-
Notifications
You must be signed in to change notification settings - Fork 393
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
tokio-epoll-uring: use it on the layer-creating code paths #6378
Merged
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
2561 tests run: 2427 passed, 0 failed, 134 skipped (full report)Code coverage* (full report)
* collected from Rust tests only The comment gets automatically updated with the latest test results
bdd5228 at 2024-03-05T09:19:50.873Z :recycle: |
a8c9912
to
7c92164
Compare
Base automatically changed from
problame/integrate-tokio-epoll-uring/wip
to
main
January 26, 2024 08:25
9bd0b1c
to
0548374
Compare
We can probably get rid of the entire trait, but, that's for another time.
…uilder-refactor' into problame/integrate-tokio-epoll-uring/write-path/simplify-write-at-api
This reverts commit b5a00b0.
…ath/refactor-blob-writer
…kio-epoll-uring/layer-write-path-fsync-cleanups
…sync-cleanups' into problame/integrate-tokio-epoll-uring/create-layer-fatal-err-on-fsync
…-err-on-fsync' into problame/integrate-tokio-epoll-uring/ioengine-par-fsync
…' into problame/integrate-tokio-epoll-uring/more-ops
problame
commented
Mar 1, 2024
koivunej
approved these changes
Mar 1, 2024
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For me this is looking good.
VladLazar
approved these changes
Mar 4, 2024
Base automatically changed from
problame/integrate-tokio-epoll-uring/ioengine-par-fsync
to
main
March 4, 2024 13:31
problame
added a commit
that referenced
this pull request
Mar 4, 2024
…ync_all()` (#6986) Except for the involvement of the VirtualFile fd cache, this is equivalent to what happened before at runtime. Future PR #6378 will implement `VirtualFile::sync_all()` using tokio-epoll-uring if that's configured as the io engine. This PR is preliminary work for that. part of #6663
problame
added a commit
that referenced
this pull request
Mar 15, 2024
refs #7136 Problem ------- Before this PR, we were using `tokio_epoll_uring::thread_local_system()`, which panics on tokio_epoll_uring::System::launch() failure As we've learned in [the past](#6373 (comment)), some older Linux kernels account io_uring instances as locked memory. And while we've raised the limit in prod considerably, we did hit it once on 2024-03-11 16:30 UTC. That was after we enabled tokio-epoll-uring fleet-wide, but before we had shipped release-5090 (c6ed86d) which did away with the last mass-creation of tokio-epoll-uring instances as per commit 3da410c Author: Christian Schwarz <christian@neon.tech> Date: Tue Mar 5 10:03:54 2024 +0100 tokio-epoll-uring: use it on the layer-creating code paths (#6378) Nonetheless, it highlighted that panicking in this situation is probably not ideal, as it can leave the pageserver process in a semi-broken state. Further, due to low sampling rate of Prometheus metrics, we don't know much about the circumstances of this failure instance. Solution -------- This PR implements a custom thread_local_system() that is pageserver-aware and will do the following on failure: - dump relevant stats to `tracing!`, hopefully they will be useful to understand the circumstances better - if it's the locked memory failure (or any other ENOMEM): abort() the process - if it's ENOMEM, retry with exponential back-off, capped at 3s. - add metric counters so we can create an alert This makes sense in the production environment where we know that _usually_, there's ample locked memory allowance available, and we know the failure rate is rare.
