From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: Christoph Lameter <cl@linux.com>
Cc: Tejun Heo <tj@kernel.org>, Pekka Enberg <penberg@kernel.org>,
Matt Mackall <mpm@selenic.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC PATCH 6/6] workqueue: use kmalloc_align() instead of hacking
Date: Mon, 26 Mar 2012 10:00:13 +0800 [thread overview]
Message-ID: <4F6FCDAD.4060701@cn.fujitsu.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1203210842200.20382@router.home>
On 03/21/2012 09:45 PM, Christoph Lameter wrote:
> On Wed, 21 Mar 2012, Lai Jiangshan wrote:
>
>> Yes, I don't want to build a complex kmalloc_align(). But after I found
>> that SLAB/SLUB's kmalloc-objects are natural/automatic aligned to
>> a proper big power of two. I will do nothing if I introduce kmalloc_align()
>> except just care the debugging.
>
> They are not guaranteed to be aligned to the big power of two! There are
> kmalloc caches that are not power of two. Debugging and other
> necessary meta data may change alignment in both SLAB and SLUB. SLAB needs
> a metadata structure in each page even without debugging that may cause
> alignment issues.
"Debugging and other necessary meta data" are handled in special way in my patches.
(You have already checked the patches.)
Normally, as I said, SLAB/SLUB's kmalloc-objects are natural/automatic aligned,
and my patch does not touch the general cases. Sorry for my bad reply.
>
>> And kmalloc_align() can be used in the following case:
>> o a type object need to be aligned with cache-line for it contains a frequent
>> update-part and a frequent read-part.
>> o The total number of these objects in a given type is not much, creating
>> a new slab cache for a given type will be overkill.
>>
>> This is a RFC patch and it seems mm gurus don't like it. I'm sorry I
>> bother all of you.
>
> Ideas are always welcome. Please do not get offended by our problems with
> your patch.
>
>
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: Christoph Lameter <cl@linux.com>
Cc: Tejun Heo <tj@kernel.org>, Pekka Enberg <penberg@kernel.org>,
Matt Mackall <mpm@selenic.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC PATCH 6/6] workqueue: use kmalloc_align() instead of hacking
Date: Mon, 26 Mar 2012 10:00:13 +0800 [thread overview]
Message-ID: <4F6FCDAD.4060701@cn.fujitsu.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1203210842200.20382@router.home>
On 03/21/2012 09:45 PM, Christoph Lameter wrote:
> On Wed, 21 Mar 2012, Lai Jiangshan wrote:
>
>> Yes, I don't want to build a complex kmalloc_align(). But after I found
>> that SLAB/SLUB's kmalloc-objects are natural/automatic aligned to
>> a proper big power of two. I will do nothing if I introduce kmalloc_align()
>> except just care the debugging.
>
> They are not guaranteed to be aligned to the big power of two! There are
> kmalloc caches that are not power of two. Debugging and other
> necessary meta data may change alignment in both SLAB and SLUB. SLAB needs
> a metadata structure in each page even without debugging that may cause
> alignment issues.
"Debugging and other necessary meta data" are handled in special way in my patches.
(You have already checked the patches.)
Normally, as I said, SLAB/SLUB's kmalloc-objects are natural/automatic aligned,
and my patch does not touch the general cases. Sorry for my bad reply.
>
>> And kmalloc_align() can be used in the following case:
>> o a type object need to be aligned with cache-line for it contains a frequent
>> update-part and a frequent read-part.
>> o The total number of these objects in a given type is not much, creating
>> a new slab cache for a given type will be overkill.
>>
>> This is a RFC patch and it seems mm gurus don't like it. I'm sorry I
>> bother all of you.
>
> Ideas are always welcome. Please do not get offended by our problems with
> your patch.
>
>
>
next prev parent reply other threads:[~2012-03-26 2:00 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-20 10:21 [RFC PATCH 0/6] add kmalloc_align() Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 10:21 ` [RFC PATCH 1/6] kenrel.h: add ALIGN_OF_LAST_BIT() Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 11:32 ` Michal Nazarewicz
2012-03-20 11:32 ` Michal Nazarewicz
2012-03-20 14:03 ` Alexey Dobriyan
2012-03-20 14:03 ` Alexey Dobriyan
2012-03-20 14:08 ` Christoph Lameter
2012-03-20 14:20 ` Peter Seebach
2012-03-20 14:20 ` Peter Seebach
2012-03-20 10:21 ` [RFC PATCH 2/6] slub: add kmalloc_align() Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 14:14 ` Christoph Lameter
2012-03-20 14:14 ` Christoph Lameter
2012-03-20 14:21 ` Christoph Lameter
2012-03-20 14:21 ` Christoph Lameter
2012-03-20 10:21 ` [RFC PATCH 3/6] slab: " Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 10:21 ` [RFC PATCH 4/6] slob: don't couple the header size with the alignment Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 10:21 ` [RFC PATCH 5/6] slob: add kmalloc_align() Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 10:21 ` [RFC PATCH 6/6] workqueue: use kmalloc_align() instead of hacking Lai Jiangshan
2012-03-20 10:21 ` Lai Jiangshan
2012-03-20 15:15 ` Christoph Lameter
2012-03-20 15:15 ` Christoph Lameter
2012-03-20 15:46 ` Tejun Heo
2012-03-20 15:46 ` Tejun Heo
2012-03-21 3:02 ` Lai Jiangshan
2012-03-21 3:02 ` Lai Jiangshan
2012-03-21 5:14 ` Tejun Heo
2012-03-21 5:14 ` Tejun Heo
2012-03-21 14:12 ` Patch workqueue: create new slab cache " Christoph Lameter
2012-03-21 14:12 ` Christoph Lameter
2012-03-21 14:49 ` Eric Dumazet
2012-03-21 14:49 ` Eric Dumazet
2012-03-21 15:03 ` Christoph Lameter
2012-03-21 15:03 ` Christoph Lameter
2012-03-21 16:04 ` Eric Dumazet
2012-03-21 16:04 ` Eric Dumazet
2012-03-21 17:54 ` Christoph Lameter
2012-03-21 17:54 ` Christoph Lameter
2012-03-21 18:05 ` Eric Dumazet
2012-03-21 18:05 ` Eric Dumazet
2012-03-21 18:20 ` Christoph Lameter
2012-03-21 18:20 ` Christoph Lameter
2012-03-21 16:09 ` Tejun Heo
2012-03-21 16:09 ` Tejun Heo
2012-03-21 17:56 ` Christoph Lameter
2012-03-21 17:56 ` Christoph Lameter
2012-03-21 13:45 ` [RFC PATCH 6/6] workqueue: use kmalloc_align() " Christoph Lameter
2012-03-21 13:45 ` Christoph Lameter
2012-03-26 2:00 ` Lai Jiangshan [this message]
2012-03-26 2:00 ` Lai Jiangshan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4F6FCDAD.4060701@cn.fujitsu.com \
--to=laijs@cn.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mpm@selenic.com \
--cc=penberg@kernel.org \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.