similar to: Fwd: RE: xenoprof passive profiling and "mode" setting

Xiaowei, I''m puzzled by the following bit of code in p4_check_ctrs():        if (guest_kernel_mode(current, regs))                 mode = 1;         else if (ring_0(regs))                 mode = 2; If I look at the definition for guest_kernel_mode() it is: include/asm-x86/x86_64/regs.h: #define guest_kernel_mode(v, r)   \     (ring_3(r) && ((v)->arch.flags &

Renato, If one creates an HVM domain (say domain 1) and then does echo 1 > /dev/oprofile/passive_domains one then gets the following on the Xen serial console: (XEN) xenoprof.c:143:d0 xenoprof/x86 with autotranslated mode enabledisn''t supported yet (XEN) xenoprof.c:143:d0 xenoprof/x86 with autotranslated mode enabledisn''t supported yet (XEN) xenoprof.c:143:d0

The original code only sets EN bit of IA32_PERFEVTSEL0 when profiling is started. Signed-off-by: Xiaowei Yang <xiaowei.yang@intel.com> Regards, Xiaowei _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Keir, The following 3 patches allow HVM (SVM and VT) guests to be passively profiled using the very latest patches from Renato. These patches apply to 11470. Renato''s patches: http://xenoprof/sourceforge.net oprofile-0.9.1-xen-r2.patch And also a patch not posted FAIK (oprofile-0.9.1-fix-hvm-addr-overlap.patch) which is in the attached tar.bz2 file. hvm_xenoprofile_1.patch - The first

I''m looking into getting Xenoprof to tun in an HVM domain, since we will eventually need a profiler for HVM domains to track down areas of poor performance. (HVMs have poor performance? :) ) Being relatively new to OProfile, Xenoprof, and Xen internals, I would appreciate any pointers, tips, and comments on how to work the implementation. I see three basic areas of work. 1. Implement

Hi Renato, This patch is to add Xenoprof passive domain support in SMP environment. Basically: - It allocates per vcpu buffers for passive domain and maps them into primary domain''s space. - When primary domain gets sampled and triggers virq, its kernel module will handle passive domain'' samples besides its owns. There is potential buffer overflow if passive is very busy while

Hi all, This patch makes it possible to build the kernel on x86_64 using todays tip (9574) of xen-unstable. / magnus _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Is it possible to monitor Core Events and Uncore Events simultaneously? Currently, it is not working now in my machine. When I type the command line like this, opcontrol --start-daemon --event=LLC_MISSES:6000::0:1 --event=LLC_REFS:6000::0:1 \ --event=MEM_UNCORE_RETIRED:6000:0x10:0:1 --event=MEM_UNCORE_RETIRED:6000:0x20:0:1 \ --xen=/boot/xen-syms-4.0.1-rc3 --no-vmlinux

Is it possible to monitor Core Events and Uncore Events simultaneously? Currently, it is not working now in my machine. When I type the command line like this, opcontrol --start-daemon --event=LLC_MISSES:6000::0:1 --event=LLC_REFS:6000::0:1 \ --event=MEM_UNCORE_RETIRED:6000:0x10:0:1 --event=MEM_UNCORE_RETIRED:6000:0x20:0:1 \ --xen=/boot/xen-syms-4.0.1-rc3 --no-vmlinux

Hello Xen Users, I am trying to Patch the linux-2.6-sparse source tree to get it working with Xenoprof. I have obtained the patch from the Xenoprof source forge website maintained by HP. http://xenoprof.sourceforge.net/ However, I am unable to apply the patch as the source-tree structure expected by the patch is different from the one in 3.0.2 distribution. Has anyone encountered this

xenoprof: flush remaining smples when sampling is stopped. Xenoprof notifies guest kernel via VIRQ_XENOPROF when sampled. But it does coarsly based on heuristic so that sometimes VIRQ_XENOPROF isn''t delivered resulting in that oprofile daemon collects no sample. To avoid that situation, always send VIRQ_XENOPROF when sampling is stopped. -- yamahata

Hi, I ran xenoprof with the event mask LLC_MISSES:10000. This should be L2 cache misses on Core2 arch. After the run when I run opreport it displays : Counted *L2_RQSTS* events (number of L2 cache requests) with a unit mask of 0x41 (multiple flags) count 10000 LLC_MISSES:10000 | ..... My questions was whether the message is incorrect or the event mask is not being set correctly by oprofile. My

>> >> Is the nmi_sanity_check() needed? We shouldn''t lose NMIs: >> even if we take one while doing NMI processing, we sholuld >> retake the NMI as soon as the first one IRETs. >> The nmi_sanity_check() should not be needed if everything is working fine. However I suggest we should keep it for now until we are sure it is safe to remove it. I would

I''m trying to use xenoprof in my machine (xeon x5650, westmere). While oprof works for this machine correctly, xenoprof doesn''t work properly. I want to use xenoprof in NMI mode (which is the opposite side of timer mode, right?) However, kernel message always shows that xenoprof works in the timer mode only. Is there any restriction or specs which is not

Hello everyone, I''m trying to run Xenoprof (Oprofile 0.9.4) in Gentoo Linux 2.6.21-xen (64 bit) on an AMD 64 system and am facing the following two issues: 1. Xenoprof complains about a write error, but starts and runs anyway. dom0 # opcontrol --start-daemon --active-domains=0 --event=CPU_CLK_UNHALTED:75000::1:1 --vmlinux=/usr/src/linux-2.6.21-xen-dom0/vmlinux

The problem was because it is missing the "loop" module. the hotplug loads it automatically, while udev does not. The error xenoprof: Initialization failed. Intel processor model 15 for P6 class family is not supported" does not interference the winxp load.. so its ok. Does anyone know how to load osx86? It hangs at "booting from cd-rom". do I need kqemu/qemu xen? I

Keir: This is to to make the IDE device model multithreading so that the VMX domain IO access completion (triggering DMA operation) can be asynchronize with the completion of DMA operation. With this patch we get 8%--14% performance gain for kernel build. Thanks, eddie Yang, Xiaowei wrote: > Originally in qemu when a IDE dma transfer is started which is > triggered by access to 0xc000

HI all : I got the message "Using timer interrupt." when trying the command "opcontrol --list-events". then I found infomation "xenoprof: Initialization failed. Intel processor model 44 for P6 class family is not supported“ after "xm dmesg". the TYPE OF CPUS here is Intel(R) Xeon(R) CPU E5620 @ 2.40GHz. So does it really not support this

Hi, I want to use xenoprof to profile the overhead of the hypervisor. I patched the oprofile-0.9.5 using the patch from xenoprof.sourceforge.net Debian GNU/Linux 5.0 (lenny) Xen-4.0.1 + 2.6.32.27 (linux-2.6-pvops.git) Dom0 My platform is Intel(R) Core(TM) i7 CPU 960 @ 3.20GHz My problems are: In Dom0, But hardware performance counters don''t be mounted after initialization