test(ci): guard watchdog alert wiring

.github/actions/schedule-failure-issue/action.yml

@@ -14,9 +14,10 @@
 
 name: "Schedule Failure Issue"
 description: >-
-  Open (or update) a tracking issue when a scheduled workflow run fails.
+  Open (or update) a tracking issue when a scheduled workflow run fails or
+  does not complete normally.
   Dedupes by workflow name: if an open issue titled
-  "[scheduled-failure] <workflow name>" already exists, the failure is
+  "[scheduled-failure] <workflow name>" already exists, the result is
   appended as a comment; otherwise a new issue is created. This is the
   single alerting mechanism for all scheduled pipelines (backlog#1149 ci-8).
 
@@ -38,6 +39,26 @@ inputs:
       Set to an empty string to skip labeling.
     required: false
     default: "infrastructure"
+  source-run-id:
+    description: "Run ID to report. Defaults to the current workflow run."
+    required: false
+    default: ${{ github.run_id }}
+  source-run-attempt:
+    description: "Run attempt to report. Defaults to the current attempt."
+    required: false
+    default: ${{ github.run_attempt }}
+  source-event:
+    description: "Trigger event of the run being reported."
+    required: false
+    default: ${{ github.event_name }}
+  source-ref-name:
+    description: "Ref name of the run being reported."
+    required: false
+    default: ${{ github.ref_name }}
+  source-sha:
+    description: "Commit SHA of the run being reported."
+    required: false
+    default: ${{ github.sha }}
 
 runs:
   using: "composite"
@@ -48,17 +69,21 @@ runs:
         GH_TOKEN: ${{ inputs.github-token }}
         WORKFLOW_NAME: ${{ inputs.workflow-name }}
         ISSUE_LABEL: ${{ inputs.label }}
+        SOURCE_RUN_ID: ${{ inputs.source-run-id }}
+        SOURCE_RUN_ATTEMPT: ${{ inputs.source-run-attempt }}
+        SOURCE_EVENT: ${{ inputs.source-event }}
+        SOURCE_REF_NAME: ${{ inputs.source-ref-name }}
+        SOURCE_SHA: ${{ inputs.source-sha }}
       run: |
         set -euo pipefail
 
         title="[scheduled-failure] ${WORKFLOW_NAME}"
-        run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
+        run_url="${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${SOURCE_RUN_ID}"
 
-        # Failed job names for this run attempt. The alert job runs while the
-        # run as a whole is still in progress, so inspect the jobs that have
-        # already completed with a non-success conclusion.
+        # Inspect the reported run attempt. It can be the current in-workflow
+        # failure or a completed run observed by the external watchdog.
         failed_jobs="$(gh api \
-          "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}/jobs" \
+          "repos/${GITHUB_REPOSITORY}/actions/runs/${SOURCE_RUN_ID}/attempts/${SOURCE_RUN_ATTEMPT}/jobs" \
           --paginate \
           --jq '.jobs[]
                 | select(.conclusion == "failure" or .conclusion == "timed_out" or .conclusion == "cancelled")
@@ -68,13 +93,13 @@ runs:
         fi
 
         body="$(cat <<EOF
-        Scheduled run of **${WORKFLOW_NAME}** failed.
+        Scheduled run of **${WORKFLOW_NAME}** did not complete successfully.
 
-        - Run: ${run_url} (attempt ${GITHUB_RUN_ATTEMPT})
-        - Event: \`${GITHUB_EVENT_NAME}\`
-        - Ref: \`${GITHUB_REF_NAME}\` @ \`${GITHUB_SHA}\`
+        - Run: ${run_url} (attempt ${SOURCE_RUN_ATTEMPT})
+        - Event: \`${SOURCE_EVENT}\`
+        - Ref: \`${SOURCE_REF_NAME}\` @ \`${SOURCE_SHA}\`
 
-        Failed jobs:
+        Non-success jobs:
         ${failed_jobs}
         EOF
         )"

.github/workflows/build.yml

@@ -1032,3 +1032,23 @@ jobs:
 
           echo "🎉 Released $TAG successfully!"
           echo "📄 Release URL: ${{ needs.create-release.outputs.release_url }}"
+
+  alert-on-failure:
+    name: Alert on scheduled failure
+    needs: [build-check, prepare-platform-matrix, build-rustfs, build-summary]
+    if: >-
+      always() && github.event_name == 'schedule' &&
+      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+        with:
+          persist-credentials: false
+      - name: Open or update failure-tracking issue
+        uses: ./.github/actions/schedule-failure-issue
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/ci.yml

@@ -1032,3 +1032,37 @@ jobs:
           path: artifacts/s3tests-single/**
           if-no-files-found: ignore
           retention-days: 3
+
+  alert-on-failure:
+    name: Alert on scheduled failure
+    needs:
+      - typos
+      - quick-checks
+      - test-and-lint
+      - test-ilm-integration-serial
+      - test-and-lint-rio-v2
+      - test-and-lint-protocols
+      - build-rustfs-debug-binary
+      - build-rustfs-debug-binary-rio-v2
+      - uring-integration
+      - e2e-tests
+      - e2e-full
+      - e2e-tests-rio-v2
+      - s3-implemented-tests
+      - s3-lifecycle-behavior-tests
+    if: >-
+      always() && github.event_name == 'schedule' &&
+      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+        with:
+          persist-credentials: false
+      - name: Open or update failure-tracking issue
+        uses: ./.github/actions/schedule-failure-issue
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/minio-interop.yml

@@ -121,3 +121,21 @@ jobs:
           cargo nextest run --run-ignored ignored-only --no-tests=fail \
             -p "$INTEROP_PACKAGE" --features "$INTEROP_FEATURES" \
             -E "$INTEROP_FILTER"
+
+  alert-on-failure:
+    name: Alert on scheduled failure
+    needs: [minio-interop]
+    if: always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+        with:
+          persist-credentials: false
+      - name: Open or update failure-tracking issue
+        uses: ./.github/actions/schedule-failure-issue
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/nightly-gnu.yml

@@ -194,3 +194,23 @@ jobs:
 
       - name: Run HA leader failover live checks (three-node Raft cluster in Docker)
         run: bash scripts/test/vault_ha_kms_live.sh
+
+  alert-on-failure:
+    name: Alert on scheduled failure
+    needs: [build, kms-vault-lane, kms-vault-ha-failover]
+    if: >-
+      always() && github.event_name == 'schedule' &&
+      (contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled'))
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+        with:
+          persist-credentials: false
+      - name: Open or update failure-tracking issue
+        uses: ./.github/actions/schedule-failure-issue
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/scheduled-validation-watchdog.yml

@@ -0,0 +1,63 @@
+# Copyright 2024 RustFS Team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name: Scheduled Validation Watchdog
+
+on:
+  workflow_run:
+    workflows:
+      - "Security Audit"
+      - "Build and Release"
+      - "Continuous Integration"
+      - "coverage"
+      - "e2e-nightly"
+      - "e2e-s3tests"
+      - "Fuzz"
+      - "mint"
+      - "minio-interop"
+      - "Nightly GNU Build"
+      - "Performance A/B"
+      - "Runner Hygiene"
+    types: [completed]
+
+permissions:
+  contents: read
+
+jobs:
+  alert-on-incomplete-run:
+    name: Alert on incomplete scheduled run
+    if: >-
+      github.event.workflow_run.event == 'schedule' &&
+      github.event.workflow_run.conclusion != 'success' &&
+      github.event.workflow_run.conclusion != 'failure'
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      actions: read
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+        with:
+          persist-credentials: false
+      - name: Open or update incomplete-run issue
+        uses: ./.github/actions/schedule-failure-issue
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          workflow-name: ${{ github.event.workflow_run.name }}
+          source-run-id: ${{ github.event.workflow_run.id }}
+          source-run-attempt: ${{ github.event.workflow_run.run_attempt }}
+          source-event: ${{ github.event.workflow_run.event }}
+          source-ref-name: ${{ github.event.workflow_run.head_branch }}
+          source-sha: ${{ github.event.workflow_run.head_sha }}

crates/ecstore/src/core/pools.rs

@@ -89,7 +89,6 @@ const DECOMMISSION_STAGE_SOURCE_CLEANUP: &str = "source_cleanup";
 const DECOMMISSION_STAGE_ENTRY_FINISHED: &str = "entry_finished";
 const DECOMMISSION_PROGRESS_SAVE_INTERVAL: Duration = Duration::seconds(30);
 const DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD: usize = 1000;
-const DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF: Duration = Duration::seconds(1);
 const DECOMMISSION_BUCKET_CONCURRENCY_ENV: &str = "RUSTFS_DECOMMISSION_BUCKET_CONCURRENCY";
 const DECOMMISSION_BUCKET_CONCURRENCY_DEFAULT_CAP: usize = 4;
 const DECOMMISSION_TARGET_CAPACITY_OVERHEAD_PERCENT: usize = 30;
@@ -639,6 +638,22 @@ fn track_decommission_current_object(meta: &mut PoolMeta, idx: usize, bucket: &s
     track_decommission_current_object_stage(meta, idx, bucket, object, "")
 }
 
+fn touch_decommission_progress(meta: &mut PoolMeta, idx: usize) -> Result<()> {
+    let pool_count = meta.pools.len();
+    ensure_valid_decommission_pool_index(pool_count, idx)?;
+
+    let Some(pool) = meta.pools.get_mut(idx) else {
+        return Err(invalid_decommission_pool_index_error(pool_count, idx));
+    };
+    let Some(info) = pool.decommission.as_mut() else {
+        return Err(decommission_metadata_not_initialized_error("touch decommission progress"));
+    };
+
+    pool.last_update = OffsetDateTime::now_utc();
+    info.mark_progress_saved();
+    Ok(())
+}
+
 fn resolve_decommission_update_after_result(result: Result<bool>) -> Result<bool> {
     result.map_err(|err| Error::other(format!("decommission metadata update failed: {err}")))
 }
@@ -1468,7 +1483,6 @@ impl TryFrom<PersistedPoolDecommissionInfo> for PoolDecommissionInfo {
             terminal_reload_attempt_at: value.terminal_reload_attempt_at,
             terminal_reload_failures: value.terminal_reload_failures,
             progress_save_item_baseline: value.items_decommissioned.saturating_add(value.items_decommission_failed),
-            progress_save_retry_after: None,
         })
     }
 }
@@ -1500,7 +1514,6 @@ impl TryFrom<LegacyPoolDecommissionInfo> for PoolDecommissionInfo {
             terminal_reload_attempt_at: None,
             terminal_reload_failures: Vec::new(),
             progress_save_item_baseline: value.items_decommissioned.saturating_add(value.items_decommission_failed),
-            progress_save_retry_after: None,
         })
     }
 }
@@ -1614,82 +1627,6 @@ impl PoolMeta {
         }
     }
 
-    fn decommission_progress_checkpoint(
-        &self,
-        idx: usize,
-        duration: Duration,
-        now: OffsetDateTime,
-    ) -> Result<Option<DecommissionProgressCheckpoint>> {
-        let pool_count = self.pools.len();
-        ensure_valid_decommission_pool_index(pool_count, idx)?;
-
-        let Some(pool) = self.pools.get(idx) else {
-            return Err(invalid_decommission_pool_index_error(pool_count, idx));
-        };
-        let Some(info) = pool.decommission.as_ref() else {
-            return Err(decommission_metadata_not_initialized_error("update decommission metadata timestamp"));
-        };
-
-        if info.progress_save_retry_after.is_some_and(|retry_after| now < retry_after) {
-            return Ok(None);
-        }
-
-        let time_threshold_reached = now.unix_timestamp() - pool.last_update.unix_timestamp() >= duration.whole_seconds();
-        let item_threshold_reached = info.items_since_last_progress_save() >= DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD;
-        if !time_threshold_reached && !item_threshold_reached {
-            return Ok(None);
-        }
-
-        Ok(Some(DecommissionProgressCheckpoint {
-            start_time: info.start_time,
-            queued: info.queued,
-            counted_items: info.counted_items(),
-            checkpoint_at: now,
-        }))
-    }
-
-    fn commit_decommission_progress_checkpoint(&mut self, idx: usize, checkpoint: DecommissionProgressCheckpoint) -> bool {
-        let Some(pool) = self.pools.get_mut(idx) else {
-            return false;
-        };
-        let Some(info) = pool.decommission.as_mut() else {
-            return false;
-        };
-
-        if info.start_time != checkpoint.start_time
-            || info.queued != checkpoint.queued
-            || !is_decommission_active(info.complete, info.failed, info.canceled)
-        {
-            return false;
-        }
-
-        info.progress_save_item_baseline = info.progress_save_item_baseline.max(checkpoint.counted_items);
-        info.progress_save_retry_after = None;
-        pool.last_update = pool.last_update.max(checkpoint.checkpoint_at);
-        true
-    }
-
-    fn defer_decommission_progress_checkpoint(
-        &mut self,
-        idx: usize,
-        checkpoint: DecommissionProgressCheckpoint,
-        retry_after: OffsetDateTime,
-    ) {
-        let Some(pool) = self.pools.get_mut(idx) else {
-            return;
-        };
-        let Some(info) = pool.decommission.as_mut() else {
-            return;
-        };
-
-        if info.start_time == checkpoint.start_time
-            && info.queued == checkpoint.queued
-            && is_decommission_active(info.complete, info.failed, info.canceled)
-        {
-            info.progress_save_retry_after = Some(retry_after);
-        }
-    }
-
     fn load_from_config_data(&mut self, data: Vec<u8>) -> Result<()> {
         if data.is_empty() {
             return Ok(());
@@ -2050,9 +1987,30 @@ impl PoolMeta {
     }
 
     pub fn update_after(&mut self, idx: usize, duration: Duration) -> Result<bool> {
-        Ok(self
-            .decommission_progress_checkpoint(idx, duration, OffsetDateTime::now_utc())?
-            .is_some())
+        let pool_count = self.pools.len();
+        ensure_valid_decommission_pool_index(pool_count, idx)?;
+
+        let (last_update, item_threshold_reached) = match self.pools.get(idx) {
+            Some(pool) if let Some(info) = pool.decommission.as_ref() => (
+                pool.last_update,
+                info.items_since_last_progress_save() >= DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
+            ),
+            Some(_) => {
+                return Err(decommission_metadata_not_initialized_error("update decommission metadata timestamp"));
+            }
+            None => return Err(invalid_decommission_pool_index_error(pool_count, idx)),
+        };
+        let now = OffsetDateTime::now_utc();
+
+        if now.unix_timestamp() - last_update.unix_timestamp() >= duration.whole_seconds() || item_threshold_reached {
+            let Some(pool) = self.pools.get_mut(idx) else {
+                return Err(invalid_decommission_pool_index_error(pool_count, idx));
+            };
+            pool.last_update = now;
+            return Ok(true);
+        }
+
+        Ok(false)
     }
 
     pub fn validate(&self, pools: Vec<Arc<Sets>>) -> Result<bool> {
@@ -2193,16 +2151,6 @@ pub struct PoolDecommissionInfo {
     pub terminal_reload_failures: Vec<String>,
     #[serde(skip)]
     pub progress_save_item_baseline: usize,
-    #[serde(skip)]
-    pub progress_save_retry_after: Option<OffsetDateTime>,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-struct DecommissionProgressCheckpoint {
-    start_time: Option<OffsetDateTime>,
-    queued: bool,
-    counted_items: usize,
-    checkpoint_at: OffsetDateTime,
 }
 
 impl PoolDecommissionInfo {
@@ -2237,7 +2185,6 @@ impl PoolDecommissionInfo {
 
     fn mark_progress_saved(&mut self) {
         self.progress_save_item_baseline = self.counted_items();
-        self.progress_save_retry_after = None;
     }
 
     pub fn bucket_push(&mut self, bucket: &DecomBucketInfo) {
@@ -2542,40 +2489,6 @@ impl ECStore {
         snapshot.save(self.pools.clone()).await
     }
 
-    async fn save_decommission_progress_checkpoint(&self, idx: usize) -> Result<bool> {
-        // Lock order: save gate, then the short pool metadata read/write sections. Peer
-        // reloads are intentionally performed by the caller after both locks are released.
-        let _save_guard = self.pool_meta_save_gate.lock().await;
-        let (snapshot, checkpoint) = {
-            let pool_meta = self.pool_meta.read().await;
-            let Some(checkpoint) = pool_meta.decommission_progress_checkpoint(
-                idx,
-                DECOMMISSION_PROGRESS_SAVE_INTERVAL,
-                OffsetDateTime::now_utc(),
-            )?
-            else {
-                return Ok(false);
-            };
-
-            let mut snapshot = pool_meta.clone();
-            let Some(pool) = snapshot.pools.get_mut(idx) else {
-                return Err(invalid_decommission_pool_index_error(snapshot.pools.len(), idx));
-            };
-            pool.last_update = checkpoint.checkpoint_at;
-            (snapshot, checkpoint)
-        };
-
-        if let Err(err) = snapshot.save(self.pools.clone()).await {
-            let retry_after = OffsetDateTime::now_utc() + DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF;
-            let mut pool_meta = self.pool_meta.write().await;
-            pool_meta.defer_decommission_progress_checkpoint(idx, checkpoint, retry_after);
-            return Err(err);
-        }
-
-        let mut pool_meta = self.pool_meta.write().await;
-        Ok(pool_meta.commit_decommission_progress_checkpoint(idx, checkpoint))
-    }
-
     async fn save_current_pool_meta_for_decommission_start(
         &self,
         indices: &[usize],
@@ -2958,7 +2871,7 @@ impl ECStore {
         Ok(())
     }
 
-    async fn track_decommission_entry_progress_stage(
+    async fn save_decommission_entry_progress_stage(
         &self,
         idx: usize,
         bucket: &str,
@@ -2969,6 +2882,22 @@ impl ECStore {
             let mut pool_meta = self.pool_meta.write().await;
             track_decommission_current_object_stage(&mut pool_meta, idx, bucket, object, stage)
                 .map_err(|err| with_decommission_entry_context(stage, bucket, object, err))?;
+            touch_decommission_progress(&mut pool_meta, idx)
+                .map_err(|err| with_decommission_entry_context(stage, bucket, object, err))?;
+        }
+
+        if let Some(err) = resolve_decommission_progress_save_result(self.save_current_pool_meta().await) {
+            warn!(
+                event = EVENT_DECOMMISSION_ENTRY,
+                component = LOG_COMPONENT_ECSTORE,
+                subsystem = LOG_SUBSYSTEM_POOLS,
+                pool_index = idx,
+                bucket = %bucket,
+                object = %object,
+                stage,
+                error = ?err,
+                "Decommission progress stage save failed"
+            );
         }
 
         Ok(())
@@ -3236,7 +3165,7 @@ impl ECStore {
                 let bucket_name = bucket.clone();
                 let object_name = rd.object_info.name.clone();
 
-                self.track_decommission_entry_progress_stage(
+                self.save_decommission_entry_progress_stage(
                     idx,
                     bucket_name.as_str(),
                     object_name.as_str(),
@@ -3330,7 +3259,7 @@ impl ECStore {
             }
             decommission_cancel_signal_result(rx.is_cancelled())?;
 
-            self.track_decommission_entry_progress_stage(
+            self.save_decommission_entry_progress_stage(
                 idx,
                 bucket.as_str(),
                 entry.name.as_str(),
@@ -3338,7 +3267,7 @@ impl ECStore {
             )
             .await?;
 
-            self.track_decommission_entry_progress_stage(
+            self.save_decommission_entry_progress_stage(
                 idx,
                 bucket.as_str(),
                 entry.name.as_str(),
@@ -3405,42 +3334,34 @@ impl ECStore {
             }
         };
 
