From: Wu Fengguang <wfg@mail.ustc.edu.cn>
To: Lee Revell <rlrevell@joe-job.com>
Cc: Andrew Morton <akpm@osdl.org>,
linux-kernel@vger.kernel.org, Con Kolivas <kernel@kolivas.org>
Subject: Re: [PATCH 07/23] readahead: insert cond_resched() calls
Date: Mon, 20 Mar 2006 21:31:47 +0800 [thread overview]
Message-ID: <20060320133147.GA5150@mail.ustc.edu.cn> (raw)
In-Reply-To: <1142740242.4532.1.camel@mindpipe>
On Sat, Mar 18, 2006 at 10:50:42PM -0500, Lee Revell wrote:
> On Sun, 2006-03-19 at 10:34 +0800, Wu Fengguang wrote:
> > Since the VM_MAX_READAHEAD is greatly enlarged and the algorithm become more
> > complex, it becomes necessary to insert some cond_resched() calls in the
> > read-ahead path.
>
> Do you have any numbers on this (say, from Ingo's latency tracer)? Have
> you confirmed it's not a latency regression with the default settings?
Now I have some from Ingo's latency tracer. When doing 1M sized readaheads,
the original kernel have ~5ms latency. This patch reduced that number to ~1ms.
The trace data are collected on the following command:
cp 3G_sparse_file /dev/null
The resulted maximum latencies are:
wfg ~% head -n5 latency_trace1
preemption latency trace v1.1.5 on 2.6.16
--------------------------------------------------------------------
latency: 1169 us, #319/319, CPU#0 | (M:server VP:0, KP:0, SP:0 HP:0 #P:1)
-----------------
| task: xmms-5077 (uid:1000 nice:0 policy:0 rt_prio:0)
wfg ~% head -n5 latency_trace2
preemption latency trace v1.1.5 on 2.6.16
--------------------------------------------------------------------
latency: 4835 us, #14102/14102, CPU#0 | (M:server VP:0, KP:0, SP:0 HP:0 #P:1)
-----------------
| task: xmms-5065 (uid:1000 nice:0 policy:0 rt_prio:0)
The folloing commands show that the 4835us latency is mainly caused by
__do_page_cache_readahead(): from 575us to 1723us
mpage_readpages(): from 1724us to 4795us
wfg ~% grep readahead latency_trace1
wfg ~% grep readpages latency_trace1
wfg ~% grep readahead latency_trace2
cp-5068 0dn.. 575us : _read_lock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 576us : radix_tree_lookup_node (__do_page_cache_readahead)
cp-5068 0dn.. 576us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 577us : __alloc_pages (__do_page_cache_readahead)
cp-5068 0dn.. 580us : _read_lock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 580us : radix_tree_lookup_node (__do_page_cache_readahead)
cp-5068 0dn.. 581us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 581us : __alloc_pages (__do_page_cache_readahead)
cp-5068 0dn.. 583us : _read_lock_irq (__do_page_cache_readahead)
......[899 LINES SKIPPED]
cp-5068 0dn.. 1712us : radix_tree_lookup_node (__do_page_cache_readahead)
cp-5068 0dn.. 1712us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1713us : __alloc_pages (__do_page_cache_readahead)
cp-5068 0dn.. 1715us : _read_lock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1716us : radix_tree_lookup_node (__do_page_cache_readahead)
cp-5068 0dn.. 1716us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1716us : __alloc_pages (__do_page_cache_readahead)
cp-5068 0dn.. 1719us : _read_lock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1719us : radix_tree_lookup_node (__do_page_cache_readahead)
cp-5068 0dn.. 1719us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1720us : __alloc_pages (__do_page_cache_readahead)
cp-5068 0dn.. 1722us : _read_lock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1723us : _read_unlock_irq (__do_page_cache_readahead)
cp-5068 0dn.. 1723us : read_pages (__do_page_cache_readahead)
cp-5068 0dn.. 4800us : readahead_cache_hit (do_generic_mapping_read)
wfg ~% grep readpages latency_trace2
cp-5068 0dn.. 1724us : ext3_readpages (read_pages)
cp-5068 0dn.. 1724us : mpage_readpages (ext3_readpages)
