- 21 Nov, 2009 4 commits
-
-
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 <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: <1258757489-5978-2-git-send-email-acme@infradead.org> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
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 13 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: -
Arnaldo Carvalho de Melo authored
Propagate the errors instead, the users are the ones to decide what to do if a library call fails. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Propagate the errors instead, the users are the ones to decide what to do if a library call fails. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Propagate the errors instead, the users are the ones to decide what to do if a library call fails. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Propagate the errors instead, the users are the ones to decide what to do if a library call fails. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Porcelain can ignore it, humans can make more sense of it. Suggested-by:
Frederic Weisbecker <fweisbec@gmail.com> Suggested-by:
-
Arnaldo Carvalho de Melo authored
Default continues to be showing all symbols. 'K' and 'U' can be used to toggle showing kernel and user symbols. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
By querying the current number of rows, if the user specifies the number of entries, use that instead. If the user uses the 'e' command to change the number of lines 0 will mean do it automatically, any other number disables the auto resizing. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We really should propagate such kinds of errors so that users of these library functions decide what to do in such cases instead of exiting in random places like now. Signed-off-by:
-
Masami Hiramatsu authored
Show symbol name if insn decoder test find a difference. This will help us to find out where the issue is. Signed-off-by:
-
Masami Hiramatsu authored
Add verbose option to insn decoder test. This dumps decoded instruction when building kernel with V=1. Signed-off-by:
-
- 16 Nov, 2009 7 commits
-
-
Arnaldo Carvalho de Melo authored
With this we can list the buildids in a perf.data file so that we can pipe them to other, distro specific tools that from the buildids can figure out separate packages (foo-debuginfo) where we can find the matching symtabs so that perf report can do its job. E.g: [acme@doppio linux-2.6-tip]$ perf buildid-list | head -5 8e08b117e5458ad3f85da16d42d0fc5cd21c5869 520c2387a587cc5acfcf881e27dba1caaeab4b1f ec8dd400904ddfcac8b1c343263a790f977159dc 7caedbca5a6d8ab39a7fe44bd28c07d3e14a3f3f 379bb828fd08859dbea73279f04abefabc95a6a3 [acme@doppio linux-2.6-tip]$ perf buildid-list -v | head -5 8e08b117e5458ad3f85da16d42d0fc5cd21c5869 /sbin/init 520c2387a587cc5acfcf881e27dba1caaeab4b1f /lib64/ld-2.10.1.so ec8dd400904ddfcac8b1c343263a790f977159dc /lib64/libc-2.10.1.so 7caedbca5a6d8ab39a7fe44bd28c07d3e14a3f3f /sbin/udevd 379bb828fd08859dbea73279f04abefabc95a6a3 /lib64/libdl-2.10.1.so [acme@doppio linux-2.6-tip]$ Signed-off-by:
-
Arnaldo Carvalho de Melo authored
To print the buildids in the list of dsos. Will be used by 'perf buildid-list' Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Renaming it to perf_header__process_sections() and passing a callback to handle each feature. The next changesets will introduce 'perf buildid-list' that will handle just the HEADER_BUILD_ID table, ignoring all the other features. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We need to pass the symbol to the filter so that, for instance, 'perf top' can do filtering and also set the private area it manages, setting the ->map pointer, etc. I found this while running 'perf top' on a machine where hits happened on PLT symbols, where ->map wasn't being set up and segfaults thus happened. Signed-off-by:
-
Peter Zijlstra authored
The purpose of perf_output_{un,}lock() is to: 1) avoid publishing incomplete data [ possible when publishing a head that is ahead of an entry that is still being written ] 2) guarantee fwd progress [ a simple refcount on pending writers doesn't need to drop to 0, making it so would end up implementing something like forced quiecent states of RCU ] To satisfy the above without undue complexity it serializes between CPUs, this means that a pending writer can only be the same cpu in a nested context, and since (under normal operation) a cpu always makes progress we're good -- if the head is only published when the bottom most writer completes. Now we don't need to disable IRQs in order to serialize between CPUs, disabling preemption ought to be sufficient, esp since we already deal with nesting due to NMIs. This avoids potentially expensive (and needless) local IRQ disable/enable ops. Signed-off-by:Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1258373161.26714.254.camel@laptop> Signed-off-by:
-
