nfs: writeback pages wait queue
Subsystems (5)
PATCH 1/2 nfs: writeback pages wait queue
The generic writeback routines are departing from congestion_wait() in preference of get_request_wait(), aka. waiting on the block queues.
Introduce the missing writeback wait queue for NFS, otherwise its writeback pages will grow out of control, exhausting all PG_dirty pages.
Feng: do more coarse grained throttle on each ->writepages rather than on each page, for better performance and avoid throttled-before-send-rpc deadlock
CC Jens Axboe <[email protected]>
CC Chris Mason <[email protected]>
CC Peter Zijlstra <[email protected]>
CC Trond Myklebust <[email protected]>
Signed-off-by Feng Tang <[email protected]>
Signed-off-by Wu Fengguang <[email protected]>
--- fs/nfs/client.c | 2 fs/nfs/write.c | 84 +++++++++++++++++++++++++++++++----- include/linux/nfs_fs_sb.h | 1 3 files changed, 77 insertions(+), 10 deletions(-)
fs/nfs/write.c +74 -10
@@ -190,11 +190,64 @@ static int wb_priority(struct writeback_* NFS congestion control */ +#define NFS_WAIT_PAGES (1024L >> (PAGE_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,struct backing_dev_info *bdi) +{ +long limit = nfs_congestion_kb >> (PAGE_SHIFT -10 ); + +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_congested (int is_sync, +struct backing_dev_info *bdi, +wait_queue_head_t *wqh) +{ +int waitbit = is_sync ? BDI_sync_congested : BDI_async_congested; +DEFINE_WAIT (wait); + +if (!test_bit (waitbit, &bdi->state)) +return ; + +for (;;) { +prepare_to_wait (&wqh[is_sync], &wait,TASK_UNINTERRUPTIBLE ); +if (!test_bit (waitbit, &bdi->state)) +break ; + +io_schedule (); + } +finish_wait (&wqh[is_sync], &wait); +} + +static void nfs_wakeup_congested (long nr, +struct backing_dev_info *bdi, +wait_queue_head_t *wqh) +{ +long limit = nfs_congestion_kb >> (PAGE_SHIFT -10 ); + +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 ])) +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 ])) +wake_up (&wqh[BLK_RW_ASYNC ]); + } +}static int nfs_set_page_writeback (struct page *page) {
@@ -205,11 +258,8 @@ static int nfs_set_page_writeback(structstruct nfs_server *nfss =NFS_SERVER (inode);page_cache_get (page); -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), + &nfss->backing_dev_info); }return ret; }
@@ -221,8 +271,10 @@ static void nfs_end_page_writeback(strucend_page_writeback (page);page_cache_release (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), + &nfss->backing_dev_info, + nfss->writeback_wait); }static struct nfs_page *nfs_find_and_lock_request (struct page *page,bool nonblock)
@@ -323,10 +375,17 @@ static int nfs_writepage_locked(struct pint 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_congested (wbc->sync_mode ==WB_SYNC_ALL , + &nfss->backing_dev_info, + nfss->writeback_wait); +return ret; }
@@ -342,6 +401,7 @@ static int nfs_writepages_callback(strucint nfs_writepages (struct address_space *mapping,struct writeback_control *wbc) {struct inode *inode = mapping->host; +struct nfs_server *nfss =NFS_SERVER (inode);unsigned long *bitlock = &NFS_I (inode)->flags;struct nfs_pageio_descriptor pgio;int err;
@@ -358,6 +418,10 @@ int nfs_writepages(struct address_space err =write_cache_pages (mapping, wbc, nfs_writepages_callback, &pgio);nfs_pageio_complete (&pgio); +nfs_wait_congested (wbc->sync_mode ==WB_SYNC_ALL , + &nfss->backing_dev_info, + nfss->writeback_wait); +clear_bit_unlock (NFS_INO_FLUSHING , bitlock);smp_mb__after_clear_bit ();wake_up_bit (bitlock,NFS_INO_FLUSHING );
include/linux/nfs_fs_sb.h +1 -0
@@ -102,6 +102,7 @@ struct nfs_server {struct nfs_iostats __percpu *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 */
fs/nfs/client.c +2 -0
@@ -1066,6 +1066,8 @@ static struct nfs_server *nfs_alloc_servINIT_LIST_HEAD (&server->layouts);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, send a message with 'unsubscribe linux-mm' in
the body to [email protected]. 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:"[email protected]"> [email protected] </a>
PATCH 2/2 nfs: scale writeback threshold proportional to dirty threshold
nfs_congestion_kb is to control the max allowed writeback and in-commit pages. It's not reasonable for them to outnumber dirty and to-commit pages. So each of them should not take more than 1/4 dirty threshold.
Considering that nfs_init_writepagecache() is called on fresh boot, at the time dirty_thresh is much higher than the real dirty limit after lots of user space memory consumptions, use 1/8 instead.
Feng: fix deadlock by preventing (nfs_congestion_kb == 0)
CC Trond Myklebust <[email protected]>
Signed-off-by Feng Tang <[email protected]>
Signed-off-by Wu Fengguang <[email protected]>
--- fs/nfs/write.c | 36 +++++++++++++++++------------------- mm/page-writeback.c | 6 ++++++ 2 files changed, 23 insertions(+), 19 deletions(-)
fs/nfs/write.c +17 -19
@@ -1782,6 +1782,22 @@ out: }#endif +void nfs_update_congestion_thresh (void ) +{ +unsigned long background_thresh; +unsigned long dirty_thresh; + +/* +* Limit to 1/8 dirty threshold, so that writeback+in_commit pages +* won't overnumber dirty+to_commit pages. +*/ +global_dirty_limits (&background_thresh, &dirty_thresh); + dirty_thresh <<=PAGE_SHIFT -10 ; + dirty_thresh +=1024 ; + + nfs_congestion_kb = dirty_thresh /8 ; +} +int __init nfs_init_writepagecache (void ) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
@@ -1801,25 +1817,7 @@ int __init nfs_init_writepagecache(void)if (nfs_commit_mempool ==NULL )return -ENOMEM ; -/* -* NFS congestion size, scale with available memory. -* -* 64MB: 8192k -* 128MB: 11585k -* 256MB: 16384k -* 512MB: 23170k -* 1GB: 32768k -* 2GB: 46340k -* 4GB: 65536k -* 8GB: 92681k -* 16GB: 131072k -* -* This allows larger machines to have larger/more transfers. -* Limit the default to 256M -*/ - nfs_congestion_kb = (16 *int_sqrt (totalram_pages)) << (PAGE_SHIFT -10 ); -if (nfs_congestion_kb >256 *1024 ) - nfs_congestion_kb =256 *1024 ; +nfs_update_congestion_thresh ();return 0 ; }
mm/page-writeback.c +6 -0
@@ -207,6 +207,10 @@ static int calc_period_shift(void)return 2 +ilog2 (dirty_total -1 ); } +void __weak nfs_update_congestion_thresh (void ) +{ +} +/* * update the period when the dirty threshold changes. */
@@ -217,6 +221,7 @@ static void update_completion_period(voiprop_change_shift (&vm_dirties, shift);writeback_set_ratelimit (); +nfs_update_congestion_thresh (); } int dirty_background_ratio_handler(struct ctl_table *table, int write,
@@ -447,6 +452,7 @@ unsigned long bdi_dirty_limit(struct bacreturn bdi_dirty; } +EXPORT_SYMBOL_GPL (global_dirty_limits);/* * Dirty position control.
Trond,
After applying these two patches, the IO-less patchset performances 45% better than the vanilla kernel and the average commit size only decreases by -16% in the common NFS-thresh=1G/nfs-1dd case :)
Thanks,
Fengguang
3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
354.65 +45.4% 515.48 TOTAL write_bw
10498.00 +91.7% 20120.00 TOTAL nfs_nr_commits
233013.00 +99.9% 465751.00 TOTAL nfs_nr_writes
895.47 +3.1% 923.62 TOTAL nfs_commit_size
5.71 -14.5% 4.88 TOTAL nfs_write_size
108269.33 -84.3% 17003.69 TOTAL nfs_write_queue_time
1836.03 -34.4% 1204.27 TOTAL nfs_write_rtt_time
110144.96 -83.5% 18220.96 TOTAL nfs_write_execute_time
2902.62 -88.6% 332.20 TOTAL nfs_commit_queue_time
16282.75 -23.3% 12490.87 TOTAL nfs_commit_rtt_time
19234.16 -33.3% 12833.00 TOTAL nfs_commit_execute_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
21.85 +97.9% 43.23 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
51.38 +42.6% 73.26 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
28.81 +145.3% 70.68 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
13.74 +57.1% 21.59 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
29.11 -0.3% 29.02 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
16.68 +90.5% 31.78 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
48.88 +41.2% 69.01 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
57.85 +32.7% 76.74 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
47.13 +63.1% 76.87 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
9.82 -33.0% 6.58 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
13.72 -18.1% 11.24 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
15.68 -65.0% 5.48 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
354.65 +45.4% 515.48 TOTAL write_bw 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
834.00 +224.2% 2704.00 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
311.00 +144.1% 759.00 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
282.00 +253.5% 997.00 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
1387.00 +334.2% 6023.00 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
1081.00 +280.3% 4111.00 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
930.00 +368.0% 4352.00 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
254.00 +108.7% 530.00 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
38.00 +55.3% 59.00 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
54.00 +96.3% 106.00 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
1321.00 -74.9% 332.00 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
1932.00 -99.1% 17.00 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
2074.00 -93.7% 130.00 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
10498.00 +91.7% 20120.00 TOTAL nfs_nr_commits 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
28359.00 -39.2% 17230.00 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
22241.00 +550.6% 144695.00 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
24969.00 +27.8% 31900.00 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
21722.00 +38.2% 30030.00 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
11015.00 +28.2% 14117.00 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
17012.00 +217.7% 54039.00 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
25616.00 +3.1% 26403.00 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
24761.00 +177.5% 68702.00 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
29235.00 +37.1% 40089.00 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
12929.00 +21.6% 15720.00 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
7683.00 +24.2% 9542.00 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
7471.00 +77.8% 13284.00 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
233013.00 +99.9% 465751.00 TOTAL nfs_nr_writes 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
7.84 -38.6% 4.81 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
49.58 -41.6% 28.94 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
30.58 -30.5% 21.27 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
2.99 -63.9% 1.08 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
8.06 -73.8% 2.12 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
5.33 -58.9% 2.19 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
57.68 -32.1% 39.15 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
465.15 -16.5% 388.43 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
261.60 -16.4% 218.80 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
2.25 +163.5% 5.93 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
2.13 +9221.2% 198.29 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
2.27 +455.3% 12.61 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
895.47 +3.1% 923.62 TOTAL nfs_commit_size 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
0.23 +227.7% 0.76 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
0.69 -78.1% 0.15 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
0.35 +92.4% 0.66 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
0.19 +13.4% 0.22 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
0.79 -22.2% 0.62 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
0.29 -39.5% 0.18 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
0.57 +37.4% 0.79 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
0.71 -53.3% 0.33 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
0.48 +19.7% 0.58 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
0.23 -45.5% 0.13 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
0.53 -34.0% 0.35 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
0.63 -80.4% 0.12 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
5.71 -14.5% 4.88 TOTAL nfs_write_size 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
6544.25 -95.1% 321.04 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
1064.82 +11.2% 1184.16 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
22801.48 -86.3% 3113.39 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
1083.47 -99.8% 2.56 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
3.82 -55.8% 1.69 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
2840.08 -99.3% 20.09 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
20227.73 -96.6% 683.65 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
2346.04 +274.0% 8774.87 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
50812.68 -94.3% 2901.88 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
417.03 -99.9% 0.25 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
1.70 -97.9% 0.04 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
126.23 -99.9% 0.08 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
