io: reduce syscalls in poll_read #4840
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
|
Does this mean that we will advance the |
|
@Darksonn yeah, the advancement amount is now set inside the closure independent of the return value of the closure. |
|
Actually, never mind. It appears that even if the readiness is cleared, this still returns |
|
So what you are saying is that there is still room for further perf gains? Most excellent! |
|
Side note: theoretically this should also be applicable to writes as well. |
|
No, I'm saying that my concern didn't apply. Returning |
|
Ah, makes more sense! |
|
Was slightly confused |
|
The way I implemented it originally (advance buffer but return pending) was mostly a hack to test out the concept. We probably don't want to use this strategy in practice. We probably just want to avoid using the We also only want to use this optimization on platforms for which we know it holds. This includes Linux at the very least but also probably kqueue. It definitely doesn't include windows as of now. |
There was a problem hiding this comment.
This strategy work on Unix (epoll and kqueue), but doesn't work on Windows as Mio uses the WouldBlock error to re-register I/O interest internally, see https://github.com/tokio-rs/mio/blob/add75b1dfff13d2b81ca40b23708996296fc4c44/src/sys/windows/mod.rs#L86-L96.
Noah-Kennedy
force-pushed
the
reduce-syscalls
branch
5 times, most recently
from
acca220
to
b3d8fad
Compare
As the [epoll documentation points out](https://man7.org/linux/man-pages/man7/epoll.7.html), a read that only partially fills a buffer is sufficient to show that the socket buffer has been drained. We can take advantage of this by clearing readiness in this case, which seems to significantly improve performance under certain conditions.
Noah-Kennedy
force-pushed
the
reduce-syscalls
branch
from
b3d8fad
to
f61d606
Compare
Thomasdezeeuw
approved these changes
Jul 26, 2022
There was a problem hiding this comment.
From Mio's side this looks good. However note that technically Mio doesn't guarantee that reading less bytes means readiness is drained, but all Unix-lie OSs we support do, so Mio guarantee is technically speaking violated here. That said, I've been in favour of switching to the Unix behaviour for Unix as well (since Mio controls it directly).
Noah-Kennedy
added a commit
that referenced
this pull request
Sep 2, 2022
This applies the same optimization made in #4840 to writes.
Noah-Kennedy
added a commit
that referenced
this pull request
Sep 2, 2022
This applies the same optimization made in #4840 to writes.
Noah-Kennedy
added a commit
that referenced
this pull request
Sep 2, 2022
This applies the same optimization made in #4840 to writes.
Noah-Kennedy
added a commit
that referenced
this pull request
Sep 2, 2022
This applies the same optimization made in #4840 to writes.
crapStone
pushed a commit
to Calciumdibromid/CaBr2
that referenced
this pull request
Sep 11, 2022
This PR contains the following updates: | Package | Type | Update | Change | |---|---|---|---| | [tokio](https://tokio.rs) ([source](https://github.com/tokio-rs/tokio)) | dependencies | minor | `1.20.1` -> `1.21.0` | | [tokio](https://tokio.rs) ([source](https://github.com/tokio-rs/tokio)) | dev-dependencies | minor | `1.20.1` -> `1.21.0` | --- ### Release Notes <details> <summary>tokio-rs/tokio</summary> ### [`v1.21.0`](https://github.com/tokio-rs/tokio/releases/tag/tokio-1.21.0) [Compare Source](tokio-rs/tokio@tokio-1.20.1...tokio-1.21.0) ##### 1.21.0 (September 2, 2022) This release is the first release of Tokio to intentionally support WASM. The `sync,macros,io-util,rt,time` features are stabilized on WASM. Additionally the wasm32-wasi target is given unstable support for the `net` feature. ##### Added - net: add `device` and `bind_device` methods to TCP/UDP sockets ([#​4882]) - net: add `tos` and `set_tos` methods to TCP and UDP sockets ([#​4877]) - net: add security flags to named pipe `ServerOptions` ([#​4845]) - signal: add more windows signal