problame
added a commit
that referenced
this pull request
Mar 15, 2024
refs #7136 Problem ------- Before this PR, we were using `tokio_epoll_uring::thread_local_system()`, which panics on tokio_epoll_uring::System::launch() failure As we've learned in [the past](#6373 (comment)), some older Linux kernels account io_uring instances as locked memory. And while we've raised the limit in prod considerably, we did hit it once on 2024-03-11 16:30 UTC. That was after we enabled tokio-epoll-uring fleet-wide, but before we had shipped release-5090 (c6ed86d) which did away with the last mass-creation of tokio-epoll-uring instances as per commit 3da410c Author: Christian Schwarz <christian@neon.tech> Date: Tue Mar 5 10:03:54 2024 +0100 tokio-epoll-uring: use it on the layer-creating code paths (#6378) Nonetheless, it highlighted that panicking in this situation is probably not ideal, as it can leave the pageserver process in a semi-broken state. Further, due to low sampling rate of Prometheus metrics, we don't know much about the circumstances of this failure instance. Solution -------- This PR implements a custom thread_local_system() that is pageserver-aware and will do the following on failure: - dump relevant stats to `tracing!`, hopefully they will be useful to understand the circumstances better - if it's the locked memory failure (or any other ENOMEM): abort() the process - if it's ENOMEM, retry with exponential back-off, capped at 3s. - add metric counters so we can create an alert This makes sense in the production environment where we know that _usually_, there's ample locked memory allowance available, and we know the failure rate is rare.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
run-benchmarks
Indicates to the CI that benchmarks should be run for PR marked with this label
run-extra-build-*
When placed on a PR, tells the CI to run all extra builds
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.
part of #6663
See that epic for more context & related commits.
Problem
Before this PR, the layer-file-creating code paths were using VirtualFile, but under the hood these were still blocking system calls.
Generally this meant we'd stall the executor thread, unless the caller "knew" and used the following pattern instead:
Solution
This PR adopts
tokio-epoll-uring
on the layer-file-creating code paths in pageserver.Note that on-demand downloads still use
tokio::fs
, these will be converted in a future PR.Design: Avoiding Regressions With
std-fs
If we make the VirtualFile write path truly async using
tokio-epoll-uring
, should we then remove thespawn_blocking
+Handle::block_on
usage upstack in the same commit?No, because if we’re still using the
std-fs
io engine, we’d then block the executor in those places where previously we were protecting us from that through thespawn_blocking
.So, if we want to see benefits from
tokio-epoll-uring
on the write path while also preserving the ability to switch betweentokio-epoll-uring
andstd-fs
, wherestd-fs
will behave identical to what we have now, we need to conditionally usespawn_blocking + Handle::block_on
.I.e., in the places where we use that know, we’ll need to make that conditional based on the currently configured io engine.
It boils down to investigating all the places where we do
spawn_blocking(... block_on(... VirtualFile::...))
.Detailed write-up of that investigation in Notion, made publicly accessible.
tl;dr: Preceding PRs addressed the relevant call sites:
metadata
file: turns out we could simply remove it (stop reading localmetadata
file #6777, stop writingmetadata
file #6769, Revert "Revert "refactor(VirtualFile::crashsafe_overwrite): avoid Handle::block_on in callers"" #6775)create_delta_layer()
: made sensitive tovirtual_file_io_engine
in layer file creation: fsync timeline directories usingVirtualFile::sync_all()
#6986NB: once we are switched over to
tokio-epoll-uring
everywhere in production, we can deprecatestd-fs
; to keep macOS support, we can usetokio::fs
instead. That will remove this whole headache.Code Changes In This PR
VirtualFile::write_at
ioengine
operation and switchVirtualFile::write_at
to itVirtualFile::metadata()
finish()
methodsMetadata
enum becausestd::fs::Metadata
cannot be constructed by code outside rust stdVirtualFile::sync_all()
and for completeness sake, addVirtualFile::sync_data()
Testing & Rollout
Before merging this PR, we ran the CI with both io engines.
Additionally, the changes will soak in staging.
We could have a feature gate / add a new io engine
tokio-epoll-uring-write-path
to do a gradual rollout. However, that's not part of this PR.Future Work
There's still some use of
std::fs
and/ortokio::fs
for directory namespace operations, e.g.std::fs::rename
.We're not addressing those in this PR, as we'll need to add the support in tokio-epoll-uring first. Note that rename itself is usually fast if the directory is in the kernel dentry cache, and only the fsync after rename is slow. These fsyncs are using tokio-epoll-uring, so, the impact should be small.