From: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
To: Mikulas Patocka <mpatocka@redhat.com>,
Alasdair G Kergon <agk@redhat.com>
Cc: "xinhui.pan" <xinhuix.pan@intel.com>,
linux-kernel@vger.kernel.org, snitzer@redhat.com,
dm-devel@redhat.com, "Liu, ShuoX" <shuox.liu@intel.com>
Subject: Re: [dm-devel] [PATCH] md/dm-ioctl.c: optimize memory allocation in copy_params
Date: Thu, 24 Jul 2014 13:53:58 +0800 [thread overview]
Message-ID: <53D09F76.80801@linux.intel.com> (raw)
In-Reply-To: <alpine.LRH.2.02.1407231307200.4177@file01.intranet.prod.int.rdu2.redhat.com>
On 2014/7/24 1:14, Mikulas Patocka wrote:
>
> On Wed, 23 Jul 2014, Alasdair G Kergon wrote:
>
>> On Wed, Jul 23, 2014 at 08:16:58AM -0400, Mikulas Patocka wrote:
>>> So, it means that you do not use device mapper at all. So, why are you
>>> trying to change memory allocation in device mapper?
>>
>> So the *test* they run is asking device-mapper to briefly reserve a 64KB
>> buffer when there is no data to report: The answer is not to run that
>> pointless test:)
>>
>> And if a single 64KB allocation really is a big deal, then patch 'vold'
>> in userspace so it doesn't ask for 64KB when it clearly doesn't need it!
>>
>> + int Devmapper::dumpState(SocketClient *c) {
>> + char *buffer = (char *) malloc(1024 * 64);
>>
>> The code has just
>> #define DEVMAPPER_BUFFER_SIZE 4096
>> for all the other dm ioctls it issues.
>>
>> Only use a larger value when it is needed i.e. if DM_BUFFER_FULL_FLAG gets set.
>>
>> Alasdair
> Device mapper shouldn't depend on allocation on any contiguous memory - it
> will fall back to vmalloc. I still can't believe that their suggested
> patch makes any difference.
>
> This pattern is being repeated over and over in the kernel - for example:
>
> if (PIDLIST_TOO_LARGE(count))
> return vmalloc(count * sizeof(pid_t));
> else
> return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
>
>
> if (is_vmalloc_addr(p))
> vfree(p);
> else
> kfree(p);
>
> - I think we should make two functions that do this operation (for example
> kvalloc and kvfree) and convert device mapper and other users to these
> functions. Then, other kernel subsystems can start to use them to fix
> memory fragmentation issues.
Thank Mikulas and Alasdair. Before sending out the patch, we know the result. :)
It's hard to balance between performance and stability.
Anyway, we would try to change seq_read.
Yanmin
next prev parent reply other threads:[~2014-07-24 5:54 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-04 10:22 [PATCH] md/dm-ioctl.c: optimize memory allocation in copy_params xinhui.pan
2014-07-08 22:39 ` [dm-devel] " Mikulas Patocka
2014-07-09 2:01 ` Zhang, Yanmin
2014-07-09 3:37 ` xinhui.pan
2014-07-09 14:53 ` Mikulas Patocka
2014-07-22 1:02 ` Zhang, Yanmin
2014-07-22 1:23 ` Alasdair G Kergon
2014-07-22 2:04 ` Alasdair G Kergon
2014-07-23 3:15 ` Zhang, Yanmin
2014-07-23 3:06 ` Zhang, Yanmin
2014-07-23 12:16 ` Mikulas Patocka
2014-07-23 12:54 ` Alasdair G Kergon
2014-07-23 17:14 ` Mikulas Patocka
2014-07-24 5:53 ` Zhang, Yanmin [this message]
2014-07-23 12:39 ` Mikulas Patocka
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=53D09F76.80801@linux.intel.com \
--to=yanmin_zhang@linux.intel.com \
--cc=agk@redhat.com \
--cc=dm-devel@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mpatocka@redhat.com \
--cc=shuox.liu@intel.com \
--cc=snitzer@redhat.com \
--cc=xinhuix.pan@intel.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).