On Sat, Mar 29, 2008 at 01:09:30AM +, Jamie Lokier wrote:
> Marcelo Tosatti wrote:
> > I don't think the first qemu_aio_flush() is necessary because the fsync
> > request will be enqueued after pending ones:
> >
> >aio_fsync() function does a sync on all outstanding
> >asynchr
From 1028321e00b0f3a60fc414484754f489a70f2400 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Sat, 29 Mar 2008 09:23:37 +0800
Subject: [PATCH] Add API for allocating Dynamic TR resouce.
Dynamic TR resouce should be managed in an uniform way.
Signed-off-by: Xiantao Zhang <[E
On Saturday 29 March 2008, Jamie Lokier wrote:
> Paul Brook wrote:
> > > That'll depend on what kind of device is emulated. Does the SCSI
> > > emulation handle multiple in-flight commands with any guarantee on
> > > order?
> >
> > SCSI definitely allows (and we emulate) multiple in flight command
>From 454e8a4473ed13ce313b2ba3b654feb926a891b7 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:57:33 +0800
Subject: [PATCH] kvm/ia64: How to boot up guests on kvm/ia64
Signed-off-by: Xiantao Zhang <[EMAIL PROTECTED]>
---
Documentation/ia64/kvm-howto.txt
Compared with V6,
1. Updated the PATCH 01 according to Tony's comments.
2. Updated the PATCH 14 according to Akio's comments.
3. Updated the PATCH 17 according to Akio's comments.
The latest patchset is located at
git://git.kernel.org/pub/scm/linux/kernel/git/xiantao/kvm-ia64.git
kvm-ia64-mc7.
Akio Takebe wrote:
> Hi,
>
> I found 3 typos.
>
>> +3. Get Guest Firmware named as Flash.fd, and put it under right
>> place: + (1) If you have the guest firmware (binary)released by
Intel
>> Corp for Xen, you can use it directly.
>> +(2) If you want to build a guest firmware form souce c
Akio Takebe wrote:
> Hi, Xiantao and Anthony
>
>> +void getfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
>> +struct kvm_pt_regs *regs)
>> +{
>> +/* Take floating register rotation into consideration*/
>> +if (regnum >= IA64_FIRST_ROTATING_FR)
>> +
INITIAL_PSR_VALUE_AT_INTERRUPTION 0x001808028034
>> +
> Xen also use this value, you had better use macros of PSR bits.
> Or you can add the same comments as Xen.
Hi, Akio.
The comment is where it is used. Anyway, using macro is better.
Changed.
-
Paul Brook wrote:
> > That'll depend on what kind of device is emulated. Does the SCSI
> > emulation handle multiple in-flight commands with any guarantee on
> > order?
>
> SCSI definitely allows (and we emulate) multiple in flight commands.
> I can't find any requirement that writes must complet
Akio Takebe wrote:
> Hi, Xiantao
>
> a comments is below.
>
>
>> +// 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
>> +ENTRY(kvm_interrupt) +mov r31=pr// prepare to
save predicates
>> +mov r19=12
>> +mov r29=cr.ipsr
>> +;;
>> +tbit.z p6,p7=r29,IA64_
> That'll depend on what kind of device is emulated. Does the SCSI
> emulation handle multiple in-flight commands with any guarantee on
> order?
SCSI definitely allows (and we emulate) multiple in flight commands.
I can't find any requirement that writes must complete before a subsequent
SYNCHRO
Marcelo Tosatti wrote:
> static void raw_flush(BlockDriverState *bs)
> {
> BDRVRawState *s = bs->opaque;
> -fsync(s->fd);
> +raw_aio_flush(bs);
> +
> +/* We rely on the fact that no other AIO will be submitted
> + * in parallel, but this should be fixed by per-device
> +
Marcelo Tosatti wrote:
> I don't think the first qemu_aio_flush() is necessary because the fsync
> request will be enqueued after pending ones:
>
>aio_fsync() function does a sync on all outstanding
>asynchronous I/O operations associated with
>aiocbp->aio_fildes.
>
>
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA512
Hi,
Guests seem to be doing a lot of timer related polling, is there any way
to reduce that (which would reduce load on the host):
select(0, [], NULL, NULL, {0, 0}) = 0 (Timeout)
clock_gettime(CLOCK_MONOTONIC, {1046993, 598906624}) = 0
clock_
I'm pleased to report that we now have working network support in the
guest, via the virtio-net driver. In fact, we can use NFS for the
guest's root filesystem. :) Boot log attached.
The bad news is that it's very slow, but the good news is that it's nice
to be improving performance rather than de
Avi Kivity wrote:
> No plans at this point. SCSI emulation should provide decent performance.
Are there plans for addressing QEMU's issues w/ the SCSI emulation for
Windows guests?
https://sourceforge.net/tracker/?func=detail&atid=893831&aid=1895893&group_id=180599
[posting this in part as a w
# HG changeset patch
# User Jerone Young <[EMAIL PROTECTED]>
# Date 1206732207 18000
# Node ID 82daf2163e7a8eb26b446550937e517be86c297c
# Parent e48cf2ad6c85c457ff64c04b83960fc305420842
[mq]: add_kvm_guest_wait_handlers
-
Ch
On Fri, Mar 28, 2008 at 03:01:13PM +0100, Andrea Arcangeli wrote:
> @@ -271,8 +292,12 @@ int __kvm_set_memory_region(struct kvm *kvm,
>
> r = -EINVAL;
> /* General sanity checks */
> + if (mem->userspace_addr & (PAGE_SIZE - 1))
> + goto out;
> if (mem->memory_siz
This is crashing at boot my lowmem reserved RAM patch. This is causing
GFP_DMA allocations at boot for no good reason. It crashes in my case
because there's no ram below 16M available to linux. Are you sure this
is needed at all, for sure if there's any bug this isn't the right fix.
Please reverse
On Fri, Mar 28, 2008 at 06:03:25PM +, Jamie Lokier wrote:
> Marcelo Tosatti wrote:
> > On Fri, Mar 28, 2008 at 03:07:03PM +, Jamie Lokier wrote:
> > > Marcelo Tosatti wrote:
> > > > Its necessary to guarantee that pending AIO writes have reached stable
> > > > storage when the flush reques
On Fri, Mar 28, 2008 at 05:00:39PM +, Paul Brook wrote:
> > > Surely you should be using the normal aio notification to wait for the
> > > aio_fsync to complete before reporting success to the device.
> >
> > qemu_aio_flush() will wait for all pending AIO requests (including
> > aio_fsync) to c
Marcelo Tosatti wrote:
> On Fri, Mar 28, 2008 at 03:07:03PM +, Jamie Lokier wrote:
> > Marcelo Tosatti wrote:
> > > Its necessary to guarantee that pending AIO writes have reached stable
> > > storage when the flush request returns.
> > >
> > > Also change fsync() to fdatasync(), since the mod
Marcelo Tosatti writes ("[Qemu-devel] [PATCH] QEMU: fsync AIO writes on flush
request "):
> Its necessary to guarantee that pending AIO writes have reached stable
> storage when the flush request returns.
Surely it isn't necessary to call qemu_aio_flush ? Because those
pending AIO writes have no
> > Surely you should be using the normal aio notification to wait for the
> > aio_fsync to complete before reporting success to the device.
>
> qemu_aio_flush() will wait for all pending AIO requests (including
> aio_fsync) to complete.
Then why do you need to separate fdatasync?
Paul
-
On Fri, Mar 28, 2008 at 04:40:54PM +, Paul Brook wrote:
> On Friday 28 March 2008, Marcelo Tosatti wrote:
> > On Fri, Mar 28, 2008 at 03:07:03PM +, Jamie Lokier wrote:
> > > Marcelo Tosatti wrote:
> > > > Its necessary to guarantee that pending AIO writes have reached stable
> > > > storage
Title: Sicoob Executivo
Caso não consiga visualizar esta mensagem
corretamente, clique aqui.
Caso você não queira receber mais
informações de nossa Cooperativa,
responda está mensagem solicitando a exclusão de seu
e-mail
--
On Friday 28 March 2008, Marcelo Tosatti wrote:
> On Fri, Mar 28, 2008 at 03:07:03PM +, Jamie Lokier wrote:
> > Marcelo Tosatti wrote:
> > > Its necessary to guarantee that pending AIO writes have reached stable
> > > storage when the flush request returns.
> > >
> > > Also change fsync() to fd
On Fri, Mar 28, 2008 at 03:07:03PM +, Jamie Lokier wrote:
> Marcelo Tosatti wrote:
> > Its necessary to guarantee that pending AIO writes have reached stable
> > storage when the flush request returns.
> >
> > Also change fsync() to fdatasync(), since the modification time is not
> > critical
Marcelo Tosatti wrote:
> Its necessary to guarantee that pending AIO writes have reached stable
> storage when the flush request returns.
>
> Also change fsync() to fdatasync(), since the modification time is not
> critical data.
> +if (aio_fsync(O_DSYNC, &acb->aiocb) < 0) {
> BDRVRawSta
Its necessary to guarantee that pending AIO writes have reached stable
storage when the flush request returns.
Also change fsync() to fdatasync(), since the modification time is not
critical data.
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Index: kvm-userspace.io/qemu/block-raw-posix.c
The best shop
Today you can buy medical goods sitting at home
*Most popular medications
*Great choice
*The cheapest cost you have ever seen
http://www.lakerub.com
-
Check out the new SourceForge.net Marketplace.
It's the
Hi,
I found 3 typos.
>+3. Get Guest Firmware named as Flash.fd, and put it under right place:
>+ (1) If you have the guest firmware (binary)released by Intel
>Corp for Xen, you can use it directly.
>+ (2) If you want to build a guest firmware form souce code.
souce ---> source
>+5. Kno
Hi,
>>From 2dbf7c93ff5e36a221761c690ff12e7be48a6bb2 Mon Sep 17 00:00:00 2001
>From: Xiantao Zhang <[EMAIL PROTECTED]>
>Date: Wed, 12 Mar 2008 13:49:38 +0800
>Subject: [PATCH] kvm/ia64: add optimization for some virtulization
>faults
>
>optvfault.S adds optimization for some performance-critical
>v
Hello list,
I encountered two Windows Server 2003 Std SP1 guests which would
randomly hang with 100% CPU after several hours of normal operation.
The guest would not respond at all, not even to ping requests. Its
process on the host uses 100% CPU.
The Host:
Dual-Core AMD Opteron(tm) Processor 2
Hi, Xiantao and Anthony
>+void getfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
>+ struct kvm_pt_regs *regs)
>+{
>+ /* Take floating register rotation into consideration*/
>+ if (regnum >= IA64_FIRST_ROTATING_FR)
>+ regnum = IA64_FIRST_RO
I thought some more about this.
BTW, for completeness: normally (with exception of vm_destroy) the
put_page run by rmap_remove won't be the last one, but still the page
can go in the freelist a moment after put_page runs (leading to the
same problem). The VM is prevented to free the page while it'
Aurelien Jarno wrote:
> On Wed, Mar 26, 2008 at 09:57:16PM -0300, Glauber Costa wrote:
>> They seem legal in real hardware, even though the EOI
>> is a write-only register. By "legal" I mean they are completely
>> ignored, but at least, don't cause any bits to be set at ESR.
>>
>> Without this patc
Hi, Xiantao
a comments is below.
>+// 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
>+ENTRY(kvm_interrupt)
>+mov r31=pr// prepare to save predicates
>+mov r19=12
>+mov r29=cr.ipsr
>+;;
>+tbit.z p6,p7=r29,IA64_PSR_VM_BIT
>+tbit.z p0,p15=r29,IA64_
Hi, Xiantao
It's good, I have some small comments.
>+
>+/* SDM vol2 5.5 - IVA based interruption handling */
>+#define INITIAL_PSR_VALUE_AT_INTERRUPTION 0x001808028034
>+
Xen also use this value, you had better use macros of PSR bits.
Or you can add the same comments as Xen.
>+
>+/*
>+ * Ha
Thomas Mueller wrote:
> hi there
>
> is the EFI BIOS (http://fabrice.bellard.free.fr/qemu/download.html ->
> efi-bios.tar.bz2) supposed to work with kvm? I wan't to try installing
> Mac OS X.
>
There is a guy called Alexander Graf that have succeeded this, see.
http://alex.csgraf.de/self/?par
hi there
is the EFI BIOS (http://fabrice.bellard.free.fr/qemu/download.html ->
efi-bios.tar.bz2) supposed to work with kvm? I wan't to try installing
Mac OS X.
README of efi-bios tells "You must use the CVS version of QEMU to use
the BIOS (the version 0.9.0 won't work)" so, which qemu version
Hi all,
I am running on kernel 2.6.24, KVM 63 trying windows guests working
quite well.
but why tells the device manager that I have 15 CPU`s (QEMU Virtual CPU
version 0.9.1)? The windows task manager is just showing one as expected.
I got this issue on winxp sp2 and on vista sp1
>From 2dbf7c93ff5e36a221761c690ff12e7be48a6bb2 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:49:38 +0800
Subject: [PATCH] kvm/ia64: add optimization for some virtulization
faults
optvfault.S adds optimization for some performance-critical
virtualization
>From f21b39650592fff4d07c94730b0f4e9aa093b9a8 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:50:13 +0800
Subject: [PATCH] kvm/ia64: Generate offset values for assembly code use.
asm-offsets.c will generate offset values used for assembly code
for some f
>From 9118d25b4e98bef3a62429f8c150e8d429396c40 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 12:58:02 +0800
Subject: [PATCH] Implement smp_call_function_mask for ia64
This function provides more flexible interface for smp
infrastructure.
