- 02 Jun, 2009 23 commits
-
-
Peter Zijlstra authored
Signed-off-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Kacur <jkacur@redhat.com> Cc: Stephane Eranian <eranian@googlemail.com> LKML-Reference: <new-submission> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
Peter Zijlstra authored
The structure isn't hw only and when I read event, I think about those things that fall out the other end. Rename the thing. Signed-off-by:
-
Peter Zijlstra authored
Reported-by:
Stephane Eranian <eranian@googlemail.com> Signed-off-by:
-
Peter Zijlstra authored
Since some people worried that 4G might not be a large enough as an mmap data window, extend it to 64 bit for capable platforms. Reported-by:
-
Peter Zijlstra authored
Do as Power already does, emulate sample periods up to 2^63-1 by composing them of smaller values limited by hardware capabilities. Only once we wrap the software period do we generate an overflow event. Just 10 lines of new code. Reported-by:
-
Peter Zijlstra authored
IRQ (non-NMI) sampling is not used anymore - remove the last few bits. Signed-off-by:
-
Peter Zijlstra authored
A few renames: s/irq_period/sample_period/ s/irq_freq/sample_freq/ s/PERF_RECORD_/PERF_SAMPLE_/ s/record_type/sample_type/ And change both the new sample_type and read_format to u64. Reported-by:
-
Peter Zijlstra authored
Stephan raised the issue that we currently cannot distinguish between similar counters within a group (PERF_RECORD_GROUP uses the config value as identifier). Therefore, generate a new ID for each counter using a global u64 sequence counter. Reported-by:
-
Peter Zijlstra authored
Apparently I'm the first to use it :-) Signed-off-by:
-
Peter Zijlstra authored
Everything is nmi these days, remove the userspace bits so that the kernel can drop the interface. Signed-off-by:
-
Ingo Molnar authored
- extra space between columns - left-aligned the symbol column - moved the no-symbols printout to -v Acked-by:
-
Peter Zijlstra authored
Provide an argument (-f) to overwrite existing data files. Signed-off-by:
-
Peter Zijlstra authored
Include code to pre-construct mappings based on /proc, on system wide recording. Fix the existing code to properly fill out ->pid and ->tid. The PID should be the Thread Group ID (PIDTYPE_PID of task->group_leader) The TID should be the Thread ID (PIDTYPE_PID of task) Furthermore, change the default sorting of report to comm,dso for a better quick overview. Signed-off-by:
-
Peter Zijlstra authored
Stop using task_struct::pid and start using PID namespaces. PIDs will be reported in the PID namespace of the monitoring task at the moment of counter creation. Signed-off-by:
-
Paul Mackerras authored
This removes the prev_state field of struct perf_counter since it is now unused. It was only used by the cpu migration counter, which doesn't use it any more. Signed-off-by:
Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <18979.35052.915728.626374@cargo.ozlabs.ibm.com> Signed-off-by:
-
Paul Mackerras authored
This fixes the cpu migration software counter to count correctly even when contexts get swapped from one task to another. Previously the cpu migration counts reported by perf stat were bogus, ranging from negative to several thousand for a single "lat_ctx 2 8 32" run. With this patch the cpu migration count reported for "lat_ctx 2 8 32" is almost always between 35 and 44. This fixes the problem by adding a call into the perf_counter code from set_task_cpu when tasks are migrated. This enables us to use the generic swcounter code (with some modifications) for the cpu migration counter. This modifies the swcounter code to allow a NULL regs pointer to be passed in to perf_swcounter_ctx_event() etc. The cpu migration counter does this because there isn't necessarily a pt_regs struct for the task available. In this case, the counter will not have interrupt capability - but the migration counter didn't have interrupt capability before, so this is no loss. Signed-off-by:
-
Paul Mackerras authored
This arranges for perf_counter's notifier for cpu hotplug operations to be called earlier than the migration notifier in sched.c by increasing its priority to 20, compared to the 10 for the migration notifier. The reason for doing this is that a subsequent commit to convert the cpu migration counter to use the generic swcounter infrastructure will add a call into the perf_counter subsystem when tasks get migrated. Therefore the perf_counter subsystem needs a chance to initialize its per-cpu data for the new cpu before it can get called from the migration code. This also adds a comment to the migration notifier noting that its priority needs to be lower than that of the perf_counter notifier. Signed-off-by:
-
Mike Galbraith authored
# make prefix=/usr/local V=1 gcc -o builtin-report.o -c -O2 -ggdb3 -Wall -Werror -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -DSHA1_HEADER='<openssl/sha.h>' builtin-report.c cc1: warnings being treated as errors builtin-report.c: In function ‘__cmd_report’: builtin-report.c:626: error: ‘cwdlen’ may be used uninitialized in this function Signed-off-by:
Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by:
