)]}' { "log": [ { "commit": "9486aa38771661e96fbb51c549b9901b5df609d8", "tree": "72cecbff0cb5124c960feeec3a6ac1fff75c649a", "parents": [ "57b84e53171ce672683faf1cab2e660965a6bdaf" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat Jan 22 20:37:02 2011 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat Jan 22 23:41:57 2011 -0200" }, "message": "perf tools: Fix 64 bit integer format strings\n\nUsing %L[uxd] has issues in some architectures, like on ppc64. Fix it\nby making our 64 bit integers typedefs of stdint.h types and using\nPRI[ux]64 like, for instance, git does.\n\nReported by Denis Kirjanov that provided a patch for one case, I went\nand changed all cases.\n\nReported-by: Denis Kirjanov \u003cdkirjanov@kernel.org\u003e\nTested-by: Denis Kirjanov \u003cdkirjanov@kernel.org\u003e\nLKML-Reference: \u003c20110120093246.GA8031@hera.kernel.org\u003e\nCc: Denis Kirjanov \u003cdkirjanov@kernel.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Pingtian Han \u003cphan@redhat.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "57b84e53171ce672683faf1cab2e660965a6bdaf", "tree": "da17c60c30b5adf374b599804d3a28aa5c5280ce", "parents": [ "01bb2dc4e47639c8e7eddb1718720a051bcdc955" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat Jan 22 23:14:20 2011 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat Jan 22 23:14:20 2011 -0200" }, "message": "perf test: Fix build on older glibcs\n\nWhere we don\u0027t have CPU_ALLOC \u0026 friends. As the tools are being used in older\ndistros where the only allowed change are to replace the kernel, like RHEL4 and\n5.\n\nReported-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "ffb5e0fb44d0829021a51f972df90166bc9b700e", "tree": "d0fc058c018522d940aceb56350e83f7a93a0be3", "parents": [ "b2f8fb237e9cc407a02aca401369c15babae35dd" ], "author": { "name": "Han Pingtian", "email": "phan@redhat.com", "time": "Thu Jan 20 19:47:07 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jan 21 16:44:14 2011 -0200" }, "message": "perf test: Use cpu_map-\u003e[cpu] when setting affinity\n\nWhen some of CPUs are offline:\n\n # cat /sys/devices/system/cpu/online\n 0,6-31\n\nperf test will fail on #3 testcase:\n\n 3: detect open syscall event on all cpus:\n --- start ---\n perf_evsel__read_on_cpu: expected to intercept 111 calls on cpu 0, got 681\n perf_evsel__read_on_cpu: expected to intercept 112 calls on cpu 1, got 117\n perf_evsel__read_on_cpu: expected to intercept 113 calls on cpu 2, got 118\n perf_evsel__read_on_cpu: expected to intercept 114 calls on cpu 3, got 119\n perf_evsel__read_on_cpu: expected to intercept 115 calls on cpu 4, got 120\n perf_evsel__read_on_cpu: expected to intercept 116 calls on cpu 5, got 121\n perf_evsel__read_on_cpu: expected to intercept 117 calls on cpu 6, got 122\n perf_evsel__read_on_cpu: expected to intercept 118 calls on cpu 7, got 123\n perf_evsel__read_on_cpu: expected to intercept 119 calls on cpu 8, got 124\n perf_evsel__read_on_cpu: expected to intercept 120 calls on cpu 9, got 125\n perf_evsel__read_on_cpu: expected to intercept 121 calls on cpu 10, got 126\n ....\n\nThis patch try to use \u0027cpus-\u003emap[cpu]\u0027 when setting cpu affinity, and\nwill check the return code of sched_setaffinity()\n\nLKML-Reference: \u003c20110120114707.GA11781@hpt.nay.redhat.com\u003e\nSigned-off-by: Han Pingtian \u003cphan@redhat.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "0252208eb52f6fe8731a47804eddc7ba93f60a87", "tree": "deaddeda57a630a1d6813ea565fc972c699e2906", "parents": [ "12f7e0364375ba1ba55abcc5ac082b68fb526c80" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jan 04 11:55:27 2011 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Jan 10 22:03:26 2011 -0200" }, "message": "perf evsel: Support perf_evsel__open(cpus \u003e 1 \u0026\u0026 threads \u003e 1)\n\nAnd a test for it:\n\n[acme@felicio linux]$ perf test\n 1: vmlinux symtab matches kallsyms: Ok\n 2: detect open syscall event: Ok\n 3: detect open syscall event on all cpus: Ok\n[acme@felicio linux]$\n\nTranslating C the test does:\n\n1. generates different number of open syscalls on each CPU\n by using sched_setaffinity\n2. Verifies that the expected number of events is generated\n on each CPU\n\nIt works as expected.