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]
Message-ID: <YiokaQLWeulWpiCx@cmpxchg.org>
Date:   Thu, 10 Mar 2022 11:16:41 -0500
From:   Johannes Weiner <hannes@...xchg.org>
To:     Christoph Hellwig <hch@...radead.org>
Cc:     cgel.zte@...il.com, axboe@...nel.dk, viro@...iv.linux.org.uk,
        linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, akpm@...ux-foundation.org,
        Yang Yang <yang.yang29@....com.cn>,
        Ran Xiaokai <ran.xiaokai@....com.cn>
Subject: Re: [PATCH] block/psi: remove PSI annotations from submit_bio

On Wed, Mar 09, 2022 at 10:46:52PM -0800, Christoph Hellwig wrote:
> On Wed, Mar 09, 2022 at 02:18:19PM -0500, Johannes Weiner wrote:
> > On Wed, Mar 09, 2022 at 09:43:24AM +0000, cgel.zte@...il.com wrote:
> > > From: Yang Yang <yang.yang29@....com.cn>
> > > 
> > > psi tracks the time spent submitting the IO of refaulting pages[1].
> > > But after we tracks refault stalls from swap_readpage[2][3], there
> > > is no need to do so anymore. Since swap_readpage already includes
> > > IO submitting time.
> > > 
> > > [1] commit b8e24a9300b0 ("block: annotate refault stalls from IO submission")
> > > [2] commit 937790699be9 ("mm/page_io.c: annotate refault stalls from swap_readpage")
> > > [3] commit 2b413a1a728f ("mm: page_io: fix psi memory pressure error on cold swapins")
> > > 
> > > Signed-off-by: Yang Yang <yang.yang29@....com.cn>
> > > Reviewed-by: Ran Xiaokai <ran.xiaokai@....com.cn>
> > 
> > It's still needed by file cache refaults!
> 
> Can we get proper annotations for those please?  These bio-level hooks are
> horrible and a maintainance nightmware.

The first version did that, but it was sprawling and not well-received:

https://lkml.org/lkml/2019/7/22/1261

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