linux-ext4 - Re: Ext4: Buffered random writes performance regression with dioread

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, 20 Sep 2022 22:41:56 -0400
From:   "Theodore Ts'o" <tytso@....edu>
To:     Thorsten Leemhuis <regressions@...mhuis.info>
Cc:     hazem ahmed mohamed <hazem.ahmed.abuelfotoh@...il.com>,
        "linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
        "adilger.kernel@...ger.ca" <adilger.kernel@...ger.ca>,
        "regressions@...ts.linux.dev" <regressions@...ts.linux.dev>,
        "stable@...r.kernel.org" <stable@...r.kernel.org>,
        "Mohamed Abuelfotoh, Hazem" <abuehaze@...zon.com>
Subject: Re: Ext4: Buffered random writes performance regression with
 dioread_nolock enabled

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/

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.

						- Ted