From: Rik van Riel <riel@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Miao Xie <miaox@cn.fujitsu.com>,
David Rientjes <rientjes@google.com>,
Christoph Lameter <cl@linux.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] cpuset: mm: Reduce large amounts of memory barrier related damage v3
Date: Mon, 26 Aug 2013 01:32:52 -0400 [thread overview]
Message-ID: <521AE884.6090605@redhat.com> (raw)
In-Reply-To: <20130823181546.GA31370@twins.programming.kicks-ass.net>
On 08/23/2013 02:15 PM, Peter Zijlstra wrote:
> So I guess the quick and ugly solution is something like the below.
This still crashes :)
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1762,19 +1762,21 @@ unsigned slab_node(void)
> static unsigned offset_il_node(struct mempolicy *pol,
> struct vm_area_struct *vma, unsigned long off)
> {
> - unsigned nnodes = nodes_weight(pol->v.nodes);
> - unsigned target;
> - int c;
> - int nid = -1;
> + unsigned nnodes, target;
> + int c, nid;
>
> +again:
> + nnodes = nodes_weight(pol->v.nodes);
> if (!nnodes)
> return numa_node_id();
> +
> target = (unsigned int)off % nnodes;
> - c = 0;
> - do {
> + for (c = 0, nid = -1; c <= target; c++)
> nid = next_node(nid, pol->v.nodes);
> - c++;
> - } while (c <= target);
> +
> + if (unlikely((unsigned)nid >= MAX_NUMNODES))
> + goto again;
I'll go kick off a compile that replaces the conditional above with:
if (unlikely(!node_online(nid)))
goto again;
> return nid;
> }
--
All rights reversed
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>,
Andrew Morton <akpm@linux-foundation.org>,
Miao Xie <miaox@cn.fujitsu.com>,
David Rientjes <rientjes@google.com>,
Christoph Lameter <cl@linux.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] cpuset: mm: Reduce large amounts of memory barrier related damage v3
Date: Mon, 26 Aug 2013 01:32:52 -0400 [thread overview]
Message-ID: <521AE884.6090605@redhat.com> (raw)
In-Reply-To: <20130823181546.GA31370@twins.programming.kicks-ass.net>
On 08/23/2013 02:15 PM, Peter Zijlstra wrote:
> So I guess the quick and ugly solution is something like the below.
This still crashes :)
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1762,19 +1762,21 @@ unsigned slab_node(void)
> static unsigned offset_il_node(struct mempolicy *pol,
> struct vm_area_struct *vma, unsigned long off)
> {
> - unsigned nnodes = nodes_weight(pol->v.nodes);
> - unsigned target;
> - int c;
> - int nid = -1;
> + unsigned nnodes, target;
> + int c, nid;
>
> +again:
> + nnodes = nodes_weight(pol->v.nodes);
> if (!nnodes)
> return numa_node_id();
> +
> target = (unsigned int)off % nnodes;
> - c = 0;
> - do {
> + for (c = 0, nid = -1; c <= target; c++)
> nid = next_node(nid, pol->v.nodes);
> - c++;
> - } while (c <= target);
> +
> + if (unlikely((unsigned)nid >= MAX_NUMNODES))
> + goto again;
I'll go kick off a compile that replaces the conditional above with:
if (unlikely(!node_online(nid)))
goto again;
> return nid;
> }
--
All rights reversed
next prev parent reply other threads:[~2013-08-26 5:33 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-07 18:08 [PATCH] cpuset: mm: Reduce large amounts of memory barrier related damage v3 Mel Gorman
2012-03-07 18:08 ` Mel Gorman
2012-03-26 10:56 ` Peter Zijlstra
2012-03-26 10:56 ` Peter Zijlstra
2012-03-26 11:07 ` Peter Zijlstra
2012-03-26 11:07 ` Peter Zijlstra
2012-03-26 15:50 ` Mel Gorman
2012-03-26 15:50 ` Mel Gorman
2012-03-26 16:20 ` Peter Zijlstra
2012-03-26 16:20 ` Peter Zijlstra
2012-03-27 12:47 ` Mel Gorman
2012-03-27 12:47 ` Mel Gorman
2012-03-27 13:14 ` [PATCH] mm: Optimize put_mems_allowed() usage Peter Zijlstra
2012-03-27 13:14 ` Peter Zijlstra
2012-05-17 10:33 ` Peter Zijlstra
2012-05-17 10:33 ` Peter Zijlstra
2012-05-17 20:16 ` Andrew Morton
2012-05-17 20:16 ` Andrew Morton
2012-05-17 20:23 ` Peter Zijlstra
2012-05-17 20:23 ` Peter Zijlstra
2012-05-18 10:20 ` [tip:sched/numa] " tip-bot for Peter Zijlstra
2013-08-23 13:03 ` [PATCH] cpuset: mm: Reduce large amounts of memory barrier related damage v3 Peter Zijlstra
2013-08-23 13:03 ` Peter Zijlstra
2013-08-23 18:15 ` Peter Zijlstra
2013-08-23 18:15 ` Peter Zijlstra
2013-08-26 5:32 ` Rik van Riel [this message]
2013-08-26 5:32 ` Rik van Riel
2013-08-29 9:28 ` Mel Gorman
2013-08-29 9:28 ` Mel Gorman
2013-08-29 9:43 ` Peter Zijlstra
2013-08-29 9:43 ` Peter Zijlstra
2013-08-29 9:45 ` Peter Zijlstra
2013-08-29 9:45 ` Peter Zijlstra
2013-08-29 10:56 ` Mel Gorman
2013-08-29 10:56 ` Mel Gorman
2013-08-29 11:14 ` Peter Zijlstra
2013-08-29 11:14 ` Peter Zijlstra
2013-08-29 12:10 ` Mel Gorman
2013-08-29 12:10 ` Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=521AE884.6090605@redhat.com \
--to=riel@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=miaox@cn.fujitsu.com \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.