All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Cooper <andrew.cooper3@citrix.com>
To: "Xu, Dongxiao" <dongxiao.xu@intel.com>,
	Jan Beulich <jbeulich@suse.com>,
	"george.dunlap@eu.citrix.com" <george.dunlap@eu.citrix.com>
Cc: "Auld, Will" <will.auld@intel.com>,
	"Ian.Campbell@citrix.com" <Ian.Campbell@citrix.com>,
	"Nakajima, Jun" <jun.nakajima@intel.com>,
	"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Subject: Re: Xen Platform QoS design discussion
Date: Thu, 29 May 2014 10:13:32 +0100	[thread overview]
Message-ID: <5386FA3C.3010201@citrix.com> (raw)
In-Reply-To: <40776A41FC278F40B59438AD47D147A911A20944@SHSMSX104.ccr.corp.intel.com>


On 29/05/2014 08:31, Xu, Dongxiao wrote:
>> -----Original Message-----
>> From: Jan Beulich [mailto:jbeulich@suse.com]
>> Sent: Thursday, May 29, 2014 3:02 PM
>> To: george.dunlap@eu.citrix.com; Xu, Dongxiao
>> Cc: andrew.cooper3@citrix.com; Ian.Campbell@citrix.com;
>> xen-devel@lists.xen.org
>> Subject: Re: RE: [Xen-devel] Xen Platform QoS design discussion
>>
>>>>> "Xu, Dongxiao" <dongxiao.xu@intel.com> 05/29/14 2:46 AM >>>
>>> I think Jan's opinion here is similar to what I proposed in the beginning of this
>> thread.
>>> The only difference is that, Jan prefers to get the CQM data per-socket and
>> per-domain
>>> with data copying, while I proposed to get the CQM data per-domain for all
>> sockets
>>> that can reduce the amount of hypercalls.
>> I don't think I ever voiced any preference between these two. All I said it
>> depends on
>> prevalent usage models, and to date I don't think I've seen a proper analysis of
>> what
>> the main usage model would be - it all seems guesswork and/or taking random
>> examples.
>>
>> What I did say I'd prefer is to have all this done outside the hypervisor, with the
>> hypervisor just providing fundamental infrastructure (MSR accesses).
> Okay. If I understand correctly, you prefer to implement a pure MSR access hypercall for one CPU, and put all other CQM things in libxc/libxl layer.
>
> In this case, if libvert/XenAPI is trying to query a domain's cache utilization in the system (say 2 sockets), then it will trigger _two_ such MSR access hypercalls for CPUs in the 2 different sockets.
> If you are okay with this idea, I am going to implement it.
>   
> Thanks,
> Dongxiao

While I can see the use and attraction of a generic MSR access 
hypercalls, using this method for getting QoS data is going to have 
subsantitally higher overhead than even the original domctl suggestion.

I do not believe it will be an effective means of getting large 
quantities of data from ring0 MSRs into dom0 userspace.  This is not to 
say that having a generic MSR interface is a bad thing, but I don't 
think it should be used for this purpose.

~Andrew

  parent reply	other threads:[~2014-05-29  9:13 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-30 16:47 Xen Platform QoS design discussion Xu, Dongxiao
2014-04-30 17:02 ` Ian Campbell
2014-05-01  0:56   ` Xu, Dongxiao
2014-05-02  9:23     ` Jan Beulich
2014-05-02 12:30       ` Xu, Dongxiao
2014-05-02 12:40         ` Jan Beulich
2014-05-04  0:46           ` Xu, Dongxiao
2014-05-06  9:10             ` Ian Campbell
2014-05-06  1:40           ` Xu, Dongxiao
2014-05-06  7:55             ` Jan Beulich
2014-05-06 10:06             ` Andrew Cooper
2014-05-07  2:08               ` Xu, Dongxiao
2014-05-07  9:10                 ` Ian Campbell
2014-05-07 13:26               ` George Dunlap
2014-05-07 21:18                 ` Andrew Cooper
2014-05-08  5:21                   ` Xu, Dongxiao
2014-05-08 11:25                     ` Andrew Cooper
2014-05-09  2:41                       ` Xu, Dongxiao
2014-05-13  1:53                       ` Xu, Dongxiao
2014-05-16  5:11                       ` Xu, Dongxiao
2014-05-19 11:28                         ` George Dunlap
2014-05-19 11:45                           ` Jan Beulich
2014-05-19 12:13                             ` George Dunlap
2014-05-19 12:41                               ` Jan Beulich
2014-05-22  8:19                                 ` Xu, Dongxiao
2014-05-22  8:39                                   ` Jan Beulich
2014-05-22  9:27                                     ` George Dunlap
2014-05-26  0:51                                       ` Xu, Dongxiao
2014-05-29  0:45                                       ` Xu, Dongxiao
2014-05-29  7:01                                         ` Jan Beulich
2014-05-29  7:31                                           ` Xu, Dongxiao
2014-05-29  9:11                                             ` Jan Beulich
2014-05-30  9:10                                               ` Ian Campbell
2014-05-30 11:17                                                 ` Jan Beulich
2014-05-30 12:33                                                   ` Ian Campbell
2014-06-05  0:48                                                   ` Xu, Dongxiao
2014-06-05 10:43                                                     ` George Dunlap
2014-05-29  9:13                                             ` Andrew Cooper [this message]
2014-05-30  1:07                                               ` Xu, Dongxiao
2014-05-30  6:23                                                 ` Jan Beulich
2014-05-30  7:51                                                   ` Xu, Dongxiao
2014-05-30 11:15                                                     ` Jan Beulich
2014-05-02 12:50         ` Andrew Cooper
2014-05-04  2:34           ` Xu, Dongxiao
2014-05-06  9:12             ` Ian Campbell
2014-05-06 10:00             ` Andrew Cooper

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=5386FA3C.3010201@citrix.com \
    --to=andrew.cooper3@citrix.com \
    --cc=Ian.Campbell@citrix.com \
    --cc=dongxiao.xu@intel.com \
    --cc=george.dunlap@eu.citrix.com \
    --cc=jbeulich@suse.com \
    --cc=jun.nakajima@intel.com \
    --cc=will.auld@intel.com \
    --cc=xen-devel@lists.xen.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 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.