linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* FUSE: [Regression] Fuse legacy path performance scaling lost in v6.14 vs v6.8/6.11 (iodepth scaling with io_uring)
@ 2025-11-26 15:07 Abhishek Gupta
  2025-11-26 19:11 ` Bernd Schubert
  0 siblings, 1 reply; 12+ messages in thread
From: Abhishek Gupta @ 2025-11-26 15:07 UTC (permalink / raw)
  To: linux-fsdevel; +Cc: miklos, bschubert, Swetha Vadlakonda

Hello Team,

I am observing a performance regression in the FUSE subsystem on
Kernel 6.14 compared to 6.8/6.11 when using the legacy/standard FUSE
interface (userspace daemon using standard read on /dev/fuse).

Summary of Issue: On Kernel 6.8 & 6.11, increasing iodepth in fio
(using ioengine=io_uring) results in near-linear performance scaling.
On Kernel 6.14, using the exact same userspace binary, increasing
iodepth yields no performance improvement (behavior resembles
iodepth=1).

Environment:
- Workload: GCSFuse (userspace daemon) + Fio
- Fio Config: Random Read, ioengine=io_uring, direct=1, iodepth=4.
- CPU: Intel.
- Daemon: Go-based. It uses a serialized reader loop on /dev/fuse that
immediately spawns a Go routine per request. So, it can serve requests
in parallel.
- Kernel Config: CONFIG_FUSE_IO_URING=y is enabled, but the daemon is
not registering for the ring (legacy mode).

Benchmark Observations:
- Kernel 6.8/6.11: With iodepth=4, we observe ~3.5-4x throughput
compared to iodepth=1.
- Kernel 6.14: With iodepth=4, throughput is identical to iodepth=1.
Parallelism is effectively lost.

Is this a known issue? I would appreciate any insights or pointers on
this issue.

Thanks & Regards,
Abhishek

^ permalink raw reply	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2025-12-17 11:41 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-11-26 15:07 FUSE: [Regression] Fuse legacy path performance scaling lost in v6.14 vs v6.8/6.11 (iodepth scaling with io_uring) Abhishek Gupta
2025-11-26 19:11 ` Bernd Schubert
2025-11-27 13:37   ` Abhishek Gupta
2025-11-27 23:05     ` Bernd Schubert
2025-12-02 10:42       ` Abhishek Gupta
     [not found]         ` <CAPr64AKYisa=_X5fAB1ozgb3SoarKm19TD3hgwhX9csD92iBzA@mail.gmail.com>
2025-12-08 17:52           ` Bernd Schubert
2025-12-08 22:56             ` Bernd Schubert
2025-12-09 17:16               ` Abhishek Gupta
2025-12-15  4:30               ` Joanne Koong
2025-12-17  9:17                 ` Abhishek Gupta
2025-12-17 10:43                   ` Bernd Schubert
2025-12-17 11:34                   ` Horst Birthelmer

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).