- 21 Nov, 2009 21 commits
-
-
Peter Zijlstra authored
Properly account the full hierarchy of counters for both the count (we already did so) and the scale times (new). Signed-off-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20091120212509.153379276@chello.nl> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
Peter Zijlstra authored
Most sites updating ctx->time and event times do so under ctx->lock, make sure they all do. This was made possible by removing the __perf_event_read() call from __perf_event_sync_stat(), which already had this lock taken. Signed-off-by:
-
Peter Zijlstra authored
cpuctx is always active, task context is always active for current the previous condition verifies that if its a task context its for current, hence we can assume ctx->is_active. Signed-off-by:
-
Peter Zijlstra authored
Removes constraints from __perf_event_read() by leaving it with a single callsite; this callsite had ctx->lock held, the other one does not. Removes some superfluous code from __perf_event_sync_stat(). Signed-off-by:
-
Peter Zijlstra authored
Both callers actually have IRQs disabled, no need doing so again. Signed-off-by:
-
Peter Zijlstra authored
Remove an update_context_time() call from the perf_event_task_sched_out() path and into the branch its needed. The call was both superfluous, because __perf_event_sched_out() already does it, and wrong, because it was done without holding ctx->lock. Place it in perf_event_sync_stat(), which is the only place it is needed and which does already hold ctx->lock. Signed-off-by:
-
Peter Zijlstra authored
As Corey reported, the total_enabled and total_running times could occasionally be 0, even though there were events counted. It turns out this is because we record the times before reading the counter while the latter updates the times. This patch corrects that. While looking at this code I found that there is a lot of locking iffyness around, the following patches correct most of that. Reported-by:
Corey Ashford <cjashfor@linux.vnet.ibm.com> Signed-off-by:
-
Peter Zijlstra authored
Remove a rcu_read_{,un}lock() pair and a few conditionals. We can remove the rcu_read_lock() by increasing the scope of one in the calling function. We can do away with the system_state check if the machine still boots after this patch (seems to be the case). We can do away with the list_empty() check because the bare list_for_each_entry_rcu() reduces to that now that we've removed everything else. Signed-off-by: -
Peter Zijlstra authored
Remove a rcu_read_{,un}lock() pair and a few conditionals. We can remove the rcu_read_lock() by increasing the scope of one in the calling function. We can do away with the system_state check if the machine still boots after this patch (seems to be the case). We can do away with the list_empty() check because the bare list_for_each_entry_rcu() reduces to that now that we've removed everything else. Signed-off-by: -
Peter Zijlstra authored
Remove a rcu_read_{,un}lock() pair and a few conditionals. We can remove the rcu_read_lock() by increasing the scope of one in the calling function. We can do away with the system_state check if the machine still boots after this patch (seems to be the case). We can do away with the list_empty() check because the bare list_for_each_entry_rcu() reduces to that now that we've removed everything else. Signed-off-by: -
Peter Zijlstra authored
Remove a rcu_read_{,un}lock() pair and a few conditionals. We can remove the rcu_read_lock() by increasing the scope of one in the calling function. We can do away with the system_state check if the machine still boots after this patch (seems to be the case). We can do away with the list_empty() check because the bare list_for_each_entry_rcu() reduces to that now that we've removed everything else. Signed-off-by: -
Peter Zijlstra authored
Avoid the rather expensive perf_swevent_set_period() if we know we have to sample every single event anyway. Signed-off-by:
-
Peter Zijlstra authored
in-kernel perf users might wish to have custom actions on the sample interrupt. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
So that the user have a clearer indication about the source of the symbols, as we only state buildid mismatches in verbose mode, because 'perf top' would overwrite such warning anyway. Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1258757489-5978-6-git-send-email-acme@infradead.org> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
E.g.: [root@doppio linux-2.6-tip]# perf top -v --vmlinux ../build/tip/vmlinux > /dev/null build_id in vmlinux is e96699725a47413a50c231864a8e7a8ced40a31b while expected is 18e7cc53db62a7d35e9d6f6c9ddc23017d38ee9a, ignoring it I.e. perf top was told to use a vmlinux file that is not the one currently running on the machine, it ignores it and falls back to using /proc/kallsyms. This solves many, at first, mysterious results when people have a stale vmlinux file while keeping the default of trying to use the vmlinux file in the current directory in things like 'perf annotate' where the DWARF info is required and thus we can't use just /proc/kallsyms. Modules buildids are already being checked as of the previous changeset in this series, because we are using the default dso__load routine, that will look at a series of places looking for the best file with a matching buildid, starting in the -debuginfo directories. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Just like we do with the other DSOs. This also simplifies the kernel_maps setup process, now all that the tools need to do is to call kernel_maps__init and the maps for the modules and kernel will be created, then, later, when kernel_maps__find_symbol() is used, it will also call maps__find_symbol that already checks if the symtab was loaded, loading it if needed. Now if one does 'perf top --hide_kernel_symbols' we won't pay the price of loading the (many) symbols in /proc/kallsyms or vmlinux. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Will be used in more places. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
In the kernel we have more than one notes section, so the linker script combines all and puts them into a ".notes" combined section. So we need to look at both sections and also traverse them looking at multiple GElf_Nhdr entries till we find the one we want, with the build_id. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
It should just load kernel symbols, not load the list of modules. There are more stuff to move to other routines, but lets do it in several steps. End goal is to be able to defer symbol table loading till we find a hit for that map address range. So that the kernel & modules are handled just like all the other DSOs in the system. Signed-off-by:
-
Ingo Molnar authored
Conflicts: arch/x86/kernel/kprobes.c kernel/trace/Makefile Merge reason: hw-breakpoints perf integration is looking good in testing and in reviews, plus conflicts are mounting up - so merge & resolve. Signed-off-by: -
Ingo Molnar authored
Conflicts: tools/perf/util/symbol.c Merge reason: this fix will get merged in .33, not .32, plus resolve the conflict. Signed-off-by:
-
- 20 Nov, 2009 1 commit
-
-
Li Zefan authored
This tool is mostly a perf version of kmemtrace-user. The following information is provided by this tool: - the total amount of memory allocated and fragmentation per call-site - the total amount of memory allocated and fragmentation per allocation - total memory allocated and fragmentation in the collected dataset - ... Sample output: # ./perf kmem record ^C # ./perf kmem --stat caller --stat alloc -l 10 ------------------------------------------------------------------------------ Callsite | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xc052f37a | 790528/4096 | 790528/4096 | 193 | 0.000% 0xc0541d70 | 524288/4096 | 524288/4096 | 128 | 0.000% 0xc051cc68 | 481600/200 | 481600/200 | 2408 | 0.000% 0xc0572623 | 297444/676 | 297440/676 | 440 | 0.001% 0xc05399f1 | 73476/164 | 73472/164 | 448 | 0.005% 0xc05243bf | 51456/256 | 51456/256 | 201 | 0.000% 0xc0730d0e | 31844/497 | 31808/497 | 64 | 0.113% 0xc0734c4e | 17152/256 | 17152/256 | 67 | 0.000% 0xc0541a6d | 16384/128 | 16384/128 | 128 | 0.000% 0xc059c217 | 13120/40 | 13120/40 | 328 | 0.000% 0xc0501ee6 | 11264/88 | 11264/88 | 128 | 0.000% 0xc04daef0 | 7504/682 | 7128/648 | 11 | 5.011% 0xc04e14a3 | 4216/191 | 4216/191 | 22 | 0.000% 