From: Dave Chinner <david@fromorbit.com>
To: viro@ZenIV.linux.org.uk
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: [PATCH 06/14] inode: convert inode_stat.nr_unused to per-cpu counters
Date: Fri, 8 Jul 2011 14:14:38 +1000 [thread overview]
Message-ID: <1310098486-6453-7-git-send-email-david@fromorbit.com> (raw)
In-Reply-To: <1310098486-6453-1-git-send-email-david@fromorbit.com>
From: Dave Chinner <dchinner@redhat.com>
Before we split up the inode_lru_lock, the unused inode counter
needs to be made independent of the global inode_lru_lock. Convert
it to per-cpu counters to do this.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/inode.c | 16 +++++++++++-----
1 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 3ef7324..14f53fd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -95,6 +95,7 @@ EXPORT_SYMBOL(empty_aops);
struct inodes_stat_t inodes_stat;
static DEFINE_PER_CPU(unsigned int, nr_inodes);
+static DEFINE_PER_CPU(unsigned int, nr_unused);
static struct kmem_cache *inode_cachep __read_mostly;
@@ -109,7 +110,11 @@ static int get_nr_inodes(void)
static inline int get_nr_inodes_unused(void)
{
- return inodes_stat.nr_unused;
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_unused, i);
+ return sum < 0 ? 0 : sum;
}
int get_nr_dirty_inodes(void)
@@ -127,6 +132,7 @@ int proc_nr_inodes(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
inodes_stat.nr_inodes = get_nr_inodes();
+ inodes_stat.nr_unused = get_nr_inodes_unused();
return proc_dointvec(table, write, buffer, lenp, ppos);
}
#endif
@@ -340,7 +346,7 @@ static void inode_lru_list_add(struct inode *inode)
spin_lock(&inode_lru_lock);
if (list_empty(&inode->i_lru)) {
list_add(&inode->i_lru, &inode_lru);
- inodes_stat.nr_unused++;
+ this_cpu_inc(nr_unused);
}
spin_unlock(&inode_lru_lock);
}
@@ -350,7 +356,7 @@ static void inode_lru_list_del(struct inode *inode)
spin_lock(&inode_lru_lock);
if (!list_empty(&inode->i_lru)) {
list_del_init(&inode->i_lru);
- inodes_stat.nr_unused--;
+ this_cpu_dec(nr_unused);
}
spin_unlock(&inode_lru_lock);
}
@@ -649,7 +655,7 @@ static void prune_icache(int nr_to_scan)
(inode->i_state & ~I_REFERENCED)) {
list_del_init(&inode->i_lru);
spin_unlock(&inode->i_lock);
- inodes_stat.nr_unused--;
+ this_cpu_dec(nr_unused);
continue;
}
@@ -686,7 +692,7 @@ static void prune_icache(int nr_to_scan)
spin_unlock(&inode->i_lock);
list_move(&inode->i_lru, &freeable);
- inodes_stat.nr_unused--;
+ this_cpu_dec(nr_unused);
}
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
--
1.7.5.1
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-07-08 4:14 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-08 4:14 [PATCH 0/14] Per superblock cache reclaim Dave Chinner
2011-07-08 4:14 ` [PATCH 01/14] dcache: fix __d_alloc prototype to use const Dave Chinner
2011-07-08 4:14 ` [PATCH 02/14] vmscan: add shrink_slab tracepoints Dave Chinner
2011-07-11 9:57 ` Christoph Hellwig
2011-07-18 1:14 ` Dave Chinner
2011-07-08 4:14 ` [PATCH 03/14] vmscan: shrinker->nr updates race and go wrong Dave Chinner
2011-07-08 4:14 ` [PATCH 04/14] vmscan: reduce wind up shrinker->nr when shrinker can't do work Dave Chinner
2011-07-08 4:14 ` [PATCH 05/14] vmscan: add customisable shrinker batch size Dave Chinner
2011-07-08 4:14 ` Dave Chinner [this message]
2011-07-08 4:14 ` [PATCH 07/14] inode: Make unused inode LRU per superblock Dave Chinner
2011-07-08 4:14 ` [PATCH 08/14] inode: move to per-sb LRU locks Dave Chinner
2011-07-11 19:21 ` Christoph Hellwig
2011-07-12 0:34 ` Dave Chinner
2011-07-08 4:14 ` [PATCH 09/14] superblock: move pin_sb_for_writeback() to fs/super.c Dave Chinner
2011-07-08 4:14 ` [PATCH 10/14] superblock: introduce per-sb cache shrinker infrastructure Dave Chinner
2011-07-08 4:14 ` [PATCH 11/14] inode: remove iprune_sem Dave Chinner
2011-07-08 4:14 ` [PATCH 12/14] superblock: add filesystem shrinker operations Dave Chinner
2011-07-08 4:14 ` [PATCH 13/14] vfs: increase shrinker batch size Dave Chinner
2011-07-11 10:05 ` Christoph Hellwig
2011-07-08 4:14 ` [PATCH 14/14] xfs: make use of new shrinker callout for the inode cache Dave Chinner
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=1310098486-6453-7-git-send-email-david@fromorbit.com \
--to=david@fromorbit.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=viro@ZenIV.linux.org.uk \
/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).