Message-ID: <35FD53F367049845BC99AC72306C23D104A310D42397@CNBJMBX05.corpusers.net>
Date:	Fri, 10 Apr 2015 13:18:04 +0800
From:	"Wang, Yalin" <Yalin.Wang@...ymobile.com>
To:	'Gregory Fong' <gregory.0xf0@...il.com>,
	Mel Gorman <mgorman@...e.de>
CC:	Russell King - ARM Linux <linux@....linux.org.uk>,
	Laura Abbott <lauraa@...eaurora.org>,
	Florian Fainelli <f.fainelli@...il.com>,
	Kees Cook <keescook@...omium.org>,
	Nicolas Pitre <nico@...aro.org>,
	Catalin Marinas <catalin.marinas@....com>,
	open list <linux-kernel@...r.kernel.org>,
	"linux-arm-kernel@...ts.infradead.org" 
	<linux-arm-kernel@...ts.infradead.org>,
	"vishnu.ps@...sung.com" <vishnu.ps@...sung.com>,
	Marek Szyprowski <m.szyprowski@...sung.com>,
	Johannes Weiner <hannes@...xchg.org>
Subject: RE: [PATCH] ARM: print cma-reserved pages from show_mem

> -----Original Message-----
> From: Gregory Fong [mailto:gregory.0xf0@...il.com]
> Sent: Friday, April 10, 2015 12:36 PM
> To: Mel Gorman
> Cc: Russell King - ARM Linux; Laura Abbott; Florian Fainelli; Kees Cook;
> Nicolas Pitre; Catalin Marinas; open list; Wang, Yalin; linux-arm-
> kernel@...ts.infradead.org; vishnu.ps@...sung.com; Marek Szyprowski;
> Johannes Weiner
> Subject: Re: [PATCH] ARM: print cma-reserved pages from show_mem
> 
> On Thu, Mar 26, 2015 at 5:30 AM, Mel Gorman <mgorman@...e.de> wrote:
> > On Thu, Mar 26, 2015 at 11:46:12AM +0000, Russell King - ARM Linux wrote:
> >> <SNIP>
> >>
> >> Looking at Mel's commit, I don't see a reason why we couldn't use that
> >> solution - it gets rid of walking the page array, which has been fraught
> >> in the past due to ARM having platforms which have holes in their
> >> physical memory.
> >>
> >> We could try that solution - I don't see much downside to it.  Most of
> >> that information is as debug information for MM stuff anyway, and IMHO
> >
> > From an MM perspective, I can tell you that the information is close to
> > useless for debugging anything. It's why I ditched it in that commit and
> > AFAIK, no one has ever cared.
> >
> >> 8<===
> >> From: Russell King <rmk+kernel@....linux.org.uk>
> >> Subject: [PATCH] ARM: switch to use the generic show_mem()
> implementation
> >>
> >> Switch ARM to use the generic show_mem() implementation, which displays
> >> the statistics from the mm zone rather than walking the page arrays.
> >>
> >> Signed-off-by: Russell King <rmk+kernel@....linux.org.uk>
> >
> > If this builds, boots and sysrq-m works as expected then for what it's
> worth
> >
> > Acked-by: Mel Gorman <mgorman <mgorman@...e.de>
> 
> Tried applying this change and the equivalent for 3.14.  Comparing
> before/after on a brcmstb platform, all of the numbers still look
> right when I run sysrq-m.
> 
> Tested-by: Gregory Fong <gregory.0xf0@...il.com>
> 
> Before:
> 
> [   12.191615] SysRq : Show Memory
> [   12.194789] Mem-info:
> [   12.197069] DMA per-cpu:
> [   12.199611] CPU    0: hi:  186, btch:  31 usd: 113
> [   12.204409] HighMem per-cpu:
> [   12.207295] CPU    0: hi:   90, btch:  15 usd:  44
> [   12.212102] active_anon:734 inactive_anon:1189 isolated_anon:0
> [   12.212102]  active_file:0 inactive_file:0 isolated_file:0
> [   12.212102]  unevictable:0 dirty:0 writeback:0 unstable:0
> [   12.212102]  free:254104 slab_reclaimable:82 slab_unreclaimable:843
> [   12.212102]  mapped:429 shmem:1815 pagetables:13 bounce:0
> [   12.212102]  free_cma:4032
> [   12.243172] DMA free:754080kB min:3472kB low:4340kB high:5208kB
> active_anon:180kB inactive_anon:0kB active_file:0kB inactive_file:0kB
> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:778240kB
> managed:759252kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB
> shmem:0kB slab_reclaimable:328kB slab_unreclaimable:3372kB
> kernel_stack:240kB pagetables:12kB unstable:0kB bounce:0kB
> free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
> [   12.283257] lowmem_reserve[]: 0 0 264 264
> [   12.287349] HighMem free:262336kB min:264kB low:572kB high:884kB
> active_anon:2756kB inactive_anon:4756kB active_file:0kB
> inactive_file:0kB unevictable:0kB isolated(anon):0kB
> isolated(file):0kB present:270336kB managed:270336kB mlocked:0kB
> dirty:0kB writeback:0kB mapped:1716kB shmem:7260kB
> slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB
> pagetables:40kB unstable:0kB bounce:0kB free_cma:16128kB
> writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
> [   12.328129] lowmem_reserve[]: 0 0 0 0
> [   12.331859] DMA: 6*4kB (M) 11*8kB (UEM) 7*16kB (UEM) 6*32kB (UM)
> 4*64kB (UM) 6*128kB (UEM) 2*256kB (M) 3*512kB (UEM) 5*1024kB (UEM)
> 6*2048kB (UEM) 3*4096kB (EM) 88*8192kB (MR) = 754080kB
> [   12.348817] HighMem: 2*4kB (UM) 1*8kB (M) 1*16kB (M) 1*32kB (M)
> 0*64kB 1*128kB (U) 2*256kB (UC) 3*512kB (UMC) 2*1024kB (UC) 2*2048kB
> (UC) 2*4096kB (UC) 30*8192kB (MRC) = 262336kB
> [   12.365058] 1815 total pagecache pages
> [   12.368816] 0 pages in swap cache
> [   12.372136] Swap cache stats: add 0, delete 0, find 0/0
> [   12.377366] Free swap  = 0kB
> [   12.380251] Total swap = 0kB
> [   12.392342] 262144 pages of RAM
> [   12.395494] 254306 free pages
> [   12.398464] 4747 reserved pages
> [   12.401609] 834 slab pages
> [   12.404319] 1069 pages shared
> [   12.407290] 0 pages swap cache
> 
> After:
> 
> [    3.743999] SysRq : Show Memory
> [    3.747171] Mem-Info:
> [    3.749451] DMA per-cpu:
> [    3.751991] CPU    0: hi:  186, btch:  31 usd: 102
> [    3.756790] HighMem per-cpu:
> [    3.759678] CPU    0: hi:   90, btch:  15 usd:  27
> [    3.764486] active_anon:724 inactive_anon:1189 isolated_anon:0
> [    3.764486]  active_file:0 inactive_file:0 isolated_file:0
> [    3.764486]  unevictable:0 dirty:0 writeback:0 unstable:0
> [    3.764486]  free:254134 slab_reclaimable:81 slab_unreclaimable:842
> [    3.764486]  mapped:429 shmem:1815 pagetables:13 bounce:0
> [    3.764486]  free_cma:4032
> [    3.795556] DMA free:754080kB min:3472kB low:4340kB high:5208kB
> active_anon:208kB inactive_anon:0kB active_file:0kB inactive_file:0kB
> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:778240kB
> managed:759252kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB
> shmem:0kB slab_reclaimable:324kB slab_unreclaimable:3368kB
> kernel_stack:240kB pagetables:36kB unstable:0kB bounce:0kB
> free_cma:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
> [    3.835641] lowmem_reserve[]: 0 0 264 264
> [    3.839734] HighMem free:262456kB min:264kB low:572kB high:884kB
> active_anon:2688kB inactive_anon:4756kB active_file:0kB
> inactive_file:0kB unevictable:0kB isolated(anon):0kB
> isolated(file):0kB present:270336kB managed:270336kB mlocked:0kB
> dirty:0kB writeback:0kB mapped:1716kB shmem:7260kB
> slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB
> pagetables:16kB unstable:0kB bounce:0kB free_cma:16128kB
> writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes
> [    3.880512] lowmem_reserve[]: 0 0 0 0
> [    3.884244] DMA: 6*4kB (M) 11*8kB (UEM) 7*16kB (UEM) 6*32kB (UM)
> 4*64kB (UM) 6*128kB (UEM) 2*256kB (M) 3*512kB (UEM) 5*1024kB (UEM)
> 6*2048kB (UEM) 3*4096kB (EM) 88*8192kB (MR) = 754080kB
> [    3.901199] HighMem: 0*4kB 1*8kB (M) 1*16kB (M) 1*32kB (M) 2*64kB
> (UM) 1*128kB (U) 2*256kB (UC) 3*512kB (UMC) 2*1024kB (UC) 2*2048kB
> (UC) 2*4096kB (UC) 30*8192kB (MRC) = 262456kB
> [    3.917441] 1815 total pagecache pages
> [    3.921198] 0 pages in swap cache
> [    3.924518] Swap cache stats: add 0, delete 0, find 0/0
> [    3.929748] Free swap  = 0kB
> [    3.932632] Total swap = 0kB
> [    3.935516] 262144 pages RAM
> [    3.938401] 67584 pages HighMem/MovableOnly
> [    3.942588] 651 pages reserved
> [    3.945646] 4096 pages cma reserved
Could we also add "834 slab pages" item into generic show_mem( )
Function? It is useful, and is it equal to slab_reclaimable + slab_unreclaimable ?
If yes, I think we can add it just like what ARM does.

Thanks

Powered by blists - more mailing lists