From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: xenpm and scheduler Date: Tue, 12 Apr 2016 23:05:22 +0200 Message-ID: <1460495122.13871.119.camel@citrix.com> References: <1460448609.13871.104.camel@citrix.com> <20160412134140.GB27920@localhost.localdomain> , <20160412170815.GA5771@char.us.oracle.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8144557394135218413==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xen.org Sender: "Xen-devel" To: tutu sky , Konrad Rzeszutek Wilk Cc: Meng Xu , "Xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org --===============8144557394135218413== Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-XpScN6ME1Ut8IqiQxo03" --=-XpScN6ME1Ut8IqiQxo03 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Tue, 2016-04-12 at 17:46 +0000, tutu sky wrote: > yeah, running xenpm gives short comments on its commands and their > options but not about how to establish it. >=20 I do not understand what you mean with 'establishing' xenpm. If you run Xen on a machine that has power management and/or frequency scaling capabilities, you'll be able to use the various xenpm commands. It most likely will have to be a real hardware box, as I don't think emulation or nested virtualization satisfies the above condition (for most of the emulator and hypervisor that I know of). You also need to use a sufficiently recent Linux dom0 kernel. Konrad knows better than me what's the minimum necessary version, but I don't think this is a problem (i.e., any kernel since the last couple of years should work fine). Or was it something else you were asking? Dario > I try my best for this :) > thanks a lot. >=20 > ________________________________________ > From: Konrad Rzeszutek Wilk > Sent: Tuesday, April 12, 2016 5:08 PM > To: tutu sky > Cc: Dario Faggioli; Meng Xu; Xen-devel@lists.xen.org > Subject: Re: [Xen-devel] xenpm and scheduler >=20 > On Tue, Apr 12, 2016 at 05:04:04PM +0000, tutu sky wrote: > >=20 > > Thanks Konrad. I will do :) > > Yeah, I believe so. as i can see that there is not any bios > > settings for power management in there (vmware).=C2=A0=C2=A0I hope you = be the > > correct party which i want to ask this question: there is a > > tutorial here in this page: > > 1) http://xenserver.org/partners/developing-products-for-xenserver/ > > 19-dev-help/138-xs-dev-perf-turbo.html > >=20 > > which i know as a quick guide for establishing xenpm. my Q is that, > > are this page and this two page of xen.wiki below enough for > > establishing xenpm and make it work totally? > >=20 > > 2) http://wiki.xenproject.org/wiki/Xenpm_command > > 3) http://wiki.xenproject.org/wiki/Xen_power_management > >=20 > > =C2=A0if yes, there is a problem, when i compiled xen from source, ther= e > > is not any xensource folder in /opt folder in dom0 to follow the > > instructions in (1) address. i did all those instructions in dom0 > > config file instead. > Xen source !=3D XenServer. >=20 >=20 > >=20 > >=20 > > if these guides are not enough in your point of view too, i think > > (just as a suggestion), xenpm needs more documentation, in order to > > clarify it's activation and usage progress. it remains a silent > > area in this giant project although is quiet usable. > >=20 > If you run 'xenpm' by itself it gives you the options. >=20 > Patches to make an manpage for xenpm are always warmly welcome! > >=20 > > thanks and regards. > >=20 > > ________________________________________ > > From: Konrad Rzeszutek Wilk > > Sent: Tuesday, April 12, 2016 1:41 PM > > To: tutu sky > > Cc: Dario Faggioli; Meng Xu; Xen-devel@lists.xen.org > > Subject: Re: [Xen-devel] xenpm and scheduler > >=20 > > On Tue, Apr 12, 2016 at 11:50:42AM +0000, tutu sky wrote: > > >=20 > > > Thanks Dario, > > > Yeah, I do like playing with xenpm and try understanding > > > relationship between this and scheduler. but i established a xen > > > environment on vmware, but xenpm does not work correctly and even > > > for 'cpufreq', it is silent at all! so it does not let me try to > > > play with :(. I asked this problem before in the user and devel > > > lists both,=C2=A0=C2=A0but no body answered me. how can i track the > > > problem, from who (I know that power management is out of your > > > maintenance scope)?? (may xenpm have the same problem on a real > > > platform (again) instead of vmware?) > > > thanks a lot. > > You will have to. > >=20 > > I don't believe VMWare exposes C and P states to guests so > > therefore > > there is no power freqeuency in play. > >=20 > > >=20 > > > regards. > > > ________________________________________ > > > From: Dario Faggioli > > > Sent: Tuesday, April 12, 2016 8:10 AM > > > To: tutu sky; Meng Xu > > > Cc: Xen-devel@lists.xen.org > > > Subject: Re: [Xen-devel] xenpm and scheduler > > >=20 > > > On Tue, 2016-04-12 at 03:52 +0000, tutu sky wrote: > > > >=20 > > > > Thanks Xu. I will do as desired about cross messaging. > > > >=20 > > > > i need it because i exactly want to know that which part of the > > > > scheduler's corde (credit), takes effect from this feature. > > > > because > > > > it is important to me knowing that where would be trade off > > > > between > > > > idle state and doing load balancing, while cpuidle feature is > > > > activated. in other side it's important again for me that what > > > > will > > > > happen for 'cap; and 'weight' decreasing in a case that one > > > > core's > > > > frequency is lower than another one in the same socket > > > > (actually when > > > > cpufreq feature is enable). > > > >=20 > > > Currently, there is no interaction between the scheduler and the > > > power > > > management and frequency scaling layers. > > >=20 > > > >=20 > > > > Am i clear enough? can you give me an answer or maybe some > > > > lines of > > > > schedule.c or sched_credit.c's code which i can track them to > > > > notice > > > > the effect of xenpm on scheduler part of the view? > > > >=20 > > > If you're saying that, for instance, the CPUs changing frequency > > > can or > > > should affect some aspects of the scheduling algorithms (like > > > credits > > > burning rate in Credit1 and Credit2, and budget burning rate in > > > RTDS), > > > that is an interesting point which may indeed make sense, or at > > > least > > > would deserve more investigation. > > >=20 > > > But again, right now, there's no line of code to read to > > > understand the > > > relationship, as there's no relationship at all. > > >=20 > > > If you want to experiment on playing with xenpm, and seeing what > > > effect > > > it has on scheduling, that will be very welcome. :-) > > >=20 > > > Regards, > > > Dario > > > -- > > > <> (Raistlin Majere) > > > ----------------------------------------------------------------- > > > Dario Faggioli, Ph.D, http://about.me/dario.faggioli > > > Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) > > >=20 > > >=20 > > > _______________________________________________ > > > Xen-devel mailing list > > > Xen-devel@lists.xen.org > > > http://lists.xen.org/xen-devel > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-XpScN6ME1Ut8IqiQxo03 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iEYEABECAAYFAlcNYxMACgkQk4XaBE3IOsSRVQCggsKeGZpIQM+NlhDBNdVESp/S neMAn2C54I0siqiBrRYWgmVIeOfd48NK =9+zz -----END PGP SIGNATURE----- --=-XpScN6ME1Ut8IqiQxo03-- --===============8144557394135218413== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KWGVuLWRldmVs IG1haWxpbmcgbGlzdApYZW4tZGV2ZWxAbGlzdHMueGVuLm9yZwpodHRwOi8vbGlzdHMueGVuLm9y Zy94ZW4tZGV2ZWwK --===============8144557394135218413==--