From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Wu Fengguang <fengguang.wu@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Mike Waychison <mikew@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rohit Seth <rohitseth@google.com>
Cc: Edwin <edwintorok@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ying Han <yinghan@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: <linux-mm@kvack.org>
Cc: <linux-fsdevel@vger.kernel.org>
Subject: [PATCH 05/14] readahead: account mmap_miss for VM_FAULT_RETRY
Date: Tue, 07 Apr 2009 19:50:44 +0800 [thread overview]
Message-ID: <20090407115234.313061952@intel.com> (raw)
In-Reply-To: 20090407115039.780820496@intel.com
[-- Attachment #1: readahead-mmap_miss-retry.patch --]
[-- Type: text/plain, Size: 1902 bytes --]
The VM_FAULT_RETRY case introduced a performance bug that leads to
excessive/unconditional mmap readarounds for wild random mmap reads.
A retried page fault means a mmap readahead miss(mmap_miss++) followed by
a hit(mmap_miss--) on the same page. This sticks mmap_miss, and thus stops
mmap readaround from being turned off for wild random reads. Fix it by an
extra mmap_miss increament in order to counteract the followed mmap hit.
Also make mmap_miss a more robust 'unsigned int', so that if ever mmap_miss
goes out of range, it only create _temporary_ performance impacts.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
include/linux/fs.h | 2 +-
mm/filemap.c | 8 ++++++--
2 files changed, 7 insertions(+), 3 deletions(-)
--- mm.orig/mm/filemap.c
+++ mm/mm/filemap.c
@@ -1574,8 +1574,10 @@ retry_find:
vmf->pgoff, 1);
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
@@ -1617,8 +1619,10 @@ retry_find:
retry_find_retry:
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
--- mm.orig/include/linux/fs.h
+++ mm/include/linux/fs.h
@@ -824,7 +824,7 @@ struct file_ra_state {
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
- int mmap_miss; /* Cache miss stat for mmap accesses */
+ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
};
--
WARNING: multiple messages have this Message-ID (diff)
From: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Wu Fengguang <fengguang.wu@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Mike Waychison <mikew@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rohit Seth <rohitseth@google.com>
Cc: Edwin <edwintorok@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ying Han <yinghan@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: <linux-mm@kvack.org>
Cc: <linux-fsdevel@vger.kernel.org>
Subject: [PATCH 05/14] readahead: account mmap_miss for VM_FAULT_RETRY
Date: Tue, 07 Apr 2009 19:50:44 +0800 [thread overview]
Message-ID: <20090407115234.313061952@intel.com> (raw)
In-Reply-To: 20090407115039.780820496@intel.com
[-- Attachment #1: readahead-mmap_miss-retry.patch --]
[-- Type: text/plain, Size: 2127 bytes --]
The VM_FAULT_RETRY case introduced a performance bug that leads to
excessive/unconditional mmap readarounds for wild random mmap reads.
A retried page fault means a mmap readahead miss(mmap_miss++) followed by
a hit(mmap_miss--) on the same page. This sticks mmap_miss, and thus stops
mmap readaround from being turned off for wild random reads. Fix it by an
extra mmap_miss increament in order to counteract the followed mmap hit.
Also make mmap_miss a more robust 'unsigned int', so that if ever mmap_miss
goes out of range, it only create _temporary_ performance impacts.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
include/linux/fs.h | 2 +-
mm/filemap.c | 8 ++++++--
2 files changed, 7 insertions(+), 3 deletions(-)
--- mm.orig/mm/filemap.c
+++ mm/mm/filemap.c
@@ -1574,8 +1574,10 @@ retry_find:
vmf->pgoff, 1);
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
@@ -1617,8 +1619,10 @@ retry_find:
retry_find_retry:
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
--- mm.orig/include/linux/fs.h
+++ mm/include/linux/fs.h
@@ -824,7 +824,7 @@ struct file_ra_state {
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
- int mmap_miss; /* Cache miss stat for mmap accesses */
+ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
};
--
--
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: Wu Fengguang <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Wu Fengguang <fengguang.wu@intel.com>,
David Rientjes <rientjes@google.com>,
Hugh Dickins <hugh@veritas.com>, Ingo Molnar <mingo@elte.hu>,
Lee Schermerhorn <lee.schermerhorn@hp.com>,
Mike Waychison <mikew@google.com>, Nick Piggin <npiggin@suse.de>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Rohit Seth <rohitseth@google.com>, Edwin <edwintorok@gmail.com>,
"H. Peter Anvin" <hpa@zytor.com>, Ying Han <yinghan@google.com>,
LKML <linux-kernel@vger.kernel.org>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 05/14] readahead: account mmap_miss for VM_FAULT_RETRY
Date: Tue, 07 Apr 2009 19:50:44 +0800 [thread overview]
Message-ID: <20090407115234.313061952@intel.com> (raw)
In-Reply-To: 20090407115039.780820496@intel.com
[-- Attachment #1: readahead-mmap_miss-retry.patch --]
[-- Type: text/plain, Size: 2127 bytes --]
The VM_FAULT_RETRY case introduced a performance bug that leads to
excessive/unconditional mmap readarounds for wild random mmap reads.
