From: Nikanth Karthikesan <knikanth@suse.de>
To: Nathan Fontenot <nfont@austin.ibm.com>
Cc: Greg KH <greg@kroah.com>,
steiner@sgi.com, linux-kernel@vger.kernel.org,
Dave Hansen <dave@linux.vnet.ibm.com>,
linux-mm@kvack.org, Robin Holt <holt@sgi.com>,
linuxppc-dev@lists.ozlabs.org,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Subject: Re: [PATCH 0/9] v3 De-couple sysfs memory directories from memory sections
Date: Thu, 21 Oct 2010 17:35:19 +0530 [thread overview]
Message-ID: <201010211735.19276.knikanth@suse.de> (raw)
In-Reply-To: <4CA62700.7010809@austin.ibm.com>
On Friday 01 October 2010 23:52:56 Nathan Fontenot wrote:
> This set of patches decouples the concept that a single memory
> section corresponds to a single directory in
> /sys/devices/system/memory/. On systems
> with large amounts of memory (1+ TB) there are performance issues
> related to creating the large number of sysfs directories. For
> a powerpc machine with 1 TB of memory we are creating 63,000+
> directories. This is resulting in boot times of around 45-50
> minutes for systems with 1 TB of memory and 8 hours for systems
> with 2 TB of memory. With this patch set applied I am now seeing
> boot times of 5 minutes or less.
>
> The root of this issue is in sysfs directory creation. Every time
> a directory is created a string compare is done against all sibling
> directories to ensure we do not create duplicates. The list of
> directory nodes in sysfs is kept as an unsorted list which results
> in this being an exponentially longer operation as the number of
> directories are created.
>
Can we simply remove this check for this case alone?! :)
Thanks
Nikanth
Do not check for an entry with the same name is already present, when
__sysfs_add_one() is directly called, bypassing sysfs_add_one().
Currently register_mem_sect_under_node() calls
sysfs_create_link_nowarn(), which is the only caller to do so.
Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>
---
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 7e54bac..14d965c 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -368,21 +368,16 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
* This function should be called between calls to
* sysfs_addrm_start() and sysfs_addrm_finish() and should be
* passed the same @acxt as passed to sysfs_addrm_start().
+ * And there should be no sibling with the same name.
*
* LOCKING:
* Determined by sysfs_addrm_start().
*
- * RETURNS:
- * 0 on success, -EEXIST if entry with the given name already
- * exists.
*/
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+void __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
struct sysfs_inode_attrs *ps_iattr;
- if (sysfs_find_dirent(acxt->parent_sd, sd->s_ns, sd->s_name))
- return -EEXIST;
-
sd->s_parent = sysfs_get(acxt->parent_sd);
sysfs_link_sibling(sd);
@@ -394,7 +389,6 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
}
- return 0;
}
/**
@@ -439,10 +433,9 @@ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
*/
int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
- int ret;
+ int ret = 0;
- ret = __sysfs_add_one(acxt, sd);
- if (ret == -EEXIST) {
+ if (sysfs_find_dirent(acxt->parent_sd, sd->s_ns, sd->s_name)) {
char *path = kzalloc(PATH_MAX, GFP_KERNEL);
WARN(1, KERN_WARNING
"sysfs: cannot create duplicate filename '%s'\n",
@@ -450,8 +443,11 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"),
sd->s_name));
kfree(path);
+ ret = -EEXIST;
}
+ __sysfs_add_one(acxt, sd);
+
return ret;
}
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index a7ac78f..7c56d34 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -72,7 +72,7 @@ static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
if (warn)
error = sysfs_add_one(&acxt, sd);
else
- error = __sysfs_add_one(&acxt, sd);
+ __sysfs_add_one(&acxt, sd);
} else {
error = -EINVAL;
WARN(1, KERN_WARNING
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d9be60a..35449c8 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -155,7 +155,7 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd);
void sysfs_put_active(struct sysfs_dirent *sd);
void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
struct sysfs_dirent *parent_sd);
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
+void __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
prev parent reply other threads:[~2010-10-21 12:02 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-01 18:22 [PATCH 0/9] v3 De-couple sysfs memory directories from memory sections Nathan Fontenot
2010-10-01 18:28 ` [PATCH 1/9] v3 Move find_memory_block routine Nathan Fontenot
2010-10-01 18:40 ` Robin Holt
2010-10-05 5:01 ` KAMEZAWA Hiroyuki
2010-10-01 18:29 ` [PATCH 2/9] v3 Add mutex for adding/removing memory blocks Nathan Fontenot
2010-10-01 18:45 ` Robin Holt
2010-10-05 5:06 ` KAMEZAWA Hiroyuki
2010-10-01 18:30 ` [PATCH 3/9] v3 Add section count to memory_block struct Nathan Fontenot
2010-10-01 18:46 ` Robin Holt
2010-10-05 5:08 ` KAMEZAWA Hiroyuki
2010-10-01 18:31 ` [PATCH 4/9] v3 Allow memory blocks to span multiple memory sections Nathan Fontenot
2010-10-01 18:52 ` Robin Holt
2010-10-01 18:56 ` Nathan Fontenot
2010-10-01 19:00 ` Nathan Fontenot
2010-10-01 19:20 ` Robin Holt
2010-10-05 5:13 ` KAMEZAWA Hiroyuki
2010-10-01 18:33 ` [PATCH 5/9] v3 rename phys_index properties of memory block struct Nathan Fontenot
2010-10-01 18:54 ` Robin Holt
2010-10-05 5:14 ` KAMEZAWA Hiroyuki
2010-10-01 18:34 ` [PATCH 6/9] v3 Update node sysfs code Nathan Fontenot
2010-10-01 18:55 ` Robin Holt
2010-10-05 5:15 ` KAMEZAWA Hiroyuki
2010-10-01 18:35 ` [PATCH 7/9] v3 Define memory_block_size_bytes for powerpc/pseries Nathan Fontenot
2010-10-01 18:56 ` Robin Holt
2010-10-03 17:55 ` Balbir Singh
2010-10-03 18:07 ` Robin Holt
2010-10-03 18:11 ` Dave Hansen
2010-10-03 18:27 ` Balbir Singh
2010-10-04 14:45 ` Nathan Fontenot
2010-10-01 18:37 ` [PATCH 8/9] v3 Define memory_block_size_bytes for x86_64 with CONFIG_X86_UV set Nathan Fontenot
2010-10-01 18:57 ` Robin Holt
2010-10-01 18:37 ` [PATCH 9/9] v3 Update memory hotplug documentation Nathan Fontenot
2010-10-01 18:58 ` Robin Holt
2010-10-05 5:18 ` KAMEZAWA Hiroyuki
2010-10-21 12:05 ` Nikanth Karthikesan [this message]
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=201010211735.19276.knikanth@suse.de \
--to=knikanth@suse.de \
--cc=dave@linux.vnet.ibm.com \
--cc=greg@kroah.com \
--cc=holt@sgi.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=nfont@austin.ibm.com \
--cc=steiner@sgi.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;
as well as URLs for NNTP newsgroup(s).