[Bug 217965] ext4(?) regression since 6.5.0 on sata hdd

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



https://bugzilla.kernel.org/show_bug.cgi?id=217965

Matteo Italia (matteo@xxxxxxxxxxx) changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |matteo@xxxxxxxxxxx

--- Comment #66 from Matteo Italia (matteo@xxxxxxxxxxx) ---
I think I'm experiencing the same problem; relatively big (1.5T), relatively
empty (716 G used) ext4 partition on a slow-ish SATA magnetic HDD
(ST3000DM007-1WY10G), stripe=32747, 6.5.0-14-generic kernel from Ubuntu 22.04
HWE stack; during the installation of COMSOL Multiphysics 6.2 (which
essentially untars ~16 GB of stuff) I got kworker flush process stuck at 100%
of CPU for multiple hours, and IO cache filling my 32 GB of RAM. I tried the
various parameters tweaking suggested here with no particular change of pace
(although maybe the pending IO still worked according to the old values?). I
run the bfq scheduler on this disk, but I tried to switch to pretty much all
other schedulers mid-process with no perceptible change.

After ~3 hours of agonizingly slow progress (with disk write performance for
the installation often in the tens of KB/s) I decided to abort the
installation. I rebooted in the Ubuntu GA kernel (5.15.0-92-generic) without
touching any specific parameter and restarted the installation; this time it
completed in ~10 minutes.

-- 
You may reply to this email to add a comment.

You are receiving this mail because:
You are watching the assignee of the bug.




[Index of Archives]     [Reiser Filesystem Development]     [Ceph FS]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite National Park]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Device Mapper]     [Linux Media]

  Powered by Linux