HDDS-14724. Fix infinite CPU spin loop in ECBlockInputStream#9833
Open
stuxuhai wants to merge 1 commit intoapache:masterfrom
Open
HDDS-14724. Fix infinite CPU spin loop in ECBlockInputStream#9833stuxuhai wants to merge 1 commit intoapache:masterfrom
stuxuhai wants to merge 1 commit intoapache:masterfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changes were proposed in this pull request?
This PR fixes a critical 100% CPU infinite spin loop bug in
ECBlockInputStreamthat occurs during transient network unavailability or DataNode unreadiness (e.g., when the underlying NIO channel returns0bytes).Currently,
ECBlockInputStream#readFromStreamonly checks ifactualRead == -1(EOF). If0bytes are returned whileexpectedRead > 0, the stream fails to advance its position but remains in thewhileloop, causing an infinite CPU spin and thread starvation.Proposed Solution:
Instead of introducing complex timeouts or backoff loops, this patch aligns the EC read path with the traditional replica read path (
BlockInputStream#readWithStrategy).By strictly validating
actualRead != expectedRead(or explicitly intercepting0), it throws anIOExceptionimmediately on inconsistent reads.This naturally integrates with the existing Ozone client architecture:
ECBlockInputStreamthrowsIOException.readWithStrategywraps it intoBadDataLocationException.ECBlockInputStreamProxycatches it and gracefully falls over tofailoverToReconstructionRead.This minimalist approach completely eliminates the spin loop while fully leveraging the ecosystem's native reconstruction/failover mechanisms without modifying the Proxy class.
What is the link to the Apache JIRA
https://issues.apache.org/jira/browse/HDDS-14724
How was this patch tested?
Added a JUnit test testZeroByteReadTriggersFailoverException to verify that a 0-byte read in ECBlockInputStream correctly throws an IOException (which translates to BadDataLocationException), instantly breaking the loop.