0xc05041ca | 3524/44 | 3520/44 | 80 | 0.114% 0xc0734fa3 | 2104/701 | 1620/540 | 3 | 23.004% 0xc05ec9f1 | 2024/289 | 2016/288 | 7 | 0.395% 0xc06a1999 | 1792/256 | 1792/256 | 7 | 0.000% 0xc0463b9a | 1584/144 | 1584/144 | 11 | 0.000% 0xc0541eb0 | 1024/16 | 1024/16 | 64 | 0.000% 0xc06a19ac | 896/128 | 896/128 | 7 | 0.000% 0xc05721c0 | 772/12 | 768/12 | 64 | 0.518% 0xc054d1e6 | 288/57 | 280/56 | 5 | 2.778% 0xc04b562e | 157/31 | 154/30 | 5 | 1.911% 0xc04b536f | 80/16 | 80/16 | 5 | 0.000% 0xc05855a0 | 64/64 | 36/36 | 1 | 43.750% ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ Alloc Ptr | Total_alloc/Per | Total_req/Per | Hit | Fragmentation ------------------------------------------------------------------------------ 0xda884000 | 1052672/4096 | 1052672/4096 | 257 | 0.000% 0xda886000 | 262144/4096 | 262144/4096 | 64 | 0.000% 0xf60c7c00 | 16512/128 | 16512/128 | 129 | 0.000% 0xf59a4118 | 13120/40 | 13120/40 | 328 | 0.000% 0xdfd4b2c0 | 11264/88 | 11264/88 | 128 | 0.000% 0xf5274600 | 7680/256 | 7680/256 | 30 | 0.000% 0xe8395000 | 5948/594 | 5464/546 | 10 | 8.137% 0xe59c3c00 | 5748/479 | 5712/476 | 12 | 0.626% 0xf4cd1a80 | 3524/44 | 3520/44 | 80 | 0.114% 0xe5bd1600 | 2892/482 | 2856/476 | 6 | 1.245% ... | ... | ... | ... | ... ------------------------------------------------------------------------------ SUMMARY ======= Total bytes requested: 2333626 Total bytes allocated: 2353712 Total bytes wasted on internal fragmentation: 20086 Internal fragmentation: 0.853375% TODO: - show sym+offset in 'callsite' column - show cross node allocation stats - collect more useful stats? - ... Signed-off-by:
Li Zefan <lizf@cn.fujitsu.com> Acked-by:
Pekka Enberg <penberg@cs.helsinki.fi> Acked-by:
Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: linux-mm@kvack.org <linux-mm@kvack.org> LKML-Reference: <4B064AF5.9060208@cn.fujitsu.com> Signed-off-by:
-
- 19 Nov, 2009 15 commits
-
-
Masami Hiramatsu authored
Since some instructions are not decoded correctly by older versions of objdump, it may cause false positive error in insn decoder posttest. This changes build error of insn decoder test to build warning. Signed-off-by:
Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Randy Dunlap <rdunlap@xenotime.net> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> LKML-Reference: <20091116230631.5250.41579.stgit@harusame> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Propagate the error, that, interestingly, are already handled by all callers :-) Signed-off-by:
-
Arnaldo Carvalho de Melo authored
This time in perf_header__adds_write, propagating the do_write error returns. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
And also don't call the constructor in it, this way it adheres to the model the other methods follow. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
[root@doppio linux-2.6-tip]# perf record -a -f sleep 3s ; perf buildid-list | grep vmlinux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.171 MB perf.data (~7489 samples) ] 18e7cc53db62a7d35e9d6f6c9ddc23017d38ee9a vmlinux [root@doppio linux-2.6-tip]# Several refactorings were needed so that we can have symmetry between dsos__load_modules() and dsos__load_kernel(), i.e. those functions will respectively create and add to the dsos list the loaded modules and kernel, with its buildids, but not load its symbols. That is something the subcomands that need will have to call dso__load_kernel_sym(), just like we do with modules with dsos__load_module_sym()/dso__load_module_sym(). Next csets will actually use this info to stop producing bogus results using mismatched vmlinux and .ko files. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
[root@doppio linux-2.6-tip]# perf record -a sleep 2s;perf buildid-list|tail [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.162 MB perf.data (~7078 samples) ] 881588fa57b3c1696bc91e5e804a11304f093535 [cfg80211] 4d47ce1da9d16bad00c962c072451b7c681e82df [snd_page_alloc] 5146377e89a7caac617f9782f1a02e46263d3a31 [rfkill] 2153b937bff0d345fea83b63a2e1d3138569f83d [i915] 4e6fb1bb97362e3ee4d306988b9ad6912d5fb9ae [drm_kms_helper] f56ef2bf853e3a798f0d8d51f797622e5dc4420e [drm] b0d157a3b5c4e017329ffc07c64623cd6ad65e95 [i2c_algo_bit] 8125374b905ef9fa8b65d98e166b008ad952f198 [i2c_core] fc875c6e5a90e7b915e9d445d0efc859e1b2678c [video] 4b43c5006589f977e9762fdfc7ac1a92b72fca52 [output] [root@doppio linux-2.6-tip]# elfutils libdwfl/linux-kernel-modules.c was used as reference, as suggested by Roland McGrath. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
