Messages in this thread | | | Subject | Re: [patch] speed up / fix the new generic semaphore code (fix AIM7 40% regression with 2.6.26-rc1) | From | Andi Kleen <> | Date | Fri, 09 May 2008 10:29:14 +0200 |
| |
Linus Torvalds <torvalds@linux-foundation.org> writes: > > Well, it turns out that Ingo's fixed statistics actually put the real cost > in fcntl/ioctl/open/release: > > 310 down <= lock_kernel <= sys_fcntl <= system_call_after_swapgs <
That must be ->fasync? If it was file locks the lock_kernel would not be inlined into sys_fcntl. Or is that an truncated back trace?
-Andi (wondering if he should plug ->fasync_unlocked again ...)
| |