From: Marcelo Tosatti <mtosatti@redhat.com>
To: "Auld, Will" <will.auld@intel.com>
Cc: "Shivappa, Vikas" <vikas.shivappa@intel.com>,
Vikas Shivappa <vikas.shivappa@linux.intel.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"x86@kernel.org" <x86@kernel.org>,
"hpa@zytor.com" <hpa@zytor.com>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"mingo@kernel.org" <mingo@kernel.org>,
"tj@kernel.org" <tj@kernel.org>,
"peterz@infradead.org" <peterz@infradead.org>,
"Fleming, Matt" <matt.fleming@intel.com>,
"Williamson, Glenn P" <glenn.p.williamson@intel.com>,
"Juvva, Kanaka D" <kanaka.d.juvva@intel.com>
Subject: Re: [PATCH 3/9] x86/intel_rdt: Cache Allocation documentation and cgroup usage guide
Date: Wed, 29 Jul 2015 16:32:08 -0300 [thread overview]
Message-ID: <20150729193208.GC3201@amt.cnet> (raw)
In-Reply-To: <96EC5A4F3149B74492D2D9B9B1602C27461EB932@ORSMSX105.amr.corp.intel.com>
On Wed, Jul 29, 2015 at 01:28:38AM +0000, Auld, Will wrote:
> > > Whenever cgroupE has zero tasks, remove exclusivity (by allowing other
> > > cgroups to use the exclusive ways of it).
> >
> > Same comment as above - Cgroup masks can always overlap and other cgroups
> > can allocate the same cache , and hence wont have exclusive cache allocation.
>
> [Auld, Will] You can define all the cbm to provide one clos with an exclusive area
>
> >
> > So natuarally the cgroup with tasks would get to use the cache if it has the same
> > mask (say representing 50% of cache in your example) as others .
>
> [Auld, Will] automatic adjustment of the cbm make me nervous. There are times
> when we want to limit the cache for a process independent of whether there is
> lots of unused cache.
How about this:
desiredclos (closid p1 p2 p3 p4)
1 1 0 0 0
2 0 0 0 1
3 0 1 1 0
p means part.
closid 1 is a exclusive cgroup.
closid 2 is a "cache hog" class.
closid 3 is "default closid".
Desiredclos is what user has specified.
Transition 1: desiredclos --> effectiveclos
Clean all bits of unused closid's
(that must be updated whenever a
closid1 cgroup goes from empty->nonempty
and vice-versa).
effectiveclos (closid p1 p2 p3 p4)
1 0 0 0 0
2 0 0 0 1
3 0 1 1 0
Transition 2: effectiveclos --> expandedclos
expandedclos (closid p1 p2 p3 p4)
1 0 0 0 0
2 0 0 0 1
3 1 1 1 0
Then you have different inplacecos for each
CPU (see pseudo-code below):
On the following events.
- task migration to new pCPU:
- task creation:
id = smp_processor_id();
for (part = desiredclos.p1; ...; part++)
/* if my cosid is set and any other
cosid is clear, for the part,
synchronize desiredclos --> inplacecos */
if (part[mycosid] == 1 &&
part[any_othercosid] == 0)
wrmsr(part, desiredclos);
next prev parent reply other threads:[~2015-07-29 19:32 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-01 22:21 [PATCH V12 0/9] Hot cpu handling changes to cqm, rapl and Intel Cache Allocation support Vikas Shivappa
2015-07-01 22:21 ` [PATCH 1/9] x86/intel_cqm: Modify hot cpu notification handling Vikas Shivappa
2015-07-29 16:44 ` Peter Zijlstra
2015-07-31 23:19 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 2/9] x86/intel_rapl: Modify hot cpu notification handling for RAPL Vikas Shivappa
2015-07-01 22:21 ` [PATCH 3/9] x86/intel_rdt: Cache Allocation documentation and cgroup usage guide Vikas Shivappa
2015-07-28 14:54 ` Peter Zijlstra
2015-08-04 20:41 ` Vikas Shivappa
2015-07-28 23:15 ` Marcelo Tosatti
2015-07-29 0:06 ` Vikas Shivappa
2015-07-29 1:28 ` Auld, Will
2015-07-29 19:32 ` Marcelo Tosatti [this message]
2015-07-30 17:47 ` Vikas Shivappa
2015-07-30 20:08 ` Marcelo Tosatti
2015-07-31 15:34 ` Marcelo Tosatti
2015-08-02 15:48 ` Martin Kletzander
2015-08-03 15:13 ` Marcelo Tosatti
2015-08-03 18:22 ` Vikas Shivappa
2015-07-30 20:22 ` Marcelo Tosatti
