linux-kernel - Re: [PATCH 7/7] CPU controller V1

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

Date:	Tue, 22 Aug 2006 11:10:36 +0000
From:	Mike Galbraith <efault@....de>
To:	vatsa@...ibm.com
Cc:	Ingo Molnar <mingo@...e.hu>, Nick Piggin <nickpiggin@...oo.com.au>,
	Sam Vilain <sam@...ain.net>, linux-kernel@...r.kernel.org,
	Kirill Korotaev <dev@...nvz.org>,
	Balbir Singh <balbir@...ibm.com>, sekharan@...ibm.com,
	Andrew Morton <akpm@...l.org>, nagar@...son.ibm.com,
	matthltc@...ibm.com, dipankar@...ibm.com
Subject: Re: [PATCH 7/7] CPU controller V1 - (temporary) cpuset interface

On Sun, 2006-08-20 at 23:18 +0530, Srivatsa Vaddagiri wrote:

> As an example, follow these steps to create metered cpusets:
> 
> 
> 	# cd /dev
> 	# mkdir cpuset
> 	# mount -t cpuset cpuset cpuset
> 	# cd cpuset
> 	# mkdir grp_a
> 	# cd grp_a
> 	# /bin/echo "6-7" > cpus	# assign CPUs 6,7 for this cpuset
> 	# /bin/echo 0 > mems		# assign node 0 for this cpuset
> 	# /bin/echo 1 > cpu_exclusive
> 	# /bin/echo 1 > meter_cpu
> 
> 	# mkdir very_imp_grp
> 	# Assign 80% bandwidth to this group
> 	# /bin/echo 80 > very_imp_grp/cpu_quota
> 
> 	# echo $apache_webserver_pid > very_imp_grp/tasks
> 
> 	# mkdir less_imp_grp
> 	# Assign 5% bandwidth to this group
> 	# /bin/echo 5 > less_imp_grp/cpu_quota
> 
> 	# echo $mozilla_browser_pid > less_imp_grp/tasks

Doesn't seem to work here, but maybe I'm doing something wrong.

I set up cpuset "all" containing cpu 0-1 (all, 1.something cpus I have;)
exactly as you created grp_a.  I then creaded sub-groups mikeg and root,
and gave them 20% and 80% sub-group/cpu_quota respectively, and plunked
one shell in mikeg/tasks, and two in root/tasks.

In each root shell, I started a proggy that munches ~80% cpu.

top - 10:51:12 up 32 min, 10 users,  load average: 2.00, 2.81, 2.69
Tasks: 114 total,   3 running, 111 sleeping,   0 stopped,   0 zombie
Cpu(s): 79.7% us,  0.0% sy,  0.0% ni, 20.3% id,  0.0% wa,  0.0% hi,  0.0% si

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
 6503 root      15   0  1368  276  228 S   79  0.0   0:31.03 f
 6504 root      15   0  1368  280  228 R   78  0.0   0:29.17 f

I then add the same to the mikeg shell.

top - 10:54:37 up 35 min, 10 users,  load average: 3.80, 2.95, 2.74
Tasks: 115 total,   6 running, 109 sleeping,   0 stopped,   0 zombie
Cpu(s): 94.7% us,  0.5% sy,  0.0% ni,  4.8% id,  0.0% wa,  0.0% hi,  0.0% si

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
 6503 root      15   0  1368  276  228 S   65  0.0   3:12.86 f
 6505 mikeg     15   0  1368  276  228 R   64  0.0   0:11.77 f
 6504 root      16   0  1368  280  228 R   59  0.0   3:10.58 f

If I add a third to root, the percentages go to roughly 50% per.

	-Mike

-
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/