From d7831a0bdf06b9f722b947bb0c205ff7d77cebd8 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Tue, 30 Jun 2009 11:41:35 -0700 Subject: mm: prevent balance_dirty_pages() from doing too much work balance_dirty_pages can overreact and move all of the dirty pages to writeback unnecessarily. balance_dirty_pages makes its decision to throttle based on the number of dirty plus writeback pages that are over the calculated limit,so it will continue to move pages even when there are plenty of pages in writeback and less than the threshold still dirty. This allows it to overshoot its limits and move all the dirty pages to writeback while waiting for the drives to catch up and empty the writeback list. A simple fio test easily demonstrates this problem. fio --name=f1 --directory=/disk1 --size=2G -rw=write --name=f2 --directory=/disk2 --size=1G --rw=write --startdelay=10 This is the simplest fix I could find, but I'm not entirely sure that it alone will be enough for all cases. But it certainly is an improvement on my desktop machine writing to 2 disks. Do we need something more for machines with large arrays where bdi_threshold * number_of_drives is greater than the dirty_ratio ? Signed-off-by: Richard Kennedy Acked-by: Peter Zijlstra Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7b0dcea4935..7687879253b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -541,8 +541,11 @@ static void balance_dirty_pages(struct address_space *mapping) * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. + * Only move pages to writeback if this bdi is over its + * threshold otherwise wait until the disk writes catch + * up. */ - if (bdi_nr_reclaimable) { + if (bdi_nr_reclaimable > bdi_thresh) { writeback_inodes(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, -- cgit v1.2.3-70-g09d2 From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 9 Jul 2009 14:52:32 +0200 Subject: Fix congestion_wait() sync/async vs read/write confusion Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke the bdi congestion wait queue logic, causing us to wait on congestion for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead. Signed-off-by: Jens Axboe --- arch/x86/lib/usercopy_32.c | 2 +- drivers/block/pktcdvd.c | 10 ++++++---- drivers/md/dm-crypt.c | 2 +- fs/fat/file.c | 2 +- fs/fuse/dev.c | 8 ++++---- fs/nfs/write.c | 8 +++++--- fs/reiserfs/journal.c | 2 +- fs/xfs/linux-2.6/kmem.c | 4 ++-- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/backing-dev.h | 6 +++--- include/linux/blkdev.h | 8 ++++---- mm/backing-dev.c | 7 +++---- mm/memcontrol.c | 2 +- mm/page-writeback.c | 8 ++++---- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 8 ++++---- 16 files changed, 43 insertions(+), 40 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 7c8ca91bb9e..1f118d462ac 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -751,7 +751,7 @@ survive: if (retval == -ENOMEM && is_global_init(current)) { up_read(¤t->mm->mmap_sem); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto survive; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 83650e00632..99a506f619b 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1372,8 +1372,10 @@ try_next_bio: wakeup = (pd->write_congestion_on > 0 && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); - if (wakeup) - clear_bdi_congested(&pd->disk->queue->backing_dev_info, WRITE); + if (wakeup) { + clear_bdi_congested(&pd->disk->queue->backing_dev_info, + BLK_RW_ASYNC); + } pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2592,10 +2594,10 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(&q->backing_dev_info, WRITE); + set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); - congestion_wait(WRITE, HZ); + congestion_wait(BLK_RW_ASYNC, HZ); spin_lock(&pd->lock); } while(pd->bio_queue_size > pd->write_congestion_off); } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9933eb861c7..529e2ba505c 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -776,7 +776,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) * But don't wait if split was due to the io size restriction */ if (unlikely(out_of_pages)) - congestion_wait(WRITE, HZ/100); + congestion_wait(BLK_RW_ASYNC, HZ/100); /* * With async crypto it is unsafe to share the crypto context diff --git a/fs/fat/file.c b/fs/fat/file.c index b28ea646ff6..f042b965c95 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -134,7 +134,7 @@ static int fat_file_release(struct inode *inode, struct file *filp) if ((filp->f_mode & FMODE_WRITE) && MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } return 0; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f58ecbc416c..6484eb75acd 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -286,8 +286,8 @@ __releases(&fc->lock) } if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->connected && fc->bdi_initialized) { - clear_bdi_congested(&fc->bdi, READ); - clear_bdi_congested(&fc->bdi, WRITE); + clear_bdi_congested(&fc->bdi, BLK_RW_SYNC); + clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } fc->num_background--; fc->active_background--; @@ -414,8 +414,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc, fc->blocked = 1; if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->bdi_initialized) { - set_bdi_congested(&fc->bdi, READ); - set_bdi_congested(&fc->bdi, WRITE); + set_bdi_congested(&fc->bdi, BLK_RW_SYNC); + set_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } list_add_tail(&req->list, &fc->bg_queue); flush_bg_queue(fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ce728829f79..0a0a2ff767c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -202,8 +202,10 @@ static int nfs_set_page_writeback(struct page *page) struct nfs_server *nfss = NFS_SERVER(inode); if (atomic_long_inc_return(&nfss->writeback) > - NFS_CONGESTION_ON_THRESH) - set_bdi_congested(&nfss->backing_dev_info, WRITE); + NFS_CONGESTION_ON_THRESH) { + set_bdi_congested(&nfss->backing_dev_info, + BLK_RW_ASYNC); + } } return ret; } @@ -215,7 +217,7 @@ static void nfs_end_page_writeback(struct page *page) end_page_writeback(page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(&nfss->backing_dev_info, WRITE); + clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } /* diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 77f5bb746bf..90622200b39 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -997,7 +997,7 @@ static int reiserfs_async_progress_wait(struct super_block *s) DEFINE_WAIT(wait); struct reiserfs_journal *j = SB_JOURNAL(s); if (atomic_read(&j->j_async_throttle)) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); return 0; } diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c index 1cd3b55ee3d..2d3f90afe5f 100644 --- a/fs/xfs/linux-2.6/kmem.c +++ b/fs/xfs/linux-2.6/kmem.c @@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } @@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 1418b916fc2..0c93c7ef3d1 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -412,7 +412,7 @@ _xfs_buf_lookup_pages( XFS_STATS_INC(xb_page_retries); xfsbufd_wakeup(0, gfp_mask); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ec2c594868..3a52a63c135 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } -void clear_bdi_congested(struct backing_dev_info *bdi, int rw); -void set_bdi_congested(struct backing_dev_info *bdi, int rw); -long congestion_wait(int rw, long timeout); +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); +long congestion_wait(int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49ae07951d5..bb3d3997870 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -779,18 +779,18 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, * congested queues, and wake up anyone who was waiting for requests to be * put back. */ -static inline void blk_clear_queue_congested(struct request_queue *q, int rw) +static inline void blk_clear_queue_congested(struct request_queue *q, int sync) { - clear_bdi_congested(&q->backing_dev_info, rw); + clear_bdi_congested(&q->backing_dev_info, sync); } /* * A queue has just entered congestion. Flag that in the queue's VM-visible * state flags and increment the global gounter of congested queues. */ -static inline void blk_set_queue_congested(struct request_queue *q, int rw) +static inline void blk_set_queue_congested(struct request_queue *q, int sync) { - set_bdi_congested(&q->backing_dev_info, rw); + set_bdi_congested(&q->backing_dev_info, sync); } extern void blk_start_queue(struct request_queue *q); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 493b468a503..c86edd24429 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; - void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { enum bdi_state bit; @@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested); /** * congestion_wait - wait for a backing_dev to become uncongested - * @rw: READ or WRITE + * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit * write congestion. If no backing_devs are congested then just wait for the * next write to be completed. */ -long congestion_wait(int rw, long timeout) +long congestion_wait(int sync, long timeout) { long ret; DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[rw]; + wait_queue_head_t *wqh = &congestion_wqh[sync]; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e2fa20dadf4..e717964cb5a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1973,7 +1973,7 @@ try_to_free: if (!progress) { nr_retries--; /* maybe some writeback is necessary */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7687879253b..81627ebcd31 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -575,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -669,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The caller might hold locks which can prevent IO completion @@ -715,7 +715,7 @@ static void background_writeout(unsigned long _min_pages) 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); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; } @@ -787,7 +787,7 @@ static void wb_kupdate(unsigned long arg) writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; /* All the old data is written */ } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ad7cd1c56b0..a35eeab2724 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1666,7 +1666,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; @@ -1831,7 +1831,7 @@ rebalance: pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { /* Wait for some write requests to complete then retry */ - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto rebalance; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 54155268dfc..dea7abd3109 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1104,7 +1104,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, */ if (nr_freed < nr_taken && !current_is_kswapd() && lumpy_reclaim) { - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The attempt at page out may have made some @@ -1721,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, /* Take a nap, wait for some writeback to complete */ if (sc->nr_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } /* top priority shrink_zones still had more to do? don't OOM, then */ if (!sc->all_unreclaimable && scanning_global_lru(sc)) @@ -1960,7 +1960,7 @@ loop_again: * another pass across the zones. */ if (total_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * We do this so kswapd doesn't build up large priorities for @@ -2233,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) goto out; if (sc.nr_scanned && prio < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); } } -- cgit v1.2.3-70-g09d2