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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Tue, 02 Jan 2024 04:44:08 +0000
From: bugzilla-daemon@...nel.org
To: linux-ext4@...r.kernel.org
Subject: [Bug 217965] ext4(?) regression since 6.5.0 on sata hdd

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

--- Comment #59 from Ojaswin Mujoo (ojaswin.mujoo@....com) ---
Hi Matthew,

Thanks for testing out the patch and for sharing the results with and without
CR_BEST_AVAIL_LEN commented. Would it be possible for you to add perf probes as
mentioned in comment 36 and share the result. That'd be helpful in
understanding why CR_BEST_AVAIL_LEN is getting stuck. Basically, I am
interested in seeing how the scan is happening in CR_GOAL_LEN_FAST vs
CR_BEST_AVAIL_LEN.

[1] https://bugzilla.kernel.org/show_bug.cgi?id=217965#c36

Also, another thing I'd request you to try is, instead of commenting out the
code can you run:

$ echo "0" > /sys/fs/ext4/<dev>/mb_best_avail_max_trim_order

and rerun the test. This disables most of the code but keeps some of the
initial logic. Might help zero down if the issue is in the initial logic or the
disabled code.

Thanks again,
ojaswin

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

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