A retried page fault means a mmap readahead miss(mmap_miss++) followed by
a hit(mmap_miss--) on the same page. This sticks mmap_miss, and thus stops
mmap readaround from being turned off for wild random reads. Fix it by an
extra mmap_miss increament in order to counteract the followed mmap hit.
Also make mmap_miss a more robust 'unsigned int', so that if ever mmap_miss
goes out of range, it only create _temporary_ performance impacts.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
include/linux/fs.h | 2 +-
mm/filemap.c | 8 ++++++--
2 files changed, 7 insertions(+), 3 deletions(-)
--- mm.orig/mm/filemap.c
+++ mm/mm/filemap.c
@@ -1574,8 +1574,10 @@ retry_find:
vmf->pgoff, 1);
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
@@ -1617,8 +1619,10 @@ retry_find:
retry_find_retry:
retry_ret = find_lock_page_retry(mapping, vmf->pgoff,
vma, &page, retry_flag);
- if (retry_ret == VM_FAULT_RETRY)
+ if (retry_ret == VM_FAULT_RETRY) {
+ ra->mmap_miss++; /* counteract the followed retry hit */
return retry_ret;
+ }
if (!page)
goto no_cached_page;
}
--- mm.orig/include/linux/fs.h
+++ mm/include/linux/fs.h
@@ -824,7 +824,7 @@ struct file_ra_state {
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
- int mmap_miss; /* Cache miss stat for mmap accesses */
+ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
};
--
--
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:[~2009-04-07 12:02 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-07 11:50 [PATCH 00/14] filemap and readahead fixes Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 01/14] mm: fix find_lock_page_retry() return value parsing Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 02/14] mm: fix major/minor fault accounting on retried fault Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 03/14] mm: remove FAULT_FLAG_RETRY dead code Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 04/14] mm: reduce duplicate page fault code Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang [this message]
2009-04-07 11:50 ` [PATCH 05/14] readahead: account mmap_miss for VM_FAULT_RETRY Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 06/14] readahead: move max_sane_readahead() calls into force_page_cache_readahead() Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 07/14] readahead: apply max_sane_readahead() limit in ondemand_readahead() Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 08/14] readahead: remove one unnecessary radix tree lookup Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 09/14] readahead: increase interleaved readahead size Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 10/14] readahead: remove sync/async readahead call dependency Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 11/14] readahead: clean up and simplify the code for filemap page fault readahead Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 15:50 ` Linus Torvalds
2009-04-07 15:50 ` Linus Torvalds
2009-04-07 11:50 ` [PATCH 12/14] readahead: sequential mmap readahead Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 13/14] readahead: enforce full readahead size on async " Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` [PATCH 14/14] readahead: record mmap read-around states in file_ra_state Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-07 11:50 ` Wu Fengguang
2009-04-10 4:36 ` [PATCH 00/14] filemap and readahead fixes Andrew Morton
2009-04-10 4:36 ` Andrew Morton
2009-04-10 4:36 ` Andrew Morton
2009-04-10 4:54 ` Wu Fengguang
2009-04-10 4:54 ` Wu Fengguang
2009-04-10 5:08 ` Andrew Morton
2009-04-10 5:08 ` Andrew Morton
2009-04-10 5:53 ` Wu Fengguang
2009-04-10 5:53 ` Wu Fengguang
-- strict thread matches above, loose matches on Subject: below --
2009-04-07 7:17 Wu Fengguang
2009-04-07 7:17 ` [PATCH 05/14] readahead: account mmap_miss for VM_FAULT_RETRY Wu Fengguang
2009-04-07 7:17 ` 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=20090407115234.313061952@intel.com \
--to=fengguang.wu@intel.com \
--cc=akpm@linux-foundation.org \
--cc=benh@kernel.crashing.org \
/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.