From: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>,
Manfred Spraul <manfred@colorfullife.com>,
aswin@hp.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
"Gotou, Yasunori" <y-goto@jp.fujitsu.com>,
chenhanxiao <chenhanxiao@cn.fujitsu.com>,
Gao feng <gaofeng@cn.fujitsu.com>
Subject: Re: [PATCH] ipc,shm: increase default size for shmmax
Date: Wed, 02 Apr 2014 10:02:36 +0900 [thread overview]
Message-ID: <533B61AC.7090808@jp.fujitsu.com> (raw)
In-Reply-To: <20140401121920.50d1dd96c2145acc81561b82@linux-foundation.org>
(2014/04/02 4:19), Andrew Morton wrote:
> On Tue, 01 Apr 2014 15:29:05 +0900 Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:
>
>>>
>>> So their system will act as if they had set SHMMAX=enormous. What
>>> problems could that cause?
>>>
>>>
>>> Look. The 32M thing is causing problems. Arbitrarily increasing the
>>> arbitrary 32M to an arbitrary 128M won't fix anything - we still have
>>> the problem. Think bigger, please: how can we make this problem go
>>> away for ever?
>>>
>>
>> Our middleware engineers has been complaining about this sysctl limit.
>> System administrator need to calculate required sysctl value by making sum
>> of all planned middlewares, and middleware provider needs to write "please
>> calculate systcl param by....." in their installation manuals.
>
> Why aren't people just setting the sysctl to a petabyte? What problems
> would that lead to?
>
They(and admin) don't know the fact, setting petabytes won't cause any pain.
In their thinking:
==
If there is a kernel's limit, it should have some (bad) side-effect and
the trade-off which must be handled by admin is represented by the limit.
In this case, they think setting this value large will consume tons of resource.
==
They don't care kernel's implemenation but takes care of what API says.
Of course, always I was asked, I answer set it to peta-bytes. But the fact
*default is small* makes them doubtful.
Thanks,
-Kame
--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>,
Manfred Spraul <manfred@colorfullife.com>,
aswin@hp.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
"Gotou, Yasunori" <y-goto@jp.fujitsu.com>,
chenhanxiao <chenhanxiao@cn.fujitsu.com>,
Gao feng <gaofeng@cn.fujitsu.com>
Subject: Re: [PATCH] ipc,shm: increase default size for shmmax
Date: Wed, 02 Apr 2014 10:02:36 +0900 [thread overview]
Message-ID: <533B61AC.7090808@jp.fujitsu.com> (raw)
In-Reply-To: <20140401121920.50d1dd96c2145acc81561b82@linux-foundation.org>
(2014/04/02 4:19), Andrew Morton wrote:
> On Tue, 01 Apr 2014 15:29:05 +0900 Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:
>
>>>
>>> So their system will act as if they had set SHMMAX=enormous. What
>>> problems could that cause?
>>>
>>>
>>> Look. The 32M thing is causing problems. Arbitrarily increasing the
>>> arbitrary 32M to an arbitrary 128M won't fix anything - we still have
>>> the problem. Think bigger, please: how can we make this problem go
>>> away for ever?
>>>
>>
>> Our middleware engineers has been complaining about this sysctl limit.
>> System administrator need to calculate required sysctl value by making sum
>> of all planned middlewares, and middleware provider needs to write "please
>> calculate systcl param by....." in their installation manuals.
>
> Why aren't people just setting the sysctl to a petabyte? What problems
> would that lead to?
>
They(and admin) don't know the fact, setting petabytes won't cause any pain.
In their thinking:
==
If there is a kernel's limit, it should have some (bad) side-effect and
the trade-off which must be handled by admin is represented by the limit.
In this case, they think setting this value large will consume tons of resource.
==
They don't care kernel's implemenation but takes care of what API says.
Of course, always I was asked, I answer set it to peta-bytes. But the fact
*default is small* makes them doubtful.
Thanks,
-Kame
next prev parent reply other threads:[~2014-04-02 1:03 UTC|newest]
Thread overview: 114+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-31 3:06 [PATCH] ipc,shm: increase default size for shmmax Davidlohr Bueso
2014-03-31 3:06 ` Davidlohr Bueso
2014-03-31 21:32 ` Andrew Morton
2014-03-31 21:32 ` Andrew Morton
2014-03-31 22:59 ` Davidlohr Bueso
2014-03-31 22:59 ` Davidlohr Bueso
2014-03-31 23:13 ` Andrew Morton
