Improve M3DBs ability to apply back pressure on writes #1482
Conversation
This file contains 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
richardartoul
requested review from
prateek,
robskillington,
simonrobb and
Haijuncao
richardartoul
added
T: Reliability
area:db
added 10 commits
March 20, 2019 19:00
richardartoul
force-pushed
the
ra/improve-m3db-backpressure
branch
from
369eb07 to
eb01ae8
Compare
Haijuncao
approved these changes
Mar 21, 2019
2 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Previously, M3DB would only apply back pressure on writes if it received a commitlog queue full error, but this would only occur after almost all of the most expensive operations have already taken place.
To improve this situation, before performing any write and all the expensive memory operations like writing to in-memory data structures, hash map lookups, pooling and object allocation etc, we'll check the current length of the commit log queue. If its over 90% of its maximum capacity, we'll fail the write early to give the system time to recover.