Date: Thu, 2 Jun 2016 15:01:03 +0200 From: Hans Petter Selasky <hps@selasky.org> To: =?UTF-8?Q?Roger_Pau_Monn=c3=a9?= <royger@FreeBSD.org> Cc: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: Re: svn commit: r301197 - head/sys/dev/xen/netfront Message-ID: <c8ef340a-e3d3-af3e-d45c-eedf4183750b@selasky.org> In-Reply-To: <20160602125422.gmdsueoeu5fiiec5@mac> References: <201606021114.u52BEQqB047172@repo.freebsd.org> <2c81e44d-65de-10f0-8837-f23896855150@selasky.org> <20160602125422.gmdsueoeu5fiiec5@mac>
next in thread | previous in thread | raw e-mail | index | archive | help
On 06/02/16 14:54, Roger Pau Monné wrote: > On Thu, Jun 02, 2016 at 01:19:56PM +0200, Hans Petter Selasky wrote: >> On 06/02/16 13:14, Roger Pau Monné wrote: >>> + callout_reset(&rxq->rx_refill, hz/10, xn_alloc_rx_buffers_callout, >>> + rxq); >> >> Maybe use callout_reset_curcpu() to take advantage of callout's SMP >> capabilities ? > > Yes, that's fine. But what's the benefit of it? I don't really care whether > the callout is run on the current CPU or not. Is callout_reset_curcpu > cheaper than callout_reset? > Hi, It is maybe not cheaper, but it will distribute the load of the xn_alloc_rx_buffers_callout() callback, to the current CPU calling callout_reset_curcpu(). Else xn_alloc_rx_buffers_callout() will always be called from callback thread zero. --HPS
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?c8ef340a-e3d3-af3e-d45c-eedf4183750b>