![]() | |||||||||||
Messages in this thread Complete thread (EXPERIMENTAL) |
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 ...) | ||||||||||
![]() | |||||||||||
| Last update: 2008-05-09 10:33 [W:0.927 / U:0.130 seconds] ©2003-2005 Jasper Spaans | |||||||||||