- 12 Aug, 2013 2 commits
-
-
David Ahern authored
This is useful to spot high latency blips. It is normal for HLT reasons to have long exit times, so strip those from the duration check. v2: changed threshold to duration per acme's request Signed-off-by:
David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1375926999-75129-1-git-send-email-dsahern@gmail.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: * Do annotation using /proc/kcore and /proc/kallsyms, removing the need for a vmlinux file kernel assembly annotation. This also improves this use case because vmlinux has just the initial kernel image, not what is actually in use after various code patchings by things like alternatives, etc. From Adrian Hunter. * Add various improvements and fixes to the "vmlinux matches kallsyms" 'perf test' entry, related to the /proc/kcore annotation feature. * Add --initial-delay option to 'perf stat' to skip measuring for the startup phase, from Andi Kleen. * Add perf kvm stat live mode that combines aspects of 'perf kvm stat' record and report, from David Ahern. * Add option to analyze specific VM in perf kvm stat report, from David Ahern. * Do not require /lib/modules/* on a guest, fix from Jason Wessel. * Group leader sampling, that allows just one event in a group to sample while the other events have just its values read, from Jiri Olsa. * Add support for a new modifier "D", which requests that the event, or group of events, be pinned to the PMU, from Michael Ellerman. * Fix segmentation fault on the gtk browser, from Namhyung Kim. Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 07 Aug, 2013 38 commits
-
-
Joonsoo Kim authored
This reverts commit 079787f2. Below commit already resolve a cross build problem. I have been noticed this too lately. commit 3c4797d4 Author: Rabin Vincent <rabin@rab.in> Date: Fri May 17 22:27:44 2013 +0200 tools lib lk: Respect CROSS_COMPILE Make lk use CROSS_COMPILE, in order to be able to cross compile perf again. Signed-off-by:
Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1373936614-22224-1-git-send-email-iamjoonsoo.kim@lge.comSigned-off-by:
-
Jason Wessel authored
For some types of work loads and special guest environments, you might have a kernel that has no kernel modules. The perf kvm record tool fails instantiate vmlinux maps when the kernel modules directory cannot be opened, even though the kallsyms has been properly processed. This leads to a perf kvm report that has no guest symbols resolved. This patch changes the failure to locate kernel modules to be non-fatal. Signed-off-by:
Jason Wessel <jason.wessel@windriver.com> Acked-by:
-
Michael Ellerman authored
Add a negative test to test__checkevent_pmu_events() to get lots of coverage of the negative case, ie. when the modifier is not specified. Add a test of a single event, and of the group case. Signed-off-by:
Michael Ellerman <michael@ellerman.id.au> Acked-by:
Jiri Olsa <jolsa@redhat.com> Acked-by:
Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1375795686-4226-2-git-send-email-michael@ellerman.id.auSigned-off-by:
-
Michael Ellerman authored
This commit adds support for a new modifier "D", which requests that the event, or group of events, be pinned to the PMU. The "p" modifier is already taken for precise, and "P" may be used in future to mean "fully precise". So we use "D", which stands for pinneD - and looks like a padlock, or if you're using the ":D" syntax perf smiles at you. This is an oft-requested feature from our HW folks, who want to be able to run a large number of events, but also want 100% accurate results for instructions per cycle. Comparison of results with and without pinning: $ perf stat -e '{cycles,instructions}:D' -e cycles,instructions,... 79,590,480,683 cycles # 0.000 GHz 166,123,716,524 instructions # 2.09 insns per cycle # 0.11 stalled cycles per insn 79,352,134,463 cycles # 0.000 GHz [11.11%] 165,178,301,818 instructions # 2.08 insns per cycle # 0.11 stalled cycles per insn [11.13%] As you can see although perf does a very good job of scaling the values in the non-pinned case, there is some small discrepancy. The patch is fairly straight forward, the one detail is that we need to make sure we only request pinning for the group leader when we have a group. Signed-off-by: -
Namhyung Kim authored
The commit 2b8bfa6b ("perf tools: Centralize default columns init in perf_hpp__init") moves initialization of common overhead column to perf_hpp__init() but forgot about the gtk code. So the gtk code added the same column to the list twice causing infinite loop when iterating it by perf_hpp__for_each_format loop. When I run perf report --gtk, I can see following messages indefinitely. (perf:11687): Gtk-CRITICAL **: IA__gtk_main_quit: assertion 'main_loops != NULL' failed perf: Segmentation fault Signed-off-by:
Pekka Enberg <penberg@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1375766056-19377-2-git-send-email-namhyung@kernel.orgSigned-off-by:
-
David Ahern authored
Add an option to analyze a specific VM within a data file. This allows the collection of kvm events for all VMs and then analyze data for each VM (or set of VMs) individually. Signed-off-by:
Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1375753297-69645-6-git-send-email-dsahern@gmail.comSigned-off-by:
-
David Ahern authored
Add max and min times for exit events. v2: address Xiao's comment to use get_event function for pulling max and min from stats struct similar to mean and count Signed-off-by: -
