Conversation
A shard's health mask is a hard filter in connForPolicySlaves, and its bits contradict each other while a master is down: the master's bit is never cleared, while its replica reports master_link_status:down for the whole failover window even though it keeps serving reads. Every MasterAndSlaves / PreferSlaves read to that shard fails with no_alive_connection until redis finishes the failover and CLUSTER SLOTS reports a new master. Health becomes a preference: hosts in the mask are tried first, the rest of the shard after them. Zero-weight hosts are tried last rather than never, since the weighted wheel cannot draw from a total of zero.
g7r
marked this pull request as draft
September 15, 2026 06:08
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A shard's health mask is a hard filter in
connForPolicySlaves, and its bitscontradict each other while a master is down: the master's bit is never
cleared, while its replica reports
master_link_status:downfor the wholefailover window even though it keeps serving reads. Every
MasterAndSlaves/PreferSlavesread to that shard fails withno_alive_connectionuntil redisfinishes the failover and
CLUSTER SLOTSreports a new master.Health becomes a preference: hosts in the mask are tried first, the rest of the
shard after them. Zero-weight hosts are tried last rather than never, since the
weighted wheel cannot draw from a total of zero.