2014-03-31 23:13 ` Andrew Morton
2014-03-31 23:25 ` Davidlohr Bueso
2014-03-31 23:25 ` Davidlohr Bueso
2014-04-01 0:05 ` Andrew Morton
2014-04-01 0:05 ` Andrew Morton
2014-04-01 6:29 ` Kamezawa Hiroyuki
2014-04-01 6:29 ` Kamezawa Hiroyuki
2014-04-01 19:19 ` Andrew Morton
2014-04-01 19:19 ` Andrew Morton
2014-04-01 20:15 ` KOSAKI Motohiro
2014-04-01 20:15 ` KOSAKI Motohiro
2014-04-01 20:26 ` Davidlohr Bueso
2014-04-01 20:26 ` Davidlohr Bueso
2014-04-02 0:11 ` Kamezawa Hiroyuki
2014-04-02 0:11 ` Kamezawa Hiroyuki
2014-04-02 1:02 ` Kamezawa Hiroyuki [this message]
2014-04-02 1:02 ` Kamezawa Hiroyuki
2014-04-02 14:55 ` One Thousand Gnomes
2014-04-02 14:55 ` One Thousand Gnomes
2014-04-02 23:47 ` Kamezawa Hiroyuki
2014-04-02 23:47 ` Kamezawa Hiroyuki
2014-04-01 17:01 ` Davidlohr Bueso
2014-04-01 17:01 ` Davidlohr Bueso
2014-04-01 18:10 ` KOSAKI Motohiro
2014-04-01 18:10 ` KOSAKI Motohiro
2014-04-01 18:31 ` Davidlohr Bueso
2014-04-01 18:31 ` Davidlohr Bueso
2014-04-01 19:51 ` KOSAKI Motohiro
2014-04-01 19:51 ` KOSAKI Motohiro
2014-04-01 21:01 ` Davidlohr Bueso
2014-04-01 21:01 ` Davidlohr Bueso
2014-04-01 21:12 ` KOSAKI Motohiro
2014-04-01 21:12 ` KOSAKI Motohiro
2014-04-01 21:29 ` Andrew Morton
2014-04-01 21:29 ` Andrew Morton
2014-04-01 21:41 ` KOSAKI Motohiro
2014-04-01 21:41 ` KOSAKI Motohiro
2014-04-01 21:48 ` Andrew Morton
2014-04-01 21:48 ` Andrew Morton
2014-04-01 22:02 ` Davidlohr Bueso
2014-04-01 22:02 ` Davidlohr Bueso
2014-04-01 22:08 ` Andrew Morton
2014-04-01 22:08 ` Andrew Morton
2014-04-13 18:05 ` Manfred Spraul
2014-04-13 18:05 ` Manfred Spraul
2014-04-13 23:15 ` Davidlohr Bueso
2014-04-13 23:15 ` Davidlohr Bueso
2014-04-16 22:46 ` Andrew Morton
2014-04-16 22:46 ` Andrew Morton
2014-04-16 23:19 ` Davidlohr Bueso
2014-04-16 23:19 ` Davidlohr Bueso
2014-04-17 10:41 ` Michael Kerrisk
2014-04-17 10:41 ` Michael Kerrisk
2014-04-17 16:41 ` Manfred Spraul
2014-04-17 16:41 ` Manfred Spraul
2014-04-17 20:19 ` Michael Kerrisk (man-pages)
2014-04-17 20:19 ` Michael Kerrisk (man-pages)
2014-04-01 22:49 ` KOSAKI Motohiro
2014-04-01 22:49 ` KOSAKI Motohiro
2014-04-01 23:28 ` Davidlohr Bueso
2014-04-01 23:28 ` Davidlohr Bueso
2014-04-01 23:56 ` KOSAKI Motohiro
2014-04-01 23:56 ` KOSAKI Motohiro
2014-04-02 0:40 ` Davidlohr Bueso
2014-04-02 0:40 ` Davidlohr Bueso
2014-04-02 1:08 ` Greg Thelen
2014-04-02 1:08 ` Greg Thelen
2014-04-02 1:58 ` Kamezawa Hiroyuki
2014-04-02 1:58 ` Kamezawa Hiroyuki
2014-04-02 2:11 ` Greg Thelen
2014-04-02 2:11 ` Greg Thelen
2014-04-03 0:20 ` [PATCH] ipc,shm: disable shmmax and shmall by default Davidlohr Bueso
2014-04-03 0:20 ` Davidlohr Bueso
2014-04-03 14:07 ` Kamezawa Hiroyuki
2014-04-03 14:07 ` Kamezawa Hiroyuki
2014-04-03 19:02 ` Manfred Spraul
2014-04-03 19:02 ` Manfred Spraul
2014-04-03 19:50 ` Davidlohr Bueso
2014-04-03 19:50 ` Davidlohr Bueso
2014-04-03 23:39 ` KOSAKI Motohiro
2014-04-03 23:39 ` KOSAKI Motohiro
2014-04-04 5:00 ` Davidlohr Bueso
2014-04-04 5:00 ` Davidlohr Bueso
2014-04-05 18:24 ` KOSAKI Motohiro
2014-04-05 18:24 ` KOSAKI Motohiro
2014-04-06 6:42 ` Manfred Spraul
2014-04-06 6:42 ` Manfred Spraul
2014-04-06 16:54 ` Davidlohr Bueso
2014-04-06 16:54 ` Davidlohr Bueso
2014-04-03 22:29 ` KOSAKI Motohiro
2014-04-03 22:29 ` KOSAKI Motohiro
2014-04-03 23:47 ` KOSAKI Motohiro
2014-04-03 23:47 ` KOSAKI Motohiro
2014-04-11 18:28 ` Manfred Spraul
2014-04-11 18:28 ` Manfred Spraul
2014-04-11 20:27 ` Davidlohr Bueso
2014-04-11 20:27 ` Davidlohr Bueso
2014-04-11 20:48 ` Davidlohr Bueso
2014-04-11 20:48 ` Davidlohr Bueso
2014-04-12 8:50 ` Manfred Spraul
2014-04-12 8:50 ` Manfred Spraul
2014-04-12 15:33 ` Davidlohr Bueso
2014-04-12 15:33 ` Davidlohr Bueso
2014-04-01 21:43 ` [PATCH] ipc,shm: increase default size for shmmax Davidlohr Bueso
2014-04-01 21:43 ` Davidlohr Bueso
2014-04-01 19:26 ` Andrew Morton
2014-04-01 19:26 ` Andrew Morton
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=533B61AC.7090808@jp.fujitsu.com \
--to=kamezawa.hiroyu@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=aswin@hp.com \
--cc=chenhanxiao@cn.fujitsu.com \
--cc=davidlohr@hp.com \
--cc=gaofeng@cn.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=manfred@colorfullife.com \
--cc=y-goto@jp.fujitsu.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 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.