diff options
| author | Matthew Ahrens <[email protected]> | 2018-05-31 10:29:12 -0700 |
|---|---|---|
| committer | Brian Behlendorf <[email protected]> | 2018-06-13 11:05:06 -0700 |
| commit | 1fac63e56f370f675b23687ee2e634744c54e818 (patch) | |
| tree | 1655183ce851b290e08c0d191ac01aeb87e2caf1 /module/zfs/dnode.c | |
| parent | 232dd8b956703bcc774524e78110d13de93dd5bd (diff) | |
OpenZFS 9577 - remove zfs_dbuf_evict_key tsd
The zfs_dbuf_evict_key TSD (thread-specific data) is not necessary -
we can instead pass a flag down in a few places to prevent recursive
dbuf eviction. Making this change has 3 benefits:
1. The code semantics are easier to understand.
2. On Linux, performance is improved, because creating/removing
TSD values (by setting to NULL vs non-NULL) is expensive, and
we do it very often.
3. According to Nexenta, the current semantics can cause a
deadlock when concurrently calling dmu_objset_evict_dbufs()
(which is rare today, but they are working on a "parallel
unmount" change that triggers this more easily):
Porting Notes:
* Minor conflict with OpenZFS 9337 which has not yet been ported.
Authored by: Matthew Ahrens <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Serapheim Dimitropoulos <[email protected]>
Reviewed by: Brad Lewis <[email protected]>
Reviewed-by: George Melikov <[email protected]>
Ported-by: Brian Behlendorf <[email protected]>
OpenZFS-issue: https://illumos.org/issues/9577
OpenZFS-commit: https://github.com/openzfs/openzfs/pull/645
External-issue: DLPX-58547
Closes #7602
Diffstat (limited to 'module/zfs/dnode.c')
| -rw-r--r-- | module/zfs/dnode.c | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/module/zfs/dnode.c b/module/zfs/dnode.c index 7620e11f0..ab687f7cc 100644 --- a/module/zfs/dnode.c +++ b/module/zfs/dnode.c @@ -1571,11 +1571,11 @@ void dnode_rele(dnode_t *dn, void *tag) { mutex_enter(&dn->dn_mtx); - dnode_rele_and_unlock(dn, tag); + dnode_rele_and_unlock(dn, tag, B_FALSE); } void -dnode_rele_and_unlock(dnode_t *dn, void *tag) +dnode_rele_and_unlock(dnode_t *dn, void *tag, boolean_t evicting) { uint64_t refs; /* Get while the hold prevents the dnode from moving. */ @@ -1606,7 +1606,8 @@ dnode_rele_and_unlock(dnode_t *dn, void *tag) * that the handle has zero references, but that will be * asserted anyway when the handle gets destroyed. */ - dbuf_rele(db, dnh); + mutex_enter(&db->db_mtx); + dbuf_rele_and_unlock(db, dnh, evicting); } } |