') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); [v3-3-test] Fix scheduler firing on_failure_callback for heartbeat-timed-out retries (#66767) by github-actions[bot] · Pull Request #69824 · apache/airflow · GitHub
Skip to content

[v3-3-test] Fix scheduler firing on_failure_callback for heartbeat-timed-out retries (#66767) - #69824

Merged
eladkal merged 1 commit into
v3-3-testfrom
backport-f2403cc-v3-3-test
Jul 13, 2026
Merged

[v3-3-test] Fix scheduler firing on_failure_callback for heartbeat-timed-out retries (#66767)#69824
eladkal merged 1 commit into
v3-3-testfrom
backport-f2403cc-v3-3-test

Conversation

@github-actions

@github-actionsgithub-actionsBot commented Jul 13, 2026

Copy link
Copy Markdown
Contributor

When a worker stops heartbeating (OOMKill, node eviction), the scheduler's
_purge_task_instances_without_heartbeats built a TaskCallbackRequest
without task_callback_type. The Dag processor's task-callback dispatch
branches on that field: UP_FOR_RETRY runs on_retry_callback, anything
else (including None) runs on_failure_callback. So heartbeat-timeout
cleanup always fired on_failure_callback even when the task still had
retries remaining, producing spurious failure alerts for tasks that
ultimately succeeded on retry.

Set task_callback_type from ti.is_eligible_to_retry(), the canonical
retry-eligibility predicate, guarded by max_tries > 0. The guard covers
the one gap the predicate has here: this path doesn't load ti.task, so the
predicate falls back to try_number <= max_tries and drops the
retries-configured check its task-loaded branch applies. Deferring to the
predicate also keeps a RESTARTING task (cleared while running) retry-
eligible past max_tries, where a hand-rolled try_number <= max_tries
check would have fired on_failure_callback.

closes: #65400
(cherry picked from commit f2403cc)

Co-authored-by: Stefan Wang 1fannnw@gmail.com
Signed-off-by: 1fanwang 1fannnw@gmail.com
Co-authored-by: kimhaggie kimhaggie@gmail.com

@1fanwang@kimhaggieYour friendly bot
[v3-3-test] Fix scheduler firing on_failure_callback for heartbeat-ti…
fd8eb34
…med-out retries (#66767)
When a worker stops heartbeating (OOMKill, node eviction), the scheduler's
``_purge_task_instances_without_heartbeats`` built a ``TaskCallbackRequest``
without ``task_callback_type``. The Dag processor's task-callback dispatch
branches on that field: ``UP_FOR_RETRY`` runs ``on_retry_callback``, anything
else (including ``None``) runs ``on_failure_callback``. So heartbeat-timeout
cleanup always fired ``on_failure_callback`` even when the task still had
retries remaining, producing spurious failure alerts for tasks that
ultimately succeeded on retry.
Set ``task_callback_type`` from ``ti.is_eligible_to_retry()``, the canonical
retry-eligibility predicate, guarded by ``max_tries > 0``. The guard covers
the one gap the predicate has here: this path doesn't load ``ti.task``, so the
predicate falls back to ``try_number <= max_tries`` and drops the
retries-configured check its task-loaded branch applies. Deferring to the
predicate also keeps a ``RESTARTING`` task (cleared while running) retry-
eligible past ``max_tries``, where a hand-rolled ``try_number <= max_tries``
check would have fired ``on_failure_callback``.
closes: #65400
(cherry picked from commit f2403cc)
Co-authored-by: Stefan Wang <1fannnw@gmail.com>
Signed-off-by: 1fanwang <1fannnw@gmail.com>
Co-authored-by: kimhaggie <kimhaggie@gmail.com>
@github-actionsgithub-actionsBot mentioned this pull request Jul 13, 2026
Merged
@boring-cyborgboring-cyborgBot added the area:Scheduler including HA (high availability) scheduler label Jul 13, 2026
@eladkal
eladkal marked this pull request as ready for review July 13, 2026 11:48
@eladkal
eladkal requested review from XD-DENG and ashb as code ownersJuly 13, 2026 11:48
@eladkal
eladkal merged commit afeb272 into v3-3-testJul 13, 2026
100 of 109 checks passed
@eladkal
eladkal deleted the backport-f2403cc-v3-3-test branch July 13, 2026 12:43
@github-actionsgithub-actionsBot added this to the Airflow 3.3.1 milestone Jul 13, 2026
@github-actions

github-actionsBot commented Jul 13, 2026

Copy link
Copy Markdown
ContributorAuthor

Hi maintainer, this PR was merged without a milestone set.
We've automatically set the milestone to Airflow 3.3.1 based on: bug fix merged to version branch
If this milestone is not correct, please update it to the appropriate milestone.

This comment was generated by Milestone Tag Assistant.

@vatsrahul1001vatsrahul1001 added the type:bug-fix Changelog: Bug Fixes label Jul 27, 2026
vatsrahul1001 pushed a commit that referenced this pull request Aug 5, 2026
@github-actions@1fanwang
@kimhaggie@vatsrahul1001
[v3-3-test] Fix scheduler firing on_failure_callback for heartbeat-ti…
02ec156
…med-out retries (#66767) (#69824)
When a worker stops heartbeating (OOMKill, node eviction), the scheduler's
``_purge_task_instances_without_heartbeats`` built a ``TaskCallbackRequest``
without ``task_callback_type``. The Dag processor's task-callback dispatch
branches on that field: ``UP_FOR_RETRY`` runs ``on_retry_callback``, anything
else (including ``None``) runs ``on_failure_callback``. So heartbeat-timeout
cleanup always fired ``on_failure_callback`` even when the task still had
retries remaining, producing spurious failure alerts for tasks that
ultimately succeeded on retry.
Set ``task_callback_type`` from ``ti.is_eligible_to_retry()``, the canonical
retry-eligibility predicate, guarded by ``max_tries > 0``. The guard covers
the one gap the predicate has here: this path doesn't load ``ti.task``, so the
predicate falls back to ``try_number <= max_tries`` and drops the
retries-configured check its task-loaded branch applies. Deferring to the
predicate also keeps a ``RESTARTING`` task (cleared while running) retry-
eligible past ``max_tries``, where a hand-rolled ``try_number <= max_tries``
check would have fired ``on_failure_callback``.
closes: #65400
(cherry picked from commit f2403cc)
Signed-off-by: 1fanwang <1fannnw@gmail.com>
Co-authored-by: Stefan Wang <1fannnw@gmail.com>
Co-authored-by: kimhaggie <kimhaggie@gmail.com>
@vatsrahul1001vatsrahul1001 mentioned this pull request Aug 7, 2026
Closed
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ashbashbAwaiting requested review from ashbashb is a code owner
@XD-DENGXD-DENGAwaiting requested review from XD-DENGXD-DENG is a code owner

Assignees

No one assigned

Labels

area:Schedulerincluding HA (high availability) schedulertype:bug-fixChangelog: Bug Fixes

Projects

None yet

Milestone

Airflow 3.3.1

Development

Successfully merging this pull request may close these issues.

3 participants

@vatsrahul1001@eladkal@1fanwang