[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240628122029.ed510073c534b739ee385521@linux-foundation.org>
Date: Fri, 28 Jun 2024 12:20:29 -0700
From: Andrew Morton <akpm@...ux-foundation.org>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org, Ben Segall
<bsegall@...gle.com>, Daniel Bristot de Oliveira <bristot@...hat.com>,
Dietmar Eggemann <dietmar.eggemann@....com>, Ingo Molnar
<mingo@...hat.com>, Juri Lelli <juri.lelli@...hat.com>, Kent Overstreet
<kent.overstreet@...ux.dev>, Klara Modin <klarasmodin@...il.com>, Mel
Gorman <mgorman@...e.de>, Peter Zijlstra <peterz@...radead.org>, Steven
Rostedt <rostedt@...dmis.org>, Suren Baghdasaryan <surenb@...gle.com>,
Thomas Gleixner <tglx@...utronix.de>, Valentin Schneider
<vschneid@...hat.com>, Vincent Guittot <vincent.guittot@...aro.org>
Subject: Re: [PATCH] sched/task_struct: Move alloc_tag to the end of the
struct.
On Fri, 28 Jun 2024 11:49:44 +0200 Sebastian Andrzej Siewior <bigeasy@...utronix.de> wrote:
> On 2024-06-21 12:27:52 [+0200], To linux-mm@...ck.org wrote:
> > The alloc_tag member has been added to task_struct at the very
> > beginning. This is a pointer and on 64bit architectures it forces 4 byte
> > padding after `ptrace' and then forcing another another 4 byte padding
> > after `on_cpu'. A few members later, `se' requires a cacheline aligned
> > due to struct sched_avg resulting in 52 hole before `se'.
> >
> > This is the case on 64bit-SMP architectures.
> > The 52 byte hole can be avoided by moving alloc_tag away where it
> > currently resides.
> >
> > Move alloc_tag to the end of task_struct. There is likely a hole before
> > `thread' due to its alignment requirement and the previous members are
> > likely to be already pointer-aligned.
> >
> > Fixes: 22d407b164ff7 ("lib: add allocation tagging support for memory allocation profiling")
> > Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
>
> Could we please get this merged and worry about possible performance
> regression later? Or once there is a test case or an idea where this
> pointer might fit better but clearly the current situation is worse.
>
All in favor of saving 56 bytes from the task_struct, but we can do
that by moving various things around. Was alloc_tag the best choice?
Powered by blists - more mailing lists