linux-kernel - Re: [PATCH] ubifs: limit the number of pages in shrink

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>] [day] [month] [year] [list]

Message-ID: <797425154.59041.1565101898396.JavaMail.zimbra@nod.at>
Date:   Tue, 6 Aug 2019 16:31:38 +0200 (CEST)
From:   Richard Weinberger <richard@....at>
To:     Liu Song <fishland@...yun.com>
Cc:     Artem Bityutskiy <dedekind1@...il.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        linux-mtd <linux-mtd@...ts.infradead.org>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        liu song11 <liu.song11@....com.cn>
Subject: Re: [PATCH] ubifs: limit the number of pages in shrink_liability

----- Ursprüngliche Mail -----
> Von: "Liu Song" <fishland@...yun.com>
> An: "richard" <richard@....at>, "Artem Bityutskiy" <dedekind1@...il.com>, "Adrian Hunter" <adrian.hunter@...el.com>
> CC: "linux-mtd" <linux-mtd@...ts.infradead.org>, "linux-kernel" <linux-kernel@...r.kernel.org>, "liu song11"
> <liu.song11@....com.cn>
> Gesendet: Dienstag, 6. August 2019 16:21:40
> Betreff: [PATCH] ubifs: limit the number of pages in shrink_liability

> From: Liu Song <liu.song11@....com.cn>
> 
> If the number of dirty pages to be written back is large,
> then writeback_inodes_sb will block waiting for a long time,
> causing hung task detection alarm. Therefore, we should limit
> the maximum number of pages written back this time, which let
> the budget be completed faster. The remaining dirty pages
> tend to rely on the writeback mechanism to complete the
> synchronization.

On which kind of system do you hit this?
Your fix makes sense but I'd like to have more background information.

UBIFS acts that way for almost a decade, see:
b6e51316daed ("writeback: separate starting of sync vs opportunistic writeback")

Thanks,
//richard