Nick Piggin beed33a816 [PATCH] sched: likely profiling ... This likely profiling is pretty fun. I found a few possible problems in sched.c. This patch may be not measurable, but when I did measure long ago, nooping (un)likely cost a couple of % on scheduler heavy benchmarks, so it all adds up. Tweak some branch hints: - the 2nd 64 bits in the bitmask is likely to be populated, because it contains the first 28 bits (nearly 3/4) of the normal priorities. (ratio of 669669:691 ~= 1000:1). - it isn't unlikely that context switching switches to another process. it might be very rapidly switching to and from the idle process (ratio of 475815:419004 and 471330:423544). Let the branch predictor decide. - preempt_enable seems to be very often called in a nested preempt_disable or with interrupts disabled (ratio of 3567760:87965 ~= 40:1) Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Daniel Walker <dwalker@mvista.com> Cc: Hua Zhong <hzhong@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>		2006-10-11 11:14:22 -07:00
..
bitops	[PATCH] sched: likely profiling	2006-10-11 11:14:22 -07:00
4level-fixup.h	[PATCH] Standardize pxx_page macros	2006-09-26 08:48:51 -07:00
atomic.h
audit_change_attr.h	[PATCH] fix missing ifdefs in syscall classes hookup for generic targets	2006-09-22 17:48:56 -07:00
audit_dir_write.h	[PATCH] fix missing ifdefs in syscall classes hookup for generic targets	2006-09-22 17:48:56 -07:00
audit_read.h	[PATCH] audit: more syscall classes added	2006-09-11 13:32:27 -04:00
audit_write.h	[PATCH] audit: more syscall classes added	2006-09-11 13:32:27 -04:00
bitops.h
bug.h	[PATCH] Fix WARN_ON / WARN_ON_ONCE regression	2006-10-06 08:53:39 -07:00
cputime.h	[CPUFREQ] Remove slowdown from ondemand sampling path.	2006-06-30 01:29:47 -04:00
div64.h
dma-mapping-broken.h
dma-mapping.h
emergency-restart.h
errno-base.h
errno.h
fcntl.h
futex.h
ide_iops.h
ioctl.h
iomap.h
ipc.h
irq_regs.h	IRQ: Maintain regs pointer globally rather than passing to IRQ handlers	2006-10-05 15:10:12 +01:00
Kbuild	[HEADERS] One line per header in Kbuild files to reduce conflicts	2006-09-19 12:43:58 +01:00
Kbuild.asm	[HEADERS] One line per header in Kbuild files to reduce conflicts	2006-09-19 12:43:58 +01:00
libata-portmap.h	[PATCH] libata: rework legacy handling to remove much of the cruft	2006-08-10 16:59:10 +09:00
local.h
memory_model.h	[PATCH] squash duplicate page_to_pfn and pfn_to_page	2006-06-23 07:42:47 -07:00
mman.h
mutex-dec.h	fix file specification in comments	2006-10-03 23:01:26 +02:00
mutex-null.h	fix file specification in comments	2006-10-03 23:01:26 +02:00
mutex-xchg.h	fix file specification in comments	2006-10-03 23:01:26 +02:00
page.h
pci-dma-compat.h
pci.h
percpu.h	[PATCH] Fix typo in "syntax error if percpu macros are incorrectly used" patch	2006-10-06 08:53:41 -07:00
pgtable-nopmd.h	[PATCH] Standardize pxx_page macros	2006-09-26 08:48:51 -07:00
pgtable-nopud.h	[PATCH] Standardize pxx_page macros	2006-09-26 08:48:51 -07:00
pgtable.h	[PATCH] paravirt: remove set pte atomic	2006-10-01 00:39:34 -07:00
resource.h
rtc.h	fix file specification in comments	2006-10-03 23:01:26 +02:00
sections.h	[PATCH] add __[start|end]_rodata sections to asm-generic/sections.h	2006-07-01 09:56:03 -07:00
siginfo.h
signal.h
statfs.h
termios.h
tlb.h	fix file specification in comments	2006-10-03 23:01:26 +02:00
topology.h
uaccess.h
unaligned.h
vmlinux.lds.h	[PATCH] Include __param section in read-only data range	2006-09-27 08:26:19 -07:00
xor.h