* [PATCH] zcache fix for 3.3-rc1.
@ 2012-01-23 21:52 Konrad Rzeszutek Wilk
2012-01-23 21:52 ` [PATCH] zcache: Set SWIZ_BITS to 8 to reduce tmem bucket lock contention Konrad Rzeszutek Wilk
2012-01-23 22:11 ` [PATCH] zcache fix for 3.3-rc1 Greg KH
0 siblings, 2 replies; 6+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-01-23 21:52 UTC (permalink / raw)
To: gregkh, linux-kernel, devel; +Cc: dave, cascardo, sjenning
Hey Greg,
I posted this patch some time ago [https://lkml.org/lkml/2012/1/13/253]
but I am not seeing it in you tree.
Was wondering if you could stick this patch in your tree? It fixes
a performance regressions which is quite noticable in small memory systems
where a 'swapoff' ends up taking more than it should.
Thanks!
Dan Magenheimer (1):
zcache: Set SWIZ_BITS to 8 to reduce tmem bucket lock contention.
drivers/staging/zcache/zcache-main.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH] zcache: Set SWIZ_BITS to 8 to reduce tmem bucket lock contention. 2012-01-23 21:52 [PATCH] zcache fix for 3.3-rc1 Konrad Rzeszutek Wilk @ 2012-01-23 21:52 ` Konrad Rzeszutek Wilk 2012-01-23 22:11 ` [PATCH] zcache fix for 3.3-rc1 Greg KH 1 sibling, 0 replies; 6+ messages in thread From: Konrad Rzeszutek Wilk @ 2012-01-23 21:52 UTC (permalink / raw) To: gregkh, linux-kernel, devel Cc: dave, cascardo, sjenning, Dan Magenheimer, Konrad Rzeszutek Wilk From: Dan Magenheimer <dan.magenheimer@oracle.com> SWIZ_BITS > 8 results in a much larger number of "tmem_obj" allocations, likely one per page-placed-in-frontswap. The tmem_obj is not huge (roughly 100 bytes), but it is large enough to add a not-insignificant memory overhead to zcache. The SWIZ_BITS=8 will get roughly the same lock contention without the space wastage. The effect of SWIZ_BITS can be thought of as "2^SWIZ_BITS is the number of unique oids that be generated" (This concept is limited to frontswap's use of tmem). Acked-by: Seth Jennings <sjenning@linux.vnet.ibm.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> --- drivers/staging/zcache/zcache-main.c | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index 642840c..9c011b7 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -1782,9 +1782,9 @@ static int zcache_frontswap_poolid = -1; * Swizzling increases objects per swaptype, increasing tmem concurrency * for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS * Setting SWIZ_BITS to 27 basically reconstructs the swap entry from - * frontswap_get_page() + * frontswap_get_page(), but has side-effects. Hence using 8. */ -#define SWIZ_BITS 27 +#define SWIZ_BITS 8 #define SWIZ_MASK ((1 << SWIZ_BITS) - 1) #define _oswiz(_type, _ind) ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK)) #define iswiz(_ind) (_ind >> SWIZ_BITS) -- 1.7.7.5 ^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH] zcache fix for 3.3-rc1. 2012-01-23 21:52 [PATCH] zcache fix for 3.3-rc1 Konrad Rzeszutek Wilk 2012-01-23 21:52 ` [PATCH] zcache: Set SWIZ_BITS to 8 to reduce tmem bucket lock contention Konrad Rzeszutek Wilk @ 2012-01-23 22:11 ` Greg KH 2012-01-23 22:22 ` Konrad Rzeszutek Wilk 1 sibling, 1 reply; 6+ messages in thread From: Greg KH @ 2012-01-23 22:11 UTC (permalink / raw) To: Konrad Rzeszutek Wilk; +Cc: linux-kernel, devel, dave, cascardo, sjenning On Mon, Jan 23, 2012 at 04:52:19PM -0500, Konrad Rzeszutek Wilk wrote: > Hey Greg, > > I posted this patch some time ago [https://lkml.org/lkml/2012/1/13/253] > but I am not seeing it in you tree. Did you copy me on it? I don't see it anywhere in my to-apply queues. > Was wondering if you could stick this patch in your tree? It fixes > a performance regressions which is quite noticable in small memory systems > where a 'swapoff' ends up taking more than it should. So this is needed for 3.3? How about older kernels? 3.2? 3.0? thanks, greg k-h ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] zcache fix for 3.3-rc1. 2012-01-23 22:11 ` [PATCH] zcache fix for 3.3-rc1 Greg KH @ 2012-01-23 22:22 ` Konrad Rzeszutek Wilk 2012-01-23 22:35 ` Greg KH 0 siblings, 1 reply; 6+ messages in thread From: Konrad Rzeszutek Wilk @ 2012-01-23 22:22 UTC (permalink / raw) To: Greg KH; +Cc: linux-kernel, devel, dave, cascardo, sjenning On Mon, Jan 23, 2012 at 02:11:55PM -0800, Greg KH wrote: > On Mon, Jan 23, 2012 at 04:52:19PM -0500, Konrad Rzeszutek Wilk wrote: > > Hey Greg, > > > > I posted this patch some time ago [https://lkml.org/lkml/2012/1/13/253] > > but I am not seeing it in you tree. > > Did you copy me on it? I don't see it anywhere in my to-apply queues. Ugh, I did not - I seemed to have forgotten to CC you and had assumed you would be omnipresent and would magically pick it up. Sorry about that mishap. > > > Was wondering if you could stick this patch in your tree? It fixes > > a performance regressions which is quite noticable in small memory systems > > where a 'swapoff' ends up taking more than it should. > > So this is needed for 3.3? How about older kernels? 3.2? 3.0? That would be splendid if you could stick it on the stable tree :-) > > thanks, > > greg k-h ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] zcache fix for 3.3-rc1. 2012-01-23 22:22 ` Konrad Rzeszutek Wilk @ 2012-01-23 22:35 ` Greg KH 2012-01-23 22:40 ` Konrad Rzeszutek Wilk 0 siblings, 1 reply; 6+ messages in thread From: Greg KH @ 2012-01-23 22:35 UTC (permalink / raw) To: Konrad Rzeszutek Wilk; +Cc: linux-kernel, devel, dave, cascardo, sjenning On Mon, Jan 23, 2012 at 05:22:38PM -0500, Konrad Rzeszutek Wilk wrote: > On Mon, Jan 23, 2012 at 02:11:55PM -0800, Greg KH wrote: > > On Mon, Jan 23, 2012 at 04:52:19PM -0500, Konrad Rzeszutek Wilk wrote: > > > Hey Greg, > > > > > > I posted this patch some time ago [https://lkml.org/lkml/2012/1/13/253] > > > but I am not seeing it in you tree. > > > > Did you copy me on it? I don't see it anywhere in my to-apply queues. > > Ugh, I did not - I seemed to have forgotten to CC you and had assumed you > would be omnipresent and would magically pick it up. Sorry about that mishap. Hm, I must be slipping, I should have caught that :) > > > Was wondering if you could stick this patch in your tree? It fixes > > > a performance regressions which is quite noticable in small memory systems > > > where a 'swapoff' ends up taking more than it should. > > > > So this is needed for 3.3? How about older kernels? 3.2? 3.0? > > That would be splendid if you could stick it on the stable tree :-) Which one(s)? thanks, greg k-h ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH] zcache fix for 3.3-rc1. 2012-01-23 22:35 ` Greg KH @ 2012-01-23 22:40 ` Konrad Rzeszutek Wilk 0 siblings, 0 replies; 6+ messages in thread From: Konrad Rzeszutek Wilk @ 2012-01-23 22:40 UTC (permalink / raw) To: Greg KH; +Cc: linux-kernel, devel, dave, cascardo, sjenning On Mon, Jan 23, 2012 at 02:35:08PM -0800, Greg KH wrote: > On Mon, Jan 23, 2012 at 05:22:38PM -0500, Konrad Rzeszutek Wilk wrote: > > On Mon, Jan 23, 2012 at 02:11:55PM -0800, Greg KH wrote: > > > On Mon, Jan 23, 2012 at 04:52:19PM -0500, Konrad Rzeszutek Wilk wrote: > > > > Hey Greg, > > > > > > > > I posted this patch some time ago [https://lkml.org/lkml/2012/1/13/253] > > > > but I am not seeing it in you tree. > > > > > > Did you copy me on it? I don't see it anywhere in my to-apply queues. > > > > Ugh, I did not - I seemed to have forgotten to CC you and had assumed you > > would be omnipresent and would magically pick it up. Sorry about that mishap. > > Hm, I must be slipping, I should have caught that :) Tsk tsk .. :-) > > > > > Was wondering if you could stick this patch in your tree? It fixes > > > > a performance regressions which is quite noticable in small memory systems > > > > where a 'swapoff' ends up taking more than it should. > > > > > > So this is needed for 3.3? How about older kernels? 3.2? 3.0? > > > > That would be splendid if you could stick it on the stable tree :-) > > Which one(s)? 3.2 please. ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2012-01-23 22:42 UTC | newest] Thread overview: 6+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2012-01-23 21:52 [PATCH] zcache fix for 3.3-rc1 Konrad Rzeszutek Wilk 2012-01-23 21:52 ` [PATCH] zcache: Set SWIZ_BITS to 8 to reduce tmem bucket lock contention Konrad Rzeszutek Wilk 2012-01-23 22:11 ` [PATCH] zcache fix for 3.3-rc1 Greg KH 2012-01-23 22:22 ` Konrad Rzeszutek Wilk 2012-01-23 22:35 ` Greg KH 2012-01-23 22:40 ` Konrad Rzeszutek Wilk
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox