From: "Michael S. Tsirkin" <mst@redhat.com> To: Sasha Levin <levinsasha928@gmail.com> Cc: avi@redhat.com, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org Subject: Re: [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible Date: Thu, 30 Aug 2012 01:52:49 +0300 [thread overview] Message-ID: <20120829225249.GB9146@redhat.com> (raw) In-Reply-To: <503E7F9B.8010402@gmail.com> On Wed, Aug 29, 2012 at 10:46:19PM +0200, Sasha Levin wrote: > On 08/29/2012 08:12 PM, Michael S. Tsirkin wrote: > >>> > > What is a good default for net? I guess max sg? > >> > > >> > I think that it depends on the workload. I'd say we should keep the default to 0 > >> > (disabled) unless we can have a good way to adjust it to the load. > > For *all* drivers? > > > > Then it is mostly useless. No one has the time to tweak module > > parameters in real life. > > > > For virtio-net, 16+1 is not too much and ensures we always > > use the cache. > > > > If that works better than 0 I would say run with 17. > > I was being extra-cautious with leaving it disabled until specifically enabled > because I assumed that this would be one of the first comments I'll get if it > was enabled by default :) > > If you're comfortable with setting it to a sane default like 17, I'm perfectly > fine with that as well. > > > Thanks, > Sasha If our testing shows it helps and does not trigger regressions, then why not? module params are mostly there for developers. They are not all that helpful to users. > _______________________________________________ > Virtualization mailing list > Virtualization@lists.linux-foundation.org > https://lists.linuxfoundation.org/mailman/listinfo/virtualization
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com> To: Sasha Levin <levinsasha928@gmail.com> Cc: virtualization@lists.linux-foundation.org, avi@redhat.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible Date: Thu, 30 Aug 2012 01:52:49 +0300 [thread overview] Message-ID: <20120829225249.GB9146@redhat.com> (raw) In-Reply-To: <503E7F9B.8010402@gmail.com> On Wed, Aug 29, 2012 at 10:46:19PM +0200, Sasha Levin wrote: > On 08/29/2012 08:12 PM, Michael S. Tsirkin wrote: > >>> > > What is a good default for net? I guess max sg? > >> > > >> > I think that it depends on the workload. I'd say we should keep the default to 0 > >> > (disabled) unless we can have a good way to adjust it to the load. > > For *all* drivers? > > > > Then it is mostly useless. No one has the time to tweak module > > parameters in real life. > > > > For virtio-net, 16+1 is not too much and ensures we always > > use the cache. > > > > If that works better than 0 I would say run with 17. > > I was being extra-cautious with leaving it disabled until specifically enabled > because I assumed that this would be one of the first comments I'll get if it > was enabled by default :) > > If you're comfortable with setting it to a sane default like 17, I'm perfectly > fine with that as well. > > > Thanks, > Sasha If our testing shows it helps and does not trigger regressions, then why not? module params are mostly there for developers. They are not all that helpful to users. > _______________________________________________ > Virtualization mailing list > Virtualization@lists.linux-foundation.org > https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2012-08-29 22:51 UTC|newest] Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top 2012-08-28 13:04 [PATCH v2 1/2] virtio-ring: Use threshold for switching to indirect descriptors Sasha Levin 2012-08-28 13:04 ` Sasha Levin 2012-08-28 13:04 ` [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible Sasha Levin 2012-08-28 13:04 ` Sasha Levin 2012-08-28 13:20 ` Michael S. Tsirkin 2012-08-28 13:20 ` Michael S. Tsirkin 2012-08-28 13:35 ` Sasha Levin 2012-08-28 13:35 ` Sasha Levin 2012-08-29 11:07 ` Michael S. Tsirkin 2012-08-29 11:07 ` Michael S. Tsirkin 2012-08-29 15:03 ` Sasha Levin 2012-08-29 15:03 ` Sasha Levin 2012-08-29 15:14 ` Michael S. Tsirkin 2012-08-29 15:14 ` Michael S. Tsirkin 2012-08-30 10:34 ` Sasha Levin 2012-08-30 10:34 ` Sasha Levin 2012-08-29 15:38 ` Michael S. Tsirkin 2012-08-29 15:38 ` Michael S. Tsirkin 2012-08-29 16:50 ` Sasha Levin 2012-08-29 16:50 ` Sasha Levin 2012-09-06 1:02 ` Rusty Russell 2012-09-06 1:02 ` Rusty Russell 2012-09-06 5:02 ` Michael S. Tsirkin 2012-09-06 5:02 ` Michael S. Tsirkin 2012-09-06 7:57 ` Rusty Russell 2012-09-06 7:57 ` Rusty Russell 2012-09-06 8:45 ` Michael S. Tsirkin 2012-09-06 8:45 ` Michael S. Tsirkin 2012-09-06 23:49 ` Rusty Russell 2012-09-07 0:06 ` Michael S. Tsirkin 2012-09-07 0:06 ` Michael S. Tsirkin 2012-09-10 15:47 ` Thomas Lendacky 2012-09-10 16:08 ` Michael S. Tsirkin 2012-09-10 16:08 ` Michael S. Tsirkin 2012-09-12 6:13 ` Rusty Russell 2012-09-12 10:44 ` Sasha Levin 2012-09-12 10:44 ` Sasha Levin 2012-10-23 15:14 ` Michael S. Tsirkin 2012-10-23 15:14 ` Michael S. Tsirkin 2012-09-12 6:13 ` Rusty Russell 2012-09-10 16:01 ` Thomas Lendacky 2012-09-10 16:01 ` Thomas Lendacky 2012-09-06 23:49 ` Rusty Russell 2012-09-10 15:52 ` Paolo Bonzini 2012-09-10 15:52 ` Paolo Bonzini 2012-09-06 0:02 ` Rusty Russell 2012-09-06 0:02 ` Rusty Russell 2012-08-29 15:38 ` Michael S. Tsirkin 2012-08-29 15:38 ` Michael S. Tsirkin 2012-08-29 17:14 ` Sasha Levin 2012-08-29 17:14 ` Sasha Levin 2012-08-29 18:12 ` Michael S. Tsirkin 2012-08-29 18:12 ` Michael S. Tsirkin 2012-08-29 20:46 ` Sasha Levin 2012-08-29 20:46 ` Sasha Levin 2012-08-29 22:52 ` Michael S. Tsirkin [this message] 2012-08-29 22:52 ` Michael S. Tsirkin 2012-08-28 13:20 ` [PATCH v2 1/2] virtio-ring: Use threshold for switching to indirect descriptors Michael S. Tsirkin 2012-08-28 13:20 ` Michael S. Tsirkin
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=20120829225249.GB9146@redhat.com \ --to=mst@redhat.com \ --cc=avi@redhat.com \ --cc=kvm@vger.kernel.org \ --cc=levinsasha928@gmail.com \ --cc=linux-kernel@vger.kernel.org \ --cc=virtualization@lists.linux-foundation.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: linkBe 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.