Tracing 'async' and *pfn is useless, since 'async' is always true,
and '*pfn' is always fault_pfn'
We can trace 'gva' and 'gfn' instead, it can help us to see the
life-cycle of an async_pf
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/mmu.c |2 +-
Use 'DECLARE_EVENT_CLASS' to cleanup async_pf tracepoints
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
include/trace/events/kvm.h | 76 ---
1 files changed, 35 insertions(+), 41 deletions(-)
diff --git a/include/trace/events/kvm.h
The 'gfn' is not recorded if the next slot is empty
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/x86.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7876ec8..16f42ff 100644
---
In current code, it checks async pf completion out of the wait context,
like this:
if (vcpu-arch.mp_state == KVM_MP_STATE_RUNNABLE
!vcpu-arch.apf.halted)
r = vcpu_enter_guest(vcpu);
else {
..
Don't make a KVM_REQ_UNHALT request after async pf is completed since it
can break guest's 'halt' instruction.
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/include/asm/kvm_host.h |1 +
arch/x86/kvm/x86.c |5 +
virt/kvm/async_pf.c |
The current way is queued a complete async pf with:
asyc_pf.page = bad_page
async_pf.arch.gfn = 0
It has two problems while kvm_check_async_pf_completion handle this
async_pf:
- since !async_pf.page, it can retry a pseudo #PF
- it can delete gfn 0 from vcpu-arch.apf.gfns[]
The async_pf number is very few since only pending interrupt can
let it re-enter to the guest mode.
During my test(Host 4 CPU + 4G, Guest 4 VCPU + 6G), it's no
more than 10 requests in the system.
So, we can only increase the completion counter in the work queue
context, and walk
It can help us to see the state of async pf
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
---
arch/x86/kvm/x86.c |3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c0e7ad0..2dd8059 100644
--- a/arch/x86/kvm/x86.c
On 10/27/2010 07:59 AM, Feng Yang wrote:
- Michael Goldish mgold...@redhat.com wrote:
From: Michael Goldish mgold...@redhat.com
To: autot...@test.kernel.org, kvm@vger.kernel.org
Cc: Michael Goldish mgold...@redhat.com
Sent: Wednesday, October 27, 2010 12:49:43 AM GMT +08:00 Beijing /
On 10/25/2010 03:58 PM, Marcelo Tosatti wrote:
drop_spte should not attempt to rmap_remove a non present shadow pte.
This fixes a BUG_ON seen on kvm-autotest.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line
On 10/22/2010 06:18 PM, Marcelo Tosatti wrote:
v2:
- remove kvm_mmu_set_base_ptes
- fix mmu_set_spte overwrite thinko
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
This patch series just change the way we allocate dirty bitmaps but don't
change timing related issues.
- Changelog
I have not changed anything about patch 1 and 2 since I got
looks good comment from Marcelo. Just rebased.
Patch 3 has become simpler by rebasing on top of this series.
This makes it easy to change the way of allocating/freeing dirty bitmaps.
Signed-off-by: Takuya Yoshikawa yoshikawa.tak...@oss.ntt.co.jp
Signed-off-by: Fernando Luis Vazquez Cao ferna...@oss.ntt.co.jp
---
virt/kvm/kvm_main.c | 30 +++---
1 files changed, 23
Currently x86's kvm_vm_ioctl_get_dirty_log() needs to allocate a bitmap by
vmalloc() which will be used in the next logging and this has been causing
bad effect to VGA and live-migration: vmalloc() consumes extra systime,
triggers tlb flush, etc.
This patch resolves this issue by pre-allocating
Currently we are using vmalloc() for all dirty bitmaps even if
they are small enough, say less than K bytes.
We use kmalloc() if dirty bitmap size is less than or equal to
PAGE_SIZE so that we can avoid vmalloc area usage for VGA.
Signed-off-by: Takuya Yoshikawa yoshikawa.tak...@oss.ntt.co.jp
On 10/26/2010 08:33 PM, Blue Swirl wrote:
Why two types? I think some devices use PIO on a PC and MMIO on other
architectures. Sharing the type would allow sharing code.
Then there are the functions provided by rwhandler.c. I think that
interface makes even more sense compared to
Signed-off-by: Michael Goldish mgold...@redhat.com
---
client/tests/kvm/kvm_vm.py | 25 +++--
1 files changed, 11 insertions(+), 14 deletions(-)
diff --git a/client/tests/kvm/kvm_vm.py b/client/tests/kvm/kvm_vm.py
index bb24c6a..02d7dff 100755
---
Clear the list of netdev IDs before generating new ones.
Signed-off-by: Michael Goldish mgold...@redhat.com
---
client/tests/kvm/kvm_vm.py |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/client/tests/kvm/kvm_vm.py b/client/tests/kvm/kvm_vm.py
index 02d7dff..a65e2e9
Add aliases to maintain compatibility with tests that use the long names.
Signed-off-by: Michael Goldish mgold...@redhat.com
---
client/tests/kvm/kvm_subprocess.py | 25 +
1 files changed, 25 insertions(+), 0 deletions(-)
diff --git a/client/tests/kvm/kvm_subprocess.py
On Wed, Oct 27, 2010 at 05:01:49PM +0800, Xiao Guangrong wrote:
Tracing 'async' and *pfn is useless, since 'async' is always true,
and '*pfn' is always fault_pfn'
We can trace 'gva' and 'gfn' instead, it can help us to see the
life-cycle of an async_pf
Make sense. This is leftover from
On Wed, Oct 27, 2010 at 05:02:50PM +0800, Xiao Guangrong wrote:
Use 'DECLARE_EVENT_CLASS' to cleanup async_pf tracepoints
Signed-off-by: Xiao Guangrong xiaoguangr...@cn.fujitsu.com
Nice
Acked-by: Gleb Natapov g...@redhat.com
---
include/trace/events/kvm.h | 76
On Wed, Oct 27, 2010 at 05:03:33PM +0800, Xiao Guangrong wrote:
The 'gfn' is not recorded if the next slot is empty
This function is not used for gfn recording, only to search for recorded
gfn, but without the fix it walks over all entries if gfn is not in the
hash.
Signed-off-by: Xiao
On Wed, Oct 27, 2010 at 05:04:58PM +0800, Xiao Guangrong wrote:
In current code, it checks async pf completion out of the wait context,
like this:
if (vcpu-arch.mp_state == KVM_MP_STATE_RUNNABLE
!vcpu-arch.apf.halted)
r = vcpu_enter_guest(vcpu);
On Wed, Oct 27, 2010 at 05:05:57PM +0800, Xiao Guangrong wrote:
Don't make a KVM_REQ_UNHALT request after async pf is completed since it
can break guest's 'halt' instruction.
Why is it a problem? CPU may be unhalted by different events so OS
shouldn't depend on it.
Signed-off-by: Xiao
On 10/26/2010 10:37 PM, H. Peter Anvin wrote:
On 10/26/2010 01:27 PM, Andi Kleen wrote:
That is an issue too, as 3.x does a lot fewer optimizations than 4.x.
Well to be fair the default -Os build disables most of the fancy stuff
(and the resulting code is often terrible)
I guess it
On Wed, Oct 27, 2010 at 05:07:32PM +0800, Xiao Guangrong wrote:
The current way is queued a complete async pf with:
asyc_pf.page = bad_page
async_pf.arch.gfn = 0
It has two problems while kvm_check_async_pf_completion handle this
async_pf:
- since !async_pf.page, it can retry a
On Wed, Oct 27, 2010 at 05:10:51PM +0800, Xiao Guangrong wrote:
It can help us to see the state of async pf
I have patch to add three async pf statistics:
apf_not_present
apf_present
apf_doublefault
But Avi now wants to deprecate debugfs interface completely and move
towards ftrace, so I had
On Wed, Oct 27, 2010 at 05:09:41PM +0800, Xiao Guangrong wrote:
The async_pf number is very few since only pending interrupt can
let it re-enter to the guest mode.
During my test(Host 4 CPU + 4G, Guest 4 VCPU + 6G), it's no
more than 10 requests in the system.
So, we can only increase the
On Wed, 2010-10-27 at 01:59 -0400, Feng Yang wrote:
- Michael Goldish mgold...@redhat.com wrote:
From: Michael Goldish mgold...@redhat.com
To: autot...@test.kernel.org, kvm@vger.kernel.org
Cc: Michael Goldish mgold...@redhat.com
Sent: Wednesday, October 27, 2010 12:49:43 AM GMT
On 10/25/2010 12:52 PM, Avi Kivity wrote:
I'm okay with making tags and branches of seabios for bug fixes. So
far qemu/kvm has just grabbed various builds of seabios - is it
worthwhile to branch off of the seabios-0.6.1 version - which would
mean qemu/kvm would pull in additional changes
On Wednesday 27 October 2010, Sridhar Samudrala wrote:
Support a new 'passthru' mode with macvlan and 'mode' parameter
with macvtap devices.
Signed-off-by: Sridhar Samudrala s...@us.ibm.com
Can you split this into two patches?
We definitely want the part adding support for macvtap device
On Wednesday 27 October 2010, Sridhar Samudrala wrote:
With the current default macvtap mode, a KVM guest using virtio with
macvtap backend has the following limitations.
- cannot change/add a mac address on the guest virtio-net
- cannot create a vlan device on the guest virtio-net
- cannot
On Wed, 27 Oct 2010, Alex Williamson wrote:
I've actually been working on porting the qemu vfio driver over to
qemu-kvm recently, and nearly have it working. For MSI-X interrupts
I've ported to the common msix.c code, which abstracts how the interrupt
is actually sent to the guest. I've also
(apologies for double posting of this message...mail client fubar)
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On 10/26/2010 10:48 AM, Glauber Costa wrote:
On Tue, 2010-10-26 at 09:59 -0700, Jeremy Fitzhardinge wrote:
If the guest domain has been suspend/resumed or migrated, then the
system clock backing the pvclock clocksource may revert to a smaller
value (ie, can be non-monotonic across the
On Wed, 2010-10-27 at 11:23 -0700, Etienne Martineau wrote:
On Wed, 27 Oct 2010, Alex Williamson wrote:
I've actually been working on porting the qemu vfio driver over to
qemu-kvm recently, and nearly have it working. For MSI-X interrupts
I've ported to the common msix.c code, which
On Wed, Oct 27, 2010 at 9:26 AM, Avi Kivity a...@redhat.com wrote:
On 10/26/2010 08:33 PM, Blue Swirl wrote:
Why two types? I think some devices use PIO on a PC and MMIO on other
architectures. Sharing the type would allow sharing code.
Then there are the functions provided by
On Wed, 2010-10-20 at 14:55 +0800, Feng Yang wrote:
If a connection and stdin are idle for more than timeout seconds,
then the connection is silently closed. withou this paramter,
nc will listen forever for a connection. This may cause our test
hang. redmine issue:
I'll check it this evening when I'm at a working network again :(
Jeremy Fitzhardinge jer...@goop.org wrote:
On 10/26/2010 10:48 AM, Glauber Costa wrote:
On Tue, 2010-10-26 at 09:59 -0700, Jeremy Fitzhardinge wrote:
If the guest domain has been suspend/resumed or migrated, then the
system
On Mon, 2010-09-27 at 17:43 +0530, Yogananth Subramanian wrote:
The patch creates two new files 'scripts/cyg_install.py' and
'tests/cyg_install'. 'scripts/cyg_install.py' is used to install cygwin in
unattended mode. This patch also introduces a new parameter 'patch_file'to
run_autotest() in
This patch will change vhost TX used buffer guest signaling from one by
one to 3/4 ring size. I have tried different size, like 4, 16, 1/4 size,
1/2 size, and found that the large size is best for message size between
256 - 4K with netperf TCP_STREAM test, so 3/4 of the ring size is picked
up for
This patch changes vhost TX used buffer signal to guest from one by
one to up to 3/4 of vring size. This change improves vhost TX message
size from 256 to 8K performance for both bandwidth and CPU utilization
without inducing any regression.
Signed-off-by: Shirley Ma x...@us.ibm.com
---
On Tue, 2010-10-26 at 18:49 +0200, Michael Goldish wrote:
PEP 8 states that class names should use the CapWords convention.
kvm_spawn - Spawn
kvm_tail - Tail
kvm_expect - Expect
kvm_shell_session - ShellSession
This is an RFC because I wonder if the proposed names are too general, even
On Wed, 27 Oct 2010, Alex Williamson wrote:
No, emulated devices trigger interrupts directly with qemu_set_irq.
irqfds are currently only used by vhost afaik, since it's being
interrupted externally, much like pass through devices are.
Fair enough. Thanks for the clarification.
Sort of.
This patch changes vhost TX used buffer guest signal from one by
one to 3/4 of vring size. This change improves vhost TX transmission
both bandwidth and CPU utilization performance for 256 to 8K messages s
ize without inducing any regression.
Signed-off-by: Shirley Ma x...@us.ibm.com
---
On Wed, 2010-10-27 at 14:43 -0700, Etienne Martineau wrote:
On Wed, 27 Oct 2010, Alex Williamson wrote:
No, emulated devices trigger interrupts directly with qemu_set_irq.
irqfds are currently only used by vhost afaik, since it's being
interrupted externally, much like pass through devices
I've been attempting to patch up the qemu-kvm package to allow me to
achieve a display resolution of 1920x2400. I followed the suggestions
from the Wiki FAQ on the subject, but ran into a wall.
I patched up the hw/vga_int.h file to bump VBE_DISPI_MAX_YRES to 2400,
and (as a test) replaced the
- Lucas Meneghel Rodrigues l...@redhat.com wrote:
From: Lucas Meneghel Rodrigues l...@redhat.com
To: Feng Yang fy...@redhat.com
Cc: autot...@test.kernel.org, kvm@vger.kernel.org
Sent: Thursday, October 28, 2010 4:26:17 AM GMT +08:00 Beijing / Chongqing /
Hong Kong / Urumqi
Subject:
Resubmit this patch for fixing some minor error (white space, typo).
Signed-off-by: Shirley Ma x...@us.ibm.com
---
drivers/vhost/net.c | 20 +++-
drivers/vhost/vhost.c | 32
drivers/vhost/vhost.h |3 +++
3 files changed, 54
On Wed, Oct 27, 2010 at 04:58:20PM -0600, Alex Williamson wrote:
On Wed, 2010-10-27 at 14:43 -0700, Etienne Martineau wrote:
On Wed, 27 Oct 2010, Alex Williamson wrote:
No, emulated devices trigger interrupts directly with qemu_set_irq.
irqfds are currently only used by vhost afaik, since
Michael S. Tsirkin m...@redhat.com wrote on 10/26/2010 04:39:13 PM:
(merging two posts into one)
I think we discussed the need for external to guest testing
over 10G. For large messages we should not see any change
but you should be able to get better numbers for small messages
assuming a MQ
On Thu, 2010-10-28 at 06:58 +0200, Michael S. Tsirkin wrote:
On Wed, Oct 27, 2010 at 04:58:20PM -0600, Alex Williamson wrote:
On Wed, 2010-10-27 at 14:43 -0700, Etienne Martineau wrote:
On Wed, 27 Oct 2010, Alex Williamson wrote:
No, emulated devices trigger interrupts directly with
On Wed, Oct 27, 2010 at 09:40:04PM -0700, Shirley Ma wrote:
Resubmit this patch for fixing some minor error (white space, typo).
Signed-off-by: Shirley Ma x...@us.ibm.com
My concern is this can delay signalling for unlimited time.
Could you pls test this with guests that do not have
On Wed, Oct 27, 2010 at 11:17:42PM -0600, Alex Williamson wrote:
On Thu, 2010-10-28 at 06:58 +0200, Michael S. Tsirkin wrote:
On Wed, Oct 27, 2010 at 04:58:20PM -0600, Alex Williamson wrote:
On Wed, 2010-10-27 at 14:43 -0700, Etienne Martineau wrote:
On Wed, 27 Oct 2010, Alex Williamson
On Thu, Oct 28, 2010 at 10:44:14AM +0530, Krishna Kumar2 wrote:
Michael S. Tsirkin m...@redhat.com wrote on 10/26/2010 04:39:13 PM:
(merging two posts into one)
I think we discussed the need for external to guest testing
over 10G. For large messages we should not see any change
but you
55 matches
Mail list logo