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

DDT: Add/use zap_lookup_length_uint64_by_dnode()

Browse Source 
Unlike other ZAP consumers due to compression DDT does not know
how big entry it is reading from ZAP.  Due to this it called
zap_length_uint64_by_dnode() and zap_lookup_uint64_by_dnode(),
each of which does full ZAP entry lookup.

Introduction of the combined ZAP method dramatically reduces the
CPU overhead and locks contention at DBUF layer.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <alexander.motin@TrueNAS.com>
Closes #18048
This commit is contained in:
Alexander Motin
2025-12-15 17:38:34 -05:00
committed by Tony Hutter
parent 4905686e67
commit 4ab2027f59
5 changed files with 46 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/zap.c
+4 -1
View File
@@ -878,7 +878,8 @@ fzap_check(zap_name_t *zn, uint64_t integer_size, uint64_t num_integers)
int
fzap_lookup(zap_name_t *zn,
uint64_t integer_size, uint64_t num_integers, void *buf,
char *realname, int rn_len, boolean_t *ncp)
char *realname, int rn_len, boolean_t *ncp,
uint64_t *actual_num_integers)
{
zap_leaf_t *l;
zap_entry_handle_t zeh;
@@ -898,6 +899,8 @@ fzap_lookup(zap_name_t *zn,
}
err = zap_entry_read(&zeh, integer_size, num_integers, buf);
if (err == 0 && actual_num_integers != NULL)
*actual_num_integers = zeh.zeh_num_integers;
(void) zap_entry_read_name(zn->zn_zap, &zeh, rn_len, realname);
if (ncp) {
*ncp = zap_entry_normalization_conflict(&zeh,