similar to: how to use xentrace and xentrace_format

The xentrace_format script doesn''t work on x86/64. Python pads the input structure because the first field is 32 bits and the next is 64 bits, whereas x86-32 doesn''t pad. The quick fix is to read the cpu id separately as a 32bit value, then read the rest of the trace record. Here is a little patch that does that. Tested on x86/32 SMP and x86/64. Signed-off-by: Rob Gardner

I am trying to learn some more about the way windows does TPR writes, and tried xentrace for the first time. I did ''xentrace --time-interval=5 xentrace.out'' to capture some data, and then ran it through ''xentrace_format'' using the supplied example defs file. I can see some PF_XEN entries with virt=0xFFFE0080 (address of TPR), but I want to know the value being

This patch (attached) fixes a small problem in xentrace_format. Signed-off-by: Yang Xiaowei <xiaowei.yang@intel.com> Zhou Ting <ting.g.zhou@intel.com> --- diff -r 0df3bf8aac1e tools/xentrace/formats --- a/tools/xentrace/formats Mon Jun 16 16:35:17 2008 +0100 +++ b/tools/xentrace/formats Thu Aug 21 17:36:03 2008 +0800 @@ -23,8 +23,8 @@ 0x00081001 CPU%(cpu)d

Package: xen-utils-4.0 Version: 4.0.1-1 Severity: normal When I invoke me at dev:~# xentrace_format I get exec: 22: /usr/lib/xen-4.0/bin/xentrace_format: not found as result. The missing python script is referenced by the /usr/sbin/xentrace_format script from the xen-utils-common package. Using the python script from another (xen 4.0.0) distribution works fine. So I assume the file is

Hello, this patch introduces HVM tracing: one tracing class for both, SVM and VMX. It adds several new trace events. So we can differentiate between them in the xentrace formats file and format each event''s data items appropriately. With this patch the xentrace_format output is much more informative. The previous simple tracing in SVM and VMX is completely replaced. Unfortunately I

Hi, xentrace_format cannot use "0x016x" format as we expect. It show only %(N) as "0x016x" format, not as "%(N+1)08x%(N)08x". So I fixed tools/xentrace/formats by using "%(N+1)08x%(N)08x" format. Also I added some TRC_PV entries. Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com> Best Regards, Akio Takebe

Hi! Attached patch adds missing entries in xentrace''s formats file to make it recognize all HVM traces. Signed-off-by: Christoph Egger <Christoph.Egger@amd.com> Still missing are entries for PV traces. -- AMD Saxony, Dresden, Germany Operating System Research Center Legal Information: AMD Saxony Limited Liability Company & Co. KG Sitz (Geschäftsanschrift): Wilschdorfer

tags 407143 +patch thanks On Fri, 2013-08-16 at 14:42 +0100, Ian Campbell wrote: > tags 688308 +patch > thanks > > A lot of /docs/ is pretty low-level and not all that interesting to be > installed by the packages. However some of it is, and in particular some > is referenced from the manpages. I've cherry-picked the bits which I > think are most interesting in that

Processing commands for control at bugs.debian.org: > #xen (4.4.0-4) UNRELEASED; urgency=medium > # > # * Make library packages multi-arch: same. (closes: #730417) > # * Use debhelper compat level 9. (closes: #692352) > # * Correct contents of /etc/xen/scripts/hotplugpath.sh (Closes: #706283) > # * Drop references cpuperf-xen and cpuperf-perfcntr. (Closes: #733847) > # *

Accepted: -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Format: 1.8 Date: Sat, 30 Aug 2014 13:34:04 +0200 Source: xen Binary: libxen-4.4 libxenstore3.0 libxen-dev xenstore-utils xen-utils-common xen-utils-4.4 xen-hypervisor-4.4-amd64 xen-system-amd64 xen-hypervisor-4.4-arm64 xen-system-arm64 xen-hypervisor-4.4-armhf xen-system-armhf Architecture: source all Version: 4.4.0-4 Distribution:

Hello, I have a question about the way Xentrace takes a trace. In previous versions of Xen, I took a trace by setting the size of buffers, activating them and writing the information into a file (optional). setsize 20 tbctl 1 xentrace /tmp/xentrace.dat Now I''m using xen-unstable and I see that setsize is already integrated in xentrace command. My question is: does start/stop buffer is

Hi, I am using xen-unstable and interested to trace the hypervisor. In previous versions, I was able to trace it by: setsize 20 tbctl 1 xentrace /tmp/xentrace.dat And these functions don''t exist in xen-unstable. xentrace --help shows that in more recent versions the buffers'' size could be determined as a parameter for xentrace. But I can not find any replacement for

Hi, I've made some SAP benchmarks on my Xen system and discovered a huge difference in the performance of a "xened" SAP system compared to a native SAP system. Hence, I tried to figure out what might cause this 'overhead' and run a xentrace (listining to all events). Xentrace produced 24gb data and I converted it to 27gb human-readable data. After I gathered the

Hello, I''ve been trying to get xenmon.py and xentrace to work, but I consistently get the following (on a couple of different machines/kernels): kibab kibab # xentrace /root/xentrace.log ERROR: Failure to get trace buffer pointer from Xen (22 = Invalid argument) Did I miss an option that has to be turned on or something? Is there some other setting that I need so that everything

On Apr 18, 2007, at 2:07 PM, Evan Cheng wrote: > > On Apr 18, 2007, at 11:25 AM, Christopher Lamb wrote: > >> I noticed that the TableGen code emitter generator assumes that >> the instruction fields are declared in the instruction format in >> the same order that operands are defined. This seems like a bad >> dependence to me, and that TableGen should match

Since TRC_MEM is defined as 0x000af000 in xen/include/public/trace.h, TRC_MEM = TRC_SCHED | TRC_VMX. I feel strange about this. I do not think scheduling is a part of memory management. Am I right? If not, please tell me the background TRC_MEM is defined as TRC_SCHED | TRC_VMX. If so, please apply this patch. This patch defines TRC_MEM as an independent event mask. In addition, xentrace

Hi All, I am running xentrace on an idle machine (dom0 has 2 cpus). There are 4 cpus in the system > date xentrace -e0x82000 > idle.out date The sampling interval is 25 seconds. However when I format and look at the output, I see the sample time is 761 seconds or something bizarre Looks like the cpu cycles have gone beserk. Any ideas as to what could be happening thanks Prabha

Package: xen-utils-3.0.3-1 Version: 3.0.3-0-2 Severity: normal # xentrace /usr/lib/xen-3.0.3-1/bin/xentrace: error while loading shared libraries: libxenctrl.so: cannot open shared object file: No such file or directory It seems that we need a /etc/ld.so.conf.d/xen file that includes directory /usr/lib/xen-3.0.3-1/lib . -- System Information: Debian Release: 4.0 APT prefers testing APT

xentrace, setsize and the hypervisor don''t seem to be on the same page. If tracing is not enabled, the hypercall will only allow TBUF_SET_SIZE and TBUF_ENABLE. However, set_size calls TBUF_GET_INFO, and xentrace wants to call TBUF_SET_EVT_MASK and TBUF_SET_CPU_MASK before calling TBUF_ENABLE. I don''t see any reason not to call SET_*_MASK and GET_INFO if tracing is not enabled.