From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dario Faggioli Subject: Re: [PATCH v3] xen/arm: introduce vwfi parameter Date: Wed, 1 Mar 2017 12:50:42 +0100 Message-ID: <1488369042.5548.131.camel@citrix.com> References: <1488316334-20434-1-git-send-email-sstabellini@kernel.org> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6217111470177555946==" Return-path: Received: from mail6.bemta5.messagelabs.com ([195.245.231.135]) by lists.xenproject.org with esmtp (Exim 4.84_2) (envelope-from ) id 1cj2mR-0006oD-2a for xen-devel@lists.xenproject.org; Wed, 01 Mar 2017 11:50:51 +0000 In-Reply-To: <1488316334-20434-1-git-send-email-sstabellini@kernel.org> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Errors-To: xen-devel-bounces@lists.xen.org Sender: "Xen-devel" To: Stefano Stabellini , julien.grall@arm.com Cc: xen-devel@lists.xenproject.org List-Id: xen-devel@lists.xenproject.org --===============6217111470177555946== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="=-rJnp+YWuX+AibIaBWXKK" --=-rJnp+YWuX+AibIaBWXKK Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Tue, 2017-02-28 at 13:12 -0800, Stefano Stabellini wrote: > --- a/docs/misc/xen-command-line.markdown > +++ b/docs/misc/xen-command-line.markdown > @@ -1638,6 +1638,20 @@ Note that if **watchdog** option is also > specified vpmu will be turned off. > =C2=A0As the virtualisation is not 100% safe, don't use the vpmu flag on > =C2=A0production systems (see http://xenbits.xen.org/xsa/advisory-163.htm= l > )! > =C2=A0 > +### vwfi > +> `=3D trap | native > + > +> Default: `trap` > + > +WFI is the ARM instruction to "wait for interrupt". WFE is similar > and > +means "wait for event". This option, which is ARM specific, changes > the > +way guest WFI and WFE are implemented in Xen. By default, Xen traps > both > +instructions. In the case of WFI, Xen blocks the guest vcpu; in the > case > +of WFE, Xen yield the guest vcpu. When setting vwfi to `native`, Xen > +doesn't trap either instruction, running them in guest context. > Setting > +vwfi to `native` reduces irq latency, but leads to suboptimal > scheduling > +decisions. > + These last few words sounds a bit generic to me. They may alarm people and discourage using 'native', even when it is actually ok. Being a bit more specific, although without going into too much technical detail, seems worth to me. So, how about something like: "Using `native` reduces irq latency significantly. It can also lead to suboptimal scheduling decisions and affect performance, but only when the system is oversubscribed (i.e., there are, in total, more vCPUs than pCPUs)." ? Regards, Dario --=20 <> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) --=-rJnp+YWuX+AibIaBWXKK 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 iQIcBAABCAAGBQJYtrWTAAoJEBZCeImluHPukVwP/iLgDRhuJRVYeg8bV5EfSbo8 uVeBo1s61MotIJTaN/ViR3QqU9OpOr1ZRLTYzhCecnfThD7/pH85l8ZprBl1FV16 eHmKwVDN/Gs0aLA/WjIOTqAvs+L4COJLpGUIBQ02U3vgwlXiokDifD4h9TDXrfho iNajIeDxX8iK0JN18DhVXVCshAs54PSRMaQWqmCBxkoQEcY4f1dF0GweaSp8rucq CHXSrqP+iWatsPM9fyo1PdSJ6pA9LqhiMxBJGL6lB07bBaNTjZxCoC/91KD+V8z4 86Cg9LEPQvW0iRlx0lp3W3oYi2SON/5fQaW7umf3mpUpFUGY2qq4VPkBpBMPHwgi bisBdgBjAGnyio/HQSroW9jTRM10BqQp/OJT3eDT490o8Y0ImYq+u9eU/UpJwrSN CLQfr7bfHh3cz1BMgFZIESQOsjQZu7ZqdOXJ5Ynkf0UNf4l0fu8b1b61dE2ex4nq QJN0UP6suxdfqxXgfiCfbhbBf+KrR7AXoH+TQsvK1mBiZLlJqPJO1QWB8Be72JBF iIu8luAuX1E6njKOzxXgLREhjG/asSPGsDuLewKevtu4nZ9+FF/z2RFZWcfdnJ9g ENzGoxC/XqPZ+3zQAJ6MamtkCW8NCO4qqLIkTyeiej7s7pCHNV3kwYJYXw7PkdMp rA0WaiA1fPQywzy2vz1I =S32D -----END PGP SIGNATURE----- --=-rJnp+YWuX+AibIaBWXKK-- --===============6217111470177555946== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KWGVuLWRldmVs IG1haWxpbmcgbGlzdApYZW4tZGV2ZWxAbGlzdHMueGVuLm9yZwpodHRwczovL2xpc3RzLnhlbi5v cmcveGVuLWRldmVsCg== --===============6217111470177555946==--