)]}' { "log": [ { "commit": "108553e1f3c45a92d23681a378ad9e4c3230eebc", "tree": "27cde88dbb3ec8438d100032135e845bd43ad92d", "parents": [ "97aa1052739c6a06cb6b0467dbf410613d20bc97" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 08 03:41:46 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 08 06:26:56 2010 +0200" }, "message": "perf: Sync callchains with period based hits\n\nHists have their hits increased by the event period. And this\nperiod based counting is the foundation of all the stats in\nperf report.\n\nBut callchains still use the raw number of hits, without taking\nthe period into account. So when we compute the percentage,\nabsolute based percentages are totally broken, and relative ones\ntoo in the first parent level. Because we pass the number of events\nmuliplied by their period as the total number of hits to the\ncallchain filtering, while callchains expect this number to be\nthe number of raw hits.\n\nperf report -g graph was simply not working, showing no graph unless\nthe min percent was zero. And even there the percentage of the\nbranches was always 0. And may be fractal filtering was broken on\nthe first branch level too.\n\nflat also was broken, but it was hidden because of other breakages.\n\nAnyway fix this by counting using periods on callchains.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "97aa1052739c6a06cb6b0467dbf410613d20bc97", "tree": "1bcf54fbe3fe39b6941f898a6927b6ac14df9996", "parents": [ "869599ceda4a035cdb3345c563b74cdeef10f790" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 08 06:06:17 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 08 06:20:15 2010 +0200" }, "message": "perf: Resurrect flat callchains\n\nInitialize the callchain radix tree root correctly.\n\nWhen we walk through the parents, we must stop after the root, but\nsince it wasn\u0027t well initialized, its parent pointer was random.\n\nAlso the number of hits was random because uninitialized, hence it\nwas part of the callchain while the root doesn\u0027t contain anything.\n\nThis fixes segfaults and percentages followed by empty callchains\nwhile running:\n\n\tperf report -g flat\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: 2.6.31.x-2.6.34.x \u003cstable@kernel.org\u003e\n" }, { "commit": "869599ceda4a035cdb3345c563b74cdeef10f790", "tree": "c92e7227a0a6242e0ed67f2471dde66356ba4d5a", "parents": [ "2190de2f59b3a371f7a5bf8dcc7a0c3f71723679" ], "author": { "name": "Thavidu Ranatunga", "email": "tharan@au1.ibm.com", "time": "Mon Jul 05 18:00:15 2010 +1000" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jul 05 10:42:58 2010 +0200" }, "message": "perf: Version String fix, for fallback if not from git\n\nThis gets rid of the default version fallback for Perf and\nchanges it so that it returns the version of the kernel from\nit\u0027s Makefile (if sources were not from git, ie. if it was\ndownloaded from a tarball)\n\nSigned-off-by: Thavidu Ranatunga \u003ctharan@au1.ibm.com\u003e\nAcked-by: Ian Munsie \u003cimunsie@au1.ibm.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003c1278316815-6099-2-git-send-email-tharan@au1.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2190de2f59b3a371f7a5bf8dcc7a0c3f71723679", "tree": "32f391645b54dde6b9714e8b6237a91cd71f45bc", "parents": [ "815c4163b6c8ebf8152f42b0a5fd015cfdcedc78" ], "author": { "name": "Thavidu Ranatunga", "email": "tharan@au1.ibm.com", "time": "Mon Jul 05 18:00:14 2010 +1000" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jul 05 10:42:58 2010 +0200" }, "message": "perf: Version String fix, using kernel version\n\nChanges the Perf --version string such that it shows the kernel\nversion as suggested by Ingo as follows:\n\nThat way the perf that comes with v2.6.34 will be:\n\n perf version v2.6.34\n\nwhile interim versions will have the version of the interim\nkernel - for example:\n\n perf version v2.6.35-rc4-70-g39ef13a\n\nThis functionality was already in the perf version generator\nfile except that it was looking for a .git in the perf directory\ninstead of the kernel directory.\n\nSigned-off-by: Thavidu Ranatunga \u003ctharan@au1.ibm.com\u003e\nAcked-by: Ian Munsie \u003cimunsie@au1.ibm.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003c1278316815-6099-1-git-send-email-tharan@au1.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c214909b36efec632432acdcbfacdd46a6e11370", "tree": "dec6f8d89bf32b387de5312ed5d0354aad6468e6", "parents": [ "a1e80fafc9f0742a1776a0490258cb64912411b0" ], "author": { "name": "Gui Jianfeng", "email": "guijianfeng@cn.fujitsu.com", "time": "Wed Jun 16 13:21:44 2010 +0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jul 01 14:02:38 2010 -0300" }, "message": "perf tools: Fix find tids routine by excluding \".\" and \"..\"\n\nIntroduce a filter function to skip \".\" and \"..\" directories when calculating\ntid number, otherwise tid 0 will be included in the all_tid result array.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c4C185F68.1020505@cn.fujitsu.com\u003e\nSigned-off-by: Gui Jianfeng \u003cguijianfeng@cn.fujitsu.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "720a3aeb7373cb49cf222d5f12e121f78d3d4410", "tree": "e2451f06fe4983c4aae971bdaf31fe538a7fec1a", "parents": [ "174787cb5144e5a45141ec7cb9d95ea29bbe22bb" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 17 08:37:44 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 17 08:37:44 2010 -0300" }, "message": "perf session: Remove threads from tree on PERF_RECORD_EXIT\n\nMove them to a session-\u003edead_threads list just like we do with maps that\nare replaced, because we may have hist_entries pointing to them.\n\nThis fixes a bug when inserting maps for a new thread that reused the\nTID, mixing maps for two different threads, causing an endless loop.\n\nThe code for insering maps should be made more robust but for .35 this\nis the minimalistic patch.