writeback: split inode_wb_list_lock into bdi_writeback.list_lock
Split the global inode_wb_list_lock into a per-bdi_writeback list_lock,
as it's currently the most contended lock in the system for metadata
heavy workloads. It won't help for single-filesystem workloads for
which we'll need the I/O-less balance_dirty_pages, but at least we
can dedicate a cpu to spinning on each bdi now for larger systems.
Based on earlier patches from Nick Piggin and Dave Chinner.
It reduces lock contentions to 1/4 in this test case:
10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram
lock_stat version 0.3
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
vanilla 2.6.39-rc3:
inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23
------------------
inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85
inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49
inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0
inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a
------------------
inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85
inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49
inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0
inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157
2.6.39-rc3 + patch:
&(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37
------------------------
&(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86
&(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150
&(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f
&(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223
------------------------
&(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b
&(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86
&(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf
&(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f
hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old
akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f032e6e..5f6553e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -45,6 +45,17 @@
static int bdi_sync_supers(void *);
static void sync_supers_timer_fn(unsigned long);
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+ if (wb1 < wb2) {
+ spin_lock(&wb1->list_lock);
+ spin_lock_nested(&wb2->list_lock, 1);
+ } else {
+ spin_lock(&wb2->list_lock);
+ spin_lock_nested(&wb1->list_lock, 1);
+ }
+}
+
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
@@ -67,14 +78,14 @@
struct inode *inode;
nr_dirty = nr_io = nr_more_io = 0;
- spin_lock(&inode_wb_list_lock);
+ spin_lock(&wb->list_lock);
list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
nr_dirty++;
list_for_each_entry(inode, &wb->b_io, i_wb_list)
nr_io++;
list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
nr_more_io++;
- spin_unlock(&inode_wb_list_lock);
+ spin_unlock(&wb->list_lock);
global_dirty_limits(&background_thresh, &dirty_thresh);
bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
@@ -628,6 +639,7 @@
INIT_LIST_HEAD(&wb->b_dirty);
INIT_LIST_HEAD(&wb->b_io);
INIT_LIST_HEAD(&wb->b_more_io);
+ spin_lock_init(&wb->list_lock);
setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
}
@@ -676,11 +688,12 @@
if (bdi_has_dirty_io(bdi)) {
struct bdi_writeback *dst = &default_backing_dev_info.wb;
- spin_lock(&inode_wb_list_lock);
+ bdi_lock_two(&bdi->wb, dst);
list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
list_splice(&bdi->wb.b_io, &dst->b_io);
list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
- spin_unlock(&inode_wb_list_lock);
+ spin_unlock(&bdi->wb.list_lock);
+ spin_unlock(&dst->list_lock);
}
bdi_unregister(bdi);
diff --git a/mm/filemap.c b/mm/filemap.c
index d7b1057..1e492c3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -81,7 +81,7 @@
* ->i_mutex
* ->i_alloc_sem (various)
*
- * inode_wb_list_lock
+ * bdi->wb.list_lock
* sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
@@ -99,9 +99,9 @@
* ->zone.lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
- * inode_wb_list_lock (page_remove_rmap->set_page_dirty)
+ * bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
* ->inode->i_lock (page_remove_rmap->set_page_dirty)
- * inode_wb_list_lock (zap_pte_range->set_page_dirty)
+ * bdi.wb->list_lock (zap_pte_range->set_page_dirty)
* ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
*
diff --git a/mm/rmap.c b/mm/rmap.c
index 0eb463e..d04e36a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -32,11 +32,11 @@
* mmlist_lock (in mmput, drain_mmlist and others)
* mapping->private_lock (in __set_page_dirty_buffers)
* inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- * inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty)
+ * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
* mapping->tree_lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
- * within inode_wb_list_lock in __sync_single_inode)
+ * within bdi.wb->list_lock in __sync_single_inode)
*
* (code doesn't rely on that order so it could be switched around)
* ->tasklist_lock