-        self.track_decommission_entry_progress_stage(
-            idx,
-            bucket.as_str(),
-            entry.name.as_str(),
-            DECOMMISSION_STAGE_ENTRY_FINISHED,
-        )
-        .await?;
+        self.save_decommission_entry_progress_stage(idx, bucket.as_str(), entry.name.as_str(), DECOMMISSION_STAGE_ENTRY_FINISHED)
+            .await?;
 
         if should_save_progress {
-            match self.save_decommission_progress_checkpoint(idx).await {
-                Ok(true) => {
-                    if let Some(notification_sys) = runtime_sources::notification_sys()
-                        && let Err(err) = resolve_decommission_entry_reload_result(
-                            notification_sys.reload_pool_meta().await,
-                            bucket.as_str(),
-                            entry.name.as_str(),
-                        )
-                    {
-                        warn!("{err}");
-                    }
-                }
-                Ok(false) => {}
-                Err(err) => {
-                    if let Some(err) = resolve_decommission_progress_save_result(Err(err)) {
-                        warn!(
-                            event = EVENT_DECOMMISSION_ENTRY,
-                            component = LOG_COMPONENT_ECSTORE,
-                            subsystem = LOG_SUBSYSTEM_POOLS,
-                            pool_index = idx,
-                            bucket = %bucket,
-                            object = %entry.name,
-                            state = "progress_save_failed",
-                            error = %err,
-                            "Decommission progress save failed; continuing and will retry at the next checkpoint"
-                        );
-                    }
+            let save_result = self.save_current_pool_meta().await;
+            if let Some(err) = resolve_decommission_progress_save_result(save_result) {
+                warn!(
+                    event = EVENT_DECOMMISSION_ENTRY,
+                    component = LOG_COMPONENT_ECSTORE,
+                    subsystem = LOG_SUBSYSTEM_POOLS,
+                    pool_index = idx,
+                    bucket = %bucket,
+                    object = %entry.name,
+                    state = "progress_save_failed",
+                    error = %err,
+                    "Decommission progress save failed; continuing and will retry at the next checkpoint"
+                );
+            } else {
+                let mut pool_meta = self.pool_meta.write().await;
+                pool_meta.mark_decommission_progress_saved();
+                if let Some(notification_sys) = runtime_sources::notification_sys()
+                    && let Err(err) = resolve_decommission_entry_reload_result(
+                        notification_sys.reload_pool_meta().await,
+                        bucket.as_str(),
+                        entry.name.as_str(),
+                    )
+                {
+                    warn!("{err}");
                 }
             }
         }
@@ -5343,11 +5264,11 @@ pub(crate) fn fallback_free_capacity_dedup(disks: &[rustfs_madmin::Disk]) -> usi
 #[cfg(test)]
 mod pools_tests {
     use super::{
-        DECOMMISSION_PROGRESS_SAVE_INTERVAL, DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD, DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF,
-        DecomBucketInfo, DecommissionStartPoolState, DecommissionTerminalState, ListCallback, PoolDecommissionInfo, PoolMeta,
-        PoolSpaceInfo, PoolStatus, apply_decommission_status_space_info, bind_decommission_cancelers,
-        bind_missing_decommission_cancelers, cancel_decommission_canceler, classify_decommission_terminal_state,
-        count_decommission_item, decommission_cancel_signal_result, decommission_item_size, decommission_meta_bucket_options,
+        DECOMMISSION_PROGRESS_SAVE_INTERVAL, DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD, DecomBucketInfo,
+        DecommissionStartPoolState, DecommissionTerminalState, ListCallback, PoolDecommissionInfo, PoolMeta, PoolSpaceInfo,
+        PoolStatus, apply_decommission_status_space_info, bind_decommission_cancelers, bind_missing_decommission_cancelers,
+        cancel_decommission_canceler, classify_decommission_terminal_state, count_decommission_item,
+        decommission_cancel_signal_result, decommission_item_size, decommission_meta_bucket_options,
         decommission_start_pool_state, dedup_indices, default_decommission_bucket_concurrency,
         ensure_decommission_cancel_allowed, ensure_decommission_clear_allowed, ensure_decommission_listing_disks_available,
         ensure_decommission_not_rebalancing, ensure_decommission_start_allowed, ensure_decommission_start_keeps_active_pool,
@@ -5372,8 +5293,9 @@ mod pools_tests {
         should_preserve_decommission_canceled_state, should_reject_decommission_cancel_as_terminal,
         should_retry_decommission_cancel_reload, should_retry_decommission_listing, should_skip_canceled_decommission_routine,
         split_decommission_buckets, take_and_cancel_decommission_canceler, take_decommission_canceler,
-        track_decommission_current_object, track_decommission_current_object_stage, validate_start_decommission_request,
-        wait_decommission_listing_retry, wait_decommission_worker_drain, with_decommission_entry_context,
+        touch_decommission_progress, track_decommission_current_object, track_decommission_current_object_stage,
+        validate_start_decommission_request, wait_decommission_listing_retry, wait_decommission_worker_drain,
+        with_decommission_entry_context,
     };
     use crate::data_movement;
     use crate::disk::endpoint::Endpoint;
@@ -6616,7 +6538,7 @@ mod pools_tests {
     }
 
