Skip to content

[WAGED Tag Isolation 9/16] Measure the blast radius of a broken clique - #289

Draft
LZD-PratyushBhatt wants to merge 1 commit into
lzd/waged-iso-08-deficitfrom
lzd/waged-iso-09-tests-blast
Draft

LZD-PratyushBhatt wants to merge 1 commit into
lzd/waged-iso-08-deficitfrom
lzd/waged-iso-09-tests-blast

Conversation

@LZD-PratyushBhatt

Copy link
Copy Markdown
Collaborator

Description

Tests only. They pin down how much of a cluster one unplaceable clique is
allowed to affect: with isolation on, a broken clique leaves every other
clique's assignment untouched and the number of carried over resources
equals the size of its share block and nothing more. With isolation off the
same cluster fails entirely, which is the behavior being replaced.

Stacked PR 9 of 16 for WAGED instance tag isolation.
Base branch: lzd/waged-iso-08-deficit. Only the top commit belongs to this PR.
The whole stack merges into waged-tag-based-isolation, which is merged into dev at the end.

Tests

TestCliqueFailureBlastRadius (new).

Tests run: 5, Failures: 0, Errors: 0, Skipped: 0

Changes that Break Backward Compatibility

None. The new cluster config flag defaults to false, and with it off every
code path added here behaves exactly as it does today.

Documentation

The design doc lands in lzd/waged-iso-13-doc as
docs/design/002-waged-instance-tag-isolation.md.

Code Quality

Formatted with helix-style.xml.

Add tests that pin down how much of a cluster one unplaceable clique is
allowed to affect.

They assert the property the whole feature rests on: with isolation on,
a broken clique leaves every other clique's assignment untouched, and
the number of resources carried over equals the size of the broken
clique's share block and nothing more. With isolation off, the same
cluster fails entirely, which is the behavior being replaced.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@LZD-PratyushBhatt
LZD-PratyushBhatt added this pull request to stack #297 September 20, 2026 05:46
@LZD-PratyushBhatt LZD-PratyushBhatt changed the title Measure the blast radius of a broken clique [WAGED Tag Isolation 9/16] Measure the blast radius of a broken clique Sep 20, 2026
@LZD-PratyushBhatt LZD-PratyushBhatt added the waged-tag-level-isolation Opt-in WAGED failure isolation per instance group tag (clique) label Sep 20, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

waged-tag-level-isolation Opt-in WAGED failure isolation per instance group tag (clique)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant