Bugs item #2976863, was opened at 2010-03-26 14:44
Message generated for change (Tracker Item Submitted) made by haoxudong
You can respond by visiting:
https://sourceforge.net/tracker/?func=detailatid=893831aid=2976863group_id=180599
Please note that this message will contain a full copy of the
On Sun, Jan 17, 2010 at 03:06:11PM +0200, Avi Kivity wrote:
On 01/10/2010 07:01 PM, Alexander Graf wrote:
While trying to compile an E500 vmlinux, I stumbled across a compilation bug
that was obviously there before I touched any of the code. A trace point
doesn't get the correct arguments.
Avi Kivity wrote:
2. ltp diotest running time is 2.54 times than before
https://sourceforge.net/tracker/?func=detailaid=2723366group_id=180599atid=893831
Can you check the performance of this with cache=writeback?
The common on the report referring to cache=writethrough is incorrect
On 26.03.2010, at 08:15, Bruce Majia wrote:
On Sun, Jan 17, 2010 at 03:06:11PM +0200, Avi Kivity wrote:
On 01/10/2010 07:01 PM, Alexander Graf wrote:
While trying to compile an E500 vmlinux, I stumbled across a compilation bug
that was obviously there before I touched any of the code. A
-Original Message-
From: Alexander Graf [mailto:ag...@suse.de]
Sent: Friday, March 26, 2010 5:10 PM
To: Bruce Majia
Cc: Avi Kivity; kvm@vger.kernel.org; kvm-ppc; Liu Yu-B13201
Subject: Re: [PATCH] KVM: PPC: E500 compile fix
On 26.03.2010, at 08:15, Bruce Majia wrote:
On
On 03/26/2010 11:39 AM, Hao, Xudong wrote:
I checked cache=writeback parameter, the diotest performance is much worse than no
this parameter(about 20 times).
Followed qemu help, my command is qemu-system-x86_64 -m 512 -smp 4 -net
nic,macaddr=00:16:3e:79:0c:db,model=rtl8139 -net
On Fri, Mar 26, 2010 at 10:10:19AM +0100, Alexander Graf wrote:
On 26.03.2010, at 08:15, Bruce Majia wrote:
On Sun, Jan 17, 2010 at 03:06:11PM +0200, Avi Kivity wrote:
On 01/10/2010 07:01 PM, Alexander Graf wrote:
While trying to compile an E500 vmlinux, I stumbled across a compilation
On Fri, Mar 26, 2010 at 11:50:10AM +0100, Alexander Graf wrote:
On 26.03.2010, at 11:40, Bruce Majia wrote:
On Fri, Mar 26, 2010 at 10:10:19AM +0100, Alexander Graf wrote:
On 26.03.2010, at 08:15, Bruce Majia wrote:
On Sun, Jan 17, 2010 at 03:06:11PM +0200, Avi Kivity wrote:
On
From 28eda49102f6886110376efbff318f1814686945 Mon Sep 17 00:00:00 2001
From: Bruce Majia bruce.ma...@gmail.com
Date: Fri, 26 Mar 2010 19:23:33 +0800
Subject: [PATCH] KVM: PPC: fix build error for un-initialised var
The '-Werror' option for cc makes compiler to distinguish warnings as
errors. So
On 26.03.2010, at 12:28, Bruce Majia wrote:
From 28eda49102f6886110376efbff318f1814686945 Mon Sep 17 00:00:00 2001
From: Bruce Majia bruce.ma...@gmail.com
Date: Fri, 26 Mar 2010 19:23:33 +0800
Subject: [PATCH] KVM: PPC: fix build error for un-initialised var
The '-Werror' option for cc
On Thu, Mar 25, 2010 at 7:32 PM, Jamie Lokier ja...@shareable.org wrote:
Cam Macdonell wrote:
An irqfd can only trigger a single vector in a guest. Right now I
only have one eventfd per guest. So ioeventfd/irqfd restricts the
current implementation to a single vector that a guest can
On 03/26/2010 01:05 AM, Cam Macdonell wrote:
I meant a unicast doorbell: 16 bits for guest ID, 16 bits for vector number.
Ah, yes. Who knew two bit registers is an ambiguous term. Do you
strongly prefer the one doorbell design?
Just floating out ideas. An advantage is that it
Chris Wright wrote:
* Hannes Reinecke (h...@suse.de) wrote:
Hi all,
I'm trying to setup a system with device-passthrough for
an ixgbe NIC.
The device itself seems to work, but it isn't using MSI-X.
So some more advanced features like DCB offloading etc
won't work.
Please send the
On Thu, Mar 25, 2010 at 11:32:57PM +0100, Alexander Graf wrote:
Am 25.03.2010 um 22:04 schrieb Avi Kivity a...@redhat.com:
On 03/25/2010 06:54 PM, Dale Farnsworth wrote:
I'm beginning to look at implementing KVM on MIPS. I've tried to
search
for any work-in-progress on this but haven't
Hi,
Is it possible to use KSM:
1) Without hardware VT support
2) For all memory in a system, without patching all applications to
register with it
TIA.
Gordan
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo
Christoph Hellwig hch at infradead.org writes:
Ok. cache=writeback performance is something I haven't bothered looking
at at all. For cache=none any streaming write or random workload with
large enough record sizes got basically the same performance as native
using kernel aio, and same for
* Hannes Reinecke (h...@suse.de) wrote:
Chris Wright wrote:
* Hannes Reinecke (h...@suse.de) wrote:
Hi all,
I'm trying to setup a system with device-passthrough for
an ixgbe NIC.
The device itself seems to work, but it isn't using MSI-X.
So some more advanced features like DCB
On Fri, Mar 26, 2010 at 09:16:19AM -0700, Dale Farnsworth wrote:
On Thu, Mar 25, 2010 at 11:32:57PM +0100, Alexander Graf wrote:
Am 25.03.2010 um 22:04 schrieb Avi Kivity a...@redhat.com:
On 03/25/2010 06:54 PM, Dale Farnsworth wrote:
I'm beginning to look at implementing KVM on MIPS.
* Gordan Bobic (gor...@bobich.net) wrote:
Is it possible to use KSM:
1) Without hardware VT support
Yes.
KSM and hardware virtualization support are technically not related.
2) For all memory in a system, without patching all applications to
register with it
No.
Right now, an app must
Chris Wright wrote:
2) For all memory in a system, without patching all applications to
register with it
No.
Right now, an app must be modified to call madvise(MADV_MERGEABLE).
Further, the core scanning loop that ksmd performs is based on per-process
virtual memory regions rather than
* Gordan Bobic (gor...@bobich.net) wrote:
Chris Wright wrote:
2) For all memory in a system, without patching all applications to
register with it
No.
Right now, an app must be modified to call madvise(MADV_MERGEABLE).
Further, the core scanning loop that ksmd performs is based on
Dale Farnsworth dale at farnsworth.org writes:
After thinking about this some more, I think this means we can't run
an unmodified guest. It should be possible to build the guest kernel
to run in supervisor or user mode/address space.
I'm new to MIPS, so I'm still looking for other
Hello,
perf tool does not count hardware performance events ( cache misses
etc) in a KVM guest ( Ubuntu 9.10 karmic, 2.6.31-14-generic kernel)
on Xeon 5530 quad-core. The host is 2.6.28 kernel , Ubuntu 8.04
LTS, Hardy.
readfile.sh reads in a large file (1430 lines), which
* Naresh Rapolu (nrap...@purdue.edu) wrote:
perf tool does not count hardware performance events ( cache misses
etc) in a KVM guest
The guest does not see a PMU. For basic profiling you can use timer
based in guest, but there is not yet support for PMU.
thanks,
-chris
--
To unsubscribe
24 matches
Mail list logo