-
Mike Galbraith authored
We currently build perf-stat/record etc, only to do nothing with them. We also install the perf binary in two places, $prefix/bin and $perfexec_instdir, which appears to be for binaries which perf would exec were a command not linked in. Correct this, and comment out broken/incomplete targets dist and coverage. Signed-off-by:
-
Mike Galbraith authored
Make .gitignore reflect perf_counter tools files so git status doesn't gripe about untracked files. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <20090601205057.GB7805@ghostprotocols.net> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
This has also a nice side effect, tools built on newer systems such as fedora 10 again work on systems with older versions of glibc: My workstation: [acme@doppio ~]$ rpm -q glibc.x86_64 glibc-2.9-3.x86_64 Test machine: [acme@emilia ~]$ rpm -q glibc.x86_64 glibc-2.5-24 Before: [acme@emilia ~]$ perf perf: /lib64/libc.so.6: version `GLIBC_2.7' not found (required by perf) [acme@emilia ~]$ nm `which perf` | grep GLIBC_2\.7 U __isoc99_sscanf@@GLIBC_2.7 [acme@emilia ~]$ After: [acme@emilia ~]$ perf usage: perf [--version] [--help] COMMAND [ARGS] The most commonly used perf commands are: record Run a command and record its profile into perf.data report Read perf.data (created by perf record) and display the profile stat Run a command and gather performance counter statistics top Run a command and profile it See 'perf help COMMAND' for more information on a specific command. [acme@emilia ~]$ nm `which perf` | grep GLIBC_2\.7 [acme@emilia ~]$ Signed-off-by: -
Arnaldo Carvalho de Melo authored
Add hex conversion libraries. We are going to replace sscanf() uses with them. Signed-off-by:
-
- 01 Jun, 2009 5 commits
-
-
Mike Galbraith authored
Signed-off-by:
-
Ingo Molnar authored
- whitespace fixlets - make local variable definitions more consistent [ Impact: cleanup ] Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: -
Paul Mackerras authored
This changes perf_swcounter_match() so that per-task software counters can count events that occur while their associated task is not running. This will allow us to use the generic software counter code for counting task migrations, which can occur while the task is not scheduled in. To do this, we have to distinguish between the situations where the counter is inactive because its task has been scheduled out, and those where the counter is inactive because it is part of a group that was not able to go on the PMU. In the former case we want the counter to count, but not in the latter case. If the context is active, we have the latter case. If the context is inactive then we need to know whether the counter was counting when the context was last active, which we can determine by comparing its ->tstamp_stopped timestamp with the context's timestamp. This also folds three checks in perf_swcounter_match, checking perf_event_raw(), perf_event_type() and perf_event_id() individually, into a single 64-bit comparison on counter->hw_event.config, as an optimization. Signed-off-by:
-
Paul Mackerras authored
This abstracts out the code for locking the context associated with a task. Because the context might get transferred from one task to another concurrently, we have to check after locking the context that it is still the right context for the task and retry if not. This was open-coded in find_get_context() and perf_counter_init_task(). This adds a further function for pinning the context for a task, i.e. marking it so it can't be transferred to another task. This adds a 'pin_count' field to struct perf_counter_context to indicate that a context is pinned, instead of the previous method of setting the parent_gen count to all 1s. Pinning the context with a pin_count is easier to undo and doesn't require saving the parent_gen value. This also adds a perf_unpin_context() to undo the effect of perf_pin_task_context() and changes perf_counter_init_task to use it. Signed-off-by:
-
Ingo Molnar authored
Merge reason: merge almost-rc8 into perfcounters/core, which was -rc6 based - to pick up the latest upstream fixes. Signed-off-by:
-
- 31 May, 2009 1 commit
-
-
Ingo Molnar authored
Arjan reported this error when entering an unknown command to perf: $ perf start fatal: Uh oh. Your system reports no Git commands at all. The Git code expects there to be perf-* commands - but since Perf is a 'pure' utility with no dash commands anymore, this old assumption of Git does not hold anymore. Remove that error check. Reported-by:
Arjan van de Ven <arjan@linux.intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by:
-
- 30 May, 2009 4 commits
-
-
Ingo Molnar authored
Import Git's nice .txt => {man/html/pdf} generation machinery. Fix various errors in the Documentation/perf*.txt description as well. Also fix a bug in builtin-help: we'd map 'perf help top' to 'perftop' if only the 'perf' binary is in the default PATH - confusing the manpage logic. I dont fully understand why Git did it this way - but i suppose it's a migration artifact from their migration from standalone git-xyz commands to 'git xyz' commands. The perf tools were always using the modern form so it's not an issue there. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: -
Ingo Molnar authored
'make install' didnt install perf itself - which needs a special rule to be copied to bindir. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: -
Ingo Molnar authored
Before: Performance counter stats for '/home/mingo/hackbench': 5728.862689 task clock ticks (msecs) 34426 context switches # 0.006 M/sec 3835 CPU migrations # 0.001 M/sec 18158 pagefaults # 0.003 M/sec 16218109156 CPU cycles # 2830.947 M/sec 13519616840 instructions # 2359.913 M/sec 55941661 cache references # 9.765 M/sec 23554938 cache misses # 4.112 M/sec Wall-clock time elapsed: 528.886980 msecs After: Performance counter stats for '/home/mingo/hackbench': 5845.443541 task clock ticks # 11.886 CPU utilization factor 38289 context switches # 0.007 M/sec 4208 CPU migrations # 0.001 M/sec 17755 pagefaults # 0.003 M/sec 16664668576 CPU cycles # 2850.882 M/sec 13468113991 instructions # 2304.036 M/sec 57445468 cache references # 9.827 M/sec 26896502 cache misses # 4.601 M/sec Wall-clock time elapsed: 491.802357 msecs Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: -
Arnaldo Carvalho de Melo authored
perf_counter tools: Add locking to perf top We need to protect the active_symbols list as two threads change it: the main thread adding entries to the head and the display thread decaying entries from any place in the list. Also related: take a snapshot of syme->count[0] before using it to calculate the weight and to show the same number used in this calc when displaying the symbol usage. Reported-by:
-
- 29 May, 2009 7 commits
-
-
Arnaldo Carvalho de Melo authored
[acme@emilia linux-2.6-tip]$ pwd /home/acme/git/linux-2.6-tip Before (still available using -P/--full-paths) [acme@emilia linux-2.6-tip]$ perf report -P | head -10 11.48% perf: 7454 [kernel]: clear_page_c 4.89% perf: 7454 [kernel]: vsnprintf 4.61% perf: 7454 /home/acme/git/linux-2.6-tip/Documentation/perf_counter/perf: dso__find_symbol 4.09% perf: 7454 [kernel]: number 4.06% perf: 7454 /home/acme/git/linux-2.6-tip/Documentation/perf_counter/perf: dso__fprintf 4.00% perf: 7454 /home/acme/git/linux-2.6-tip/Documentation/perf_counter/perf: symbol_filter New default: [acme@emilia linux-2.6-tip]$ perf report | head -10 11.48% perf: 7454 [kernel]: clear_page_c 4.89% perf: 7454 [kernel]: vsnprintf 4.61% perf: 7454 ./Documentation/perf_counter/perf: dso__find_symbol 4.09% perf: 7454 [kernel]: number 4.06% perf: 7454 ./Documentation/perf_counter/perf: dso__fprintf 4.00% perf: 7454 ./Documentation/perf_counter/perf: symbol_filter Suggested-by: -
git://git.infradead.org/~dwmw2/mtd-2.6.30Linus Torvalds authored
* git://git.infradead.org/~dwmw2/mtd-2.6.30: jffs2: Fix corruption when flash erase/write failure mtd: MXC NAND driver fixes (v5)
-
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb-2.6Linus Torvalds authored
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb-2.6: Revert "USB: Correct Makefile to make isp1760 buildable" usb-serial: fix crash when sub-driver updates firmware USB: isp1760: urb_dequeue doesn't always find the urbs USB: Yet another Conexant Clone to add to cdc-acm.c USB: atmel_usb_udc: Use kzalloc() to allocate ep structures USB: atmel-usba-udc : fix control out requests.
-
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6Linus Torvalds authored
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: Driver Core: do not oops when driver_unregister() is called for unregistered drivers sysfs: file.c: use create_singlethread_workqueue()
-
git://linux-nfs.org/~bfields/linuxLinus Torvalds authored
* 'for-2.6.30' of git://linux-nfs.org/~bfields/linux: svcrdma: dma unmap the correct length for the RPCRDMA header page. nfsd: Revert "svcrpc: take advantage of tcp autotuning" nfsd: fix hung up of nfs client while sync write data to nfs server
-
git://git.kernel.org/pub/scm/linux/kernel/git/dtor/inputLinus Torvalds authored
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input: Input: libps2 - better handle bad scheduler decisions Input: usb1400_ts - fix access to "device data" in resume function Input: multitouch - augment event semantics documentation Input: multitouch - add tracking ID to the protocol
-
git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intelLinus Torvalds authored
* 'drm-intel-next' of git://git.kernel.org/pub/scm/linux/kernel/git/anholt/drm-intel: i915: Set object to gtt domain when faulting it back in drm/i915: Apply a big hammer to 865 GEM object CPU cache flushing. drm/i915: Fix tiling pitch handling on 8xx.
-