Signed-off-by: Xia
>From 56d3f7acf8d45d2491646be77ced344dcc516cd7 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:45:40 +0800
Subject: [PATCH] kvm/ia64: Add TLB virtulization support.
vtlb.c includes tlb/VHPT virtulization.
Signed-off-by: Anthony Xu <[EMAIL PROTECTED]>
Sign
>From 5f82ea88c095cf89cbae920944c05e578f35365f Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 14:48:09 +0800
Subject: [PATCH] kvm/ia64: Add mmio decoder for kvm/ia64.
mmio.c includes mmio decoder routines.
Signed-off-by: Anthony Xu <[EMAIL PROTECTED]>
Signe
Refined according to Tony's comments.
>From 837f0508a617ea0386808de9fd0f42ef4aefe5e0 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Thu, 27 Mar 2008 10:18:29 +0800
Subject: [PATCH] Add API for allocating TR resouce.
Dynamic TR resouce should be managed in an uniform way.
>From cf64ba3c5464b7da6c6fb2871b8424a08ade3ab2 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Fri, 28 Mar 2008 09:48:10 +0800
Subject: [PATCH] kvm/ia64: Add header files for kvm/ia64.
Three header files are added:
asm-ia64/kvm.h
asm-ia64/kvm_host.h
asm-ia64/kvm_para.h
Signe
>From 0639faa4a3347771e793e33652667272cc140240 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Fri, 28 Mar 2008 14:58:47 +0800
Subject: [PATCH] kvm:ia64 Enable kvm build for ia64
Update the related Makefile and KConfig for kvm build
Signed-off-by: Xiantao Zhang <[EMAIL PROTE
>From 6af8b4d7ca1d4ec40cc634cf8b0d5ae8d2dc53ce Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:44:37 +0800
Subject: [PATCH] kvm/ia64: VMM module interfaces.
vmm.c adds the interfaces with kvm/module, and initialize global data
area.
Signed-off-by: Xiantao
>From 517a89fd248193f6a7049832e2c1b811afe98f96 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:57:33 +0800
Subject: [PATCH] kvm/ia64: How to boot up guests on kvm/ia64
Signed-off-by: Xiantao Zhang <[EMAIL PROTECTED]>
---
Documentation/ia64/kvm-howto.txt
>From ba064fc79c5d8577543ae6e4a201f622f0c4b777 Mon Sep 17 00:00:00 2001
From: Xiantao Zhang <[EMAIL PROTECTED]>
Date: Wed, 12 Mar 2008 13:42:18 +0800
Subject: [PATCH] kvm/ia64: Add kvm sal/pal virtulization support.
Some sal/pal calls would be traped to kvm for virtulization
from guest firmware.
S
Hi
This patchset enables kvm on ia64 platform. And it targets for Avi's
pull to mainline. Please review. If you don't have concerns, I will ask
Avi's pull for kvm.git. Thanks!
Also, you can get it from
git://git.kernel.org/pub/scm/linux/kernel/git/xiantao/kvm-ia64.git
kvm-ia64-mc6
Tony,
remove dependency to the pci linux headers added since
c10bf6159ff24501852c91a342c3077d5388b184 and that was generating the
following conflict :
qemu/hw/cirrus_vga.c:193:1: warning: "PCI_COMMAND_SERR" redefined
In file included from /usr/include/linux/pci.h:21,
from qemu
Hi, all,
This is today's KVM test result against kvm.git
2d3898859c4eafc8e67f805f38acae8f31bd24a4 and kvm-userspace.git
64173d009c1f4d163c425b14aa650df5b982428a.
One issue fixed:
1. slab error in kmem_cache_destroy(): cache `kvm_vcpu':
https://sourceforge.net/tracker/?func=detail&atid=893831&a
included through "qemu-kvm.h" -> "cpu.h" -> "cpu-defs.h" for all architectures
and resulting otherwise in :
qemu/qemu-kvm-x86.c:23:1: warning: "ARRAY_SIZE" redefined In file included
from ../cpu-defs.h:30,
from qemu/target-i386/cpu.h:45,
from ../qemu-common.h:62,
from qemu/hw/hw.h:5
On Fri, Mar 28, 2008 at 10:04:21AM +0300, Avi Kivity wrote:
> Carlo Marcelo Arenas Belon wrote:
> >qemu/qemu-kvm-x86.c:23:1: warning: "ARRAY_SIZE" redefined
> >In file included from ../cpu-defs.h:30,
> > from
> >
> > /var/tmp/portage/app-emulation/kvm-64/work/kvm-6
58 matches
Mail list logo