No need for this struct and its allocations, we can just use the ->build_id member we already have in struct dso, then ask for it to be read, and later traverse the dsos list, writing the buildid table to the perf.data file. As a bonus, one more die() function got killed. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
When we read the build_id from the DSO name to then index into /usr/lib/debug/.buildid/DSO_BUILD_ID[0:2]/DSO_BUILD_ID[2:], we were jumping directly to the comparision with the buildid we already have in dso->build_id (that came from the perf.data build_id section, collected at perf record time) unconditionally, even if we didn't had recorded it, and furthermore, comparing a formatted buildid with a rawbuildid, yikes. Fix it by deleting the dso__read_build_id() function, that was really misdesigned anyway, and do the necessary checks and correct comparison of raw buildids. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Defer to parse_source() time allocating it. Now we use about this much memory: 1724 root 20 0 42104 10m 940 S 0.0 0.4 0:00.23 perf Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Reducing memory consumption on a typical desktop machine: From: 32710 root 20 0 172m 142m 1056 S 0.0 4.7 0:00.37 perf To: 420 root 20 0 47528 16m 1056 R 0.3 0.5 0:00.24 perf Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Signed-off-by:
-
Arnaldo Carvalho de Melo authored
E.g. [root@doppio ~]# perf top -U --------------------------------------------------------------------------- PerfTop: 482 irqs/sec kernel:100.0% [1000Hz cycles], (all, 2 CPUs) --------------------------------------------------------------------------- DSO: vmlinux samples pcnt function _______ _____ _________________________ 471.00 47.9% read_hpet 57.00 5.8% acpi_os_read_port 30.00 3.1% hpet_next_event 30.00 3.1% find_busiest_group 22.00 2.2% schedule 18.00 1.8% sched_clock_local 14.00 1.4% _spin_lock_irqsave 14.00 1.4% native_read_tsc 13.00 1.3% trace_hardirqs_off 9.00 0.9% fget_light 9.00 0.9% ioread8 8.00 0.8% do_sys_poll Signed-off-by: -
Arnaldo Carvalho de Melo authored
We pre-calculate the symbol name length, then after we sort the entries to print, calculate the biggest one and use that for the symbol name width justification, then use the dso->long_name->len to justificate the DSO name, deciding whether using the short or long name depending on how much space we have on the terminal. IOW give as much info to the user as the terminal width allows. Suggested-by:
-
Arnaldo Carvalho de Melo authored
Using a two bytes hole we already had and since we also need to calculate this strlen for fetching the buildids. We'll use it in 'perf top' to auto-adjust the output based on the terminal width. Signed-off-by:
-
Luck, Tony authored
Compiler on ia64 rejects the "-m64" option. Add arch specific pieces to perf.h Signed-off-by:
Tony Luck <tony.luck@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <4b02d7f43514327a@agluck-desktop.sc.intel.com> Signed-off-by:
-
- 17 Nov, 2009 3 commits
-
-
Nick Piggin authored
Symbol offset history table size does not get updated properly when it is being resized. This leads to garbage results in perf annotate. Signed-off-by:
Nick Piggin <npiggin@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by:
-
Michael S. Tsirkin authored
This makes it possible to build perf statically, by performing: make LDFLAGS=-static Since static libraries are only searched in the order they are specified, move library list from LDFLAGS to EXTLIBS, so that they are put at the end of linker command line. Signed-off-by:
Michael S. Tsirkin <mst@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <20091029152002.GA5406@redhat.com> [ v2: resolved conflicts ] Signed-off-by:
-
Ingo Molnar authored
Resolved merge conflict in tools/perf/Makefile Merge reason: we want to queue up a dependent patch. Signed-off-by:
-