2015-07-30 23:03 ` Vikas Shivappa
2015-07-31 14:45 ` Marcelo Tosatti
2015-07-31 16:41 ` [summary] " Vikas Shivappa
2015-07-31 18:38 ` Marcelo Tosatti
2015-07-29 20:07 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 4/9] x86/intel_rdt: Add support for Cache Allocation detection Vikas Shivappa
2015-07-28 16:25 ` Peter Zijlstra
2015-07-28 22:07 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 5/9] x86/intel_rdt: Add new cgroup and Class of service management Vikas Shivappa
2015-07-28 17:06 ` Peter Zijlstra
2015-07-30 18:01 ` Vikas Shivappa
2015-07-28 17:17 ` Peter Zijlstra
2015-07-30 18:10 ` Vikas Shivappa
2015-07-30 19:44 ` Tejun Heo
2015-07-31 15:12 ` Marcelo Tosatti
2015-08-02 16:23 ` Tejun Heo
2015-08-03 20:32 ` Marcelo Tosatti
2015-08-04 12:55 ` Marcelo Tosatti
2015-08-04 18:36 ` Tejun Heo
2015-08-04 18:32 ` Tejun Heo
2015-07-31 16:24 ` Vikas Shivappa
2015-08-02 16:31 ` Tejun Heo
2015-08-04 18:50 ` Vikas Shivappa
2015-08-04 19:03 ` Tejun Heo
2015-08-05 2:21 ` Vikas Shivappa
2015-08-05 15:46 ` Tejun Heo
2015-08-06 20:58 ` Vikas Shivappa
2015-08-07 14:48 ` Tejun Heo
2015-08-05 12:22 ` Matt Fleming
2015-08-05 16:10 ` Tejun Heo
2015-08-06 0:24 ` Marcelo Tosatti
2015-08-06 20:46 ` Vikas Shivappa
2015-08-07 13:15 ` Marcelo Tosatti
2015-08-18 0:20 ` Marcelo Tosatti
2015-08-21 0:06 ` Vikas Shivappa
2015-08-21 0:13 ` Vikas Shivappa
2015-08-22 2:28 ` Marcelo Tosatti
2015-08-23 18:47 ` Vikas Shivappa
2015-08-24 13:06 ` Marcelo Tosatti
2015-07-01 22:21 ` [PATCH 6/9] x86/intel_rdt: Add support for cache bit mask management Vikas Shivappa
2015-07-28 16:35 ` Peter Zijlstra
2015-07-28 22:08 ` Vikas Shivappa
2015-07-28 16:37 ` Peter Zijlstra
2015-07-30 17:54 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 7/9] x86/intel_rdt: Implement scheduling support for Intel RDT Vikas Shivappa
2015-07-29 13:49 ` Peter Zijlstra
2015-07-30 18:16 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 8/9] x86/intel_rdt: Hot cpu support for Cache Allocation Vikas Shivappa
2015-07-29 15:53 ` Peter Zijlstra
2015-07-31 23:21 ` Vikas Shivappa
2015-07-01 22:21 ` [PATCH 9/9] x86/intel_rdt: Intel haswell Cache Allocation enumeration Vikas Shivappa
2015-07-29 16:35 ` Peter Zijlstra
2015-08-03 20:49 ` Vikas Shivappa
2015-07-29 16:36 ` Peter Zijlstra
2015-07-30 18:45 ` Vikas Shivappa
2015-07-13 17:13 ` [PATCH V12 0/9] Hot cpu handling changes to cqm, rapl and Intel Cache Allocation support Vikas Shivappa
2015-07-16 12:55 ` Thomas Gleixner
2015-07-24 16:52 ` Thomas Gleixner
2015-07-24 18:28 ` Vikas Shivappa
2015-07-24 18:39 ` Thomas Gleixner
2015-07-24 18:45 ` Vikas Shivappa
2015-07-29 16:47 ` Peter Zijlstra
2015-07-29 22:53 ` Vikas Shivappa
2015-07-24 18:32 ` Vikas Shivappa
-- strict thread matches above, loose matches on Subject: below --
2015-08-06 21:55 [PATCH V13 0/9] Intel cache allocation and Hot cpu handling changes to cqm, rapl Vikas Shivappa
2015-08-06 21:55 ` [PATCH 3/9] x86/intel_rdt: Cache Allocation documentation and cgroup usage guide Vikas Shivappa
2015-06-25 19:25 [PATCH V11 0/9] Hot cpu handling changes to cqm,rapl and Intel Cache Allocation support Vikas Shivappa
2015-06-25 19:25 ` [PATCH 3/9] x86/intel_rdt: Cache Allocation documentation and cgroup usage guide Vikas Shivappa
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=20150729193208.GC3201@amt.cnet \
--to=mtosatti@redhat.com \
--cc=glenn.p.williamson@intel.com \
--cc=hpa@zytor.com \
--cc=kanaka.d.juvva@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=matt.fleming@intel.com \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vikas.shivappa@intel.com \
--cc=vikas.shivappa@linux.intel.com \
--cc=will.auld@intel.com \
--cc=x86@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome