| commit | f62402828c638bc3d40d94bd1a4160fcc37db0a5 | |
| author | Matthew Dillon <dillon@apollo.backplane.com> | |
| Mon, 23 Apr 2018 07:19:46 +0000 (23 00:19 -0700) | ||
| committer | Matthew Dillon <dillon@apollo.backplane.com> | |
| Mon, 23 Apr 2018 07:19:46 +0000 (23 00:19 -0700) | ||
| tree | 46d3f5ce2ca5c802be1895b147f4229f95400ce4 | treesnapshot (tar.gz zip) |
| parent | f56151fa43e3b9a933b2c10ac2bbab0421823e12 | commitdiff |
kernel - Improve lockf performance
* Improve fcntl lockf performance with two small optimizations.
Together these add a little over 10% in non-contended
performance.
* Add a 2-entry-per-cpu range lock allocation cache. This
covers the most typical lock/unlock situations.
* Conditionalize the setting of VMAYHAVELOCKS to avoid unnecessary
atomic ops.
* Remove the clearing of VMAYHAVELOCKS. The cost in close() is
basically nothing while the cost in the lockf critical path
is several branches and an atomic op.
* Improve fcntl lockf performance with two small optimizations.
Together these add a little over 10% in non-contended
performance.
* Add a 2-entry-per-cpu range lock allocation cache. This
covers the most typical lock/unlock situations.
* Conditionalize the setting of VMAYHAVELOCKS to avoid unnecessary
atomic ops.
* Remove the clearing of VMAYHAVELOCKS. The cost in close() is
basically nothing while the cost in the lockf critical path
is several branches and an atomic op.
| sys/kern/kern_lockf.c | diffblobblamehistory |