-on-error: false
     strategy:
@@ -88,18 +88,22 @@ jobs:
           'generic-cxx20',
           'generic-cxx23'
         ]
-        cc: [ 'clang-20' ]
-        cxx: [ 'clang++-20' ]
+        cc: [ 'clang-21' ]
+        cxx: [ 'clang++-21' ]
         include:
           - config: 'generic-gcc-cxx11'
             cc: 'gcc-14'
             cxx: 'g++-14'
-          - config: 'generic-cxx23'
-            cc: 'clang-18'
-            cxx: 'clang++-18'
+          - config: 'generic-cxx26'
+            cc: 'clang-20'
+            cxx: 'clang++-20'
           - config: 'generic-cxx26'
             cc: 'clang-19'
             cxx: 'clang++-19'
+          # Release transition
+          - config: 'generic-cxx23'
+            cc: 'clang-18'
+            cxx: 'clang++-18'
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}
@@ -163,14 +167,14 @@ jobs:
         - config: 'generic-msan'
           machine: libcxx-self-hosted-linux
     runs-on: ${{ matrix.machine }}
-    container: ghcr.io/llvm/libcxx-linux-builder:d8a0709b1090350a7fe3604d8ab78c7d62f10698
+    container: ghcr.io/llvm/libcxx-linux-builder:b319dfef21f6c7b0bc6a356d6b9f41a3b3b98ae9
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}
         run: libcxx/utils/ci/run-buildbot ${{ matrix.config }}
         env:
-          CC: clang-20
-          CXX: clang++-20
+          CC: clang-21
+          CXX: clang++-21
       - uses: actions/upload-artifact@26f96dfa697d77e81fd5907df203aa23a56210a8 # v4.3.0
         if: always()
         with:

.github/workflows/premerge.yaml

@@ -33,11 +33,11 @@ jobs:
     runs-on: llvm-premerge-linux-runners
     steps:
       - name: Checkout LLVM
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 2
       - name: Setup ccache
-        uses: hendrikmuhs/[email protected].14
+        uses: hendrikmuhs/ccache-action@a1209f81afb8c005c13b4296c32e363431bffea5 # v1.2.17
         with:
           max-size: "2000M"
       - name: Build and Test
@@ -94,11 +94,11 @@ jobs:
         shell: bash
     steps:
       - name: Checkout LLVM
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 2
       - name: Setup ccache
-        uses: hendrikmuhs/[email protected].14
+        uses: hendrikmuhs/ccache-action@a1209f81afb8c005c13b4296c32e363431bffea5 # v1.2.17
         with:
           variant: "sccache"
           max-size: "2000M"
@@ -144,7 +144,7 @@ jobs:
           call C:\\BuildTools\\Common7\\Tools\\VsDevCmd.bat -arch=amd64 -host_arch=amd64
           bash .ci/monolithic-windows.sh "${{ steps.vars.outputs.windows-projects }}" "${{ steps.vars.outputs.windows-check-targets }}"
 
-  permerge-check-macos:
+  premerge-check-macos:
     runs-on: macos-14
     if: >-
       github.repository_owner == 'llvm' &&
@@ -153,11 +153,11 @@ jobs:
       (github.event_name != 'pull_request' || github.event.action != 'closed')
     steps:
       - name: Checkout LLVM
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 2
       - name: Setup ccache
-        uses: hendrikmuhs/[email protected].14
+        uses: hendrikmuhs/ccache-action@a1209f81afb8c005c13b4296c32e363431bffea5 # v1.2.17
         with:
           max-size: "2000M"
       - name: Install Ninja