github/ocf
4
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Optimize cacheline locking in ocf_engine_prepare_clines

Browse Source 
Hash bucket read/write lock is sufficient to safely attempt
cacheline trylock/lock. This change removes cacheline lock
global RW semaprhore and moves cacheline trylock/lock under
hash bucket read/write lock respectively.

Signed-off-by: Adam Rutkowski <adam.j.rutkowski@intel.com>
This commit is contained in:
Adam Rutkowski
2019-07-31 15:13:32 -04:00
parent 5248093e1f
commit 30f22d4f47
8 changed files with 161 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/engine/engine_wo.c
View File

@@ -223,10 +223,16 @@ int ocf_read_wo(struct ocf_request *req)
/* There are mapped cache lines,
* lock request for READ access
*/
lock = ocf_req_async_lock_rd(req, ocf_engine_on_resume);
lock = ocf_req_trylock_rd(req);
}
ocf_req_hash_unlock_rd(req); /*- END Metadata RD access -----------------*/
if (lock != OCF_LOCK_ACQUIRED) {
ocf_req_hash_lock_upgrade(req);
lock = ocf_req_async_lock_rd(req, ocf_engine_on_resume);
ocf_req_hash_unlock_wr(req);
} else {
ocf_req_hash_unlock_rd(req);
}
if (lock >= 0) {
if (lock != OCF_LOCK_ACQUIRED) {