handlers ([#​4924]) - sync: add `mpsc::Sender::max_capacity` method ([#​4904]) - sync: implement Weak version of `mpsc::Sender` ([#​4595]) - task: add `LocalSet::enter` ([#​4765]) - task: stabilize `JoinSet` and `AbortHandle` ([#​4920]) - tokio: add `track_caller` to public APIs ([#​4805], [#​4848], [#​4852]) - wasm: initial support for `wasm32-wasi` target ([#​4716]) ##### Fixed - miri: improve miri compatibility by avoiding temporary references in `linked_list::Link` impls ([#​4841]) - signal: don't register write interest on signal pipe ([#​4898]) - sync: add `#[must_use]` to lock guards ([#​4886]) - sync: fix hang when calling `recv` on closed and reopened broadcast channel ([#​4867]) - task: propagate attributes on task-locals ([#​4837]) ##### Changed - fs: change panic to error in `File::start_seek` ([#​4897]) - io: reduce syscalls in `poll_read` ([#​4840]) - process: use blocking threadpool for child stdio I/O ([#​4824]) - signal: make `SignalKind` methods const ([#​4956]) ##### Internal changes - rt: extract `basic_scheduler::Config` ([#​4935]) - rt: move I/O driver into `runtime` module ([#​4942]) - rt: rename internal scheduler types ([#​4945]) ##### Documented - chore: fix typos and grammar ([#​4858], [#​4894], [#​4928]) - io: fix typo in `AsyncSeekExt::rewind` docs ([#​4893]) - net: add documentation to `try_read()` for zero-length buffers ([#​4937]) - runtime: remove incorrect panic section for `Builder::worker_threads` ([#​4849]) - sync: doc of `watch::Sender::send` improved ([#​4959]) - task: add cancel safety docs to `JoinHandle` ([#​4901]) - task: expand on cancellation of `spawn_blocking` ([#​4811]) - time: clarify that the first tick of `Interval::tick` happens immediately ([#​4951]) ##### Unstable - rt: add unstable option to disable the LIFO slot ([#​4936]) - task: fix incorrect signature in `Builder::spawn_on` ([#​4953]) - task: make `task::Builder::spawn*` methods fallible ([#​4823]) [#​4595]: tokio-rs/tokio#4595 [#​4716]: tokio-rs/tokio#4716 [#​4765]: tokio-rs/tokio#4765 [#​4805]: tokio-rs/tokio#4805 [#​4811]: tokio-rs/tokio#4811 [#​4823]: tokio-rs/tokio#4823 [#​4824]: tokio-rs/tokio#4824 [#​4837]: tokio-rs/tokio#4837 [#​4840]: tokio-rs/tokio#4840 [#​4841]: tokio-rs/tokio#4841 [#​4845]: tokio-rs/tokio#4845 [#​4848]: tokio-rs/tokio#4848 [#​4849]: tokio-rs/tokio#4849 [#​4852]: tokio-rs/tokio#4852 [#​4858]: tokio-rs/tokio#4858 [#​4867]: tokio-rs/tokio#4867 [#​4877]: tokio-rs/tokio#4877 [#​4882]: tokio-rs/tokio#4882 [#​4886]: tokio-rs/tokio#4886 [#​4893]: tokio-rs/tokio#4893 [#​4894]: tokio-rs/tokio#4894 [#​4897]: tokio-rs/tokio#4897 [#​4898]: tokio-rs/tokio#4898 [#​4901]: tokio-rs/tokio#4901 [#​4904]: tokio-rs/tokio#4904 [#​4920]: tokio-rs/tokio#4920 [#​4924]: tokio-rs/tokio#4924 [#​4928]: tokio-rs/tokio#4928 [#​4935]: tokio-rs/tokio#4935 [#​4936]: tokio-rs/tokio#4936 [#​4937]: tokio-rs/tokio#4937 [#​4942]: tokio-rs/tokio#4942 [#​4945]: tokio-rs/tokio#4945 [#​4951]: tokio-rs/tokio#4951 [#​4953]: tokio-rs/tokio#4953 [#​4956]: tokio-rs/tokio#4956 [#​4959]: tokio-rs/tokio#4959 </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, click this checkbox. --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzMi4xODcuMCIsInVwZGF0ZWRJblZlciI6IjMyLjE4Ny4wIn0=--> Co-authored-by: cabr2-bot <[email protected]> Reviewed-on: https://codeberg.org/Calciumdibromid/CaBr2/pulls/1532 Reviewed-by: crapStone <[email protected]> Co-authored-by: Calciumdibromid Bot <[email protected]> Co-committed-by: Calciumdibromid Bot <[email protected]>
nomeaning777
added a commit
to nomeaning777/wsld
that referenced
this pull request
Jun 12, 2023
vsock connection is not working correctly because of changes in 1.21 tokio-rs/tokio#4840
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.
As the epoll documentation points out, a read that only partially fills a buffer is sufficient to show that the socket buffer has been drained.
We can take advantage of this by clearing readiness in this case, which seems to significantly improve performance under certain conditions.