Messages in this thread | | | Date | Tue, 31 May 2011 14:57:57 +0900 | From | Minchan Kim <> | Subject | Re: [PATCH] mm, vmstat: Use cond_resched only when !CONFIG_PREEMPT |
| |
On Tue, May 31, 2011 at 02:55:28PM +0900, Minchan Kim wrote: > On Mon, May 30, 2011 at 10:59:04PM +0600, Rakib Mullick wrote: > > commit 468fd62ed9 (vmstats: add cond_resched() to refresh_cpu_vm_stats()) added cond_resched() in refresh_cpu_vm_stats. Purpose of that patch was to allow other threads to run in non-preemptive case. This patch, makes sure that cond_resched() gets called when !CONFIG_PREEMPT is set. In a preemptiable kernel we don't need to call cond_resched(). > > > > Signed-off-by: Rakib Mullick <rakib.mullick@gmail.com> > > Let me ask questions. > > 1. What's bad if we call cond_resched on CONFIG_PREEMPT? > Is refresh_cpu_vm_stats a hot path? > 2. There is no help to call explicit scheduling point on CONFIG_PREEMPTION? > > We used cond_resched without any ifdef/endif of CONFIG_PREEMPT. > In addtion, cond_resched includes __might_sleep which is debugging help for lock. > So I hope let it be if you have a big concern. typo ^^ unless
-- Kind regards Minchan Kim
| |