Re: Ext4: Buffered random writes performance regression with dioread_nolock enabled

[Thorsten Leemhuis <regressions@leemhuis.info>]

On 21.09.22 04:41, Theodore Ts'o wrote:
> Hazem started separate e-mail threads on this issue (separated by
> about an hour), and I replied to the earlier one here:
> 
>     https://lore.kernel.org/all/Yypx6VQRbl3bFP2v@mit.edu/

#regbot monitor: https://lore.kernel.org/all/Yypx6VQRbl3bFP2v@mit.edu/

> TL;DR:
> 
> 1)  The patch landed in 5.6, and improved performance for some
> workloads, and also fixed a potential security problem (exposure of
> stale data caused by a race).
> 
> 2)  If you are using a storage device >= 128GB, and a version of
> e2fsprogs v1.43.2 (released six years ago), the journal size will be
> 1GB, which Hazem reported resolved the problem.
> 
> 3) I disagree that we should revert this commit, as it only changes a
> default.  If you prefer the older behavior, you can change it with a
> mount option.

Great, thx for clarifying, in that case let me remove this from the
tracking:

#regzbot invalid: caused by a change of defaults that (among others) was
done for security reasons, see Ted's answer in
https://lore.kernel.org/all/Yypx6VQRbl3bFP2v@mit.edu/ for details

Ciao, Thorsten (wearing his 'the Linux kernel's regression tracker' hat)

P.S.: As the Linux kernel's regression tracker I deal with a lot of
reports and sometimes miss something important when writing mails like
this. If that's the case here, don't hesitate to tell me in a public
reply, it's in everyone's interest to set the public record straight.