From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: Xen on ARM IRQ latency and scheduler overhead Date: Mon, 20 Feb 2017 12:40:06 +0100 Message-ID: <1487590806.6732.197.camel@citrix.com> References: <1487356845.6732.100.camel@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6436313748572137326==" 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: George Dunlap , Stefano Stabellini Cc: george.dunlap@eu.citrix.com, edgar.iglesias@xilinx.com, julien.grall@arm.com, xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============6436313748572137326== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="=-Hj9ksx9K+Bs0y7fOTBny" --=-Hj9ksx9K+Bs0y7fOTBny Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Mon, 2017-02-20 at 11:04 +0000, George Dunlap wrote: > On 18/02/17 00:41, Stefano Stabellini wrote: > >=20 > > On Fri, 17 Feb 2017, Dario Faggioli wrote:=09 > > > =C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0cyclictest 1us cycli= ctest 1ms cyclictest > > > 100ms =09 > > > (cycles) Credit1 Credit2 Credit1 Cred > > > it2 Credit1 Credit2 =09 > > > wakeup-avg 2429 2035 1980 1633=09 > > > 2535 1979 =09 > > > wakeup-max 14577 113682 15153 203136=09 > > > 12285 115164 =09 > >=20 > > I am not that familiar with the x86 side of things, but the 113682 > > and > > 203136 look worrisome, especially considering that credit1 doesn't > > have > > them. >=20 > Dario, >=20 > Do you reckon those 'MAX' values could be the load balancer running > (both for credit1 and credit2)? >=20 If they were max-es of do_schedule, that would have been my first guess. But not in this case, as the load balancer is never called during wakeup (neither in Credit nor Credit2). But I'm curious about what happen, and am going to investigate that. It should not be too hard has: 1) looks reproducible on my (x86) testbox that I have here; 2) since it's x86 I have tracing! :-P Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-Hj9ksx9K+Bs0y7fOTBny 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 iQIcBAABCAAGBQJYqtWWAAoJEBZCeImluHPu60sQAMOlBdPyIUwKHCGrnZjsoWVV QNkmFHnSvSLzBn0trLJgzRR6828Hsv9fvCgqQtAgFYxT/Pcfyi91iT6FQ9A3WPm6 9qbUxRSzB8+6W5Ch/thEqinGeCEeCBDPREC4ogdUVEtjUbjpbIyGBh/58ur7nJp3 +1IY02rs2S1IzG4SOWHp6AHHX04K0YOT26eMPaM4uFTZoZ8VPk/As4wdd0HAJjh3 BvJdZFAcTdwVX18FKb8g5JFO/SC49ZKbk5Pes0OFMHt3vMu89rgmBglYy1f35C/I J4SoNARWgiO4GPxOGeqdrIAnxvYCGj/7mP8/NacYhtg/vU98oKG0Hld2/yxBzXSe oROhvagKRIrZsk6ASftZtpPzPubnIJFNadDyp6oWJxfEwMAuTTxcjFozy0MJK3QH 10QLWc+rZ0ruVFnXb0gznAr/1dmKcZHPTecLMINBlFgX4ivzbjnDquWiLc07En3o 7OsG/TC7wmh/a3BgHW5qyPZbji6id/SPu7T/zNEeKzM6g1r0zhqV+Ik8vdCWwJO8 fI/2koh6QAFlSUdQtBRUKT5fjI9rTLxeM6d3l1cU8Uf+7SSq9Yd9Hw/lY+X7yfXc qrB93iGJcTRu4ryv2hLzNAMJmqAuGmBhnz7KwlvmyzXVyLtm8ZWZZDZJxCuKJQSl SkdulB5KuPSxN1oPD0jS =emB4 -----END PGP SIGNATURE----- --=-Hj9ksx9K+Bs0y7fOTBny-- --===============6436313748572137326== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KWGVuLWRldmVs IG1haWxpbmcgbGlzdApYZW4tZGV2ZWxAbGlzdHMueGVuLm9yZwpodHRwczovL2xpc3RzLnhlbi5v cmcveGVuLWRldmVsCg== --===============6436313748572137326==--