From: "Michael S. Tsirkin" <mst@redhat.com> To: Ilya Lesokhin <ilyal@mellanox.com> Cc: "virtio-dev@lists.oasis-open.org" <virtio-dev@lists.oasis-open.org>, "virtualization@lists.linux-foundation.org" <virtualization@lists.linux-foundation.org> Subject: Re: packed ring layout proposal v3 Date: Wed, 25 Oct 2017 19:20:01 +0300 [thread overview] Message-ID: <20171025191346-mutt-send-email-mst@kernel.org> (raw) In-Reply-To: <AM4PR0501MB27236B71E1B02176F1844ACBD4770@AM4PR0501MB2723.eurprd05.prod.outlook.com> On Sun, Oct 08, 2017 at 06:16:44AM +0000, Ilya Lesokhin wrote: > > > -----Original Message----- > > > From: virtualization-bounces@lists.linux-foundation.org > > > [mailto:virtualization-bounces@lists.linux-foundation.org] On Behalf > > > Of Michael S. Tsirkin > > > > > > This is an update from v2 version. > >> ... > > > When driver descriptors are chained in this way, multiple descriptors > > > are treated as a part of a single transaction containing an optional > > > write buffer followed by an optional read buffer. > > > All descriptors in the chain must have the same ID. > > > > > I apologize for the repost, I didn't realize I have to be a member of the > virtio-dev mailing list. > > I'm concerned about the "same ID" requirement in chained descriptors. It's there really just so we can remove the doubt about which descriptor's ID should be used. My testing does not show a performance win from this, so I'm fine with removing this requirement though I'd be curious to know why is it a problem. > Assuming out of order execution, how is the driver supposed to re-assign > unique IDs to the previously chained descriptor? For example, driver can have a simple allocator for the IDs. > Is the driver expected to copy original IDs somewhere else before the > chaining and then restore the IDs after the chain is executed? > > Thanks, > Ilya As device overwrites the ID, driver will have to write it out each time, that's true. It's going to be a requirement even if descriptors on the chain do not need to have the same ID. -- MST
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com> To: Ilya Lesokhin <ilyal@mellanox.com> Cc: "virtio-dev@lists.oasis-open.org" <virtio-dev@lists.oasis-open.org>, "virtualization@lists.linux-foundation.org" <virtualization@lists.linux-foundation.org> Subject: [virtio-dev] Re: packed ring layout proposal v3 Date: Wed, 25 Oct 2017 19:20:01 +0300 [thread overview] Message-ID: <20171025191346-mutt-send-email-mst@kernel.org> (raw) In-Reply-To: <AM4PR0501MB27236B71E1B02176F1844ACBD4770@AM4PR0501MB2723.eurprd05.prod.outlook.com> On Sun, Oct 08, 2017 at 06:16:44AM +0000, Ilya Lesokhin wrote: > > > -----Original Message----- > > > From: virtualization-bounces@lists.linux-foundation.org > > > [mailto:virtualization-bounces@lists.linux-foundation.org] On Behalf > > > Of Michael S. Tsirkin > > > > > > This is an update from v2 version. > >> ... > > > When driver descriptors are chained in this way, multiple descriptors > > > are treated as a part of a single transaction containing an optional > > > write buffer followed by an optional read buffer. > > > All descriptors in the chain must have the same ID. > > > > > I apologize for the repost, I didn't realize I have to be a member of the > virtio-dev mailing list. > > I'm concerned about the "same ID" requirement in chained descriptors. It's there really just so we can remove the doubt about which descriptor's ID should be used. My testing does not show a performance win from this, so I'm fine with removing this requirement though I'd be curious to know why is it a problem. > Assuming out of order execution, how is the driver supposed to re-assign > unique IDs to the previously chained descriptor? For example, driver can have a simple allocator for the IDs. > Is the driver expected to copy original IDs somewhere else before the > chaining and then restore the IDs after the chain is executed? > > Thanks, > Ilya As device overwrites the ID, driver will have to write it out each time, that's true. It's going to be a requirement even if descriptors on the chain do not need to have the same ID. -- MST --------------------------------------------------------------------- To unsubscribe, e-mail: virtio-dev-unsubscribe@lists.oasis-open.org For additional commands, e-mail: virtio-dev-help@lists.oasis-open.org
next prev parent reply other threads:[~2017-10-25 16:20 UTC|newest] Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-09-10 5:06 [virtio-dev] packed ring layout proposal v3 Michael S. Tsirkin 2017-02-08 13:37 ` packed ring layout proposal v2 Christian Borntraeger 2017-02-09 17:43 ` Michael S. Tsirkin [not found] ` <20170209181955-mutt-send-email-mst@kernel.org> 2017-02-09 18:27 ` Christian Borntraeger 2017-02-08 17:41 ` [virtio-dev] " Paolo Bonzini 2017-02-08 19:59 ` Michael S. Tsirkin [not found] ` <20170208214435-mutt-send-email-mst@kernel.org> 2017-02-09 15:48 ` Paolo Bonzini 2017-02-09 16:11 ` Cornelia Huck 2017-02-09 18:24 ` Michael S. Tsirkin [not found] ` <20170209202203-mutt-send-email-mst@kernel.org> 2017-02-10 11:32 ` Paolo Bonzini [not found] ` <c229269b-1702-ffec-62e8-002c7c142904@redhat.com> 2017-02-10 15:20 ` Michael S. Tsirkin 2017-02-10 16:17 ` Paolo Bonzini [not found] ` <20170209171105.075a9d9c.cornelia.huck@de.ibm.com> 2017-02-22 16:43 ` Michael S. Tsirkin [not found] ` <20170222181333-mutt-send-email-mst@kernel.org> 2017-03-07 15:53 ` Cornelia Huck 2017-03-07 20:33 ` Michael S. Tsirkin [not found] ` <20170307223057-mutt-send-email-mst@kernel.org> 2017-07-10 16:27 ` Amnon Ilan 2017-07-10 16:27 ` Amnon Ilan 2017-02-22 4:27 ` packed ring layout proposal - todo list Michael S. Tsirkin [not found] ` <20170222054336-mutt-send-email-mst@kernel.org> 2017-02-22 9:19 ` [virtio-dev] " Gray, Mark D [not found] ` <738D45BC1F695740A983F43CFE1B7EA94E93CA7E@IRSMSX108.ger.corp.intel.com> 2017-02-22 15:13 ` Michael S. Tsirkin 2017-02-28 4:29 ` Yuanhan Liu [not found] ` <20170228042943.GH18844@yliu-dev.sh.intel.com> 2017-03-01 1:07 ` Michael S. Tsirkin 2017-03-08 7:09 ` Yuanhan Liu [not found] ` <20170308070948.GC18844@yliu-dev.sh.intel.com> 2017-03-08 7:56 ` Yuanhan Liu [not found] ` <20170308075624.GF18844@yliu-dev.sh.intel.com> 2017-03-29 12:39 ` Michael S. Tsirkin 2017-04-01 7:30 ` Yuanhan Liu 2017-02-22 14:46 ` [virtio-dev] packed ring layout proposal v2 Chien, Roger S 2017-02-28 5:02 ` Yuanhan Liu 2017-02-28 5:47 ` [RFC] packed (virtio-net) headers Yuanhan Liu [not found] ` <20170228050218.GI18844@yliu-dev.sh.intel.com> 2017-03-01 1:02 ` [virtio-dev] packed ring layout proposal v2 Michael S. Tsirkin [not found] ` <20170301024951-mutt-send-email-mst@kernel.org> 2017-03-01 3:57 ` Yuanhan Liu [not found] ` <20170301035715.GP18844@yliu-dev.sh.intel.com> 2017-03-01 4:14 ` Michael S. Tsirkin 2017-03-01 4:57 ` Yuanhan Liu [not found] ` <20170228054719.GJ18844@yliu-dev.sh.intel.com> 2017-03-01 1:28 ` [RFC] packed (virtio-net) headers Michael S. Tsirkin 2017-07-16 6:00 ` [virtio-dev] packed ring layout proposal v2 Lior Narkis 2017-07-18 16:23 ` Michael S. Tsirkin 2017-07-18 16:23 ` Michael S. Tsirkin 2017-07-19 7:41 ` Lior Narkis 2017-07-20 13:06 ` Michael S. Tsirkin 2017-07-20 13:06 ` Michael S. Tsirkin 2017-07-19 7:41 ` Lior Narkis 2017-07-16 6:00 ` Lior Narkis 2017-09-11 7:47 ` [virtio-dev] Re: packed ring layout proposal v3 Jason Wang 2017-09-12 16:23 ` Willem de Bruijn 2017-09-13 1:26 ` Jason Wang 2017-09-13 1:26 ` Jason Wang 2017-09-12 16:23 ` Willem de Bruijn 2017-09-11 7:47 ` Jason Wang 2017-09-12 16:20 ` [virtio-dev] " Willem de Bruijn 2017-09-12 16:20 ` Willem de Bruijn 2017-09-14 8:23 ` Ilya Lesokhin 2017-09-20 9:11 ` [virtio-dev] " Liang, Cunming 2017-09-20 9:11 ` Liang, Cunming 2017-09-25 22:24 ` Michael S. Tsirkin 2017-09-25 22:24 ` Michael S. Tsirkin 2017-09-26 23:38 ` Steven Luong (sluong) 2017-09-27 23:49 ` Michael S. Tsirkin 2017-09-27 23:49 ` Michael S. Tsirkin 2017-09-28 9:44 ` Liang, Cunming 2017-10-01 4:08 ` Michael S. Tsirkin 2017-10-01 4:08 ` Michael S. Tsirkin 2017-10-04 12:39 ` Jens Freimann 2017-10-04 12:58 ` Michael S. Tsirkin 2017-10-04 12:58 ` Michael S. Tsirkin 2017-10-10 9:56 ` Liang, Cunming 2017-10-10 9:56 ` Liang, Cunming 2017-10-11 12:22 ` Jens Freimann 2017-09-28 9:44 ` Liang, Cunming 2017-09-28 21:13 ` Michael S. Tsirkin 2017-09-28 21:13 ` Michael S. Tsirkin 2017-09-26 23:38 ` Steven Luong (sluong) 2017-09-21 13:36 ` Liang, Cunming 2017-09-21 13:36 ` Liang, Cunming 2017-09-28 21:27 ` Michael S. Tsirkin 2017-09-28 21:27 ` Michael S. Tsirkin 2017-10-08 6:16 ` Ilya Lesokhin 2017-10-08 6:16 ` [virtio-dev] " Ilya Lesokhin 2017-10-25 16:20 ` Michael S. Tsirkin [this message] 2017-10-25 16:20 ` [virtio-dev] " Michael S. Tsirkin 2017-10-29 9:05 ` Ilya Lesokhin 2017-10-29 9:05 ` [virtio-dev] " Ilya Lesokhin 2017-10-29 14:21 ` Michael S. Tsirkin 2017-10-29 14:21 ` [virtio-dev] " Michael S. Tsirkin 2017-10-29 14:34 ` Ilya Lesokhin 2017-10-29 14:34 ` [virtio-dev] " Ilya Lesokhin 2017-10-30 2:08 ` Michael S. Tsirkin 2017-10-30 2:08 ` [virtio-dev] " Michael S. Tsirkin 2017-10-30 6:30 ` [virtio-dev] " Ilya Lesokhin 2017-10-30 16:30 ` Michael S. Tsirkin 2017-10-30 16:30 ` [virtio-dev] " Michael S. Tsirkin 2017-10-30 6:30 ` Ilya Lesokhin 2017-09-10 5:06 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=20171025191346-mutt-send-email-mst@kernel.org \ --to=mst@redhat.com \ --cc=ilyal@mellanox.com \ --cc=virtio-dev@lists.oasis-open.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.