From: Andrew Morton <akpm@linux-foundation.org>
To: Ying Han <yinghan@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>,
linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Venkatesh Pallipadi <venki@google.com>,
Rik van Riel <riel@redhat.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Johannes Weiner <hannes@cmpxchg.org>
Subject: Re: [PATCH] vmscan: prevent background aging of anon page in no swap system
Date: Fri, 3 Sep 2010 14:56:46 -0700 [thread overview]
Message-ID: <20100903145646.15063c1d.akpm@linux-foundation.org> (raw)
In-Reply-To: <AANLkTimTpj+CSvGx=HC4qnArBV9jxORkKoDA9eap3_cN@mail.gmail.com>
On Fri, 3 Sep 2010 14:47:03 -0700
Ying Han <yinghan@google.com> wrote:
> > We don't have any quantitative data on the effect of these excess tlb
> > flushes, which makes it difficult to decide which kernel versions
> > should receive this patch.
> >
> > Help?
>
> Andrew:
>
> We observed the degradation on 2.6.34 compared to 2.6.26 kernel. The
> workload we are running is doing 4k-random-write which runs about 3-4
> minutes. We captured the TLB shootsdowns before/after:
>
> Before the change:
> TLB: 29435 22208 37146 25332 47952 43698 43545 40297 49043 44843 46127
> 50959 47592 46233 43698 44690 TLB shootdowns [HSUM = 662798 ]
>
> After the change:
> TLB: 2340 3113 1547 1472 2944 4194 2181 1212 2607 4373 1690 1446 2310
> 3784 1744 1134 TLB shootdowns [HSUM = 38091 ]
Do you have data on how much additional CPU time (and/or wall time) was
consumed?
> Also worthy to mention, we are running in fake numa system where each
> fake node is 128M size. That makes differences on the check
> inactive_anon_is_low() since the active/inactive ratio falls to 1.
WARNING: multiple messages have this Message-ID (diff)
From: Andrew Morton <akpm@linux-foundation.org>
To: Ying Han <yinghan@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>,
linux-mm <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>,
Venkatesh Pallipadi <venki@google.com>,
Rik van Riel <riel@redhat.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Johannes Weiner <hannes@cmpxchg.org>
Subject: Re: [PATCH] vmscan: prevent background aging of anon page in no swap system
Date: Fri, 3 Sep 2010 14:56:46 -0700 [thread overview]
Message-ID: <20100903145646.15063c1d.akpm@linux-foundation.org> (raw)
In-Reply-To: <AANLkTimTpj+CSvGx=HC4qnArBV9jxORkKoDA9eap3_cN@mail.gmail.com>
On Fri, 3 Sep 2010 14:47:03 -0700
Ying Han <yinghan@google.com> wrote:
> > We don't have any quantitative data on the effect of these excess tlb
> > flushes, which makes it difficult to decide which kernel versions
> > should receive this patch.
> >
> > Help?
>
> Andrew:
>
> We observed the degradation on 2.6.34 compared to 2.6.26 kernel. The
> workload we are running is doing 4k-random-write which runs about 3-4
> minutes. We captured the TLB shootsdowns before/after:
>
> Before the change:
> TLB: 29435 22208 37146 25332 47952 43698 43545 40297 49043 44843 46127
> 50959 47592 46233 43698 44690 TLB shootdowns [HSUM = 662798 ]
>
> After the change:
> TLB: 2340 3113 1547 1472 2944 4194 2181 1212 2607 4373 1690 1446 2310
> 3784 1744 1134 TLB shootdowns [HSUM = 38091 ]
Do you have data on how much additional CPU time (and/or wall time) was
consumed?
> Also worthy to mention, we are running in fake numa system where each
> fake node is 128M size. That makes differences on the check
> inactive_anon_is_low() since the active/inactive ratio falls to 1.
--
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>
next prev parent reply other threads:[~2010-09-03 21:57 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-29 15:43 [PATCH] vmscan: prevent background aging of anon page in no swap system Minchan Kim
2010-08-29 15:43 ` Minchan Kim
2010-08-29 15:49 ` Rik van Riel
2010-08-29 15:49 ` Rik van Riel
2010-08-29 17:45 ` Ying Han
2010-08-29 17:45 ` Ying Han
2010-08-29 20:03 ` Rik van Riel
2010-08-29 20:03 ` Rik van Riel
2010-08-29 20:56 ` Ying Han
2010-08-29 21:23 ` Ying Han
2010-08-29 21:23 ` Ying Han
2010-08-29 22:26 ` Rik van Riel
2010-08-29 22:26 ` Rik van Riel
2010-08-30 0:18 ` Minchan Kim
2010-08-30 0:18 ` Minchan Kim
2010-08-30 5:40 ` Ying Han
2010-08-30 5:40 ` Ying Han
2010-08-30 6:16 ` Minchan Kim
2010-08-30 6:16 ` Minchan Kim
2010-08-31 0:56 ` KOSAKI Motohiro
2010-08-31 0:56 ` KOSAKI Motohiro
2010-08-31 1:10 ` Minchan Kim
2010-08-31 1:10 ` Minchan Kim
2010-08-31 1:18 ` KOSAKI Motohiro
2010-08-31 1:18 ` KOSAKI Motohiro
2010-08-31 1:36 ` Minchan Kim
2010-08-31 1:36 ` Minchan Kim
2010-08-31 1:41 ` KOSAKI Motohiro
2010-08-31 1:41 ` KOSAKI Motohiro
2010-08-31 0:56 ` KOSAKI Motohiro
2010-08-31 0:56 ` KOSAKI Motohiro
2010-08-31 1:23 ` Minchan Kim
2010-08-31 1:23 ` Minchan Kim
2010-08-31 1:38 ` KOSAKI Motohiro
2010-08-31 1:38 ` KOSAKI Motohiro
2010-08-31 2:02 ` Minchan Kim
2010-08-31 2:02 ` Minchan Kim
2010-08-31 2:09 ` KOSAKI Motohiro
2010-08-31 2:09 ` KOSAKI Motohiro
2010-08-31 3:47 ` Minchan Kim
2010-08-31 3:47 ` Minchan Kim
2010-08-31 2:30 ` Rik van Riel
2010-08-31 2:30 ` Rik van Riel
2010-08-31 3:46 ` Minchan Kim
2010-08-31 3:46 ` Minchan Kim
2010-09-03 21:06 ` Andrew Morton
2010-09-03 21:06 ` Andrew Morton
2010-09-03 21:23 ` Rik van Riel
2010-09-03 21:23 ` Rik van Riel
2010-09-03 21:45 ` Ying Han
2010-09-03 21:47 ` Ying Han
2010-09-03 21:47 ` Ying Han
2010-09-03 21:56 ` Andrew Morton [this message]
2010-09-03 21:56 ` Andrew Morton
2010-09-04 1:12 ` Venkatesh Pallipadi
2010-09-04 1:12 ` Venkatesh Pallipadi
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=20100903145646.15063c1d.akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=riel@redhat.com \
--cc=venki@google.com \
--cc=yinghan@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.