From: Avi Kivity <avi@redhat.com>
To: Jan Kiszka <jan.kiszka@siemens.com>
Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: Re: [RFC v2 03/20] memory: merge adjacent segments of a single memory region
Date: Mon, 27 Jun 2011 17:11:52 +0300 [thread overview]
Message-ID: <4E088FA8.8010705@redhat.com> (raw)
In-Reply-To: <4E088C08.3090408@siemens.com>
On 06/27/2011 04:56 PM, Jan Kiszka wrote:
> On 2011-06-27 15:21, Avi Kivity wrote:
> > Simple implementations of memory routers, for example the Cirrus VGA memory banks
> > or the 440FX PAM registers can generate adjacent memory regions which are contiguous.
> > Detect these and merge them; this saves kvm memory slots and shortens lookup times.
>
> That reminds me of KVM_CAP_JOIN_MEMORY_REGIONS_WORKS. Have you checked
> if things still work in the absence of the feature or if we need to lift
> our requirements on the host kernel (would be 2.6.30, not that problematic)?
Good catch.
We should probably disable merging if it doesn't work. Or we should
declare that a kernel bug should be fixed in the kernel, not userspace,
and backport the fix to 2.6.27.whatever.
--
error compiling committee.c: too many arguments to function
WARNING: multiple messages have this Message-ID (diff)
From: Avi Kivity <avi@redhat.com>
To: Jan Kiszka <jan.kiszka@siemens.com>
Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: Re: [Qemu-devel] [RFC v2 03/20] memory: merge adjacent segments of a single memory region
Date: Mon, 27 Jun 2011 17:11:52 +0300 [thread overview]
Message-ID: <4E088FA8.8010705@redhat.com> (raw)
In-Reply-To: <4E088C08.3090408@siemens.com>
On 06/27/2011 04:56 PM, Jan Kiszka wrote:
> On 2011-06-27 15:21, Avi Kivity wrote:
> > Simple implementations of memory routers, for example the Cirrus VGA memory banks
> > or the 440FX PAM registers can generate adjacent memory regions which are contiguous.
> > Detect these and merge them; this saves kvm memory slots and shortens lookup times.
>
> That reminds me of KVM_CAP_JOIN_MEMORY_REGIONS_WORKS. Have you checked
> if things still work in the absence of the feature or if we need to lift
> our requirements on the host kernel (would be 2.6.30, not that problematic)?
Good catch.
We should probably disable merging if it doesn't work. Or we should
declare that a kernel bug should be fixed in the kernel, not userspace,
and backport the fix to 2.6.27.whatever.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2011-06-27 14:11 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-27 13:21 [RFC v2 00/20] Memory API Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 01/20] Hierarchical memory region API Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-28 10:03 ` Michael S. Tsirkin
2011-06-28 10:03 ` [Qemu-devel] " Michael S. Tsirkin
2011-06-28 10:28 ` Jan Kiszka
2011-06-28 10:28 ` [Qemu-devel] " Jan Kiszka
2011-06-28 11:53 ` Avi Kivity
2011-06-28 11:53 ` [Qemu-devel] " Avi Kivity
2011-06-28 12:07 ` Jan Kiszka
2011-06-28 12:07 ` [Qemu-devel] " Jan Kiszka
2011-06-28 12:09 ` Avi Kivity
2011-06-28 12:09 ` [Qemu-devel] " Avi Kivity
2011-06-28 12:46 ` Jan Kiszka
2011-06-28 12:46 ` [Qemu-devel] " Jan Kiszka
2011-06-28 12:53 ` Avi Kivity
2011-06-28 12:53 ` [Qemu-devel] " Avi Kivity
2011-06-28 13:25 ` Peter Maydell
2011-06-28 13:36 ` Avi Kivity
2011-06-28 16:27 ` Olivier Galibert
2011-06-28 11:51 ` Avi Kivity
2011-06-28 11:51 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 02/20] memory: implement dirty tracking Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 03/20] memory: merge adjacent segments of a single memory region Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:56 ` Jan Kiszka
2011-06-27 13:56 ` [Qemu-devel] " Jan Kiszka
2011-06-27 14:11 ` Avi Kivity [this message]
2011-06-27 14:11 ` Avi Kivity
2011-06-27 13:21 ` [RFC v2 04/20] Internal interfaces for memory API Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 05/20] exec.c: initialize memory map Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 06/20] pc: grab system_memory Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 07/20] pc: convert pc_memory_init() to memory API Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 08/20] pc: move global memory map out of pc_init1() and into its callers Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 09/20] pci: pass address space to pci bus when created Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 10/20] pci: add MemoryRegion based BAR management API Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 11/20] sysbus: add MemoryRegion based memory " Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:21 ` [RFC v2 12/20] usb-ohci: convert to MemoryRegion Avi Kivity
2011-06-27 13:21 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 13/20] pci: add API to get a BAR's mapped address Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 14/20] vmsvga: don't remember pci BAR address in callback any more Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 15/20] vga: convert vga and its derivatives to the memory API Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 16/20] cirrus: simplify mmio BAR access functions Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 17/20] cirrus: simplify bitblt " Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 18/20] cirrus: simplify vga window mmio " Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 19/20] vga: " Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 13:22 ` [RFC v2 20/20] cirrus: simplify linear framebuffer " Avi Kivity
2011-06-27 13:22 ` [Qemu-devel] " Avi Kivity
2011-06-27 15:13 ` [RFC v2 00/20] Memory API Avi Kivity
2011-06-27 15:13 ` [Qemu-devel] " Avi Kivity
2011-06-27 15:52 ` Michael S. Tsirkin
2011-06-27 15:52 ` [Qemu-devel] " Michael S. Tsirkin
2011-06-27 15:54 ` Avi Kivity
2011-06-27 15:54 ` [Qemu-devel] " Avi Kivity
2011-06-27 15:59 ` Michael S. Tsirkin
2011-06-27 15:59 ` [Qemu-devel] " Michael S. Tsirkin
2011-06-27 16:10 ` Avi Kivity
2011-06-27 16:10 ` [Qemu-devel] " Avi Kivity
2011-06-27 20:28 ` Anthony Liguori
2011-06-27 20:28 ` Anthony Liguori
2011-06-27 15:37 ` Anthony Liguori
2011-06-27 15:44 ` 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=4E088FA8.8010705@redhat.com \
--to=avi@redhat.com \
--cc=jan.kiszka@siemens.com \
--cc=kvm@vger.kernel.org \
--cc=qemu-devel@nongnu.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 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.