Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 2620:137:e000::3:6 as permitted sender) client-ip=2620:137:e000::3:6;
From:   bugzilla-daemon@kernel.org
To:     linux-ext4@vger.kernel.org
Subject: [Bug 217965] ext4(?) regression since 6.5.0 on sata hdd
Date:   Wed, 04 Oct 2023 12:44:30 +0000
Message-ID: <bug-217965-13602-moueCdh1e5@https.bugzilla.kernel.org/>
In-Reply-To: <bug-217965-13602@https.bugzilla.kernel.org/>
References: <bug-217965-13602@https.bugzilla.kernel.org/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Auto-Submitted: auto-generated
MIME-Version: 1.0
Precedence: bulk

https://bugzilla.kernel.org/show_bug.cgi?id=3D217965

--- Comment #10 from Ojaswin Mujoo (ojaswin.mujoo@ibm.com) ---
Hi Ivan,=20

So unfortunately I'm not able to replicate it yet at my end. While I try th=
at,
wanted to check if you can give a few things a try,

So it seems like the CPU is stuck at mb_find_order_for_block() called from
mb_find_extent(). I do see a while loop in mb_find_order_for_block() but its
not obvious if its stuck there and if so why.

If possible can you:

1. Recompile the kernel with CONFIG_DEBUG_INFO=3Dy CONFIG_SOFTLOCKUP_DETECT=
OR=3Dy
and CONFIG_HARDLOCKUP_DETECTOR=3Dy which might provide more information in =
dmesg
when the lockup happens.

2. Replicate it once more and note the RIP value in the trace of stuck CPU,=
 for
example in the above trace it was mb_find_order_for_block+0x68 for CPU2.

3. Run the following kernel's source dir to get the corresponding line numb=
er
(CONFIG_DEBUG_INFO needed):

$ ./scripts/faddr2line vmlinux mb_find_order_for_block+0x68

Maybe you can share the code you see in and around those lines as well as t=
he
exact kernel version.

This will help pinpoint the location where the code might be stuck (for exa=
mple
in a loop), which can help root cause this.

Also, you mentioned that the CPU gets stuck at 100% util for 10-15mins, doe=
s it
ever come back to normal or does it stay stuck?=20

Regards,
ojaswin

--=20
You may reply to this email to add a comment.

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