| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1236868428-20408-3-git-send-email-jens.axboe@oracle.com>
Date: Thu, 12 Mar 2009 15:33:43 +0100
From: Jens Axboe <jens.axboe@...cle.com>
To: linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org
Cc: chris.mason@...cle.com, david@...morbit.com, npiggin@...e.de,
Jens Axboe <jens.axboe@...cle.com>
Subject: [PATCH 2/7] writeback: switch to per-bdi threads for flushing data
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
This is an experiment to see if we get better writeout behaviour with
per-bdi flushing. Some initial tests look pretty encouraging. A sample
ffsb workload that does random writes to files is about 8% faster here
on a simple SATA drive during the benchmark phase. File layout also seems
a LOT more smooth in vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
So apart from seemingly behaving better for buffered writeout, this also
allows us to potentially have more than one bdi thread flushing out data.
This may be useful for NUMA type setups.
Signed-off-by: Jens Axboe <jens.axboe@...cle.com>
---
fs/buffer.c | 2 +-
fs/fs-writeback.c | 318 ++++++++++++++++++++++++++-----------------
fs/ntfs/super.c | 32 +----
fs/sync.c | 2 +-
include/linux/backing-dev.h | 19 +++
include/linux/fs.h | 3 +-
include/linux/writeback.h | 2 +-
mm/backing-dev.c | 17 ++-
mm/page-writeback.c | 139 +------------------
mm/vmscan.c | 2 +-
10 files changed, 244 insertions(+), 292 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 9f69741..89a26bc 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -426,7 +426,7 @@ static void free_more_memory(void)
struct zone *zone;
int nid;
- wakeup_pdflush(1024);
+ wakeup_flusher_threads(1024);
yield();
for_each_online_node(nid) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c107cff..209c6fa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -19,6 +19,8 @@
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -61,10 +63,184 @@ int writeback_in_progress(struct backing_dev_info *bdi)
*/
static void writeback_release(struct backing_dev_info *bdi)
{
- BUG_ON(!writeback_in_progress(bdi));
+ WARN_ON_ONCE(!writeback_in_progress(bdi));
+ bdi->wb_arg.nr_pages = 0;
+ bdi->wb_arg.sb = NULL;
clear_bit(BDI_pdflush, &bdi->state);
}
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+ long nr_pages)
+{
+ /*
+ * Should not happen, complain?
+ */
+ if (unlikely(!bdi->task))
+ return;
+
+ if (writeback_acquire(bdi)) {
+ bdi->wb_arg.nr_pages = nr_pages;
+ bdi->wb_arg.sb = sb;
+ /*
+ * make above store seen before the task is woken
+ */
+ smp_mb();
+ wake_up(&bdi->wait);
+ }
+}
+
+/*
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation. We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode. Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES 1024
+
+/*
+ * Periodic writeback of "old" data.
