On Wed, 2010-06-23 at 08:51 +0300, Avi Kivity wrote:
On 06/23/2010 06:12 AM, Zhang, Yanmin wrote:
This design is to deal with a task context perf collection in guest os.
Scenario 1:
1) guest os starts to collect statistics of process A on vcpu 0;
2) process A is scheduled to vcpu 1
On Mon, 2010-06-21 at 16:56 +0300, Gleb Natapov wrote:
On Mon, Jun 21, 2010 at 05:31:43PM +0800, Zhang, Yanmin wrote:
The 3rd patch is to implement para virt perf at host kernel.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
snip
+
+static void kvm_copy_event_to_guest
On Tue, 2010-06-22 at 09:14 +0200, Jes Sorensen wrote:
On 06/22/10 03:49, Zhang, Yanmin wrote:
On Mon, 2010-06-21 at 14:45 +0300, Avi Kivity wrote:
Since the guest can use NMI to read the
counter, it should have the highest possible priority, and thus it
shouldn't see any overflow
On Tue, 2010-06-22 at 10:24 +0200, Jes Sorensen wrote:
On 06/21/10 11:31, Zhang, Yanmin wrote:
@@ -583,10 +584,20 @@ static void x86_pmu_disable_all(void)
}
}
+#ifdef CONFIG_KVM_PERF
+static int kvm_hw_perf_enable(void);
+static int kvm_hw_perf_disable(void);
+#endif
On Tue, 2010-06-22 at 12:12 +0300, Avi Kivity wrote:
On 06/22/2010 05:08 AM, Zhang, Yanmin wrote:
Something that is worrying is that we don't expose group information.
perf will multiplex the events for us, but there will be a loss in
accuracy.
#ifdef
On Tue, 2010-06-22 at 10:00 +0200, Jes Sorensen wrote:
On 06/22/10 09:55, Peter Zijlstra wrote:
On Tue, 2010-06-22 at 15:47 +0800, Zhang, Yanmin wrote:
Besides the para virt perf interface, I'm also considering the direct
exposition
of PMU hardware to guest os.
NAK NAK NAK NAK
On Tue, 2010-06-22 at 09:58 +0200, Jes Sorensen wrote:
On 06/22/10 09:47, Zhang, Yanmin wrote:
On Tue, 2010-06-22 at 09:14 +0200, Jes Sorensen wrote:
On 06/22/10 03:49, Zhang, Yanmin wrote:
On Mon, 2010-06-21 at 14:45 +0300, Avi Kivity wrote:
So I think above discussion is around how
On Tue, 2010-06-22 at 11:04 +0300, Avi Kivity wrote:
On 06/22/2010 08:47 AM, Zhang, Yanmin wrote:
On Mon, 2010-06-21 at 16:56 +0300, Gleb Natapov wrote:
On Mon, Jun 21, 2010 at 05:31:43PM +0800, Zhang, Yanmin wrote:
The 3rd patch is to implement para virt perf at host kernel
On Tue, 2010-06-22 at 11:29 +0300, Avi Kivity wrote:
On 06/22/2010 06:12 AM, Zhang, Yanmin wrote:
On Mon, 2010-06-21 at 15:33 +0300, Avi Kivity wrote:
On 06/21/2010 12:31 PM, Zhang, Yanmin wrote:
The 3rd patch is to implement para virt perf at host kernel.
@@ -64,6
tip/master tree of June 20st.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
--- linux-2.6_tip0620/Documentation/kvm/paravirt-perf.txt 1970-01-01
08:00:00.0 +0800
+++ linux-2.6_tip0620perfkvm/Documentation/kvm/paravirt-perf.txt
2010-06-21 15:21:39.312999849
The 2nd patch is to change the definition of perf_event to facilitate
perf attr copy when a hypercall happens.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
--- linux-2.6_tip0620/include/linux/perf_event.h2010-06-21
15:19:52.821999849 +0800
+++ linux-2.6_tip0620perfkvm
The 3rd patch is to implement para virt perf at host kernel.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
--- linux-2.6_tip0620/arch/x86/include/asm/kvm_para.h 2010-06-21
15:19:38.992999849 +0800
+++ linux-2.6_tip0620perfkvm/arch/x86/include/asm/kvm_para.h2010-06-21
15
The 5th patch is applied to the latest qemu-kvm tree.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
diff -Nraup qemu-kvm_0621/kvm/include/linux/kvm.h
qemu-kvm_0621_perf/kvm/include/linux/kvm.h
--- qemu-kvm_0621/kvm/include/linux/kvm.h 2010-06-21 11:00:28.0
+0800
The 4th patch is to implement para virt perf at guest side.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
--- linux-2.6_tip0620/arch/x86/Kconfig 2010-06-21 15:19:39.180999849 +0800
+++ linux-2.6_tip0620perfkvm/arch/x86/Kconfig 2010-06-21 15:21:39.30849
+0800
@@ -552,6
On Mon, 2010-06-21 at 14:45 +0300, Avi Kivity wrote:
On 06/21/2010 12:31 PM, Zhang, Yanmin wrote:
Here is the version 2.
ChangeLog since V1: Mostly changes based on Avi's suggestions.
1) Use a id to identify the perf_event between host and guest;
2) Changes lots of codes to deal
On Mon, 2010-06-21 at 15:00 +0300, Avi Kivity wrote:
On 06/21/2010 12:31 PM, Zhang, Yanmin wrote:
The 2nd patch is to change the definition of perf_event to facilitate
perf attr copy when a hypercall happens.
Signed-off-by: Zhang Yanminyanmin_zh...@linux.intel.com
---
--- linux
On Mon, 2010-06-21 at 15:33 +0300, Avi Kivity wrote:
On 06/21/2010 12:31 PM, Zhang, Yanmin wrote:
The 3rd patch is to implement para virt perf at host kernel.
@@ -64,6 +73,85 @@ struct kvm_mmu_op_release_pt {
#ifdef __KERNEL__
#includeasm/processor.h
+/*
+ * In host kernel
On Mon, 2010-06-21 at 15:37 +0300, Avi Kivity wrote:
On 06/21/2010 12:31 PM, Zhang, Yanmin wrote:
The 5th patch is applied to the latest qemu-kvm tree.
--- qemu-kvm_0621/target-i386/kvm.c 2010-06-21 11:00:29.0 +0800
+++ qemu-kvm_0621_perf/target-i386/kvm.c2010-06-21 13:00
On Thu, 2010-06-10 at 11:50 +0200, Peter Zijlstra wrote:
On Thu, 2010-06-10 at 10:21 +0800, Zhang, Yanmin wrote:
. The ABI mostly includes the definition of struct perf_event_attr,
guest_perf_counter,
and hypercalls.
Note that perf_event_attr isn't guaranteed to be stable between
On Wed, 2010-06-09 at 11:33 +0300, Avi Kivity wrote:
On 06/09/2010 06:30 AM, Zhang, Yanmin wrote:
From: Zhang, Yanminyanmin_zh...@linux.intel.com
Based on Ingo's idea, I implement a para virt interface for perf to support
statistics collection in guest os. That means we could run tool
On Wed, 2010-06-09 at 11:59 +0300, Avi Kivity wrote:
On 06/09/2010 06:30 AM, Zhang, Yanmin wrote:
From: Zhang, Yanminyanmin_zh...@linux.intel.com
Based on Ingo's idea, I implement a para virt interface for perf to support
statistics collection in guest os. That means we could run tool
On Wed, 2010-06-09 at 12:41 +0300, Avi Kivity wrote:
On 06/09/2010 12:21 PM, Zhang, Yanmin wrote:
One thing that's missing is documentation of the guest/host ABI. It
will be a requirement for inclusion, but it will also be a great help
for review, so please provide it ASAP.
I
On Thu, 2010-06-10 at 06:06 +0300, Avi Kivity wrote:
On 06/10/2010 05:21 AM, Zhang, Yanmin wrote:
I see. So put it in a union. Or perhaps not even in a union - what if
a kvm guest is also acting as a kvm host?
My patch has consideration on it. I compiled kernel with host
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Based on Ingo's idea, I implement a para virt interface for perf to support
statistics collection in guest os. That means we could run tool perf in guest
os directly.
Great thanks to Peter Zijlstra. He is really the architect and gave me
On Fri, 2010-04-23 at 13:50 +0300, Avi Kivity wrote:
On 04/22/2010 01:27 PM, Liu Yu-B13201 wrote:
I met this error when built kernel. Anything wrong?
CC init/main.o
In file included from include/linux/ftrace_event.h:8,
from include/trace/syscall.h:6,
On Tue, 2010-04-20 at 08:09 +0200, Ingo Molnar wrote:
* Ingo Molnar mi...@elte.hu wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
unsigned long perf_misc_flags(struct pt_regs *regs)
{
int misc = 0;
+
if (perf_guest_cbs perf_guest_cbs-is_in_guest
On Mon, 2010-04-19 at 11:37 +0300, Avi Kivity wrote:
On 04/19/2010 08:32 AM, Zhang, Yanmin wrote:
Below patch introduces perf_guest_info_callbacks and related
register/unregister
functions. Add more PERF_RECORD_MISC_XXX bits meaning guest kernel and
guest user
space
On Mon, 2010-04-19 at 11:59 +0300, Avi Kivity wrote:
On 04/19/2010 11:55 AM, Zhang, Yanmin wrote:
On Mon, 2010-04-19 at 11:37 +0300, Avi Kivity wrote:
On 04/19/2010 08:32 AM, Zhang, Yanmin wrote:
Below patch introduces perf_guest_info_callbacks and related
register
parameter needs name even if unused
- missing space after opening curly brace
Please provide delta fixes.
Here is the fix on the top of the prior 3 patches of V5.
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Fix some programming style issues on the top of perf kvm
enhancement V5.
Signed-off
kvm stat'.
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Based on the discussion in KVM community, I worked out the patch to support
perf to collect guest os statistics from host side. This patch is implemented
with Ingo, Peter and some other guys' kind help. Yang Sheng pointed out a
critical
Below patch introduces perf_guest_info_callbacks and related register/unregister
functions. Add more PERF_RECORD_MISC_XXX bits meaning guest kernel and guest
user
space.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
diff -Nraup --exclude-from=exclude.diff
linux-2.6_tip0417/arch
Below patch implements the perf_guest_info_callbacks on kvm.
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
diff -Nraup linux-2.6_tip0417/arch/x86/kvm/vmx.c
linux-2.6_tip0417_perfkvm/arch/x86/kvm/vmx.c
--- linux-2.6_tip0417/arch/x86/kvm/vmx.c2010-04-19 09:51:47.908673911
parameter -p to collect specific guest os instance statistics.
ChangeLog V2:
1) Based on Avi's suggestion, I moved callback functions
to generic code area. So the kernel part of the patch is
clearer.
2) Add 'perf kvm stat'.
From: Zhang, Yanmin yanmin_zh
);
+ kvm_after_handle_nmi(vmx-vcpu);
Signed-off-by: Zhang Yanmin yanmin_zh...@linux.intel.com
---
diff -Nraup --exclude=tools linux-2.6_tip0413/arch/x86/include/asm/perf_event.h
linux-2.6_tip0413_perfkvm/arch/x86/include/asm/perf_event.h
--- linux-2.6_tip0413/arch/x86/include/asm/perf_event.h
On Thu, 2010-04-15 at 11:05 +0300, Avi Kivity wrote:
On 04/15/2030 04:04 AM, Zhang, Yanmin wrote:
An even more accurate way to determine this is to check whether the
interrupt frame points back at the 'int $2' instruction. However we
plan to switch to a self-IPI method to inject the NMI
On Wed, 2010-04-14 at 12:20 +0300, Avi Kivity wrote:
On 04/14/2030 12:05 PM, Zhang, Yanmin wrote:
Here is the new patch of V3 against tip/master of April 13th
if anyone wants to try it.
Thanks for persisting despite the flames.
Can you please separate arch/x86/kvm part
On Thu, 2010-03-25 at 16:02 +0800, Li Zefan wrote:
Zhang, Yanmin wrote:
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Parameter --pid (or -p) of perf currently means a thread-wide collection.
For exmaple, if a process whose id is has 10 threads, 'perf top -p
'
just
On Wed, 2010-03-24 at 20:20 +0200, Avi Kivity wrote:
On 03/24/2010 07:47 PM, Arnaldo Carvalho de Melo wrote:
Em Wed, Mar 24, 2010 at 06:09:30PM +0200, Avi Kivity escreveu:
Doesn't perf already has a dependency on naming conventions for finding
debug information?
It looks at
On Tue, 2010-03-23 at 10:15 -0300, Arnaldo Carvalho de Melo wrote:
Em Tue, Mar 23, 2010 at 11:14:41AM +0800, Zhang, Yanmin escreveu:
On Mon, 2010-03-22 at 13:44 -0300, Arnaldo Carvalho de Melo wrote:
Em Mon, Mar 22, 2010 at 03:24:47PM +0800, Zhang, Yanmin escreveu:
On Fri, 2010-03-19
On Sun, 2010-03-21 at 22:20 +0100, Ingo Molnar wrote:
* Avi Kivity a...@redhat.com wrote:
Well, for what it's worth, I rarely ever use anything else. My virtual
disks are raw so I can loop mount them easily, and I can also switch my
guest kernels from outside... without ever needing
On Fri, 2010-03-19 at 09:21 +0100, Ingo Molnar wrote:
Nice progress!
This bit:
1) perf kvm top
[r...@lkp-ne01 norm]# perf kvm --host --guest
--guestkallsyms=/home/ymzhang/guest/kallsyms
--guestmodules=/home/ymzhang/guest/modules top
Will be really be painful to developers - to
On Mon, 2010-03-22 at 13:44 -0300, Arnaldo Carvalho de Melo wrote:
Em Mon, Mar 22, 2010 at 03:24:47PM +0800, Zhang, Yanmin escreveu:
On Fri, 2010-03-19 at 09:21 +0100, Ingo Molnar wrote:
So some sort of --guestmount option would be the natural solution, which
points to the guest system's
On Thu, 2010-03-18 at 10:45 +0800, Zhang, Yanmin wrote:
On Wed, 2010-03-17 at 17:26 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-16 at 10:47 +0100, Ingo Molnar wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
On Tue, 2010-03-16 at 15:48 +0800, Zhang, Yanmin wrote
and enhance perf to be more user-friendly.
Subject: [PATCH 1/3] perf events: Enable counters when collecting process-wide
or system-wide data by 'perf stat'
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Command 'perf stat' doesn't enable counters when collecting an existing (by -p)
process
or a system
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
'perf record' starts counters before subcommand is execed, so the statistics is
not precise because it includes data of some preparation steps. I fix it with
the
patch.
In addition, Change the condition to fork/exec subcommand
From: Zhang, Yanmin yanmin_zh...@linux.intel.com
Parameter --pid (or -p) of perf currently means a thread-wide collection.
For exmaple, if a process whose id is has 10 threads, 'perf top -p '
just collects the main thread statistics. That's misleading. Users are
used to attach a whole
On Tue, 2010-03-16 at 10:47 +0100, Ingo Molnar wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
On Tue, 2010-03-16 at 15:48 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-16 at 07:41 +0200, Avi Kivity wrote:
On 03/16/2010 07:27 AM, Zhang, Yanmin wrote:
From: Zhang
On Wed, 2010-03-17 at 17:26 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-16 at 10:47 +0100, Ingo Molnar wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
On Tue, 2010-03-16 at 15:48 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-16 at 07:41 +0200, Avi Kivity wrote:
On 03/16
On Tue, 2010-03-16 at 07:41 +0200, Avi Kivity wrote:
On 03/16/2010 07:27 AM, Zhang, Yanmin wrote:
From: Zhang, Yanminyanmin_zh...@linux.intel.com
Based on the discussion in KVM community, I worked out the patch to support
perf to collect guest os statistics from host side. This patch
On Tue, 2010-03-16 at 15:48 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-16 at 07:41 +0200, Avi Kivity wrote:
On 03/16/2010 07:27 AM, Zhang, Yanmin wrote:
From: Zhang, Yanminyanmin_zh...@linux.intel.com
Based on the discussion in KVM community, I worked out the patch to
support
On Tue, 2010-03-16 at 11:32 +0200, Avi Kivity wrote:
On 03/16/2010 09:48 AM, Zhang, Yanmin wrote:
Excellent, support for guest kernel != host kernel is critical (I can't
remember the last time I ran same kernels).
How would we support multiple guests with different kernels
On Thu, 2010-03-11 at 09:50 +0200, Avi Kivity wrote:
On 03/11/2010 09:46 AM, Sheng Yang wrote:
On Thursday 11 March 2010 15:36:01 Avi Kivity wrote:
On 03/11/2010 09:20 AM, Sheng Yang wrote:
Currently we can only get the cpu_stat of whole guest as one. This patch
enhanced
On Thu, 2010-03-04 at 09:00 +0800, Zhang, Yanmin wrote:
On Wed, 2010-03-03 at 11:15 +0100, Peter Zijlstra wrote:
On Wed, 2010-03-03 at 17:27 +0800, Zhang, Yanmin wrote:
-#ifndef perf_misc_flags
-#define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER
On Wed, 2010-03-03 at 11:32 +0800, Zhang, Yanmin wrote:
On Tue, 2010-03-02 at 10:36 +0100, Ingo Molnar wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
On Fri, 2010-02-26 at 10:17 +0100, Ingo Molnar wrote:
My suggestion, as always, would be to start very simple and very
On Wed, 2010-03-03 at 11:13 +0100, Peter Zijlstra wrote:
On Wed, 2010-03-03 at 17:27 +0800, Zhang, Yanmin wrote:
+static inline u64 perf_instruction_pointer(struct pt_regs *regs)
+{
+ u64 ip;
+ ip = percpu_read(perf_virt_ip.ip);
+ if (!ip)
+ ip
On Wed, 2010-03-03 at 11:15 +0100, Peter Zijlstra wrote:
On Wed, 2010-03-03 at 17:27 +0800, Zhang, Yanmin wrote:
-#ifndef perf_misc_flags
-#define perf_misc_flags(regs) (user_mode(regs) ? PERF_RECORD_MISC_USER : \
-PERF_RECORD_MISC_KERNEL)
-#define
On Tue, 2010-03-02 at 10:36 +0100, Ingo Molnar wrote:
* Zhang, Yanmin yanmin_zh...@linux.intel.com wrote:
On Fri, 2010-02-26 at 10:17 +0100, Ingo Molnar wrote:
My suggestion, as always, would be to start very simple and very minimal:
Enable 'perf kvm top' to show guest overhead
On Fri, 2010-02-26 at 10:17 +0100, Ingo Molnar wrote:
* Joerg Roedel j...@8bytes.org wrote:
On Fri, Feb 26, 2010 at 10:55:17AM +0800, Zhang, Yanmin wrote:
On Thu, 2010-02-25 at 18:34 +0100, Joerg Roedel wrote:
On Thu, Feb 25, 2010 at 04:04:28PM +0100, Jes Sorensen wrote:
1
On Thu, 2010-02-25 at 10:20 +0100, Peter Zijlstra wrote:
On Thu, 2010-02-25 at 11:27 +0800, Zhang, Yanmin wrote:
Ingo,
I did some testing with KVM virtualization. perf shows vmx_vcpu_run
consumes more than 50% cpu time. Actually, the info is incorrect because
when perf counter
On Thu, 2010-02-25 at 17:26 +0100, Ingo Molnar wrote:
* Jan Kiszka jan.kis...@siemens.com wrote:
Jes Sorensen wrote:
Hi,
It looks like several of us have been looking at how to use the PMU
for virtualization. Rather than continuing to have discussions in
smaller groups, I
On Thu, 2010-02-25 at 18:34 +0100, Joerg Roedel wrote:
On Thu, Feb 25, 2010 at 04:04:28PM +0100, Jes Sorensen wrote:
1) Add support to perf to allow it to monitor a KVM guest from the
host.
This shouldn't be a big problem. The PMU of AMD Fam10 processors can be
configured to count
61 matches
Mail list logo