Messages in this thread | | | Subject | Re: [PATCH 03/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled | From | Vlastimil Babka <> | Date | Thu, 1 Oct 2015 09:35:49 +0200 |
| |
On 10/01/2015 12:22 AM, David Rientjes wrote: > On Mon, 21 Sep 2015, Mel Gorman wrote: >> @@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void) >> */ >> static inline bool read_mems_allowed_retry(unsigned int seq) >> { >> + if (!cpusets_enabled()) >> + return false; >> + >> return read_seqcount_retry(¤t->mems_allowed_seq, seq); >> } >> > > I thought this was going to test nr_cpusets() <= 1?
That was another patch in prior iteration of the series, but turns out it was unnecessary, because cpusets_enabled() is already only true when nr_cpusets() > 1 - see https://lkml.org/lkml/2015/8/25/300
| |