     #[test]
-    fn test_track_decommission_stage_does_not_advance_checkpoint_state() {
+    fn test_touch_decommission_progress_updates_last_update_and_save_baseline() {
         let mut meta = PoolMeta {
             pools: vec![PoolStatus {
                 id: 0,
@@ -6631,13 +6553,11 @@ mod pools_tests {
             ..Default::default()
         };
 
-        track_decommission_current_object_stage(&mut meta, 0, "bucket", "object", "migrate_object")
-            .expect("valid decommission progress should be tracked");
+        touch_decommission_progress(&mut meta, 0).expect("valid decommission progress should be touched");
 
-        assert_eq!(meta.pools[0].last_update, OffsetDateTime::UNIX_EPOCH);
+        assert!(meta.pools[0].last_update > OffsetDateTime::UNIX_EPOCH);
         let info = meta.pools[0].decommission.as_ref().expect("decommission info should exist");
-        assert_eq!(info.items_since_last_progress_save(), 5);
-        assert_eq!(info.stage, "migrate_object");
+        assert_eq!(info.items_since_last_progress_save(), 0);
     }
 
     #[test]
@@ -6712,134 +6632,6 @@ mod pools_tests {
         assert_eq!(info.items_since_last_progress_save(), 1);
     }
 
-    #[test]
-    fn test_pool_meta_update_after_does_not_advance_last_update_before_save() {
-        let last_update = OffsetDateTime::UNIX_EPOCH;
-        let mut meta = PoolMeta {
-            pools: vec![PoolStatus {
-                id: 0,
-                cmd_line: "pool-0".to_string(),
-                last_update,
-                decommission: Some(PoolDecommissionInfo {
-                    start_time: Some(last_update),
-                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
-                    ..Default::default()
-                }),
-            }],
-            ..Default::default()
-        };
-
-        assert!(
-            meta.update_after(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL)
-                .expect("item threshold should request a checkpoint")
-        );
-        assert_eq!(meta.pools[0].last_update, last_update);
-    }
-
-    #[test]
-    fn test_decommission_progress_checkpoint_commits_exact_snapshot_watermark() {
-        let start_time = OffsetDateTime::UNIX_EPOCH;
-        let checkpoint_at = start_time + Duration::seconds(30);
-        let mut meta = PoolMeta {
-            pools: vec![PoolStatus {
-                id: 0,
-                cmd_line: "pool-0".to_string(),
-                last_update: start_time,
-                decommission: Some(PoolDecommissionInfo {
-                    start_time: Some(start_time),
-                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
-                    ..Default::default()
-                }),
-            }],
-            ..Default::default()
-        };
-
-        let checkpoint = meta
-            .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
-            .expect("valid decommission state should produce a checkpoint")
-            .expect("item threshold should produce a checkpoint");
-        meta.count_item(0, 1, false);
-
-        assert!(meta.commit_decommission_progress_checkpoint(0, checkpoint));
-        let info = meta.pools[0].decommission.as_ref().expect("decommission info should exist");
-        assert_eq!(info.progress_save_item_baseline, checkpoint.counted_items);
-        assert_eq!(info.items_since_last_progress_save(), 1);
-        assert_eq!(meta.pools[0].last_update, checkpoint_at);
-    }
-
-    #[test]
-    fn test_decommission_progress_checkpoint_backoff_does_not_advance_baseline() {
-        let start_time = OffsetDateTime::UNIX_EPOCH;
-        let checkpoint_at = start_time + Duration::seconds(30);
-        let retry_after = checkpoint_at + DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF;
-        let mut meta = PoolMeta {
-            pools: vec![PoolStatus {
-                id: 0,
-                cmd_line: "pool-0".to_string(),
-                last_update: start_time,
-                decommission: Some(PoolDecommissionInfo {
-                    start_time: Some(start_time),
-                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
-                    ..Default::default()
-                }),
-            }],
-            ..Default::default()
-        };
-
-        let checkpoint = meta
-            .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
-            .expect("valid decommission state should produce a checkpoint")
-            .expect("item threshold should produce a checkpoint");
-        meta.defer_decommission_progress_checkpoint(0, checkpoint, retry_after);
-
-        assert!(
-            meta.decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
-                .expect("retry backoff check should succeed")
-                .is_none()
-        );
-        assert_eq!(meta.pools[0].last_update, start_time);
-        assert_eq!(
-            meta.pools[0]
-                .decommission
-                .as_ref()
-                .expect("decommission info should exist")
-                .progress_save_item_baseline,
-            0
-        );
-    }
-
-    #[test]
-    fn test_decommission_progress_checkpoint_count_scales_with_threshold() {
-        let start_time = OffsetDateTime::UNIX_EPOCH;
-        let checkpoint_at = start_time;
-        let mut meta = PoolMeta {
-            pools: vec![PoolStatus {
-                id: 0,
-                cmd_line: "pool-0".to_string(),
-                last_update: start_time,
-                decommission: Some(PoolDecommissionInfo {
-                    start_time: Some(start_time),
-                    ..Default::default()
-                }),
-            }],
-            ..Default::default()
-        };
-        let mut checkpoint_count = 0;
-
-        for _ in 0..(DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD * 10) {
-            meta.count_item(0, 1, false);
-            if let Some(checkpoint) = meta
-                .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
-                .expect("valid decommission state should produce a checkpoint")
-            {
-                checkpoint_count += 1;
-                assert!(meta.commit_decommission_progress_checkpoint(0, checkpoint));
-            }
-        }
-
-        assert_eq!(checkpoint_count, 10);
-    }
-
     #[test]
     fn test_ensure_decommission_not_rebalancing_rejects_running_rebalance() {
         let err = ensure_decommission_not_rebalancing(true).expect_err("rebalance running should be rejected");