108269.33 -84.3% 17003.69 TOTAL nfs_write_queue_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
276.99 -41.1% 163.20 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
106.71 -67.0% 35.21 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
76.32 +13.4% 86.53 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
335.96 -41.8% 195.49 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
33.67 +70.7% 57.48 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
159.03 -46.0% 85.80 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
340.25 -67.6% 110.23 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
47.88 +12.7% 53.96 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
118.13 -53.8% 54.62 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
223.24 -53.0% 104.83 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
58.89 +12.8% 66.43 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
58.97 +223.0% 190.49 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
1836.03 -34.4% 1204.27 TOTAL nfs_write_rtt_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
6821.43 -92.9% 484.70 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
1173.98 +4.0% 1220.80 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
22878.44 -86.0% 3201.00 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
1419.50 -86.0% 198.20 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
37.72 +57.1% 59.27 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
2999.22 -96.5% 106.41 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
20570.86 -96.1% 795.46 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
2416.09 +265.6% 8832.81 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
50941.27 -94.2% 2960.10 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
640.32 -83.6% 105.13 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
60.78 +9.4% 66.49 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
185.35 +2.8% 190.59 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
110144.96 -83.5% 18220.96 TOTAL nfs_write_execute_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
54.75 -89.4% 5.82 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
88.26 -98.7% 1.12 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
38.41 -92.1% 3.05 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
7.59 -91.0% 0.68 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
0.42 -93.3% 0.03 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
2.57 -75.1% 0.64 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
784.08 -93.8% 48.69 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
1338.39 -81.4% 248.51 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
586.69 -96.0% 23.32 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
1.27 -84.3% 0.20 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
0.02 +147.1% 0.06 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
0.16 -41.3% 0.09 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
2902.62 -88.6% 332.20 TOTAL nfs_commit_queue_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
702.80 +8.2% 760.66 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
538.99 -35.8% 346.08 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
704.42 -37.1% 443.00 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
228.96 -18.4% 186.78 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
155.88 -54.6% 70.75 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
169.51 -28.9% 120.53 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
3791.44 -11.4% 3361.05 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
4229.79 -17.8% 3476.80 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
5534.04 -35.4% 3574.73 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
96.34 -31.4% 66.11 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
60.95 -35.5% 39.29 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
69.64 -35.3% 45.08 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
16282.75 -23.3% 12490.87 TOTAL nfs_commit_rtt_time 3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
757.92 +1.2% 766.73 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
627.36 -44.6% 347.25 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
743.59 -40.0% 446.39 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
236.73 -20.8% 187.57 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
156.31 -54.7% 70.79 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
172.16 -29.6% 121.26 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
4579.56 -25.5% 3411.34 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
5568.53 -33.1% 3725.49 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
6163.54 -41.5% 3605.27 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
97.67 -32.1% 66.35 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
60.99 -35.5% 39.35 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
69.82 -35.3% 45.20 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
19234.16 -33.3% 12833.00 TOTAL nfs_commit_execute_timeHi,
Aside from the big improvements in the 1G,100M,10M cases, the thresh=1M cases show big regressions. But there is a good reason.
Quoted 7 lines
3.1.0-rc8-vanilla+ 3.1.0-rc8-nfs-wq4+
------------------------ ------------------------
21.85 +97.9% 43.23 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
51.38 +42.6% 73.26 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
28.81 +145.3% 70.68 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
13.74 +57.1% 21.59 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
29.11 -0.3% 29.02 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-XQuoted 8 lines
16.68 +90.5% 31.78 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
48.88 +41.2% 69.01 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
57.85 +32.7% 76.74 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
47.13 +63.1% 76.87 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
9.82 -33.0% 6.58 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
13.72 -18.1% 11.24 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
15.68 -65.0% 5.48 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
354.65 +45.4% 515.48 TOTAL write_bwThe regressions in the thresh=1M cases are reasonably caused by the much reduced dirty/writeback/unstable pages.
The attached graphs for the NFS-thresh=1M/nfs-10dd cases show the differences. The vanilla kernel (first graph) is much more permissive to allow dirty pages to exceed the global dirty limit, while the IO-less one applies the global dirty limit much more rigidly.
Given the 18MB vs. 3MB max dirty+writeback+unstable pages, it's not surprising to see the better performance in the vanilla kernel. And it does not mean anything inherently wrong in the IO-less logic.
Thanks,
Fengguang
Quoted 5 lines · Wu Fengguang
Trond,
After applying these two patches, the IO-less patchset performances 45% better than the vanilla kernel and the average commit size only decreases by -16% in the common NFS-thresh=1G/nfs-1dd case :)
To better understand how the NFS writeback wait queue helps, I visualized the network traffic over time. Attached are the graphs for the vanilla kernel and the one with the IO-less + NFS wait queue patches.
nfs-1dd-4k-32p-32016M-1024M:10-3.1.0-rc8-vanilla+/dstat-bw.png nfs-1dd-4k-32p-31951M-1024M:10-3.1.0-rc8-nfs-wq4+/dstat-bw.png
The obvious difference is, the network traffic become now more distributed and the "zero traffic" periods are mostly reduced.
The other 2dd, 10dd cases have similar results.
Thanks,
Fengguang
Quoted 12 lines · Wu Fengguang
Quoted 5 lines · Wu Fengguang
Trond,
After applying these two patches, the IO-less patchset performances 45% better than the vanilla kernel and the average commit size only decreases by -16% in the common NFS-thresh=1G/nfs-1dd case :)
To better understand how the NFS writeback wait queue helps, I visualized the network traffic over time. Attached are the graphs for the vanilla kernel and the one with the IO-less + NFS wait queue patches.
Quoted 7 lines
nfs-1dd-4k-32p-32016M-1024M:10-3.1.0-rc8-vanilla+/dstat-bw.png nfs-1dd-4k-32p-31951M-1024M:10-3.1.0-rc8-nfs-wq4+/dstat-bw.png
The obvious difference is, the network traffic become now more distributed and the "zero traffic" periods are mostly reduced.
The other 2dd, 10dd cases have similar results.
To better explore the internal NFS server states and to make it clear where the performance gain comes from, I collected the dstat data in the NFS server and visualized the network/disk throughputs over time. The results are attached for the following test cases.
nfs-1dd-4k-32p-32016M-1024M:10-3.1.0-rc10-vanilla+ nfs-1dd-4k-32p-31951M-1024M:10-3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
In the above cases, the vanilla kernel is shown to have roughly _interleaved_ disk/net activities. After the patches, the disk/net pipeline is well established, hence the impressive performance improvements.
3.1.0-rc10-vanilla+ 3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
------------------------ ------------------------
57.48 +25.5% 72.11 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
63.86 +27.1% 81.15 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
47.51 +80.1% 85.54 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
168.85 +41.4% 238.80 TOTAL write_bw 3.1.0-vanilla+ 3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
------------------------ ------------------------
21.93 +97.0% 43.21 NFS-thresh=100M/nfs-10dd-4k-32p-32768M-100M:10-X
55.91 +27.4% 71.23 NFS-thresh=100M/nfs-1dd-4k-32p-32768M-100M:10-X
26.73 +129.2% 61.25 NFS-thresh=100M/nfs-2dd-4k-32p-32768M-100M:10-X
15.66 +40.3% 21.96 NFS-thresh=10M/nfs-10dd-4k-32p-32768M-10M:10-X
29.01 +0.7% 29.20 NFS-thresh=10M/nfs-1dd-4k-32p-32768M-10M:10-X
20.52 +7.9% 22.13 NFS-thresh=10M/nfs-2dd-4k-32p-32768M-10M:10-X
56.30 +28.1% 72.11 NFS-thresh=1G/nfs-10dd-4k-32p-32768M-1024M:10-X
63.33 +28.1% 81.15 NFS-thresh=1G/nfs-1dd-4k-32p-32768M-1024M:10-X
51.95 +64.6% 85.54 NFS-thresh=1G/nfs-2dd-4k-32p-32768M-1024M:10-X
9.87 -48.2% 5.11 NFS-thresh=1M/nfs-10dd-4k-32p-32768M-1M:10-X
14.52 -24.0% 11.03 NFS-thresh=1M/nfs-1dd-4k-32p-32768M-1M:10-X
15.69 -67.4% 5.12 NFS-thresh=1M/nfs-2dd-4k-32p-32768M-1M:10-X
381.42 +33.5% 509.05 TOTAL write_bwThe vanilla kernel's disk idle periods indicate that the background flusher work is not running. This is true. The NFS server has 12GB memory and hence 1.2GB background dirty thresh. So when the client side has dirty thresh <= 1GB, it won't send enough data to trigger the background work in NFS server. So the server disk IOs will be triggered mostly by NFS commits. The patched kernel seems to generate smoother commit pattern to prevent most disk idles.
