Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.debian.kernel > #89685 > unrolled thread
| Started by | Ben Hutchings <ben@decadent.org.uk> |
|---|---|
| First post | 2025-10-20 19:30 +0200 |
| Last post | 2025-10-20 19:30 +0200 |
| Articles | 1 — 1 participant |
Back to article view | Back to linux.debian.kernel
This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by
below is the oldest one visible, not the original post.
Re: slow memory I/O on AMD EPYC 9334 Ben Hutchings <ben@decadent.org.uk> - 2025-10-20 19:30 +0200
| From | Ben Hutchings <ben@decadent.org.uk> |
|---|---|
| Date | 2025-10-20 19:30 +0200 |
| Subject | Re: slow memory I/O on AMD EPYC 9334 |
| Message-ID | <LI1RL-6F8i-7@gated-at.bofh.it> |
[Multipart message — attachments visible in raw view] — view raw
On Fri, 2025-10-17 at 14:11 +0200, Gero wrote: > Dear experts, > > thanks a lot for your work and commitment on the Debian system. I'm > using Debian for years and I am generally very pleased with it. :-) > > With my company we do numerical simulations and recently did some > benchmarking tests on new AMD EPYC 9334 processors that showed a > significant performance loss of a current Debian system compared to an > older Red Hat or Rocky Linux. We could narrow that down to the following > finding: > > Running these commands: > > cd /dev/shm > echo 3 > /proc/sys/vm/drop_caches > fio --name=random-write --ioengine=posixaio --rw=randwrite --bs=4k > --numjobs=1 --size=4g --iodepth=1 --runtime=60 --time_based --end_fsync=1 [...] > I would like to know if you have an explanation or an idea. I think for this specific test, the explanation is "this is a stupid I/O pattern that no-one optimises for". Using AIO with a depth of 1 is effectively doing synchronous I/O in a less efficient way. Added to that, POSIX AIO was never that efficient on Linux, and the upstream developers seem to have more-or-less given up on it in favour of io_uring. > And I wonder > if you would be interested in investigating the issue any further. Or if > you have a suggestion who I might address preferably. If you can also see a regression for io_uring and a more sensible I/O depth then this would probably be interesting for the upstream developers, Ben. -- Ben Hutchings Computers are not intelligent. They only think they are.
Back to top | Article view | linux.debian.kernel
csiph-web