scripts/check_test_wiring.py

@@ -15,6 +15,20 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
+SCHEDULED_ALERT_WORKFLOWS = (
+    ".github/workflows/audit.yml",
+    ".github/workflows/build.yml",
+    ".github/workflows/ci.yml",
+    ".github/workflows/coverage.yml",
+    ".github/workflows/e2e-replication-nightly.yml",
+    ".github/workflows/e2e-s3tests.yml",
+    ".github/workflows/fuzz.yml",
+    ".github/workflows/mint.yml",
+    ".github/workflows/minio-interop.yml",
+    ".github/workflows/nightly-gnu.yml",
+    ".github/workflows/performance-ab.yml",
+    ".github/workflows/runner-hygiene.yml",
+)
 
 
 def words(value: str) -> set[str]:
@@ -252,6 +266,79 @@ def check_profile_definitions(root: Path) -> list[str]:
     return errors
 
 
+def check_scheduled_alerts(root: Path) -> list[str]:
+    errors: list[str] = []
+    for relative in SCHEDULED_ALERT_WORKFLOWS:
+        path = root / relative
+        try:
+            lines = path.read_text().splitlines()
+        except FileNotFoundError:
+            errors.append(f"{relative}: missing scheduled validation workflow")
+            continue
+
+        try:
+            start = lines.index("  alert-on-failure:") + 1
+        except ValueError:
+            errors.append(f"{relative}: missing alert-on-failure job")
+            continue
+        end = next(
+            (index for index in range(start, len(lines)) if re.fullmatch(r"  [A-Za-z0-9_-]+:", lines[index])),
+            len(lines),
+        )
+        job = "\n".join(line.split("#", 1)[0] for line in lines[start:end])
+        required = (
+            "always()",
+            "github.event_name == 'schedule'",
+            "contains(needs.*.result, 'failure')",
+            "issues: write",
+            "uses: ./.github/actions/schedule-failure-issue",
+            "github-token: ${{ secrets.GITHUB_TOKEN }}",
+        )
+        missing = [token for token in required if token not in job]
+        if missing:
+            errors.append(f"{relative}: alert-on-failure missing {', '.join(missing)}")
+
+    watchdog_path = root / ".github/workflows/scheduled-validation-watchdog.yml"
+    try:
+        watchdog = "\n".join(
+            line.split("#", 1)[0] for line in watchdog_path.read_text().splitlines()
+        )
+    except FileNotFoundError:
+        errors.append(".github/workflows/scheduled-validation-watchdog.yml: missing completion watchdog")
+        return errors
+    for relative in SCHEDULED_ALERT_WORKFLOWS:
+        path = root / relative
+        if not path.is_file():
+            continue
+        source = path.read_text()
+        match = re.search(r"^name:\s*[\"']?([^\"'\n]+)", source, re.MULTILINE)
+        if not match:
+            errors.append(f"{relative}: missing workflow name")
+        elif f'- "{match.group(1).strip()}"' not in watchdog:
+            errors.append(f"{relative}: missing from scheduled completion watchdog")
+    required = (
+        "github.event.workflow_run.event == 'schedule'",
+        "github.event.workflow_run.conclusion != 'success'",
+        "github.event.workflow_run.conclusion != 'failure'",
+        "actions: read",
+        "issues: write",
+        "uses: ./.github/actions/schedule-failure-issue",
+        "github-token: ${{ secrets.GITHUB_TOKEN }}",
+        "workflow-name: ${{ github.event.workflow_run.name }}",
+        "source-event: ${{ github.event.workflow_run.event }}",
+        "source-ref-name: ${{ github.event.workflow_run.head_branch }}",
+        "source-sha: ${{ github.event.workflow_run.head_sha }}",
+        "source-run-id: ${{ github.event.workflow_run.id }}",
+        "source-run-attempt: ${{ github.event.workflow_run.run_attempt }}",
+    )
+    missing = [token for token in required if token not in watchdog]
+    if missing:
+        errors.append(
+            ".github/workflows/scheduled-validation-watchdog.yml: missing " + ", ".join(missing)
+        )
+    return errors
+
+
 def check_profile_listing(root: Path, profile: str, listing: Path) -> list[str]:
     try:
         expected_digest = profile_selection(root, profile)
@@ -281,6 +368,7 @@ def validate(root: Path) -> list[str]:
     errors.extend(check_runner_selection(root))
     errors.extend(check_s3_tests_runner(root))
     errors.extend(check_profile_definitions(root))
+    errors.extend(check_scheduled_alerts(root))
     return errors
 
 
@@ -363,6 +451,7 @@ class SelfTests(unittest.TestCase):
                 mock.patch(__name__ + ".check_fuzz_targets", return_value=[]),
                 mock.patch(__name__ + ".check_runner_selection", return_value=[]),
                 mock.patch(__name__ + ".check_profile_definitions", return_value=[]),
+                mock.patch(__name__ + ".check_scheduled_alerts", return_value=[]),
             ):
                 self.assertEqual(len(validate(root)), 1)
 
@@ -413,6 +502,75 @@ class SelfTests(unittest.TestCase):
             with mock.patch.object(sys, "platform", "linux"):
                 self.assertEqual(len(check_profile_listing(root, "e2e-full", listing)), 1)
 
+    def test_scheduled_alerts_require_completion_watchdog(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            alert = (
+                "  alert-on-failure:\n"
+                "    if: always() && github.event_name == 'schedule' && "
+                "contains(needs.*.result, 'failure')\n"
+                "    permissions:\n"
+                "      issues: write\n"
+                "    steps:\n"
+                "      - uses: ./.github/actions/schedule-failure-issue\n"
+                "        with:\n"
+                "          github-token: ${{ secrets.GITHUB_TOKEN }}\n"
+            )
+            names: list[str] = []
+            for relative in SCHEDULED_ALERT_WORKFLOWS:
+                path = root / relative
+                path.parent.mkdir(parents=True, exist_ok=True)
+                names.append(path.stem)
+                path.write_text(f'name: "{path.stem}"\n{alert}')
+            watchdog = root / ".github/workflows/scheduled-validation-watchdog.yml"
+            watchdog_source = (
+                "\n".join(f'- "{name}"' for name in names)
+                + "\ngithub.event.workflow_run.event == 'schedule'\n"
+                + "github.event.workflow_run.conclusion != 'success'\n"
+                + "github.event.workflow_run.conclusion != 'failure'\n"
+                + "actions: read\n"
+                + "issues: write\n"
+                + "uses: ./.github/actions/schedule-failure-issue\n"
+                + "github-token: ${{ secrets.GITHUB_TOKEN }}\n"
+                + "workflow-name: ${{ github.event.workflow_run.name }}\n"
+                + "source-event: ${{ github.event.workflow_run.event }}\n"
+                + "source-ref-name: ${{ github.event.workflow_run.head_branch }}\n"
+                + "source-sha: ${{ github.event.workflow_run.head_sha }}\n"
+                + "source-run-id: ${{ github.event.workflow_run.id }}\n"
+                + "source-run-attempt: ${{ github.event.workflow_run.run_attempt }}\n"
+            )
+            watchdog.write_text(watchdog_source)
+            self.assertEqual(check_scheduled_alerts(root), [])
+
+            first = root / SCHEDULED_ALERT_WORKFLOWS[0]
+            mutations = (
+                ("contains(needs.*.result, 'failure')", "false"),
+                ("issues: write", "issues: read"),
+                ("uses: ./.github/actions/schedule-failure-issue", "uses: actions/checkout@v7"),
+                ("github-token: ${{ secrets.GITHUB_TOKEN }}", "github-token: missing"),
+            )
+            for required, replacement in mutations:
+                original = first.read_text()
+                first.write_text(original.replace(required, replacement))
+                self.assertEqual(len(check_scheduled_alerts(root)), 1)
+                first.write_text(original)
+
+            watchdog.write_text(watchdog_source.replace(f'- "{names[0]}"\n', ""))
+            self.assertEqual(len(check_scheduled_alerts(root)), 1)
+
+            watchdog_mutations = (
+                ("actions: read", "actions: none"),
+                ("issues: write", "issues: read"),
+                ("uses: ./.github/actions/schedule-failure-issue", "uses: actions/checkout@v7"),
+                ("github-token: ${{ secrets.GITHUB_TOKEN }}", "github-token: missing"),
+                ("source-event: ${{ github.event.workflow_run.event }}", "source-event: wrong"),
+                ("source-ref-name: ${{ github.event.workflow_run.head_branch }}", "source-ref-name: wrong"),
+                ("source-sha: ${{ github.event.workflow_run.head_sha }}", "source-sha: wrong"),
+            )
+            for required, replacement in watchdog_mutations:
+                watchdog.write_text(watchdog_source.replace(required, replacement))
+                self.assertEqual(len(check_scheduled_alerts(root)), 1)
+
 def main() -> int:
     if sys.argv[1:] == ["--self-test"]:
         suite = unittest.defaultTestLoader.loadTestsFromTestCase(SelfTests)
@@ -436,7 +594,7 @@ def main() -> int:
         for error in errors:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
-    print("OK: e2e modules, runner selection, fuzz matrices, profiles, and bounded diagnostics are wired")
+    print("OK: e2e modules, runner selection, fuzz matrices, profiles, scheduled alerts, and bounded diagnostics are wired")
     return 0