linux-kernel - Re: [PATCH] hugepage: allow parallelization of the hugepage fault path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <51EE2B16.3020605@gmail.com>
Date:	Tue, 23 Jul 2013 15:04:54 +0800
From:	Hush Bensen <hush.bensen@...il.com>
To:	Joonsoo Kim <iamjoonsoo.kim@....com>
CC:	Davidlohr Bueso <davidlohr.bueso@...com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	David Gibson <david@...son.dropbear.id.au>,
	Hugh Dickins <hughd@...gle.com>,
	Rik van Riel <riel@...hat.com>,
	Michel Lespinasse <walken@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Konstantin Khlebnikov <khlebnikov@...nvz.org>,
	Michal Hocko <mhocko@...e.cz>,
	"AneeshKumarK.V" <aneesh.kumar@...ux.vnet.ibm.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	Hillf Danton <dhillf@...il.com>, linux-mm@...ck.org,
	LKML <linux-kernel@...r.kernel.org>,
	Eric B Munson <emunson@...bm.net>,
	Anton Blanchard <anton@...ba.org>
Subject: Re: [PATCH] hugepage: allow parallelization of the hugepage fault
 path

On 07/18/2013 05:07 PM, Joonsoo Kim wrote:
> On Wed, Jul 17, 2013 at 12:50:25PM -0700, Davidlohr Bueso wrote:
>
>> From: Davidlohr Bueso <davidlohr.bueso@...com>
>>
>> - Cleaned up and forward ported to Linus' latest.
>> - Cache aligned mutexes.
>> - Keep non SMP systems using a single mutex.
>>
>> It was found that this mutex can become quite contended
>> during the early phases of large databases which make use of huge pages - for instance
>> startup and initial runs. One clear example is a 1.5Gb Oracle database, where lockstat
>> reports that this mutex can be one of the top 5 most contended locks in the kernel during
>> the first few minutes:
>>
>>      	     hugetlb_instantiation_mutex:   10678     10678
>>               ---------------------------
>>               hugetlb_instantiation_mutex    10678  [<ffffffff8115e14e>] hugetlb_fault+0x9e/0x340
>>               ---------------------------
>>               hugetlb_instantiation_mutex    10678  [<ffffffff8115e14e>] hugetlb_fault+0x9e/0x340
>>
>> contentions:          10678
>> acquisitions:         99476
>> waittime-total: 76888911.01 us
> Hello,
> I have a question :)
>
> So, each contention takes 7.6 ms in your result.
> Do you map this area with VM_NORESERVE?
> If we map with VM_RESERVE, when page fault, we just dequeue a huge page from a queue and clear
> a page and then map it to a page table. So I guess, it shouldn't take so long.

I don't think there is clear page operation after dequeue huge page, 
actually it's even not done during hugetlb_reserve_pages, do you know 
why? There is just clear operation in hugetlb_no_page.

> I'm wondering why it takes so long.
>
> And do you use 16KB-size hugepage?
> If so, region handling could takes some times. If you access the area as random order,
> the number of region can be more than 90000. I guess, this can be one reason to too long
> waittime.
>
> Thanks.
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@...ck.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@...ck.org"> email@...ck.org </a>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/