To explore how it performs when the NFS server's background writeback kicks in, I further tried lowering the NFS server's dirty thresholds to
dirty_bytes = 1GB, background threshold = 512MB
-----------------------------------------------
graphs attached for cases:
nfs-1dd-1M-32p-32016M-1024M:10-3.1.0-vanilla+
nfs-1dd-1M-32p-31951M-1024M:10-3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
3.1.0-vanilla+ 3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
------------------------ ------------------------
25.23 +71.2% 43.21 NFS-thresh=100M/nfs-10dd-1M-32p-32768M-100M:10-X
60.21 +15.1% 69.29 NFS-thresh=100M/nfs-1dd-1M-32p-32768M-100M:10-X
33.46 +82.8% 61.18 NFS-thresh=100M/nfs-2dd-1M-32p-32768M-100M:10-X
21.81 +2.8% 22.42 NFS-thresh=10M/nfs-10dd-1M-32p-32768M-10M:10-X
28.71 -11.0% 25.55 NFS-thresh=10M/nfs-1dd-1M-32p-32768M-10M:10-X
28.11 -13.0% 24.46 NFS-thresh=10M/nfs-2dd-1M-32p-32768M-10M:10-X
54.10 +42.3% 76.97 NFS-thresh=1G/nfs-10dd-1M-32p-32768M-1024M:10-X
64.88 +29.1% 83.76 NFS-thresh=1G/nfs-1dd-1M-32p-32768M-1024M:10-X
53.64 +56.2% 83.79 NFS-thresh=1G/nfs-2dd-1M-32p-32768M-1024M:10-X
13.00 -61.0% 5.06 NFS-thresh=1M/nfs-10dd-1M-32p-32768M-1M:10-X
13.53 -33.9% 8.95 NFS-thresh=1M/nfs-1dd-1M-32p-32768M-1M:10-X
16.51 -72.5% 4.54 NFS-thresh=1M/nfs-2dd-1M-32p-32768M-1M:10-X
413.20 +23.2% 509.18 TOTAL write_bwdirty_bytes = 100MB, background threshold = 50MB
------------------------------------------------
graphs attached for cases:
nfs-1dd-100k-32p-32016M-1024M:10-3.1.0-vanilla+
nfs-1dd-100k-32p-31951M-1024M:10-3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
3.1.0-vanilla+ 3.1.0-rc9-ioless-full-nfs-wq5-next-20111014+
------------------------ ------------------------
24.93 +71.1% 42.67 NFS-thresh=100M/nfs-10dd-100k-32p-32768M-100M:10-X
58.35 +23.0% 71.78 NFS-thresh=100M/nfs-1dd-100k-32p-32768M-100M:10-X
28.47 +123.0% 63.48 NFS-thresh=100M/nfs-2dd-100k-32p-32768M-100M:10-X
18.44 +22.5% 22.60 NFS-thresh=10M/nfs-10dd-100k-32p-32768M-10M:10-X
28.75 +0.1% 28.78 NFS-thresh=10M/nfs-1dd-100k-32p-32768M-10M:10-X
20.84 +12.0% 23.34 NFS-thresh=10M/nfs-2dd-100k-32p-32768M-10M:10-X
71.78 +6.4% 76.38 NFS-thresh=1G/nfs-10dd-100k-32p-32768M-1024M:10-X
91.02 -4.7% 86.72 NFS-thresh=1G/nfs-1dd-100k-32p-32768M-1024M:10-X
78.84 +9.9% 86.64 NFS-thresh=1G/nfs-2dd-100k-32p-32768M-1024M:10-X
421.42 +19.2% 502.39 TOTAL write_bwThe conclusion is,
- it helps the vanilla kernel performance to lower the NFS server's dirty threshold
- when NFS server's background writeback is not running, the patches will help establish good net/disk pipeline and improve performance; otherwise it maintains roughly the same performance
Thanks,
Fengguang