c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-24 11:18:52 +03:00
Code Issues Packages Projects Releases Wiki Activity

OpenZFS 7004 - dmu_tx_hold_zap() does dnode_hold() 7x on same object

Browse Source 
Using a benchmark which has 32 threads creating 2 million files in the
same directory, on a machine with 16 CPU cores, I observed poor
performance. I noticed that dmu_tx_hold_zap() was using about 30% of
all CPU, and doing dnode_hold() 7 times on the same object (the ZAP
object that is being held).

dmu_tx_hold_zap() keeps a hold on the dnode_t the entire time it is
running, in dmu_tx_hold_t:txh_dnode, so it would be nice to use the
dnode_t that we already have in hand, rather than repeatedly calling
dnode_hold(). To do this, we need to pass the dnode_t down through
all the intermediate calls that dmu_tx_hold_zap() makes, making these
routines take the dnode_t* rather than an objset_t* and a uint64_t
object number. In particular, the following routines will need to have
analogous *_by_dnode() variants created:

dmu_buf_hold_noread()
dmu_buf_hold()
zap_lookup()
zap_lookup_norm()
zap_count_write()
zap_lockdir()
zap_count_write()

This can improve performance on the benchmark described above by 100%,
from 30,000 file creations per second to 60,000. (This improvement is on
top of that provided by working around the object allocation issue. Peak
performance of ~90,000 creations per second was observed with 8 CPUs;
adding CPUs past that decreased performance due to lock contention.) The
CPU used by dmu_tx_hold_zap() was reduced by 88%, from 340 CPU-seconds
to 40 CPU-seconds.

Sponsored by: Intel Corp.

Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>

OpenZFS-issue: https://www.illumos.org/issues/7004
OpenZFS-commit: https://github.com/openzfs/openzfs/pull/109
Closes #4641
Closes #4972
This commit is contained in:
Matthew Ahrens
2016-07-20 15:42:13 -07:00
committed by Brian Behlendorf
parent 8bea981504
commit 2bce8049c3
8 changed files with 146 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/zap.c
+16 -3
View File
@@ -270,6 +270,7 @@ zap_table_load(zap_t *zap, zap_table_phys_t *tbl, uint64_t idx, uint64_t *valp)
uint64_t blk, off;
int err;
dmu_buf_t *db;
dnode_t *dn;
int bs = FZAP_BLOCK_SHIFT(zap);
ASSERT(RW_LOCK_HELD(&zap->zap_rwlock));
@@ -277,8 +278,15 @@ zap_table_load(zap_t *zap, zap_table_phys_t *tbl, uint64_t idx, uint64_t *valp)
blk = idx >> (bs-3);
off = idx & ((1<<(bs-3))-1);
err = dmu_buf_hold(zap->zap_objset, zap->zap_object,
/*
* Note: this is equivalent to dmu_buf_hold(), but we use
* _dnode_enter / _by_dnode because it's faster because we don't
* have to hold the dnode.
*/
dn = dmu_buf_dnode_enter(zap->zap_dbuf);
err = dmu_buf_hold_by_dnode(dn,
(tbl->zt_blk + blk) << bs, FTAG, &db, DMU_READ_NO_PREFETCH);
dmu_buf_dnode_exit(zap->zap_dbuf);
if (err)
return (err);
*valp = ((uint64_t *)db->db_data)[off];
@@ -292,9 +300,11 @@ zap_table_load(zap_t *zap, zap_table_phys_t *tbl, uint64_t idx, uint64_t *valp)
*/
blk = (idx*2) >> (bs-3);
err = dmu_buf_hold(zap->zap_objset, zap->zap_object,
dn = dmu_buf_dnode_enter(zap->zap_dbuf);
err = dmu_buf_hold_by_dnode(dn,
(tbl->zt_nextblk + blk) << bs, FTAG, &db,
DMU_READ_NO_PREFETCH);
dmu_buf_dnode_exit(zap->zap_dbuf);
if (err == 0)
dmu_buf_rele(db, FTAG);
}
@@ -502,6 +512,7 @@ zap_get_leaf_byblk(zap_t *zap, uint64_t blkid, dmu_tx_t *tx, krw_t lt,
zap_leaf_t *l;
int bs = FZAP_BLOCK_SHIFT(zap);
int err;
dnode_t *dn;
ASSERT(RW_LOCK_HELD(&zap->zap_rwlock));
@@ -515,8 +526,10 @@ zap_get_leaf_byblk(zap_t *zap, uint64_t blkid, dmu_tx_t *tx, krw_t lt,
if (blkid == 0)
return (ENOENT);
err = dmu_buf_hold(zap->zap_objset, zap->zap_object,
dn = dmu_buf_dnode_enter(zap->zap_dbuf);
err = dmu_buf_hold_by_dnode(dn,
blkid << bs, NULL, &db, DMU_READ_NO_PREFETCH);
dmu_buf_dnode_exit(zap->zap_dbuf);
if (err)
return (err);