+ *
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space. So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
+ *
+ * Try to run once per dirty_writeback_interval. But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
+ *
+ * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
+ */
+static void bdi_kupdated(struct backing_dev_info *bdi)
+{
+ long nr_to_write;
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .nr_to_write = 0,
+ .for_kupdate = 1,
+ .range_cyclic = 1,
+ };
+
+ sync_supers();
+
+ nr_to_write = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ while (nr_to_write > 0) {
+ wbc.more_io = 0;
+ wbc.encountered_congestion = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ generic_sync_bdi_inodes(NULL, &wbc);
+ if (wbc.nr_to_write > 0)
+ break; /* All the old data is written */
+ nr_to_write -= MAX_WRITEBACK_PAGES;
+ }
+}
+
+static void bdi_pdflush(struct backing_dev_info *bdi)
+{
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ };
+ long nr_pages = bdi->wb_arg.nr_pages;
+
+ for (;;) {
+ unsigned long background_thresh, dirty_thresh;
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+ if ((global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) < background_thresh) &&
+ nr_pages <= 0)
+ break;
+
+ wbc.more_io = 0;
+ wbc.encountered_congestion = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.pages_skipped = 0;
+ generic_sync_bdi_inodes(bdi->wb_arg.sb, &wbc);
+ nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ /*
+ * If we ran out of stuff to write, bail unless more_io got set
+ */
+ if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+ if (wbc.more_io)
+ continue;
+ break;
+ }
+ }
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
+ */
+int bdi_writeback_task(void *ptr)
+{
+ struct backing_dev_info *bdi = ptr;
+ struct task_struct *tsk = current;
+
+ tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
+ set_freezable();
+
+ /*
+ * Our parent may run at a different priority, just set us to normal
+ */
+ set_user_nice(tsk, 0);
+
+ while (!kthread_should_stop()) {
+ DECLARE_WAITQUEUE(wait, tsk);
+
+ add_wait_queue(&bdi->wait, &wait);
+ set_task_state(tsk, TASK_INTERRUPTIBLE);
+ schedule_timeout(dirty_writeback_interval);
+ try_to_freeze();
+
+ /*
+ * We get here in two cases:
+ *
+ * schedule_timeout() returned because the dirty writeback
+ * interval has elapsed. If that happens, we will be able
+ * to acquire the writeback lock and will proceed to do
+ * kupdated style writeout.
+ *
+ * Someone called bdi_start_writeback(), which will acquire
+ * the writeback lock. This means our writeback_acquire()
+ * below will fail and we call into bdi_pdflush() for
+ * pdflush style writeout.
+ *
+ */
+ if (writeback_acquire(bdi))
+ bdi_kupdated(bdi);
+ else
+ bdi_pdflush(bdi);
+
+ writeback_release(bdi);
+ set_task_state(tsk, TASK_RUNNING);
+ finish_wait(&bdi->wait, &wait);
+ }
+
+ return 0;
+}
+
+void bdi_writeback_all(struct super_block *sb, long nr_pages)
+{
+ struct backing_dev_info *bdi;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
+ if (bdi_has_dirty_io(bdi))
+ bdi_start_writeback(bdi, sb, nr_pages);
+
+ rcu_read_unlock();
+}
+
/**
* __mark_inode_dirty - internal function
* @inode: inode to mark
@@ -248,46 +424,6 @@ static void queue_io(struct backing_dev_info *bdi,
move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
}
-static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
-{
- struct inode *inode;
- int ret = 0;
-
- spin_lock(&inode_lock);
- list_for_each_entry(inode, list, i_list) {
- if (inode->i_sb == sb) {
- ret = 1;
- break;
- }
- }
- spin_unlock(&inode_lock);
- return ret;
-}
-
-int sb_has_dirty_inodes(struct super_block *sb)
-{
- struct backing_dev_info *bdi;
- int ret = 0;
-
- /*
- * This is REALLY expensive right now, but it'll go away
- * when the bdi writeback is introduced
- */
- rcu_read_lock();
- list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
- if (sb_on_inode_list(sb, &bdi->b_dirty) ||
- sb_on_inode_list(sb, &bdi->b_io) ||
- sb_on_inode_list(sb, &bdi->b_more_io)) {
- ret = 1;
- break;
- }
- }
- rcu_read_unlock();
-
- return ret;
-}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
-
/*
* Write a single inode's dirty pages and inode data out to disk.
* If `wait' is set, wait on the writeout.
@@ -444,10 +580,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return __sync_single_inode(inode, wbc);
}
-static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
- struct writeback_control *wbc,
- int is_blkdev)
+void generic_sync_bdi_inodes(struct super_block *sb,
+ struct writeback_control *wbc)
{
+ const int is_blkdev_sb = sb_is_blkdev_sb(sb);
+ struct backing_dev_info *bdi = wbc->bdi;
const unsigned long start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
@@ -459,9 +596,17 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
struct inode, i_list);
long pages_skipped;
+ /*
+ * super block given and doesn't match, skip this inode
+ */
+ if (sb && sb != inode->i_sb) {
+ redirty_tail(inode);
+ continue;
+ }
+
if (!bdi_cap_writeback_dirty(bdi)) {
redirty_tail(inode);
- if (is_blkdev) {
+ if (is_blkdev_sb) {
/*
* Dirty memory-backed blockdev: the ramdisk
* driver does this. Skip just this inode
@@ -478,33 +623,20 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
- if (!is_blkdev)
+ if (!is_blkdev_sb)
break; /* Skip a congested fs */
requeue_io(inode);
continue; /* Skip a congested blockdev */
}
- if (wbc->bdi && bdi != wbc->bdi) {
- if (!is_blkdev)
- break; /* fs has the wrong queue */
- requeue_io(inode);
- continue; /* blockdev has wrong queue */
- }
-
/* Was this inode dirtied after sync_sb_inodes was called? */
if (time_after(inode->dirtied_when, start))
break;
- /* Is another pdflush already flushing this queue? */
- if (current_is_pdflush() && !writeback_acquire(bdi))
- break;
-
BUG_ON(inode->i_state & I_FREEING);
__iget(inode);
pages_skipped = wbc->pages_skipped;
__writeback_single_inode(inode, wbc);
- if (current_is_pdflush())
- writeback_release(bdi);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
@@ -543,11 +675,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
* a variety of queues, so all inodes are searched. For other superblocks,
* assume that all inodes are backed by the same queue.
*
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
- *
* The inodes to be written are parked on bdi->b_io. They are moved back onto
* bdi->b_dirty as they are selected for writing. This way, none can be missed
* on the writer throttling path, and we get decent balancing between many
@@ -556,13 +683,10 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
void generic_sync_sb_inodes(struct super_block *sb,
struct writeback_control *wbc)
{
- const int is_blkdev = sb_is_blkdev_sb(sb);
- struct backing_dev_info *bdi;
-
- rcu_read_lock();
- list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
- generic_sync_bdi_inodes(bdi, wbc, is_blkdev);
- rcu_read_unlock();
+ if (wbc->bdi)
+ bdi_start_writeback(wbc->bdi, sb, 0);
+ else
+ bdi_writeback_all(sb, 0);
if (wbc->sync_mode == WB_SYNC_ALL) {
struct inode *inode, *old_inode = NULL;
@@ -617,58 +741,6 @@ static void sync_sb_inodes(struct super_block *sb,
}
/*
- * Start writeback of dirty pagecache data against all unlocked inodes.
- *
- * Note:
- * We don't need to grab a reference to superblock here. If it has non-empty
- * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
- * empty. Since __sync_single_inode() regains inode_lock before it finally moves
- * inode from superblock lists we are OK.
- *
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
- *
- * If `bdi' is non-zero then we will scan the first inode against each
- * superblock until we find the matching ones. One group will be the dirty
- * inodes against a filesystem. Then when we hit the dummy blockdev superblock,
- * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not
- * super-efficient but we're about to do a ton of I/O...
- */
-void
-writeback_inodes(struct writeback_control *wbc)
-{
- struct super_block *sb;
-
- might_sleep();
- spin_lock(&sb_lock);
-restart:
- list_for_each_entry_reverse(sb, &super_blocks, s_list) {
- if (sb_has_dirty_inodes(sb)) {
- /* we're making our own get_super here */
- sb->s_count++;
- spin_unlock(&sb_lock);
- /*
- * If we can't get the readlock, there's no sense in
- * waiting around, most of the time the FS is going to
- * be unmounted by the time it is released.
- */
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- sync_sb_inodes(sb, wbc);
- up_read(&sb->s_umount);
- }
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
- }
- if (wbc->nr_to_write <= 0)
- break;
- }
- spin_unlock(&sb_lock);
-}
-
-/*
* writeback and wait upon the filesystem's dirty inodes. The caller will
* do this in two passes - one to write, and one to wait.
*
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 4a46743..ffa4853 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2373,39 +2373,13 @@ static void ntfs_put_super(struct super_block *sb)
vol->mftmirr_ino = NULL;
}
/*
- * If any dirty inodes are left, throw away all mft data page cache
- * pages to allow a clean umount. This should never happen any more
- * due to mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
- * the underlying mft records are written out and cleaned. If it does,
+ * We should have no dirty inodes left, due to
+ * mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
+ * the underlying mft records are written out and cleaned.
* happen anyway, we want to know...
*/
ntfs_commit_inode(vol->mft_ino);
write_inode_now(vol->mft_ino, 1);
- if (sb_has_dirty_inodes(sb)) {
- const char *s1, *s2;
-
- mutex_lock(&vol->mft_ino->i_mutex);
- truncate_inode_pages(vol->mft_ino->i_mapping, 0);
- mutex_unlock(&vol->mft_ino->i_mutex);
- write_inode_now(vol->mft_ino, 1);
- if (sb_has_dirty_inodes(sb)) {
- static const char *_s1 = "inodes";
- static const char *_s2 = "";
- s1 = _s1;
- s2 = _s2;
- } else {
- static const char *_s1 = "mft pages";
- static const char *_s2 = "They have been thrown "
- "away. ";
- s1 = _s1;
- s2 = _s2;
- }
- ntfs_error(sb, "Dirty %s found at umount time. %sYou should "
- "run chkdsk. Please email "
- "linux-ntfs-dev@...ts.sourceforge.net and say "
- "that you saw this message. Thank you.", s1,
- s2);
- }
#endif /* NTFS_RW */
iput(vol->mft_ino);
diff --git a/fs/sync.c b/fs/sync.c
index a16d53e..f4ddcef 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -23,7 +23,7 @@
*/
static void do_sync(unsigned long wait)
{
- wakeup_pdflush(0);
+ wakeup_flusher_threads(0);
sync_inodes(0); /* All mappings, inodes and their blockdevs */
DQUOT_SYNC(NULL);
sync_supers(); /* Write the superblocks */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index bb58c95..3c94fbd 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -39,6 +39,11 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
+struct bdi_writeback_arg {
+ unsigned long nr_pages;
+ struct super_block *sb;
+};
+
struct backing_dev_info {
struct list_head bdi_list;
@@ -60,6 +65,9 @@ struct backing_dev_info {
struct device *dev;
+ struct task_struct *task; /* writeback task */
+ wait_queue_head_t wait;
+ struct bdi_writeback_arg wb_arg; /* protected by BDI_pdflush */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
@@ -77,10 +85,21 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+ long nr_pages);
+int bdi_writeback_task(void *);
+void bdi_writeback_all(struct super_block *sb, long nr_pages);
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
+static inline int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+ return !list_empty(&bdi->b_dirty) ||
+ !list_empty(&bdi->b_io) ||
+ !list_empty(&bdi->b_more_io);
+}
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3c90eb4..7d44bda 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1832,6 +1832,8 @@ extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
extern void generic_sync_sb_inodes(struct super_block *sb,
struct writeback_control *wbc);
+extern void generic_sync_bdi_inodes(struct super_block *sb,
+ struct writeback_control *);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
@@ -1950,7 +1952,6 @@ extern int bdev_read_only(struct block_device *);
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 7300ecd..3697e91 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -99,7 +99,7 @@ static inline void inode_sync_wait(struct inode *inode)
/*
* mm/page-writeback.c
*/
-int wakeup_pdflush(long nr_pages);
+int wakeup_flusher_threads(long nr_pages);
void laptop_io_completion(void);
void laptop_sync_completion(void);
void throttle_vm_writeout(gfp_t gfp_mask);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index cf1528b..bf9c0e0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,8 +1,10 @@
#include <linux/wait.h>
#include <linux/backing-dev.h>
+#include <linux/kthread.h>
#include <linux/fs.h>
#include <linux/sched.h>
+#include <linux/mm.h>
#include <linux/module.h>
#include <linux/writeback.h>
#include <linux/device.h>
@@ -188,6 +190,13 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
+ bdi->task = kthread_run(bdi_writeback_task, bdi, "bdi-%s",
+ dev_name(dev));
+ if (!bdi->task) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
spin_lock(&bdi_lock);
list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
spin_unlock(&bdi_lock);
@@ -223,6 +232,10 @@ void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
bdi_remove_from_list(bdi);
+ if (bdi->task) {
+ kthread_stop(bdi->task);
+ bdi->task = NULL;
+ }
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -232,14 +245,14 @@ EXPORT_SYMBOL(bdi_unregister);
int bdi_init(struct backing_dev_info *bdi)
{
- int i;
- int err;
+ int i, err;
bdi->dev = NULL;
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ init_waitqueue_head(&bdi->wait);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->b_io);
INIT_LIST_HEAD(&bdi->b_dirty);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3ec11d8..9d37be6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,15 +36,6 @@
#include <linux/pagevec.h>
/*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
-/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
@@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
-static void background_writeout(unsigned long _min_pages);
-
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
@@ -541,7 +530,7 @@ static void balance_dirty_pages(struct address_space *mapping)
* been flushed to permanent storage.
*/
if (bdi_nr_reclaimable) {
- writeback_inodes(&wbc);
+ generic_sync_bdi_inodes(NULL, &wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
@@ -592,7 +581,7 @@ static void balance_dirty_pages(struct address_space *mapping)
(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS)
> background_thresh)))
- pdflush_operation(background_writeout, 0);
+ bdi_start_writeback(bdi, NULL, 0);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -677,151 +666,36 @@ void throttle_vm_writeout(gfp_t gfp_mask)
}
/*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
- */
-static void background_writeout(unsigned long _min_pages)
-{
- long min_pages = _min_pages;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = 0,
- .nonblocking = 1,
- .range_cyclic = 1,
- };
-
- for ( ; ; ) {
- unsigned long background_thresh;
- unsigned long dirty_thresh;
-
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
- if (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) < background_thresh
- && min_pages <= 0)
- break;
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- wbc.pages_skipped = 0;
- writeback_inodes(&wbc);
- min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- /* Wrote less than expected */
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(WRITE, HZ/10);
- else
- break;
- }
- }
-}
-
-/*
* Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
* the whole world. Returns 0 if a pdflush thread was dispatched. Returns
* -1 if all pdflush threads were busy.
*/
-int wakeup_pdflush(long nr_pages)
+int wakeup_flusher_threads(long nr_pages)
{
if (nr_pages == 0)
nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
- return pdflush_operation(background_writeout, nr_pages);
+ bdi_writeback_all(NULL, nr_pages);
+ return 0;
}
-static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space. So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval. But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write. So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
- unsigned long oldest_jif;
- unsigned long start_jif;
- unsigned long next_jif;
- long nr_to_write;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = &oldest_jif,
- .nr_to_write = 0,
- .nonblocking = 1,
- .for_kupdate = 1,
- .range_cyclic = 1,
- };
-
- sync_supers();
-
- oldest_jif = jiffies - dirty_expire_interval;
- start_jif = jiffies;
- next_jif = start_jif + dirty_writeback_interval;
- nr_to_write = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- while (nr_to_write > 0) {
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- writeback_inodes(&wbc);
- if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(WRITE, HZ/10);
- else
- break; /* All the old data is written */
- }
- nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- }
- if (time_before(next_jif, jiffies + HZ))
- next_jif = jiffies + HZ;
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, next_jif);
-}
-
-/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
- else
- del_timer(&wb_timer);
return 0;
}
-static void wb_timer_fn(unsigned long unused)
-{
- if (pdflush_operation(wb_kupdate, 0) < 0)
- mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
-{
- sys_sync();
-}
-
static void laptop_timer_fn(unsigned long unused)
{
- pdflush_operation(laptop_flush, 0);
+ wakeup_flusher_threads(0);
}
/*
@@ -904,7 +778,6 @@ void __init page_writeback_init(void)
{
int shift;
- mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6177e3b..b5e2802 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1649,7 +1649,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
*/
if (total_scanned > sc->swap_cluster_max +
sc->swap_cluster_max / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
--
1.6.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists