mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH] Cpuset: memory_spread_slab drop useless PF_SPREAD_PAGE check
@ 2006-03-19  8:57 Paul Jackson
  0 siblings, 0 replies; only message in thread
From: Paul Jackson @ 2006-03-19  8:57 UTC (permalink / raw)
  To: Andrew Morton; +Cc: Simon.Derr, Paul Jackson, linux-kernel

From: Paul Jackson <pj@sgi.com>

The hook in the slab cache allocation path to handle cpuset
memory spreading for tasks in cpusets with 'memory_spread_slab'
enabled has a modest performance bug.  The hook calls into
the memory spreading handler alternate_node_alloc() if either of
'memory_spread_slab' or 'memory_spread_page' is enabled, even
though the handler does nothing (albeit harmlessly) for the page
case

Fix - drop PF_SPREAD_PAGE from the set of flag bits that are
used to trigger a call to alternate_node_alloc().

The page case is handled by separate hooks -- see the calls
conditioned on cpuset_do_page_mem_spread() in mm/filemap.c

Signed-off-by: Paul Jackson <pj@sgi.com>

---

 mm/slab.c |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

--- 2.6.16-rc6-mm2.orig/mm/slab.c	2006-03-18 17:30:15.254950360 -0800
+++ 2.6.16-rc6-mm2/mm/slab.c	2006-03-18 21:40:42.465283732 -0800
@@ -2835,8 +2835,7 @@ static inline void *____cache_alloc(stru
 	struct array_cache *ac;
 
 #ifdef CONFIG_NUMA
-	if (unlikely(current->flags & (PF_SPREAD_PAGE | PF_SPREAD_SLAB |
-							PF_MEMPOLICY))) {
+	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
 		objp = alternate_node_alloc(cachep, flags);
 		if (objp != NULL)
 			return objp;
@@ -2875,7 +2874,7 @@ static __always_inline void *__cache_all
 
 #ifdef CONFIG_NUMA
 /*
- * Try allocating on another node if PF_SPREAD_PAGE|PF_SPREAD_SLAB|PF_MEMPOLICY.
+ * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
  *
  * If we are in_interrupt, then process context, including cpusets and
  * mempolicy, may not apply and should not be used for allocation policy.

-- 
                          I won't rest till it's the best ...
                          Programmer, Linux Scalability
                          Paul Jackson <pj@sgi.com> 1.650.933.1373

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2006-03-19  8:58 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-03-19  8:57 [PATCH] Cpuset: memory_spread_slab drop useless PF_SPREAD_PAGE check Paul Jackson

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome