From: Rusty Russell <rusty-8n+1lVoiYb80n/F98K4Iww@public.gmane.org>
To: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
virtualization
<virtualization-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>
Subject: Re: [PATCH 00/10] PV-IO v3
Date: Tue, 21 Aug 2007 09:24:46 +1000 [thread overview]
Message-ID: <1187652286.19435.137.camel@localhost.localdomain> (raw)
In-Reply-To: <46C9A150.60101-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
On Mon, 2007-08-20 at 17:12 +0300, Avi Kivity wrote:
> Dor Laor wrote:
> > Using Rusty's code there is no waste.
> > Each descriptor has a flag (head|next). Next flag stands for pointer to
> > the
> > next descriptor with u32 next index. So the waste is 4 bytes.
> > Sg descriptors are chained on the same descriptor ring.
> >
>
> Block I/O can easily require 256 sglist entries, eating up your ring.
Absolutely; I think we'd want this variable sized, rather than a single
page as the current implementation does for no really sound reason.
That said, I don't have a problem with Avi's out-of-band mechanism. A
"DMA" hypercall can follow that almost as easily, and it does give that
nice "fixed number of slots" effect.
Cheers,
Rusty.
-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
next prev parent reply other threads:[~2007-08-20 23:24 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-16 23:13 [PATCH 00/10] PV-IO v3 Gregory Haskins
[not found] ` <20070816231357.8044.55943.stgit-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-16 23:14 ` [PATCH 01/10] IOQ: Adding basic definitions for IO-Queue logic Gregory Haskins
2007-08-16 23:14 ` [PATCH 02/10] PARAVIRTUALIZATION: Add support for a bus abstraction Gregory Haskins
2007-08-16 23:14 ` [PATCH 03/10] IOQ: Add an IOQ network driver Gregory Haskins
2007-08-16 23:14 ` [PATCH 04/10] IOQNET: Add a test harness infrastructure to IOQNET Gregory Haskins
2007-08-16 23:14 ` [PATCH 05/10] IRQ: Export create_irq/destroy_irq Gregory Haskins
2007-08-16 23:14 ` [PATCH 06/10] KVM: Add a guest side driver for IOQ Gregory Haskins
2007-08-16 23:14 ` [PATCH 07/10] KVM: Add a gpa_to_hva helper function Gregory Haskins
2007-08-16 23:14 ` [PATCH 08/10] KVM: Add support for IOQ Gregory Haskins
2007-08-16 23:14 ` [PATCH 09/10] KVM: Add PVBUS support to the KVM host Gregory Haskins
2007-08-16 23:14 ` [PATCH 10/10] KVM: Add an IOQNET backend driver Gregory Haskins
2007-08-17 1:25 ` [PATCH 00/10] PV-IO v3 Rusty Russell
[not found] ` <1187313953.6449.70.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-17 5:26 ` Gregory Haskins
[not found] ` <1187328402.4363.110.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-17 7:43 ` Rusty Russell
[not found] ` <1187336618.6449.106.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-17 13:50 ` Gregory Haskins
[not found] ` <1187358614.4363.135.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-20 23:28 ` Rusty Russell
[not found] ` <1187652496.19435.141.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-21 7:33 ` Dor Laor
[not found] ` <64F9B87B6B770947A9F8391472E032160D464FEB-yEcIvxbTEBqsx+V+t5oei8rau4O3wl8o3fe8/T/H7NteoWH0uzbU5w@public.gmane.org>
2007-08-21 7:58 ` Rusty Russell
[not found] ` <1187683122.19435.171.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-21 12:00 ` Gregory Haskins
[not found] ` <1187697638.4363.277.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-21 12:25 ` Avi Kivity
[not found] ` <46CAD9CC.6050209-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-08-21 13:11 ` Gregory Haskins
2007-08-21 13:47 ` Rusty Russell
[not found] ` <1187704038.19435.194.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-21 14:06 ` Gregory Haskins
[not found] ` <1187705162.4363.323.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-21 16:47 ` Gregory Haskins
[not found] ` <1187714864.4363.358.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-21 17:12 ` Avi Kivity
[not found] ` <46CB1D06.1040005-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-08-21 17:17 ` Gregory Haskins
2007-08-22 3:29 ` Rusty Russell
[not found] ` <1187753365.6174.26.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-22 9:18 ` Christian Borntraeger
[not found] ` <200708221118.00990.borntraeger-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
2007-08-22 9:26 ` Dor Laor
[not found] ` <64F9B87B6B770947A9F8391472E032160D503D81-yEcIvxbTEBqsx+V+t5oei8rau4O3wl8o3fe8/T/H7NteoWH0uzbU5w@public.gmane.org>
2007-08-22 9:30 ` Christian Borntraeger
[not found] ` <200708221130.17364.borntraeger-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
2007-08-22 10:05 ` Dor Laor
2007-08-22 10:40 ` Rusty Russell
[not found] ` <1187779205.6174.87.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2007-08-22 11:47 ` Avi Kivity
2007-08-21 12:29 ` Avi Kivity
2007-08-19 9:24 ` Avi Kivity
[not found] ` <46C80C5B.7070009-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-08-20 13:50 ` Gregory Haskins
2007-08-20 14:03 ` [kvm-devel] " Dor Laor
[not found] ` <64F9B87B6B770947A9F8391472E032160D4649E2-yEcIvxbTEBqsx+V+t5oei8rau4O3wl8o3fe8/T/H7NteoWH0uzbU5w@public.gmane.org>
2007-08-20 14:12 ` Avi Kivity
[not found] ` <46C9A150.60101-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-08-20 23:24 ` Rusty Russell [this message]
2007-08-20 14:17 ` Gregory Haskins
[not found] ` <1187617806.4363.179.camel-5CR4LY5GPkvLDviKLk5550HKjMygAv58XqFh9Ls21Oc@public.gmane.org>
2007-08-20 14:14 ` Avi Kivity
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=1187652286.19435.137.camel@localhost.localdomain \
--to=rusty-8n+1lvoiyb80n/f98k4iww@public.gmane.org \
--cc=avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org \
--cc=kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
--cc=virtualization-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox