Redwood chunked file growth and low priority IO starvation prevention #5936
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
… reduce truncate() calls for expansion. PriorityMultiLock has limit on consecutive same-priority lock release. Increased Redwood max priority level to 3 for more separation at higher BTree levels.
…ss the simulated process has been set to have an unreliable disk.
…esponse to writes, which wait on only the necessary truncate operations. Increased buggified chunk size because truncate can be very slow in simulation.
…o-priority # Conflicts: # flow/genericactors.actor.h
…o-priority # Conflicts: # fdbserver/VersionedBTree.actor.cpp
…ait until at least the target timeout interval past the point when simulation is sped up.
…o-priority # Conflicts: # fdbclient/ServerKnobs.cpp # fdbclient/ServerKnobs.h # fdbserver/VersionedBTree.actor.cpp
… and do in place value updates if the new value is the same size as the old value.
AWS CodeBuild CI Report for macOS Catalina 10.15
|
AWS CodeBuild CI Report for macOS Catalina 10.15
|
AWS CodeBuild CI Report for Linux CentOS 7
|
AWS CodeBuild CI Report for Linux CentOS 7
|
…tchToLinearMerge() since it is only used in one place.
AWS CodeBuild CI Report for Linux CentOS 7
|
1 similar comment
AWS CodeBuild CI Report for Linux CentOS 7
|
AWS CodeBuild CI Report for Linux CentOS 7
|
sfc-gh-satherton
force-pushed
the
redwood-io-priority
branch
from
5994501
to
80707a0
Compare
AWS CodeBuild CI Report for Linux CentOS 7
|
AWS CodeBuild CI Report for macOS Catalina 10.15
|
fdbserver/VersionedBTree.actor.cpp
Outdated
| self->filePageCountPending = newPageCount; | ||
|
|
||
| // Wait for any previous extensions to complete | ||
| wait(self->fileExtension); |
There was a problem hiding this comment.
Just to confirm my understanding, the reason this works along with line 2607 updating self->FileExtension to this future is because extendToCoverwill run up to the wait, including passing the current self->fileExtension to the wait, before updating self->fileExtension on line 2607?
This seems like a weird interaction with futures that might at least warrant a comment or something?
…n future as a parameter. Fixed initialization warning.
AWS CodeBuild CI Report for macOS Catalina 10.15
|
AWS CodeBuild CI Report for Linux CentOS 7
|
sfc-gh-jslocum
approved these changes
Nov 12, 2021
5 tasks
This was referenced Feb 10, 2022
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.
Redwood now grows files in chunks of 20k pages by default, controlled by a knob.
To prevent high read rates from starving lower priority write ops, PriorityMultiLock now
Simulation bug fix:
ioTimeoutError()andioDegradedOrTimeoutErrorwon't trigger until afterspeedUpSimulationis set since before then IO can be extremely slow in sim time.This PR also includes #5925.
The general guidelines can be found here.
Please check each of the following things and check all boxes before accepting a PR.
For Release-Branches
If this PR is made against a release-branch, please also check the following:
release-branchormasterif this is the youngest branch)