From e4231c9816dc532b4d4eb0c9e8d7e8e347d0ebe4 Mon Sep 17 00:00:00 2001
From: Vincent Ambo <mail@tazj.in>
Date: Fri, 10 Dec 2021 10:10:02 +0300
Subject: refactor(ops/pipelines): Move :duck: logic into static pipeline

This simplifies the fallback logic used in case of Nix evaluation
failure and makes it so that the evaluation step itself is the one
that is marked as failed in Buildkite.

This is possible because the pipeline upload command will insert new
steps at the point where it runs in the pipeline, and not later.

Change-Id: I870534c004ebc457a1602623c4e5f9c0c68e28fc
---
 ops/pipelines/static-pipeline.yaml | 44 ++++++++++++++++++++++++++++++++------
 1 file changed, 37 insertions(+), 7 deletions(-)

(limited to 'ops/pipelines/static-pipeline.yaml')

diff --git a/ops/pipelines/static-pipeline.yaml b/ops/pipelines/static-pipeline.yaml
index c864aea657..2c7767820b 100644
--- a/ops/pipelines/static-pipeline.yaml
+++ b/ops/pipelines/static-pipeline.yaml
@@ -7,14 +7,44 @@
 steps:
   - label: ":llama:"
     command: |
-      function fallback() {
-        echo 'Using fallback pipeline ...'
-        buildkite-agent pipeline upload ops/pipelines/fallback.yaml
-        exit
-      }
+      set -ue
+      nix-build -A ops.pipelines.depot -o depot.yaml --show-trace && \
+        buildkite-agent pipeline upload depot.yaml
 
-      nix-build -A ops.pipelines.depot -o depot.yaml --show-trace || fallback
-      buildkite-agent pipeline upload depot.yaml || fallback
+  # Wait for all previous steps to complete.
+  - wait: null
+    continue_on_failure: true
+
+  # Exit with success or failure depending on whether any other steps
+  # failed.
+  #
+  # This information is checked by querying the Buildkite GraphQL API
+  # and fetching the count of failed steps.
+  #
+  # This step must be :duck: (yes, really!) because the post-command
+  # hook will inspect this name.
+  #
+  # Note that this step has requirements for the agent environment, which
+  # are enforced in our NixOS configuration:
+  #
+  #  * curl and jq must be on the $PATH of build agents
+  #  * besadii configuration must be readable to the build agents
+  - label: ":duck:"
+    key: ":duck:"
+    command: |
+      set -ueo pipefail
+
+      readonly FAILED_JOBS=$(curl 'https://graphql.buildkite.com/v1' \
+        --silent \
+        -H "Authorization: Bearer $(cat /etc/secrets/buildkite-besadii)" \
+        -d "{\"query\": \"query BuildStatusQuery { build(uuid: \\\"$BUILDKITE_BUILD_ID\\\") { jobs(passed: false) { count } } }\"}" | \
+        jq -r '.data.build.jobs.count')
+
+      echo "$$FAILED_JOBS build jobs failed."
+
+      if (( $$FAILED_JOBS > 0 )); then
+        exit 1
+      fi
 
   # Create a revision number for the current commit for builds on
   # canon.
-- 
cgit 1.4.1