\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\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": "1d90f2e707e75afdb6b644f774cf5e54dc9c33fc", "tree": "d5bc78d60ac4462ff544f394da94361ead1447d3", "parents": [ "d11007703c31db534674ebeeb9eb047bbbe758bd" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed Jun 09 07:13:16 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 10 08:29:19 2010 -0300" }, "message": "perf record: Don\u0027t call newt functions when not initialized\n\nWhen processing events we want to give visual feedback to the user when\nusing the newt browser, so there are ui_progress calls in\n__perf_session__process_events, but those should check if newt is being\nused.\n\nReported-by: Srikar Dronamraju \u003csrikar@linux.vnet.ibm.com\u003e\nTested-by: Srikar Dronamraju \u003csrikar@linux.vnet.ibm.com\u003e\nCc: Ananth N Mavinakayanahalli \u003cananth@in.ibm.com\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Masami Hiramatsu \u003cmasami.hiramatsu.pt@hitachi.com\u003e,\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Srikar Dronamraju \u003csrikar@linux.vnet.ibm.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003c20100609123530.GB9471@ghostprotocols.net\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "e7dadc0089da730a1ba2638a1a03533be0c67f11", "tree": "fe85a16eb85cf4c2750fddb347a3fd1f69e1c6e3", "parents": [ "da3fd1a0010ccc9fe6fd5ae2b9e85e1aacc03e4d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Jun 03 18:35:55 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jun 04 07:07:52 2010 -0300" }, "message": "perf symbols: Set the DSO long name when using symbol_conf.vmlinux_name\n\nWe need to set the long name to the name specified via, for instance,\n\u0027perf annotate --vmlinux /path/to/vmlinux\u0027, if not it will remain as\n\u0027[kernel.kallsyms]\u0027 and that will make annotate fail when passing this\nas the vmlinux name in the call to objdump.\n\nThe way this is setup grew unwieldly and dso__load_vmlinux is the\nfunction that should allocate space for the long name, with callers not\nassuming that filenames should be allocated somehow by then (strdup,\ndso__build_id_filename, etc).\n\nFor now this is the minimalistic patch, a proper fix for .36 will be\nmade.\n\nReported-by: Stephane Eranian \u003ceranian@google.com\u003e\nTested-by: Stephane Eranian \u003ceranian@google.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Frédéric 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: \u003c20100604003900.GD10469@ghostprotocols.net\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "da3fd1a0010ccc9fe6fd5ae2b9e85e1aacc03e4d", "tree": "84ee4a69289d06802ebc2ba0e4e69a53c91db72a", "parents": [ "2fb750e825b5347de0390315f4284f13709a9856", "b5c874f14c5f57cc8654e9184694196c466147bb" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jun 02 09:13:12 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jun 02 09:13:12 2010 +0200" }, "message": "Merge branch \u0027perf/urgent\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/urgent\n" }, { "commit": "c02514850d67be8db6b2b6658cbc23ac1fbf8bc7", "tree": "309a7df9e2cb7ae681479ae36fd39e710721c472", "parents": [ "75d9ef1707cf3db264a549142a1f54a5380d63dc" ], "author": { "name": "Pierre Tardy", "email": "tardyp@gmail.com", "time": "Mon May 31 23:12:09 2010 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jun 01 06:12:35 2010 -0300" }, "message": "perf scripts python: Give field dict to unhandled callback\n\ntrace_unhandled() callback does not allow to access event fields, this patch\nresolves the problem.\n\nIt can also been used as a more pythonic and flexible way for script writters\nto demux event types\n\nThis will for example greatly simplify pytimechart event demux.\n\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e,\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003c1275340329-2397-1-git-send-email-tardyp@gmail.com\u003e\nSigned-off-by: Pierre Tardy \u003ctardyp@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "75d9ef1707cf3db264a549142a1f54a5380d63dc", "tree": "b23265c9b0ad7fb042e3f472ca5fed7b0a0205d3", "parents": [ "546cf44a1b507c1cbb5cf42bbe6169780567f36f" ], "author": { "name": "Konstantin Stepanyuk", "email": "kostyas@cqg.com", "time": "Thu May 27 02:10:11 2010 +0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Jun 01 05:44:36 2010 -0300" }, "message": "perf hist: fix objdump output parsing\n\nhist_entry__annotate() runs objdump with -S option so the output may contain\nlines of any format. If a line starts with a colon strtoull() returns 0 and\ncalculated offset will be negative. This causes perf annotate segfaults.\n\nMake sure that strtoull() has parsed at least one digit.\n\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Frédéric 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: Konstantin Stepanyuk \u003ckonstantin.stepanyuk@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "dd833d713ccc79e00176eb1b3a6c65638c44e27b", "tree": "96f04a64e8d67f6dd5fc5f77882fc97ee840ec8b", "parents": [ "af64865ba6825e10fe62a3105fea5cadffeb52c6" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Jun 01 00:43:07 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Jun 01 00:43:07 2010 +0200" }, "message": "perf: Do the comm inheritance per thread in event__process_task\n\nevent__process_task() doesn\u0027t propagate the comm copy on clone,\nbut only on process fork. So we loose all the tid:comm resolution\nfor tasks that aren\u0027t a main process thread.\n\nProgragate the per thread granularity to event__process_task for\npid resolution.