Messages in this thread | | | From | riel@redhat ... | Subject | [PATCH 0/3] reduce nohz_full syscall overhead by 10% | Date | Thu, 30 Apr 2015 17:23:52 -0400 |
| |
Profiling reveals that a lot of the overhead from the nohz_full accounting seems to come not from the accounting itself, but from disabling and re-enabling interrupts.
This patch series removes the interrupt disabling & re-enabling from __acct_update_integrals, which is called on both syscall entry and exit, as well as from the user_exit called on syscall entry.
Together they speed up a benchmark that calls getpriority in a row 10 million times by about 10%:
run time system time vanilla 5.49s 2.08s __acct patch 5.21s 1.92s both patches 4.88s 1.71s
| |