\n\nLKML-Reference: \u003cnew-submission\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "23a2f3ab46596d9fd0b0e592d2101bea90970594", "tree": "6b3d9e3755a3e71bb0e6b47e62b269e50b6cf37d", "parents": [ "6b01f2c4f6188da50d8fe094e369a9c0390424ab" ], "author": { "name": "Lin Ming", "email": "ming.m.lin@intel.com", "time": "Fri Jan 07 11:11:09 2011 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jan 07 01:44:36 2011 -0200" }, "message": "perf tools: Pass whole attr to event selectors\n\nSince commit 69aad6f1(perf tools: Introduce event selectors), only\nperf_event_attr::type and ::config are passed to event selector, which\nmakes perf tool not work correctly.\n\nFor example, PEBS does not work because perf_event_attr::precise_ip is\nnot passed to the syscall.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLKML-Reference: \u003c1294369869.20563.19.camel@minggr.sh.intel.com\u003e\nSigned-off-by: Lin Ming \u003cming.m.lin@intel.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "454a3bbe9b75eb8cbddffcf383fbb8e97ea78f52", "tree": "d10cbe4a83a625908abf35581922b8ed3d6df2eb", "parents": [ "74d91e3c6a66359bb754fb5d8a5b54fb6ba2f9a6" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jan 04 10:40:08 2011 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Jan 05 14:52:01 2011 -0200" }, "message": "perf test: Clarify some error reports in the open syscall test\n\nRebooted my devel machine, first thing I ran was perf test, that expects\ndebugfs to be mounted, test fails. Be more clear about it.\n\nAlso add missing newlines and add more informative message when\nsys_perf_event_open fails.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "d854861c4292a4e675a5d3bfd862c5f7421c81e8", "tree": "59a4012085b68bb302c61a9ebb8bb81477b59d98", "parents": [ "4eed11d5e24540dc133003b6e8f904cb747ac4bb" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jan 04 00:16:20 2011 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jan 04 00:32:06 2011 -0200" }, "message": "perf test: Add test for counting open syscalls\n\nTo test the use of the perf_evsel class on something other than\nthe tools from where we refactored code to create it.\n\nIt calls open() N times and then checks if the event created to\nmonitor it returns N events.\n\n[acme@felicio linux]$ perf test\n 1: vmlinux symtab matches kallsyms: Ok\n 2: detect open syscall event: Ok\n[acme@felicio linux]$\n\nIt does.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Han Pingtian \u003cphan@redhat.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "d3678758048308049cdad31ec3eae063be17c0db", "tree": "717d3995a21b4b60bf949b087eabb12a7a75a51c", "parents": [ "3b01a413c196c91040d41c86e5b56f76bb369f74" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Dec 21 23:38:37 2010 -0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Dec 22 20:31:59 2010 -0200" }, "message": "perf test: Look forward for symbol aliases\n\nNot just before, fixing these false positives:\n\n[acme@mica linux]$ perf test -v 1\n 1: vmlinux symtab matches kallsyms:\n--- start ---\nLooking at the vmlinux_path (6 entries long)\nUsing //lib/modules/2.6.37-rc5-00180-ge06b6bf/build/vmlinux for symbols\n0xffffffff81058dc0: diff name v: sys_vm86old k: sys_ni_syscall\n0xffffffff81058dc0: diff name v: sys_vm86 k: sys_ni_syscall\n0xffffffff81058dc0: diff name v: sys_subpage_prot k: sys_ni_syscall\n0xffffffff810b5f7c: diff name v: probe_kernel_write k: __probe_kernel_write\n0xffffffff810b5fe5: diff name v: probe_kernel_read k: __probe_kernel_read\n0xffffffff811bc380: diff name v: __memset k: memset\n0xffffffff81384a98: diff name v: __sched_text_start k: sleep_on_common\n0xffffffff81386750: diff name v: __sched_text_end k: _raw_spin_trylock\n0xffffffff8138cee8: diff name v: __irqentry_text_start k: do_IRQ\n0xffffffff8138f079: diff name v: __start_notes k: _etext\n0xffffffff8138f079: diff name v: __stop_notes k: _etext\n---- end ----\nvmlinux symtab matches kallsyms: FAILED!\n\n[acme@mica linux]$\n\nSome are weak functions, others are just markers, etc. They get in the rb tree\nwith the same addr, so we need to look around to find the symbol with the same\nname.