\n\nThis fixes various unresolved pids in perf sched, especially when\nwe trace multithread processes. The problem is quickly reproducible\nwith the messaging benchmark using the multithread mode \"-t\" :\n\n\tperf sched record perf bench sched messaging -t\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\n" }, { "commit": "13eb04fdbeb9d21dfe4696630daefe18ef6a1a84", "tree": "47edb43ab193dfc99227f760ee70bb9c393d14c4", "parents": [ "546cf44a1b507c1cbb5cf42bbe6169780567f36f" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon May 31 23:38:44 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon May 31 23:59:50 2010 +0200" }, "message": "perf: Process comm events by tid\n\nWhen we synthetize the existing running tasks though procfs,\nwe walk through every threads of a process, queuing one comm\nevents per tid.\n\nBut then on report time, event__process_comm() only creates and\nsets the comm on a per process granularity. This is the right\nthing for comm events that came from the kernel, as they are\nonly created on exec. Sub-threads then inherit their comm\nfrom fork events. But that doesn\u0027t work with our synthetized\ncomm events taken from procfs informations as the per thread\ngranularity is done on comm events directly there.\n\nHence we need event__process_comm() to work with the tid rather\nthan the pid. It won\u0027t change anything for comm events coming\nfrom the kernel but this will fix the synthetized ones.\n\nBefore:\n\n\t$ ./perf report -D | grep COMM | grep firefox\n\n\t0x2c7b8 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c7d0 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c7e8 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c800 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c818 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c830 [0x18]: PERF_RECORD_COMM: firefox:5297\n\nAfter:\n\t$ ./perf report -D | grep COMM | grep firefox\n\n\t0x2c7b8 [0x18]: PERF_RECORD_COMM: firefox:5297\n\t0x2c7d0 [0x18]: PERF_RECORD_COMM: firefox:5299\n\t0x2c7e8 [0x18]: PERF_RECORD_COMM: firefox:5300\n\t0x2c800 [0x18]: PERF_RECORD_COMM: firefox:5308\n\t0x2c818 [0x18]: PERF_RECORD_COMM: firefox:5309\n\t0x2c830 [0x18]: PERF_RECORD_COMM: firefox:5312\n\nThis fixes various unresolved pid on perf sched.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\n" }, { "commit": "c4fe52a8ee730ed340eba8fe6ccbf26347ebe9aa", "tree": "84af3dc87ba3b1ef71ec94275fc94dbcfc0d4b10", "parents": [ "5ad90e4ea4a096af9f0a362e34dfae5686a191ef" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 27 09:53:40 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 27 09:53:40 2010 -0300" }, "message": "perf tui: Fix last use_browser problem related to .perfconfig\n\nWhen we moved to using ~/.perfconfig to set the value of use_browser,\nit changed from a boolean to an int so that the convention used for\nuse_pager was followed.\n\nThat convention is:\n\n-1: unspecified, that is what use_{browser,pager} is initialized\n 0: Don\u0027t use the browser (should be TUI), because was explicitely\n set to 0/off/false on ~/.perfconfig [tui] cmd \u003d, or because\n we\u0027re redirecting the stdout to a file or piping it to some\n other command (!isatty()).\n 1: Use the TUI\n\nSome code was not properly audited and continued testing it as a\nboolean, this seems to be the last one.\n\nReported-by: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nTested-by: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\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": "5ad90e4ea4a096af9f0a362e34dfae5686a191ef", "tree": "f537aae3fd9e04395658c19cc97a401431c972fa", "parents": [ "62e3436b5f3461662929eae102beefbd12127cb1" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 26 13:26:02 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 26 13:26:02 2010 -0300" }, "message": "perf symbols: Add the build id cache to the vmlinux path\n\nSo that if the kernel DSO has a build id because record inserted it in\nthe perf.data build id table in the header, or a BUILD_ID event was\ninserted in the stream, we first look at the build id cache\n($HOME/.debug/).\n\nIf we find it there, try to use it, allowing offline annotation in\naddition to \u0027perf report\u0027.\n\nReported-by: Stephane Eranian \u003ceranian@google.com\u003e\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": "62e3436b5f3461662929eae102beefbd12127cb1", "tree": "f106ccc10a03dd182edefe4717875bd787473840", "parents": [ "49c177461bfbedeccbab22bf3905db2f9da7f1c3" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 26 13:22:26 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 26 13:22:26 2010 -0300" }, "message": "perf tui: Reset use_browser if stdout is not a tty\n\nThe newt initialization routines weren\u0027t being called because the output\nwas a file (perf annotate \u003e /tmp/bla) but use_browser was still 1,\nbecause ~/.perfconfig had it as \u0027on\u0027, so, later on newt routines\nsegfaulted.\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": "d67f088e084755bdceb4f15bc6e05e309db1eea7", "tree": "6eaae7aed4f990233e73851053f2a36b32ce55b2", "parents": [ "44bf460649a9b91f291176097e9d7e846e8c001e" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 23 22:36:51 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 23 22:36:51 2010 -0300" }, "message": "perf report: Support multiple events on the TUI\n\nThe hists__tty_browse_tree function was created with the loop to print\nall events, and its equivalent, hists__tui_browse_tree, was created in a\nsimilar fashion, where it is possible to switch among the multiple\nevents, if present, using TAB to go the next event, and shift+TAB\n(UNTAB) to go to the previous.\n\nThe report TUI now shows as the window title the name of the event and a\nleak was fixed wrt pstacks.\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": "44bf460649a9b91f291176097e9d7e846e8c001e", "tree": "9ae7d7df29e058fc43e9ca8cee25ff9fc19a0973", "parents": [ "c392c4c6dccf7c64c113b473c7eceedf25eddd51" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 23 19:12:25 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 23 22:35:07 2010 -0300" }, "message": "perf annotate: Fix up usage of the build id cache\n\nIt was assuming that the cache was always available and also wasn\u0027t\nchecking if the file found in the build id cache was just a kallsyms\nfile, that is not supported by objdump for disassembly.