cp-5068 0dn.. 1725us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 1728us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 1742us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 1744us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 1753us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 1755us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 1764us : add_to_page_cache (mpage_readpages)
......[508 LINES SKIPPED]
cp-5068 0dn.. 4716us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4726us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4728us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4737us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4739us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4748us : __pagevec_lru_add (mpage_readpages)
cp-5068 0dn.. 4750us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4752us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4761us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4763us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4772us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4774us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4784us : add_to_page_cache (mpage_readpages)
cp-5068 0dn.. 4785us : do_mpage_readpage (mpage_readpages)
cp-5068 0dn.. 4795us : __pagevec_lru_add (mpage_readpages)
Cheers,
Wu
next prev parent reply other threads:[~2006-03-20 13:26 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-03-19 2:34 [PATCH 00/23] Adaptive read-ahead V11 Wu Fengguang
2006-03-19 2:34 ` [PATCH 01/23] readahead: kconfig options Wu Fengguang
2006-03-19 2:34 ` [PATCH 02/23] radixtree: look-aside cache Wu Fengguang
2006-03-20 16:01 ` Christoph Lameter
2006-03-21 2:19 ` Wu Fengguang
2006-03-19 2:34 ` [PATCH 03/23] radixtree: hole scanning functions Wu Fengguang
2006-03-19 2:34 ` [PATCH 04/23] readahead: page flag PG_readahead Wu Fengguang
2006-03-19 2:34 ` [PATCH 05/23] readahead: refactor do_generic_mapping_read() Wu Fengguang
2006-03-19 2:34 ` [PATCH 06/23] readahead: refactor __do_page_cache_readahead() Wu Fengguang
2006-03-19 2:34 ` [PATCH 07/23] readahead: insert cond_resched() calls Wu Fengguang
2006-03-19 3:50 ` Lee Revell
2006-03-19 5:32 ` Wu Fengguang
2006-03-20 13:31 ` Wu Fengguang [this message]
2006-03-19 2:34 ` [PATCH 08/23] readahead: common macros Wu Fengguang
2006-03-19 2:34 ` [PATCH 09/23] readahead: events accounting Wu Fengguang
2006-03-19 2:34 ` [PATCH 10/23] readahead: support functions Wu Fengguang
2006-03-19 2:34 ` [PATCH 11/23] readahead: sysctl parameters Wu Fengguang
2006-03-19 2:34 ` [PATCH 12/23] readahead: min/max sizes Wu Fengguang
2006-03-19 2:34 ` [PATCH 13/23] readahead: page cache aging accounting Wu Fengguang
2006-03-19 2:34 ` [PATCH 14/23] readahead: state based method Wu Fengguang
2006-03-19 2:34 ` [PATCH 15/23] readahead: context " Wu Fengguang
2006-03-19 2:34 ` [PATCH 16/23] readahead: other methods Wu Fengguang
2006-03-19 2:34 ` [PATCH 17/23] readahead: call scheme Wu Fengguang
2006-03-19 2:34 ` [PATCH 18/23] readahead: laptop mode Wu Fengguang
2006-03-19 2:34 ` [PATCH 19/23] readahead: loop case Wu Fengguang
2006-03-19 2:34 ` [PATCH 20/23] readahead: nfsd case Wu Fengguang
2006-03-19 2:34 ` [PATCH 21/23] readahead: debug radix tree new functions Wu Fengguang
2006-03-19 2:34 ` [PATCH 22/23] readahead: debug traces showing accessed file names Wu Fengguang
2006-03-19 2:34 ` [PATCH 23/23] readahead: debug traces showing read patterns Wu Fengguang
2006-03-19 3:10 ` [PATCH 00/23] Adaptive read-ahead V11 Jon Smirl
2006-03-19 3:47 ` Wu Fengguang
2006-03-19 4:10 ` Jon Smirl
2006-03-19 5:09 ` Wu Fengguang
2006-03-19 15:53 ` Jon Smirl
2006-03-20 13:54 ` Wu Fengguang
2006-03-27 21:38 ` Matt Heler
2006-03-28 3:44 ` Wu Fengguang
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=20060320133147.GA5150@mail.ustc.edu.cn \
--to=wfg@mail.ustc.edu.cn \
--cc=akpm@osdl.org \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rlrevell@joe-job.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome