The generic writeback routines are departing from congestion_wait()
in preferance of get_request_wait(), aka. waiting on the block queues.
Introduce the missing writeback wait queue for NFS, otherwise its
writeback pages may grow out of control.
In perticular, balance_dirty_pages() will exit after it pushes
write_chunk pages into the PG_writeback page pool, _OR_ when the
background writeback work quits. The latter is new behavior, and could
not only quit (normally) after below background threshold, but also
quit when it finds _zero_ dirty pages to write. The latter case gives
rise to the number of PG_writeback pages if it is not explicitly limited.
CC: Jens Axboe <jens.axboe@xxxxxxxxxx>
CC: Chris Mason <chris.mason@xxxxxxxxxx>
CC: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
CC: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
The wait time and network throughput varies a lot! this is a major problem.
This means nfs_end_page_writeback() is not called smoothly over time,
even when there are plenty of PG_writeback pages on the client side.
[ 397.828509] write_bandwidth: comm=nfsiod pages=192 time=16ms
[ 397.850976] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 403.065244] write_bandwidth: comm=nfsiod pages=192 time=5212ms
[ 403.549134] write_bandwidth: comm=nfsiod pages=1536 time=144ms
[ 403.570717] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 403.595749] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 403.622171] write_bandwidth: comm=nfsiod pages=192 time=24ms
[ 403.651779] write_bandwidth: comm=nfsiod pages=192 time=28ms
[ 403.680543] write_bandwidth: comm=nfsiod pages=192 time=24ms
[ 403.712572] write_bandwidth: comm=nfsiod pages=192 time=28ms
[ 403.751552] write_bandwidth: comm=nfsiod pages=192 time=36ms
[ 403.785979] write_bandwidth: comm=nfsiod pages=192 time=28ms
[ 403.823995] write_bandwidth: comm=nfsiod pages=192 time=36ms
[ 403.858970] write_bandwidth: comm=nfsiod pages=192 time=32ms
[ 403.880786] write_bandwidth: comm=nfsiod pages=192 time=16ms
[ 403.902732] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 403.925925] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 403.952044] write_bandwidth: comm=nfsiod pages=258 time=24ms
[ 403.974006] write_bandwidth: comm=nfsiod pages=192 time=16ms
[ 403.995989] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 405.031049] write_bandwidth: comm=nfsiod pages=192 time=1032ms
[ 405.257635] write_bandwidth: comm=nfsiod pages=1536 time=192ms
[ 405.279069] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 405.300843] write_bandwidth: comm=nfsiod pages=192 time=16ms
[ 405.326031] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 405.350843] write_bandwidth: comm=nfsiod pages=192 time=24ms
[ 405.375160] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 409.331015] write_bandwidth: comm=nfsiod pages=192 time=3952ms
[ 409.587928] write_bandwidth: comm=nfsiod pages=1536 time=152ms
[ 409.610068] write_bandwidth: comm=nfsiod pages=192 time=20ms
[ 409.635736] write_bandwidth: comm=nfsiod pages=192 time=24ms
# vmmon -d 1 nr_writeback nr_dirty nr_unstable
nr_writeback nr_dirty nr_unstable
11227 41463 38044
11227 41463 38044
11227 41463 38044
11227 41463 38044
11045 53987 6490
11033 53120 8145
11195 52143 10886
11211 52144 10913
11211 52144 10913
11211 52144 10913
11056 56887 3876
11062 55298 8155
11214 54485 9838
11225 54461 9852
11225 54461 9852
11225 54461 4582
22342 35535 7823
----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
usr sys idl wai hiq siq| read writ| recv send| in out | int csw
0 0 9 92 0 0| 0 0 | 66B 306B| 0 0 |1003 377
0 1 39 60 0 1| 0 0 | 90k 1361k| 0 0 |1765 1599
0 15 12 43 0 31| 0 0 |2292k 34M| 0 0 | 12k 16k
0 0 16 84 0 0| 0 0 | 132B 306B| 0 0 |1003 376
0 0 43 57 0 0| 0 0 | 66B 306B| 0 0 |1004 376
0 7 25 55 0 13| 0 0 |1202k 18M| 0 0 |7331 8921
0 8 21 55 0 15| 0 0 |1195k 18M| 0 0 |5382 6579
0 0 38 62 0 0| 0 0 | 66B 306B| 0 0 |1002 371
0 0 33 67 0 0| 0 0 | 66B 306B| 0 0 |1003 376
0 14 20 41 0 24| 0 0 |1621k 24M| 0 0 |8549 10k
0 5 31 55 0 9| 0 0 | 769k 11M| 0 0 |4444 5180
0 0 18 82 0 0| 0 0 | 66B 568B| 0 0 |1004 377
0 1 41 54 0 3| 0 0 | 184k 2777k| 0 0 |2609 2619
1 13 22 43 0 22| 0 0 |1572k 23M| 0 0 |8138 10k
0 11 9 59 0 20| 0 0 |1861k 27M| 0 0 |9576 13k
0 5 23 66 0 5| 0 0 | 540k 8122k| 0 0 |2816 2885
fs/nfs/client.c | 2
fs/nfs/write.c | 81 +++++++++++++++++++++++++++++++-----
include/linux/nfs_fs_sb.h | 1
3 files changed, 73 insertions(+), 11 deletions(-)
--- linux.orig/fs/nfs/write.c 2009-10-06 23:37:46.000000000 +0800
+++ linux/fs/nfs/write.c 2009-10-07 10:44:42.000000000 +0800
@@ -187,11 +187,54 @@ static int wb_priority(struct writeback_
* NFS congestion control
*/
+#define NFS_WAIT_PAGES (1024L >> (PAGE_CACHE_SHIFT - 10))
int nfs_congestion_kb;
-#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10))
-#define NFS_CONGESTION_OFF_THRESH \
- (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))
+/*
+ * SYNC requests will block on (2*limit) and wakeup on (2*limit-NFS_WAIT_PAGES)
+ * ASYNC requests will block on (limit) and wakeup on (limit - NFS_WAIT_PAGES)
+ * In this way SYNC writes will never be blocked by ASYNC ones.
+ */
+
+static void nfs_set_congested(long nr, long limit,
+ struct backing_dev_info *bdi)
+{
+ if (nr > limit && !test_bit(BDI_async_congested, &bdi->state))
+ set_bdi_congested(bdi, BLK_RW_ASYNC);
+ else if (nr > 2 * limit && !test_bit(BDI_sync_congested, &bdi->state))
+ set_bdi_congested(bdi, BLK_RW_SYNC);
+}
+
+static void nfs_wait_contested(int is_sync,
+ struct backing_dev_info *bdi,
+ wait_queue_head_t *wqh)
+{
+ int waitbit = is_sync ? BDI_sync_congested : BDI_async_congested;
+
+ wait_event(wqh[is_sync], !test_bit(waitbit, &bdi->state));
+}
+
+static void nfs_wakeup_congested(long nr, long limit,
+ struct backing_dev_info *bdi,
+ wait_queue_head_t *wqh)
+{
+ if (nr < 2*limit - min(limit/8, NFS_WAIT_PAGES)) {
+ if (test_bit(BDI_sync_congested, &bdi->state))
+ clear_bdi_congested(bdi, BLK_RW_SYNC);
+ if (waitqueue_active(&wqh[BLK_RW_SYNC])) {
+ smp_mb__after_clear_bit();
+ wake_up(&wqh[BLK_RW_SYNC]);
+ }
+ }
+ if (nr < limit - min(limit/8, NFS_WAIT_PAGES)) {
+ if (test_bit(BDI_async_congested, &bdi->state))
+ clear_bdi_congested(bdi, BLK_RW_ASYNC);
+ if (waitqueue_active(&wqh[BLK_RW_ASYNC])) {
+ smp_mb__after_clear_bit();
+ wake_up(&wqh[BLK_RW_ASYNC]);
+ }
+ }
+}
static int nfs_set_page_writeback(struct page *page)
{
@@ -201,11 +244,9 @@ static int nfs_set_page_writeback(struct
struct inode *inode = page->mapping->host;
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,
- BLK_RW_ASYNC);
- }
+ nfs_set_congested(atomic_long_inc_return(&nfss->writeback),
+ nfs_congestion_kb >> (PAGE_SHIFT-10),
+ &nfss->backing_dev_info);
}
return ret;
}
@@ -216,8 +257,11 @@ static void nfs_end_page_writeback(struc
struct nfs_server *nfss = NFS_SERVER(inode);
end_page_writeback(page);
- if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
- clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
+ nfs_wakeup_congested(atomic_long_dec_return(&nfss->writeback),
+ nfs_congestion_kb >> (PAGE_SHIFT-10),
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
}
static struct nfs_page *nfs_find_and_lock_request(struct page *page)
@@ -309,19 +353,34 @@ static int nfs_writepage_locked(struct p
int nfs_writepage(struct page *page, struct writeback_control *wbc)
{
+ struct inode *inode = page->mapping->host;
+ struct nfs_server *nfss = NFS_SERVER(inode);
int ret;
ret = nfs_writepage_locked(page, wbc);
unlock_page(page);
+
+ nfs_wait_contested(wbc->sync_mode == WB_SYNC_ALL,
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
+
return ret;
}
-static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data)
+static int nfs_writepages_callback(struct page *page,
+ struct writeback_control *wbc, void *data)
{
+ struct inode *inode = page->mapping->host;
+ struct nfs_server *nfss = NFS_SERVER(inode);
int ret;
ret = nfs_do_writepage(page, wbc, data);
unlock_page(page);
+
+ nfs_wait_contested(wbc->sync_mode == WB_SYNC_ALL,
+ &nfss->backing_dev_info,
+ nfss->writeback_wait);
+
return ret;
}
--- linux.orig/include/linux/nfs_fs_sb.h 2009-10-06 23:37:46.000000000 +0800
+++ linux/include/linux/nfs_fs_sb.h 2009-10-06 23:38:44.000000000 +0800
@@ -108,6 +108,7 @@ struct nfs_server {
struct nfs_iostats * io_stats; /* I/O statistics */
struct backing_dev_info backing_dev_info;
atomic_long_t writeback; /* number of writeback pages */
+ wait_queue_head_t writeback_wait[2];
int flags; /* various flags */
unsigned int caps; /* server capabilities */
unsigned int rsize; /* read size */
--- linux.orig/fs/nfs/client.c 2009-10-06 23:37:46.000000000 +0800
+++ linux/fs/nfs/client.c 2009-10-06 23:38:44.000000000 +0800
@@ -991,6 +991,8 @@ static struct nfs_server *nfs_alloc_serv
INIT_LIST_HEAD(&server->master_link);
atomic_set(&server->active, 0);
+ init_waitqueue_head(&server->writeback_wait[BLK_RW_SYNC]);
+ init_waitqueue_head(&server->writeback_wait[BLK_RW_ASYNC]);
server->io_stats = nfs_alloc_iostats();
if (!server->io_stats) {
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
