From: Coly Li <colyli@suse.de>
To: Rolf Fokkens <rolf@rolffokkens.nl>,
Thorsten Knabe <linux@thorsten-knabe.de>
Cc: linux-bcache@vger.kernel.org
Subject: Re: PROBLEM: bcache related kernel BUG() since Linux 5.12
Date: Mon, 7 Jun 2021 18:11:04 +0800 [thread overview]
Message-ID: <2d1d76b3-5eca-f0a6-c300-8e16d25ea1cf@suse.de> (raw)
In-Reply-To: <ec9f73fa-a16c-b0c1-d1f8-2bf4e585be5f@rolffokkens.nl>
On 6/4/21 9:38 PM, Rolf Fokkens wrote:
> Hoi Coly,
>
> The common applications I used, which for sure benefit from bcache:
>
> * Gnome 3.38
> * Libreoffice-7.0.6.2
> * teams-1.4.00.7556
> * Terminator
> * Evolution-3.38.4
> * Thunderbird evolution-3.38.4
> * thunderbird-78.10.1
> * firefox-88.0.1
> * google-chrome-stable-91.0.4472.77
>
> So it's a typical desktop wordload with most I/O during startup of
> applications.
>
> For overall stress/stability testing:
>
> * Doom (steam/proton)
> * Rise of the Tombraider (steam)
> * The Witcher 3 (steam)
>
> Overall stats after (should have done before) starting the steam games:
>
> bash-5.0$ bcache-status
> --- bcache ---
> UUID b191549d-4455-43ca-b9b8-8e32dd68751c
> Block Size 512 B
> Bucket Size 512.00 KiB
> Congested? False
> Read Congestion 0.0ms
> Write Congestion 20.0ms
> Total Cache Size 128 GiB
> Total Cache Used 128 GiB (100%)
> Total Cache Unused 0 B (0%)
> Evictable Cache 106 GiB (83%)
> Replacement Policy [lru] fifo random
> Cache Mode writethrough [writeback] writearound none
> Total Hits 3006361 (95%)
> Total Misses 126463
> Total Bypass Hits 4552 (68%)
> Total Bypass Misses 2061
> Total Bypassed 730.1 MiB
> bash-5.0$
>
> Hope this gives you a good impression of the workload.
>
> Let me know if you like me to do specific stress tests.
[snipped]
Hi Rolf and Thorsten,
I run the following workloads for 48+ hours, no panic or data corruption
so far,
- tar, untar, gzip, gunzip
- git clone/fsck/gc/archive
- copy iso files, checksum calculation and check for all the iso files
- kernel source code compiling
- ext4 file system check
The fix might not be perfect yet, but IMHO we should provide a fix now.
If there is any other known issue triggered, let's fix and verify later.
Thank you all for the testing and verification these days.
Coly Li
prev parent reply other threads:[~2021-06-07 10:11 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-15 19:06 PROBLEM: bcache related kernel BUG() since Linux 5.12 Thorsten Knabe
2021-05-16 8:42 ` Matthias Ferdinand
2021-05-16 14:43 ` Coly Li
2021-05-31 9:37 ` Rolf Fokkens
2021-06-01 15:34 ` Coly Li
2021-06-01 21:04 ` Rolf Fokkens
2021-06-01 21:46 ` Rolf Fokkens
2021-06-02 8:33 ` Thorsten Knabe
2021-06-02 9:45 ` Rolf Fokkens
2021-06-02 11:08 ` Coly Li
2021-06-04 9:07 ` Rolf Fokkens
2021-06-04 10:35 ` Coly Li
2021-06-04 12:06 ` Thorsten Knabe
2021-06-05 15:20 ` Coly Li
[not found] ` <ec9f73fa-a16c-b0c1-d1f8-2bf4e585be5f@rolffokkens.nl>
2021-06-07 10:11 ` Coly Li [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2d1d76b3-5eca-f0a6-c300-8e16d25ea1cf@suse.de \
--to=colyli@suse.de \
--cc=linux-bcache@vger.kernel.org \
--cc=linux@thorsten-knabe.de \
--cc=rolf@rolffokkens.nl \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).