Mastouille

0 message0 participant0 message aujourd’hui

Andrés GómezMy <a href="https://floss.social/@igalia" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@igalia</a> colleague Luís Henriques has just published a very interesting post about the work he has been doing lately in the Linux <a href="https://hostux.social/tags/kernel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#kernel</a> about <a href="https://hostux.social/tags/FUSE" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#FUSE</a> over <a href="https://hostux.social/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a>.<a href="https://luis.camandro.org/2025-06-14-fuse-over-io_uring.html" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://luis.camandro.org/2025-06-14-fuse-over-io_uring.html</a>

Marcel WaldvogelAll you never wanted to know about creating fast socket I/O on <a href="https://waldvogel.family/tags/Linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Linux</a>. Unless you are a real geek.A small, ultra-high performance publish-subscribe server doing kind of TCP <a href="https://waldvogel.family/tags/multicast" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#multicast</a> using <a href="https://waldvogel.family/tags/sendfile" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#sendfile</a>, <a href="https://waldvogel.family/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a>, <a href="https://waldvogel.family/tags/splice" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#splice</a>, (mapped) files, and <a href="https://waldvogel.family/tags/fallocate" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#fallocate</a> for file hole punching.Saturating a 10 Gbps link with useful data with just 8 cores.A beautiful writeup for anyone into fast Linux networking. Not just for <a href="https://waldvogel.family/tags/ATproto" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ATproto</a> h/t <a href="https://smnn.ch/@nohillside" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@nohillside</a> <a href="https://waldvogel.family/tags/PubSub" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#PubSub</a> <a href="https://waldvogel.family/tags/Kernel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Kernel</a> <a href="https://waldvogel.family/tags/Hacking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Hacking</a> <a href="https://www.asayers.com/jetrelay" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://www.asayers.com/jetrelay</a>

argv minus oneDo any operating systems other than <a href="https://mastodon.sdf.org/tags/Linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Linux</a> (<a href="https://mastodon.sdf.org/tags/Windows" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Windows</a>, <a href="https://mastodon.sdf.org/tags/macOS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#macOS</a>, <a href="https://mastodon.sdf.org/tags/FreeBSD" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#FreeBSD</a>, <a href="https://mastodon.sdf.org/tags/OpenBSD" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#OpenBSD</a>, etc) have an API for non-blocking file IO?I know Linux has that in <a href="https://mastodon.sdf.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a>, which can do almost any IO operation (even fsync) in the background and tell you when it's done, but is that the only OS with such a feature?<a href="https://mastodon.sdf.org/tags/programming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#programming</a> <a href="https://mastodon.sdf.org/tags/async" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#async</a>

Nils Goroll 🕊️:varnishcache:Does anyone happen to have any information on the relevance of UIO_FASTIOV (defined as 8 on <a href="https://fosstodon.org/tags/Linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Linux</a>). I understand that submitting vectored io with within this limit can avoid dynamic memory allocation in the kernel, but is this relevant in any way in practice? Is it relevant with <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> ?

Nils Goroll 🕊️:varnishcache:using <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> for storage in <a href="https://fosstodon.org/tags/varnishcache" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#varnishcache</a> <a href="https://fosstodon.org/tags/allsystemsgo" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#allsystemsgo</a> <a href="https://fosstodon.org/tags/ASG2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ASG2024</a> <a href="https://media.ccc.de/v/all-systems-go-2024-305-using-iouring-for-storage" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://media.ccc.de/v/all-systems-go-2024-305-using-iouring-for-storage</a>From: <a href="https://botsin.space/@mediacccde" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@mediacccde</a> <a href="https://botsin.space/@mediacccde/113203506819669014" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://botsin.space/@mediacccde/113203506819669014</a>

Nils Goroll 🕊️:varnishcache:the <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> example/proxy.c code really is super helpful. thank you, <a href="https://fosstodon.org/@axboe" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@axboe</a> !

Lars WirzeniusFun: <a href="https://toot.liw.fi/tags/Rust" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Rust</a> bindings to <a href="https://toot.liw.fi/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> using the io-uring crate can do 10 thousand NOP operations per second on my laptop.This isn't useful, but it's the "hello, world" for me for learning about io_uring.

Nils Goroll 🕊️:varnishcache:HAPPY 18TH BIRTHDAY <a href="https://fosstodon.org/tags/VarnishCache" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#VarnishCache</a> ! To celebrate this memorable occasion, we have just tagged Version 1.0.0-rc1 of <a href="https://gitlab.com/uplex/varnish/slash" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://gitlab.com/uplex/varnish/slash</a>, which contains fellow, our advanced, <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> based, high performance, eventually persistent, always consistent <a href="https://fosstodon.org/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#opensource</a> storage engine. Read the full announcement: <a href="https://varnish-cache.org/lists/pipermail/varnish-announce/2024-February/000762.html" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://varnish-cache.org/lists/pipermail/varnish-announce/2024-February/000762.html</a> And the changelog: <a href="https://gitlab.com/uplex/varnish/slash/-/blob/master/CHANGES.rst?ref_type=heads" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://gitlab.com/uplex/varnish/slash/-/blob/master/CHANGES.rst?ref_type=heads</a>

Chris Gioran 💔I added an opcode to <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> in the <a href="https://fosstodon.org/tags/linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#linux</a> kernelThen I exposed it to the userspace uring library from <a href="https://fosstodon.org/tags/tokio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#tokio</a> And finally I wrote an application with it.It's easier than it sounds. But I still learned a lot. Here, I wrote it up:<a href="https://radiki.dev/posts/add-zero-opcode-to-io-uring/" rel="nofollow noopener noreferrer" target="_blank">https://radiki.dev/posts/add-zero-opcode-to-io-uring/</a>If you find this useful let me know, and I'll write more.<a href="https://fosstodon.org/tags/rust" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#rust</a> <a href="https://fosstodon.org/tags/rustlang" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#rustlang</a>

Nils Goroll 🕊️:varnishcache:This month, SLASH/fellow <a href="https://gitlab.com/uplex/varnish/slash" rel="nofollow noopener noreferrer" target="_blank">https://gitlab.com/uplex/varnish/slash</a>, our advanced, <a href="https://fosstodon.org/tags/io_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> based, high performance, eventually persistent, always consistent <a href="https://fosstodon.org/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#opensource</a> storage engine for <a href="https://fosstodon.org/tags/varnishcache" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#varnishcache</a> has received bug fixes and relevant performance improvements: - reduced memory footprint - improve cache lookup performance - made memory allocation priorities more fine grained - reduced overhead for concurrent access to disk objects - improved disk space allocationPlease try it out, all feedback is welcome!

Julien M.<a class="hashtag" href="https://social.alternativebit.fr/tag/infosec" rel="nofollow noopener noreferrer" target="_blank">#InfoSec</a> <blockquote>Learnings from <a class="hashtag" href="https://social.alternativebit.fr/tag/kctf" rel="nofollow noopener noreferrer" target="_blank">#kCTF</a> VRP's 42 <a class="hashtag" href="https://social.alternativebit.fr/tag/linuxkernel" rel="nofollow noopener noreferrer" target="_blank">#LinuxKernel</a> exploits submissions Since its inception, the program has rewarded researchers with a total of 1.8 million USD, and in the past year, there has been a clear trend: 60% of the submissions exploited the <a class="hashtag" href="https://social.alternativebit.fr/tag/io_uring" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> component of the <a class="hashtag" href="https://social.alternativebit.fr/tag/linux" rel="nofollow noopener noreferrer" target="_blank">#Linux</a> <a class="hashtag" href="https://social.alternativebit.fr/tag/kernel" rel="nofollow noopener noreferrer" target="_blank">#kernel</a> (we paid out around 1 million USD for <a class="hashtag" href="https://social.alternativebit.fr/tag/io_uring" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> alone). Furthermore, <a class="hashtag" href="https://social.alternativebit.fr/tag/io_uring" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> vulnerabilities were used in all the submissions which bypassed our mitigations. To protect our users, we decided to limit the usage of <a class="hashtag" href="https://social.alternativebit.fr/tag/io_uring" rel="nofollow noopener noreferrer" target="_blank">#io_uring</a> in <a class="hashtag" href="https://social.alternativebit.fr/tag/google" rel="nofollow noopener noreferrer" target="_blank">#Google</a> products </blockquote><a href="https://security.googleblog.com/2023/06/learnings-from-kctf-vrps-42-linux.html" rel="nofollow noopener noreferrer" target="_blank">https://security.googleblog.com/2023/06/learnings-from-kctf-vrps-42-linux.html</a>

PhoronixGoogle Limiting <a href="https://noc.social/tags/IO_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#IO_uring</a> Use Due To Security Vulnerabilities<a href="https://www.phoronix.com/news/Google-Restricting-IO_uring" rel="nofollow noopener noreferrer" target="_blank">https://www.phoronix.com/news/Google-Restricting-IO_uring</a>Original tweet : <a href="https://twitter.com/phoronix/status/1669650034344730626" rel="nofollow noopener noreferrer" target="_blank">https://twitter.com/phoronix/status/1669650034344730626</a>

Phoronix<a href="https://noc.social/tags/libuv" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#libuv</a> Adds <a href="https://noc.social/tags/IO_uring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#IO_uring</a> Support For ~8x Throughput Boost<a href="https://www.phoronix.com/news/libuv-io-uring" rel="nofollow noopener noreferrer" target="_blank">https://www.phoronix.com/news/libuv-io-uring</a>Original tweet : <a href="https://twitter.com/phoronix/status/1648333901176135682" rel="nofollow noopener noreferrer" target="_blank">https://twitter.com/phoronix/status/1648333901176135682</a>

Recherches récentes

Options de recherche

Administré par :

Statistiques du serveur :

#io_uring