David Ahern authored
perf kvm stat currently requires back to back record and report commands to see stats. e.g,. perf kvm stat record -p $pid -- sleep 1 perf kvm stat report This is inconvenvient for on box monitoring of a VM. This patch introduces a 'live' mode that in effect combines the record plus report into one command. e.g., to monitor a single VM: perf kvm stat live -p $pid or all VMs: perf kvm stat live Same stats options for the record+report path work with the live mode. Display rate defaults to 1 second and can be changed using the -d option. v4: - address comments from Xiao -- verify_vcpu check should not look at processors on line for the host, prune configurable options. - set attr->{mmap,comm,task} to 0 - don't need task events so trim events we have to deal with - better control of time for queue event flushing to reduce frequency of "Timestamp below last timeslice flush" failures. v3: updated to use existing tracepoint parsing code v2: removed ABSTIME arg from timerfd_settime as mentioned by Namhyung only call perf_kvm__handle_stdin when poll returns activity. Signed-off-by: -
David Ahern authored
Taking a lesson from perf-trace and bringing in control of event processing to perf-kvm-stat-live: parse the sample to get access the time leaving just the need to queue it to the ordered samples list. For that the queue_event function needs to be exported. Unexport perf_session__process_event. Signed-off-by:
-
Ingo Molnar authored
Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The previous description: "Search previous string" is usually associated with the 'N' following a '/string', the opposite of 'n', which is 'Search next string' in the direction established with '/' or '?'. So change it to 'Search string backwards', to clarify that. The 'N' hotkey remains to be implemented with the semantic described above. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-5lw5y15d7vv308xbpm8pqe4g@git.kernel.orgSigned-off-by:
-
Adrian Hunter authored
The /proc/kcore file has no symbols, so the call target name does not display. Fix by looking up the symbol name if it is on the same map. Reported-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1375875537-4509-14-git-send-email-adrian.hunter@intel.comSigned-off-by:
-
Adrian Hunter authored
When kcore is used for annotation, symbols do not have correct sizes because they come from kallsyms, that has only its start address, with the end address being the next symbol's minus one. That sometimes results in an extra nop being seen after the end of a function. Remove it. Suggested-by:
-
Adrian Hunter authored
Currently the symbol name is displayed at the top when displaying symbol annotation. Add to this the dso long name. Suggested-by:
-
Adrian Hunter authored
Annotation with /proc/kcore is possible so the logic is adjusted to allow it. The main difference is that /proc/kcore had no symbols so the parsing logic needed a tweak to read jump offsets. The other difference is that objdump cannot always read from kcore. That seems to be a bug with objdump. Signed-off-by:
-
Adrian Hunter authored
Make the "object code reading" test attempt to read from kcore. The test uses objdump which struggles with kcore. i.e. doesn't always work, sometimes takes a long time. The test has been made to work around those issues. Signed-off-by:
-
Adrian Hunter authored
The kallsyms maps now may map to kcore and the symbol values now may be file offsets. For comparison with vmlinux the virtual memory address is needed which is obtained by unmapping the symbol value. The "vmlinux symtab matches kallsyms" is adjusted accordingly. Signed-off-by:
-
Adrian Hunter authored
In the absence of vmlinux, perf tools uses kallsyms for symbols. If the user has access, now also map to /proc/kcore. The dso data_type is now set to either DSO_BINARY_TYPE__KCORE or DSO_BINARY_TYPE__GUEST_KCORE as approprite. This patch breaks the "vmlinux symtab matches kallsyms" test. That is fixed in a following patch. Signed-off-by:
-
Adrian Hunter authored
The new "object code reading" test shows that it is not possible to read object code from kernel modules. That is because the mappings do not map to the dsos. This patch fixes that. This involves identifying and flagging relocatable (ELF type ET_REL) files (e.g. kernel modules) for symbol adjustment and updating map__rip_2objdump() accordingly. The kmodule parameter of dso__load_sym() is taken into use and the module map altered to map to the dso. Signed-off-by:
-
Adrian Hunter authored
The vmlinux maps now map to the dso and the symbol values are now file offsets. For comparison with kallsyms the virtual memory address is needed which is obtained by unmapping the symbol value. The "vmlinux symtab matches kallsyms" is adjusted accordingly. Signed-off-by:
-
Adrian Hunter authored
The new "object code reading" test shows that it is not possible to read object code from vmlinux. That is because the mappings do not map to the dso. This patch fixes that. A side-effect of changing the kernel map is that the "reloc" offset must be taken into account. As a result of that separate map functions for relocation are no longer needed. Also fixing up the maps to match the symbols no longer makes sense and so is not done. The vmlinux dso data_type is now set to either DSO_BINARY_TYPE__VMLINUX or DSO_BINARY_TYPE__GUEST_VMLINUX as approprite, which enables the correct file name to be determined by dso__binary_type_file(). This patch breaks the "vmlinux symtab matches kallsyms" test. That is fixed in a following patch. Signed-off-by:
-
Adrian Hunter authored
In order to use kernel maps to read object code, those maps must be adjusted to map to the dso file offset. Because lazy-initialization is used, that is not done until symbols are loaded. However the maps are first used by thread__find_addr_map() before symbols are loaded. So this patch changes thread__find_addr() to "load" kernel maps before using them. Signed-off-by:
-
Adrian Hunter authored
Using the information in mmap events, perf tools can read object code associated with sampled addresses. A test is added that compares bytes read by perf with the same bytes read using objdump. Signed-off-by:
-
Adrian Hunter authored
When removing duplicate symbols, prefer to remove syscall aliases starting with SyS or compat_SyS. A side-effect of that is that it results in slightly improved results for the "vmlinux symtab matches kallsyms" test. Signed-off-by:
-
Andi Kleen authored
When interval mode is outputting to a pipe, each measurement should be flushed individually, so that the reader sees it timely. With a terminal each line is automatically flushed by stdio, but that is disabled with non terminal output. Simply fflush output after each time interval Signed-off-by:
Andi Kleen <ak@linux.intel.com> Reviewed-by:
-
Andi Kleen authored
When measuring workloads the startup phase -- doing page faults, dynamic linking, opening files -- is often very different from the rest of the workload. Especially with smaller kernels and using counter multiplexing this can give significant measurement errors. Multiplexing assumes that the workload is mostly the same over longer periods. But at startup there is typically some spike of activity which is relatively short. If many groups are multiplexing the one group seeing the spike, and which is then scaled up over the time to run all groups, may see a significant error. Also in general it's often not useful to measure the startup, because it is so different from the rest. One way around this is to use interval mode and discard the first sample, but this can be awkward because interval mode doesn't support intervals of less than 100ms, and also a useful interval is not necessarily the same as a useful startup delay. This patch adds a new --initial-delay / -D option to skip measuring for the startup phase. The time can be specified in ms Here's a simple example: perf stat -e page-faults bash -c 'for i in $(seq 100000) ; do true ; done' ... 3,721 page-faults ... If we just wait 20 ms the number of page faults is 1/3 less: perf stat -D 20 -e page-faults bash -c 'for i in $(seq 100000) ; do true ; done' ... 2,823 page-faults ... So we filtered out most of the startup noise from bash. Signed-off-by: -
Andi Kleen authored
Add support for enabling already set up counters by using an ioctl. I share some code with the filter setup. Signed-off-by:
-
Andi Kleen authored
Minor cleanup. The dummy execve to pre-resolve the PLT is obsolete since "enable_on_execve" was added. The counters are only running after the execve anyways. So just remove it. Signed-off-by:
-
David Ahern authored
Needed by kvm live command. Make record_args a local while we are messing with the args. Signed-off-by:
-
David Ahern authored
Allows kvm live mode to reuse the event processing and ordered samples processing used by the perf-report path. v2: removed flush_sample_queue as noticed by Jiri Signed-off-by:
-
David Ahern authored
Need an initialization function to set min to -1 to differentiate from an actual min of 0. Signed-off-by:
-
David Ahern authored
For use with kvm-live mode. Signed-off-by:
-
Namhyung Kim authored
The parse_nsec_time() function is for parsing a string of time into 64-bit nsec value. It's a preparation of time filtering in some of perf commands. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thiago Peixoto <thiagolcpeixoto@gmail.com> Link: http://lkml.kernel.org/n/tip-jurgz6myq125o1ql6lldh6f7@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
It is an errno, so print an error string. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-zt68gijvvoe8gd7kmclo43si@git.kernel.orgSigned-off-by:
-
David Ahern authored
On Fedora 18, with gcc 4.6.4 compile fails with: arch/x86/util/tsc.c: In function ‘perf_time_to_tsc’: arch/x86/util/tsc.c:13:6: error: declaration of ‘time’ shadows a global declaration [-Werror=shadow] cc1: all warnings being treated as errors make: *** [/tmp/junk/arch/x86/util/tsc.o] Error 1 make: *** Waiting for unfinished jobs.... Fix by renaming the local variable. Signed-off-by:
-
David Ahern authored
Symbol offset is one of the fields that can be requested in perf-script. Currently you do not get that data when requested. e.g., perf script -f comm,tid,pid,time,cpu,sym,symoff,ip ... gcc 6201/6201 [006] 762250.617897: ffffffff81090d95 update_curr ffffffff810911b8 dequeue_entity ffffffff81091825 dequeue_task_fair ffffffff81087163 dequeue_task ffffffff81087c03 deactivate_task ... With this patch you get the offset: ... gcc 6201/6201 [006] 762250.617897: ffffffff81090d95 update_curr+0x1c5 ffffffff810911b8 dequeue_entity+0x28 ffffffff81091825 dequeue_task_fair+0x45 ffffffff81087163 dequeue_task+0x93 ffffffff81087c03 deactivate_task+0x23 ... Signed-off-by: -
Jiri Olsa authored
Adding 2 more tests to the automated parse events suite for following event config: '{cycles,cache-misses,branch-misses}:S' '{instructions,branch-misses}:Su' Signed-off-by:
-