\n\nWe were looking just at the previous entries with the same addr, look forward\ntoo.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Han Pingtian \u003cphan@redhat.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "8035458fbb567ae138c77a5f710050107c6a7066", "tree": "0bd6e3730d96aa5d574e73d500f1820d2b195d8c", "parents": [ "1967936d688c475b85d34d84e09858cf514c893c" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 15:51:10 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 16:22:37 2010 -0300" }, "message": "perf options: Type check OPT_BOOLEAN and fix the offenders\n\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "1c6a800cde3b818fd8320b5d402f2d77d2948c00", "tree": "2feb2a077e0dbc8c0cb24a70e92ca1d1daaef817", "parents": [ "5c0541d53ef3897494768decb09eb8f1087953a5" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Apr 29 18:58:32 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Apr 29 18:59:23 2010 -0300" }, "message": "perf test: Initial regression testing command\n\nFirst an example with the first internal test:\n\n[acme@doppio linux-2.6-tip]$ perf test\n 1: vmlinux symtab matches kallsyms: Ok\n\nSo it run just one test, that is \"vmlinux symtab matches kallsyms\", and it was\nsuccessful.\n\nIf we run it in verbose mode, we\u0027ll see details about errors and extra warnings\nfor non-fatal problems:\n\n[acme@doppio linux-2.6-tip]$ perf test -v\n 1: vmlinux symtab matches kallsyms:\n--- start ---\nLooking at the vmlinux_path (5 entries long)\nNo build_id in vmlinux, ignoring it\nNo build_id in /boot/vmlinux, ignoring it\nNo build_id in /boot/vmlinux-2.6.34-rc4-tip+, ignoring it\nUsing /lib/modules/2.6.34-rc4-tip+/build/vmlinux for symbols\nMaps only in vmlinux:\n ffffffff81cb81b1-ffffffff81e1149b 0 [kernel].init.text\n ffffffff81e1149c-ffffffff9fffffff 0 [kernel].exit.text\n ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0\n ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn\n ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1\n ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2\nMaps in vmlinux with a different name in kallsyms:\n ffffffffff600000-ffffffffff6000ff 0 [kernel].vsyscall_0 in kallsyms as [kernel].0\n ffffffffff600100-ffffffffff6003ff 0 [kernel].vsyscall_fn in kallsyms as:\n*ffffffffff600100-ffffffffff60012f 0 [kernel].2\n ffffffffff600400-ffffffffff6007ff 0 [kernel].vsyscall_1 in kallsyms as [kernel].6\n ffffffffff600800-ffffffffffffffff 0 [kernel].vsyscall_2 in kallsyms as [kernel].8\nMaps only in kallsyms:\n ffffffffff600130-ffffffffff6003ff 0 [kernel].4\n---- end ----\nvmlinux symtab matches kallsyms: Ok\n[acme@doppio linux-2.6-tip]$\n\nIn the above case we only know the name of the non contiguous kernel ranges in\nthe address space when reading the symbol information from the ELF symtab in\nvmlinux.\n\nThe /proc/kallsyms file lack this, we only notice they are separate because\nthere are modules after the kernel and after that more kernel functions, so we\nneed to have a module rbtree backed by the module .ko path to get symtabs in\nthe vmlinux case.\n\nThe tool uses it to match by address to emit appropriate warning, but don\u0027t\nconsiders this fatal.\n\nThe .init.text and .exit.text ines, of course, aren\u0027t in kallsyms, so I left\nthese cases just as extra info in verbose mode.\n\nThe end of the sections also aren\u0027t in kallsyms, so we the symbols layer does\nanother pass and sets the end addresses as the next map start minus one, which\nsometimes pads, causing harmless mismatches.\n\nBut at least the symbols match, tested it by copying /proc/kallsyms to\n/tmp/kallsyms and doing changes to see if they were detected.\n\nThis first test also should serve as a first stab at documenting the\nsymbol library by providing a self contained example that exercises it\ntogether with comments about what is being done.\n\nMore tests to check if actions done on a monitored app, like doing mmaps, etc,\nmakes the kernel generate the expected events should be added next.\n\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" } ] }