From: James A. Sutherland <jas88@cam.ac.uk>
To: Szabolcs Szakacsits <szaka@f-secure.com>
Cc: Dave McCracken <dmc@austin.ibm.com>, linux-mm@kvack.org
Subject: Re: suspend processes at load (was Re: a simple OOM ...)
Date: Sun, 22 Apr 2001 11:19:07 +0100 [thread overview]
Message-ID: <0tb5et46n2bqpos4qnhmqjvc5ni1vusv49@4ax.com> (raw)
In-Reply-To: <Pine.LNX.4.30.0104201223390.20939-100000@fs131-224.f-secure.com>
On Fri, 20 Apr 2001 14:18:34 +0200 (MET DST), you wrote:
>On Thu, 19 Apr 2001, Dave McCracken wrote:
>> --On Wednesday, April 18, 2001 23:32:25 +0200 Szabolcs Szakacsits
>> > How you want to avoid "deadlocks" when running processes have
>> > dependencies on suspended processes?
>> I think there's a semantic misunderstanding here. If I understand Rik's
>> proposal right, he's not talking about completely suspending a process ala
>> SIGSTOP. He's talking about removing it from the run queue for some small
>> length of time (ie a few seconds, probably) during which all the other
>> processes can make progress.
>
>Yes, I also didn't mean deadlocks in its classical sense this is the
>reason I put it in quote. The issue is the unexpected potentially huge
>communication latencies between processes/threads or between user and
>system. App developers do write code taking load/latency into account
>but not in mind some of their processes/threads can get suspended for
>indeterminated interval from time to time.
If some part of the multi-threaded/multi-process system overloads the
system to the point of thrashing, it has already failed, and is likely
to encounter a SIGKILL from the sysadmin - if and when the sysadmin is
able to issue a SIGKILL...
>> This kind of suspension won't be noticeable to users/administrators
>> or permanently block dependent processes. In fact, it should make
>> the system appear more responsive than one in a thrashing state.
>
>With occasionally suspended X, sshd, etc, etc, etc ;)
If sshd blows up to the point of getting suspended, it's already gone
wrong... Suspending X could happen, and would be a *GOOD* thing under
the circumstances: it would then enable you to kill the rogue
process(es) on a virtual console or network login.
James.
--
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.eu.org/Linux-MM/
next prev parent reply other threads:[~2001-04-22 10:19 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-04-12 16:58 [PATCH] a simple OOM killer to save me from Netscape Slats Grobnik
2001-04-12 18:25 ` Rik van Riel
2001-04-12 18:49 ` James A. Sutherland
2001-04-13 6:45 ` Eric W. Biederman
2001-04-13 16:20 ` Rik van Riel
2001-04-14 1:20 ` Stephen C. Tweedie
2001-04-16 21:06 ` James A. Sutherland
2001-04-16 21:40 ` Jonathan Morton
2001-04-16 22:12 ` Rik van Riel
2001-04-16 22:21 ` James A. Sutherland
2001-04-17 14:26 ` Jonathan Morton
2001-04-17 19:53 ` Rik van Riel
2001-04-17 20:44 ` James A. Sutherland
2001-04-17 20:59 ` Jonathan Morton
2001-04-17 21:09 ` James A. Sutherland
2001-04-14 7:00 ` Eric W. Biederman
2001-04-15 5:05 ` Rik van Riel
2001-04-15 5:20 ` Rik van Riel
2001-04-16 11:52 ` Szabolcs Szakacsits
2001-04-16 12:17 ` suspend processes at load (was Re: a simple OOM ...) Szabolcs Szakacsits
2001-04-17 19:48 ` Rik van Riel
2001-04-18 21:32 ` Szabolcs Szakacsits
2001-04-18 20:38 ` James A. Sutherland
2001-04-18 23:25 ` Szabolcs Szakacsits
2001-04-18 22:29 ` Rik van Riel
2001-04-19 10:14 ` Stephen C. Tweedie
2001-04-19 13:23 ` Szabolcs Szakacsits
2001-04-19 2:11 ` Rik van Riel
2001-04-19 7:08 ` James A. Sutherland
2001-04-19 13:37 ` Szabolcs Szakacsits
2001-04-19 12:26 ` Christoph Rohland
2001-04-19 12:30 ` James A. Sutherland
2001-04-19 9:15 ` James A. Sutherland
2001-04-19 18:34 ` Dave McCracken
2001-04-19 18:47 ` James A. Sutherland
2001-04-19 18:53 ` Dave McCracken
2001-04-19 19:10 ` James A. Sutherland
2001-04-20 14:58 ` Rik van Riel
2001-04-21 6:10 ` James A. Sutherland
2001-04-19 19:13 ` Rik van Riel
2001-04-19 19:47 ` Gerrit Huizenga
2001-04-20 12:44 ` Szabolcs Szakacsits
2001-04-19 20:06 ` James A. Sutherland
2001-04-20 12:29 ` Szabolcs Szakacsits
2001-04-20 11:50 ` Jonathan Morton
2001-04-20 13:32 ` Szabolcs Szakacsits
2001-04-20 14:30 ` Rik van Riel
2001-04-22 10:21 ` James A. Sutherland
2001-04-20 12:25 ` Szabolcs Szakacsits
2001-04-21 6:08 ` James A. Sutherland
2001-04-20 12:18 ` Szabolcs Szakacsits
2001-04-22 10:19 ` James A. Sutherland [this message]
2001-04-17 10:58 ` limit for number of processes Uman
2001-04-19 14:03 suspend processes at load (was Re: a simple OOM ...) Jonathan Morton
2001-04-19 18:25 ` Dave McCracken
2001-04-19 18:32 ` James A. Sutherland
2001-04-19 20:23 ` Jonathan Morton
2001-04-20 12:14 ` Szabolcs Szakacsits
2001-04-20 12:02 ` Jonathan Morton
2001-04-20 14:48 ` Dave McCracken
2001-04-21 5:49 ` James A. Sutherland
2001-04-21 19:16 ` Joseph A. Knapka
2001-04-21 19:41 ` Jonathan Morton
2001-04-22 10:08 ` James A. Sutherland
2001-04-22 16:53 ` Jonathan Morton
2001-04-22 17:06 ` James A. Sutherland
2001-04-22 18:18 ` Jonathan Morton
2001-04-22 18:57 ` Rik van Riel
2001-04-22 19:41 ` James A. Sutherland
2001-04-22 20:33 ` Jean Francois Martinez
2001-04-22 20:21 ` Jonathan Morton
2001-04-22 20:36 ` Jonathan Morton
2001-04-22 19:01 ` James A. Sutherland
2001-04-22 19:11 ` Rik van Riel
2001-04-22 20:36 ` James A. Sutherland
2001-04-22 19:30 ` Jonathan Morton
2001-04-22 20:35 ` James A. Sutherland
2001-04-22 20:41 ` Rik van Riel
2001-04-22 20:58 ` James A. Sutherland
2001-04-22 21:26 ` Rik van Riel
2001-04-22 22:26 ` Jonathan Morton
2001-04-23 5:55 ` James A. Sutherland
2001-04-23 5:59 ` Rik van Riel
2001-04-21 20:29 ` Rik van Riel
2001-04-22 10:08 ` James A. Sutherland
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=0tb5et46n2bqpos4qnhmqjvc5ni1vusv49@4ax.com \
--to=jas88@cam.ac.uk \
--cc=dmc@austin.ibm.com \
--cc=linux-mm@kvack.org \
--cc=szaka@f-secure.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