\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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": "46e3e055ce69a00d735e458445ab1d24718ff751", "tree": "06829420acf27f2deb05ac6ccc230268bf271318", "parents": [ "6e78c9fd1bc2c7e04b3d7052e9eb27aa536e4e2c" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 22 11:25:40 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 22 11:25:40 2010 -0300" }, "message": "perf annotate: Add TUI interface\n\nWhen annotating multiple entries, for instance, when running simply as:\n\n$ perf annotate\n\nthe right and left keys, as well as TAB can be used to cycle thru the\nmultiple symbols being annotated.\n\nIf one doesn\u0027t like TUI annotate, disable it by editing ~/.perfconfig\nand adding:\n\n[tui]\n\n\tannotate \u003d off\n\nJust like it is possible for report.\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": "6e78c9fd1bc2c7e04b3d7052e9eb27aa536e4e2c", "tree": "f1f17a81de35430dec2774985e8afb41fb3acecb", "parents": [ "0e8dc2597487848bb076d6b3d8440c85dde521e7" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 22 11:20:24 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 22 11:20:24 2010 -0300" }, "message": "perf tui: Remove annotate from popup menu after failure\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": "598357eba6a55d27ddc7ead80ebb83fe1aad9b83", "tree": "105630cd5d71f6ea82c4b10782c7540ce310a8b2", "parents": [ "580d607cd666dfabfc1c7b0fb08c8ac690c7c87f" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri May 21 12:48:39 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 21 13:55:32 2010 +0200" }, "message": "perf: Fix getline undeclared\n\nWe need to have stdio.h included with _GNU_SOURCEfopr getline,\nwhich is broken with the inclusion of build-id.h.\n\nKeep util.h included first in hist.c\n\nFixes:\n\tutil/hist.c: Dans la fonction «hist_entry__parse_objdump_line» :\n\tutil/hist.c:938: attention : déclaration implicite de la fonction « «getline» »\n\tutil/hist.c:938: attention : nested extern declaration of «getline»\n\tmake: *** [util/hist.o] Erreur 1\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLKML-Reference: \u003c1274438919-5104-1-git-send-regression-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1c34bde13a3cdcd4c7c6322f8052e67c2c91caf1", "tree": "3be33fd17c7b3101acb638771075cf6681334c36", "parents": [ "915e555822629421d97f851c6b87bf4c314ed8c9", "5d06e6915b1b76653e6fe3369b0b18fdbf75f0a5" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 21 09:50:09 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 21 09:50:09 2010 +0200" }, "message": "Merge branch \u0027perf\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core\n" }, { "commit": "5d06e6915b1b76653e6fe3369b0b18fdbf75f0a5", "tree": "6ed4257dd38a923aa027988bd7dda627ff217c65", "parents": [ "ef365cefbc53d8674a18520a1d4c2e5590127299" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 20 22:01:10 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 20 22:01:10 2010 -0300" }, "message": "perf tui: Allow disabling the TUI on a per command basis in ~/.perfconfig\n\nUsing the same scheme as for git\u0027s/perf\u0027s pager setup, i.e. if one\ndoesn\u0027t want to, on a newt enabled perf binary, to disable the TUI for\n\u0027perf report\u0027, its just a matter of doing:\n\n [root@doppio linux-2.6-tip]# printf \"[tui]\\n\\nreport \u003d off\\n\" \u003e\n /root/.perfconfig\n [root@doppio linux-2.6-tip]# cat /root/.perfconfig\n [tui]\n\n report \u003d off\n [root@doppio linux-2.6-tip]#\n\nSystem wide settings are also possible, by editing /etc/perfconfig, etc,\ni.e. the git machinery for config files applies to perf as well, so when\nin doubt where to put your settings, consult the git documentation, if\nit fails, please let us know.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nDiscussed-with: Stephane Eranian \u003ceranian@google.com\u003e\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": "b36f19d572151abb987ce308a3e066b977a2146f", "tree": "07f520f8b3da969d288e34a121cc31a0209eb519", "parents": [ "17930b405e0ecdc8ecc4d336377a92950e2de76a" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 20 12:15:33 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 20 12:15:33 2010 -0300" }, "message": "perf annotate: Use build-ids to find the right DSO\n\nWe were still using the pathname found on the MMAP event, that could not\nbe the one we used when recording, so use the build-id cache for that,\nonly falling back to use the pathname in the MMAP event if no build-ids\nare available.\n\nWith this we now also are able to do secure, seamless offline annotation.\n\nExample:\n\n[root@doppio linux-2.6-tip]# perf report -g none -v 2\u003e /dev/null | head -10\n 8.12% Xorg /usr/lib64/libpixman-1.so.0.14.0 0x0000000000026d02 B [.] pixman_rasterize_edges\n 4.68% firefox /usr/lib64/xulrunner-1.9.1/libxul.so 0x00000000005dbdba B [.] 0x000000005dbdba\n 3.70% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet\n 2.96% init /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet\n 2.73% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff8100a738 ! [k] mwait_idle_with_hints\n[root@doppio linux-2.6-tip]# perf annotate -v pixman_rasterize_edges 2\u003e\u00261 | grep Executing\nExecuting: objdump --start-address\u003d0x000000371ce26670 --stop-address\u003d0x000000371ce2709f -dS /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|grep -v /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|expand\n[root@doppio linux-2.6-tip]# perf buildid-list | grep libpixman-1.so.0.14.0\nbd6ac5199137aaeb279f864717d8d061477466c1 /usr/lib64/libpixman-1.so.0.14.0\n[root@doppio linux-2.6-tip]#\n\nReported-by: Stephane Eranian \u003ceranian@google.com\u003e\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": "17930b405e0ecdc8ecc4d336377a92950e2de76a", "tree": "bbd6d3f7e73f2047fcc95efa7c9fe9cd535b6c9e", "parents": [ "dfacc4d6c98b89609250269f518c1f54c30454ef" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 19 16:03:51 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 20 11:35:22 2010 -0300" }, "message": "perf TUI: Make \u0027space\u0027 be an alias to \u0027PgDn\u0027\n\nJust like if one is using the stdio based pager, or more/less, for that\nmatter.\n\nSuggested-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "dfacc4d6c98b89609250269f518c1f54c30454ef", "tree": "e7effbee7bdc85d18f7b26ab9cb5c9f700d1481a", "parents": [ "f869097e884d8cb65b2bb7831ca57b7dffb66fdd", "85cb68b27c428d477169f3aa46c72dba103a17bd" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 20 14:38:55 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 20 14:38:55 2010 +0200" }, "message": "Merge branch \u0027perf/urgent\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core\n" }, { "commit": "85cb68b27c428d477169f3aa46c72dba103a17bd", "tree": "78a1f0b444f53d28760ece50ab47f820b0ba7b45", "parents": [ "49f135ed02828a58b2401f149926c2e3c9cb0116" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu May 20 10:34:59 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu May 20 11:21:57 2010 +0200" }, "message": "perf: Fix unaligned accesses while fetching trace values\n\nAccessing trace values of an 8 size may end up in a segfault\non archs that can\u0027t deal with misaligned access, which is the\ncase for sparc 64. This is because PERF_SAMPLE_RAW are aligned\nto 4 and not to 8.\n\nFix this on the macros that get the values of 8 size.\n\nThis fixes segfaults on perf tools in sparc 64.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cbb5cf7ff6b298beacfe23db3386335b0b9c0a2d", "tree": "153901937a7ce3acffc536c48652e0d87a52685b", "parents": [ "537b60d17894b7c19a6060feae40299d7109d6e7" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Tue May 04 23:02:10 2010 -0500" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu May 20 08:37:17 2010 +0200" }, "message": "perf: Use read() instead of lseek() in trace_event_read.c:skip()\n\nThis is a small fix for a problem affecting live-mode, introduced\nrecently:\n\nroot@tropicana:~# perf trace rwtop\nperf trace started with Perl\nscript /root/libexec/perf-core/scripts/perl/rwtop.pl\n\n Fatal: did not read header event\n\ncommit d00a47cce569a3e660a8c9de5d57af28d6a9f0f7 added a skip()\nfunction to skip over e.g. header_page, but this doesn\u0027t work for\nlive mode. This patch re-implements skip() to use read() instead of\nlseek() to fix that.\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLKML-Reference: \u003c1273032130.6383.28.camel@tropicana\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "f869097e884d8cb65b2bb7831ca57b7dffb66fdd", "tree": "4a12562d3121571b19d877b5ed2a1749caf1354e", "parents": [ "f6e1467d8303a397ce40bcfb5f72f97d3ebc768f" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 19 13:41:23 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 19 13:45:08 2010 -0300" }, "message": "perf session: Make read_build_id routines look at the host_machine too\n\nThe changes made to support host and guest machines in a session, that\nstarted when the \u0027perf kvm\u0027 tool was introduced ended up introducing a\nbug where the host_machine was not having its DSOs traversed for\nbuild-id processing.\n\nFix it by moving some methods to the right classes and considering the\nhost_machine when processing build-ids.\n\nReported-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nReported-by: Stephane Eranian \u003ceranian@google.com\u003e\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": "f6e1467d8303a397ce40bcfb5f72f97d3ebc768f", "tree": "b97e7f51f3a752888df041ce999218864026471a", "parents": [ "ce7f15452cc1dc1eca795542367871a07f37aa79" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 19 11:13:02 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 19 13:44:41 2010 -0300" }, "message": "perf symbols: Don\u0027t try to read the build-id twice\n\nIn __dsos__read_build_ids if the dso already had its build-id read,\ndon\u0027t try again.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "151f85a471d29fc81f70348143d009a729901bc0", "tree": "5860102465e3fa3cf660884d91a82d86dbfc4835", "parents": [ "8a7ddad8e756a72906851fdd5a6e149cbb056e0d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 18:54:30 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 23:05:28 2010 -0300" }, "message": "perf tools: remove xstrndup, xmalloc, xzalloc\n\nAll the functions that call this can handle the equivalent, non\npanic\u0027ing wrapped routines.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "b448c4b613542c16ad66042017946e68da4e422b", "tree": "31f351ef2875a2ae749a6ae765b1f66820716b96", "parents": [ "a41794cdd7ee94a5199e14f642c26d649d383fa5" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 23:04:28 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 23:04:28 2010 -0300" }, "message": "perf probe: Fix some error exit paths\n\nThat could leave filedescriptors open and leak memory. Also stop using\nxmalloc, use malloc and handle results just like other error cases in\nthe same routine that used it.\n\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "a41794cdd7ee94a5199e14f642c26d649d383fa5", "tree": "17fdd252cf12f184f6a75702f140f799b4f20a7b", "parents": [ "5af52b51f76d8f8dce0e5b2a33c20b2231c8046d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 18:29:23 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 23:03:35 2010 -0300" }, "message": "perf tools: Remove some unused functions\n\nWithout the bloated cplus_demangle from binutils, i.e building with:\n\n$ make NO_DEMANGLE\u003d1 O\u003d~acme/git/build/perf -j3 -C tools/perf/ install\n\nBefore:\n\n text\t data\t bss\t dec\t hex\tfilename\n 471851\t 29280\t4025056\t4526187\t 45106b\t/home/acme/bin/perf\n\nAfter:\n\n[acme@doppio linux-2.6-tip]$ size ~/bin/perf\n text\t data\t bss\t dec\t hex\tfilename\n 446886\t 29232\t4008576\t4484694\t 446e56\t/home/acme/bin/perf\n\nSo its a 5.3% size reduction in code, but the interesting part is in the git\ndiff --stat output:\n\n 19 files changed, 20 insertions(+), 1909 deletions(-)\n\nIf we ever need some of the things we got from git but weren\u0027t using, we just\nhave to go to the git repo and get fresh, uptodate source code bits.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "4d7b4ac22fbec1a03206c6cde353f2fd6942f828", "tree": "2d96a9e9c28cf6fa628a278decc00ad55a8b043b", "parents": [ "3aaf51ace5975050ab43c7d4d7e439e0ae7d13d7", "94f3ca95787ada3d64339a4ecb2754236ab563f6" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 18 08:19:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 18 08:19:03 2010 -0700" }, "message": "Merge branch \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (311 commits)\n perf tools: Add mode to build without newt support\n perf symbols: symbol inconsistency message should be done only at verbose\u003d1\n perf tui: Add explicit -lslang option\n perf options: Type check all the remaining OPT_ variants\n perf options: Type check OPT_BOOLEAN and fix the offenders\n perf options: Check v type in OPT_U?INTEGER\n perf options: Introduce OPT_UINTEGER\n perf tui: Add workaround for slang \u003c 2.1.4\n perf record: Fix bug mismatch with -c option definition\n perf options: Introduce OPT_U64\n perf tui: Add help window to show key associations\n perf tui: Make \u003c- exit menus too\n perf newt: Add single key shortcuts for zoom into DSO and threads\n perf newt: Exit browser unconditionally when CTRL+C, q or Q is pressed\n perf newt: Fix the \u0027A\u0027/\u0027a\u0027 shortcut for annotate\n perf newt: Make \u003c- exit the ui_browser\n x86, perf: P4 PMU - fix counters management logic\n perf newt: Make \u003c- zoom out filters\n perf report: Report number of events, not samples\n perf hist: Clarify events_stats fields usage\n ...\n\nFix up trivial conflicts in kernel/fork.c and tools/perf/builtin-record.c\n" }, { "commit": "32ec6acfdcc066313261d0fbe6a966cb1804a7cd", "tree": "0a9325139d71ea56b5a9c59a9bd335351dddcc4e", "parents": [ "7752f1b096e13991f20b59fd11ba73da3809d93c" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 00:23:14 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 18 00:25:36 2010 -0300" }, "message": "perf tui: Fix build problem with slang \u003c\u003d 2.0.6\n\nslang versions \u003c\u003d 2.0.6 have a \"#if HAVE_LONG_LONG\" that breaks the\nbuild if it isn\u0027t defined. Use the equivalent one that glibc has on\nfeatures.h.\n\nReported-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\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: Steven Rostedt \u003crostedt@goodmis.org\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": "7752f1b096e13991f20b59fd11ba73da3809d93c", "tree": "9a30ef1d2a8f665bc0d1d00d2011e5036b21ef73", "parents": [ "94f3ca95787ada3d64339a4ecb2754236ab563f6" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Mon May 10 13:12:07 2010 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 22:13:51 2010 -0300" }, "message": "perf probe: Don\u0027t compile CFI related code if elfutils is old\n\nCheck elfutils version, and if it is old don\u0027t compile CFI analysis code. This\nallows to compile perf with old elfutils.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nTested-by: Stephane Eranian \u003ceranian@google.com\u003e\nReported-by: Robert Richter \u003crobert.richter@amd.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c20100510171207.26029.97604.stgit@localhost6.localdomain6\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "2f51903bc3139e25ec908f8944a0001c7b868e90", "tree": "1aa0f66347d73b4951f50306625a707b840535f4", "parents": [ "63aa9e7e3ab28ad5362502b1a69fae945367ad65" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 17:57:59 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 17:57:59 2010 -0300" }, "message": "perf symbols: symbol inconsistency message should be done only at verbose\u003d1\n\nThat happened for an old perf.data file that had no fake MMAP events for\nthe kernel modules, but even then it should warn once for each module,\nnot one time for every symbol in every module not found.\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "edb7c60e27c1baff38d82440dc52eaffac9a45f4", "tree": "fc49d1f862fd5f1393c8b6245d571d97b208d91a", "parents": [ "8035458fbb567ae138c77a5f710050107c6a7066" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 16:22:41 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 16:22:41 2010 -0300" }, "message": "perf options: Type check all the remaining OPT_ variants\n\nOPT_SET_INT was renamed to OPT_SET_UINT since the only use in these\ntools is to set something that has an enum type, that is builtin\ncompatible with unsigned int.\n\nSeveral string constifications were done to make OPT_STRING require a\nconst char * type.\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": "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": "1967936d688c475b85d34d84e09858cf514c893c", "tree": "e9788fe79c7d2af4ad1fab0d9cfe4b3822f468ff", "parents": [ "c100edbee8dbf033ec4095a976a74c1c75c9fc1d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 15:39:16 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 15:43:38 2010 -0300" }, "message": "perf options: Check v type in OPT_U?INTEGER\n\nTo avoid problems like the one fixed by Stephane Eranian in 3de29ca, now\nwe\u0027ll got this instead:\n\n\tbench/sched-messaging.c:259: error: negative width in bit-field ‘\u003canonymous\u003e’\n\tbench/sched-messaging.c:261: error: negative width in bit-field ‘\u003canonymous\u003e’\n\nWhich is rather cryptic, but is how BUILD_BUG_ON_ZERO works, so kernel\nhackers should be already used to this.\n\nWith it in place found some problems, fixed by changing the affected\nvariables to sensible types or changed some OPT_INTEGER to OPT_UINTEGER.\n\nNext csets will go thru converting each of the remaining OPT_ so that\nreview can be made easier by grouping changes per type per patch.\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": "c100edbee8dbf033ec4095a976a74c1c75c9fc1d", "tree": "ff4d16bfe5fb31c78e78fb6f99a297000ee07353", "parents": [ "dc4ff19341126155c5714119396efbae62ab40bf" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 15:30:00 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 15:30:00 2010 -0300" }, "message": "perf options: Introduce OPT_UINTEGER\n\nFor unsigned int options to be parsed, next patches will make use of it.\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": "dc4ff19341126155c5714119396efbae62ab40bf", "tree": "b0d73a3146a79341bbbdebbb1139b84067306315", "parents": [ "3de29cab1f8d62db557a4afed0fb17eebfe64438" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 12:25:09 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 12:28:34 2010 -0300" }, "message": "perf tui: Add workaround for slang \u003c 2.1.4\n\nOlder versions of the slang library didn\u0027t used the \u0027const\u0027 specifier,\ncausing problems with modern compilers of this kind:\n\nutil/newt.c:252: error: passing argument 1 of ‘SLsmg_printf’ discards\nqualifiers from pointer target type\n\nFix it by using some wrappers that when needed const the affected\nparameters back to plain (char *).\n\nReported-by: Lin Ming \u003cming.m.lin@intel.com\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Lin Ming \u003cming.m.lin@intel.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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003c20100517145421.GD29052@ghostprotocols.net\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "6ba85cea872954a36d79e46bf6a9c6ea92794f01", "tree": "0831a7adc633ff0e493b53beb088cf91b827d5c6", "parents": [ "a9a4ab747e2d45bf08fddbc1568f080091486af9" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 12:16:48 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 17 12:16:48 2010 -0300" }, "message": "perf options: Introduce OPT_U64\n\nWe have things like user_interval (-c/--count) in \u0027perf record\u0027 that\nneeds this.\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": "a9a4ab747e2d45bf08fddbc1568f080091486af9", "tree": "d6a1815e5a0775210bf23d611f849749a1ed2772", "parents": [ "a308f3a868185d4f804fe71d0400e2b058c6d9af" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 16 21:04:27 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 16 21:04:27 2010 -0300" }, "message": "perf tui: Add help window to show key associations\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "a308f3a868185d4f804fe71d0400e2b058c6d9af", "tree": "2c0ff9d6d0aba272060a453056e9c8cfe5c5dbb3", "parents": [ "9d192e118a094087494997ea1c8a2faf39af38c5" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 16 20:29:38 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 16 20:29:38 2010 -0300" }, "message": "perf tui: Make \u003c- exit menus too\n\nIn fact it is now added to the hot key list when newt_form__new is used,\nallowing us to remove the explicit assignment in all its users.\n\nThe visible change is that \u003c- will exit the menu that pops up when -\u003e is\npressed (and Enter when callchains are not being used).\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "9d192e118a094087494997ea1c8a2faf39af38c5", "tree": "849bc6750ef1edf5627405e4041702bfa4979e3d", "parents": [ "29351db6a05e7e42be457569428425520a18beec" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 21:15:01 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 21:15:01 2010 -0300" }, "message": "perf newt: Add single key shortcuts for zoom into DSO and threads\n\n\u0027D\u0027/\u0027d\u0027 for zooming into the DSO in the current highlighted hist entry,\n\u0027T\u0027/\u0027t\u0027 for zooming into the current thread.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "29351db6a05e7e42be457569428425520a18beec", "tree": "fc6bb2bd3a4b371f41fd7ee698fbdcaac4bf94a3", "parents": [ "c1ec5fefd9cd9ccb020966a49a3c7f44b25d9e84" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 21:06:58 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 21:06:58 2010 -0300" }, "message": "perf newt: Exit browser unconditionally when CTRL+C, q or Q is pressed\n\nESC still asks for confirmation.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c1ec5fefd9cd9ccb020966a49a3c7f44b25d9e84", "tree": "96a48d105a71123c84bb0cbce29b1752892511e5", "parents": [ "605539034f208d365f76af8e2152cb25f702367d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 20:45:31 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 20:48:25 2010 -0300" }, "message": "perf newt: Fix the \u0027A\u0027/\u0027a\u0027 shortcut for annotate\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "605539034f208d365f76af8e2152cb25f702367d", "tree": "e424f78b1b91d4c9392a17bf7fb65cf82a47267a", "parents": [ "7ebaa2838a751125c113072486334d7b4e63f9ad" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 20:40:34 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sat May 15 20:48:24 2010 -0300" }, "message": "perf newt: Make \u003c- exit the ui_browser\n\nRight now that means that pressing the left arrow willl make the symbol\nannotation window to exit back to the main symbol histogram browser.\n\nThis is another improvement on the UI fastpath, i.e. just the arrows and\nenter are enough for most browsing.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "3e1bbdc3a721f4b1ed44f4554402a8dbc60fa97f", "tree": "36dce578a3f530c72e30051ded963759dc40a716", "parents": [ "c82ee828aa20487d254a5225d256cd422acee459" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 20:05:21 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 20:05:21 2010 -0300" }, "message": "perf newt: Make \u003c- zoom out filters\n\nAfter we use the filters to zoom into DSOs or threads, we can use \u003c-\n(left arrow) to zoom out from the last filter applied.\n\nIt is still possible to zoom out of order by using the popup menu.\n\nWith this we now have the zoom out operation on the browsing fast path,\nby allowing fast navigation using just the four arrors and the enter key\nto expand collapse callchains.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c82ee828aa20487d254a5225d256cd422acee459", "tree": "6f8132442237bc4f2393e04a5f30b3711a8f91ca", "parents": [ "cee75ac7ecc27084accdb9d9d6fde65a09f047ae" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 14:19:35 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 14:19:35 2010 -0300" }, "message": "perf report: Report number of events, not samples\n\nNumber of samples is meaningless after we switched to auto-freq, so\nreport the number of events, i.e. not the sum of the different periods,\nbut the number PERF_RECORD_SAMPLE emitted by the kernel.\n\nWhile doing this I noticed that naming \"count\" to the sum of all the\nevent periods can be confusing, so rename it to .period, just like in\nstruct sample.data, so that we become more consistent.\n\nThis helps with the next step, that was to record in struct hist_entry\nthe number of sample events for each instance, we need that because we\nuse it to generate the number of events when applying filters to the\ntree of hist entries like it is being done in the TUI report browser.\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "cee75ac7ecc27084accdb9d9d6fde65a09f047ae", "tree": "686208e18b1ab5356658980ee92c96486384412e", "parents": [ "c8446b9bdabcb0caa61bb341bd73c58f7104b503" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 13:16:55 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 13:16:55 2010 -0300" }, "message": "perf hist: Clarify events_stats fields usage\n\nThe events_stats.total field is too generic, rename it to .total_period,\nand also add a comment explaining that it is the sum of all the .period\nfields in samples, that is needed because we use auto-freq to avoid\nsampling artifacts.\n\nDitto for events_stats.lost, that is the sum of all lost_event.lost\nfields, i.e. the number of events the kernel dropped.\n\nLooking at the users, builtin-sched.c can make use of these fields and\nstop doing it again.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c8446b9bdabcb0caa61bb341bd73c58f7104b503", "tree": "b2530bfbbd893017e9515bd48f2ffa8845860759", "parents": [ "5d2be7cb198a0a6bc6088d3806fb7261b184ad89" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 10:36:42 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 14 10:36:42 2010 -0300" }, "message": "perf hist: Make event__totals per hists\n\nThis is one more thing that started global but are more useful per hist\nor per session.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "8a0ecfb8b47dc765fdf460913231876bbc95385e", "tree": "0075da13b34a88a9e65aaa0b4b6d4a266f2db8dc", "parents": [ "8769e1c7177fd9f6981042bcc6c2851c99a4a7e7" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu May 13 19:47:16 2010 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 13 16:32:58 2010 -0300" }, "message": "perf hist: Fix missing getline declaration\n\nhist.c needs to include util.h so that it gets stdio.h\ninclusion with __GNU_SOURCE defined.\n\nFixes:\n\tutil/hist.c: In function ‘hist_entry__parse_objdump_line’:\n\tutil/hist.c:931: erreur: implicit declaration of function ‘getline’\n\tutil/hist.c:931: erreur: nested extern declaration of ‘getline’\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLKML-Reference: \u003c1273772836-11533-1-git-send-regression-fweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "8769e1c7177fd9f6981042bcc6c2851c99a4a7e7", "tree": "8b3aa1032ce74157d991d80acb73a9abe8eb1d04", "parents": [ "720019908fd5a1bb442bb0a35a6027ba21864d25" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu May 13 19:22:58 2010 +0200" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu May 13 16:32:28 2010 -0300" }, "message": "perf hist: Fix hists__browse no-newt case\n\nFix mistake in a parameter type of the no-newt hists__browse()\nversion.\n\nFixes:\n\tbuiltin-report.c: In function ‘__cmd_report’:\n\tbuiltin-report.c:314: erreur: incompatible type for argument 1 of ‘hists__browse’\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLKML-Reference: \u003c1273771378-8577-1-git-send-regression-fweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "ef7b93a11904c6ba10604233d318d9e8ec88cddc", "tree": "7ae6fa9cbe19be8fbbc18c8fdeb7edfdb7bdab60", "parents": [ "3798ed7bc7ade26d3f59506cd06288615dfc7585" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 23:18:06 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 23:23:20 2010 -0300" }, "message": "perf report: Librarize the annotation code and use it in the newt browser\n\nNow we don\u0027t anymore use popen to run \u0027perf annotate\u0027 for the selected\nsymbol, instead we collect per address samplings when processing samples\nin \u0027perf report\u0027 if we\u0027re using the newt browser, then we use this data\ndirectly to do annotation.\n\nDone this way we can actually traverse the objdump_line objects\ndirectly, matching the addresses to the collected samples and colouring\nthem appropriately using lower level slang routines.\n\nThe new ui_browser class will be reused for the main, callchain aware,\nhistogram browser, when it will be made generic and don\u0027t assume that\nthe objects are always instances of the objdump_line class maintained\nusing list_heads.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "3798ed7bc7ade26d3f59506cd06288615dfc7585", "tree": "a7df9d321398edf6994dbfc10134add08f2621b3", "parents": [ "d11c7addfe0fa501cb54c824c0fac3481d527433" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 18:01:23 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 18:01:23 2010 -0300" }, "message": "perf ui: Add ui_helpline methods\n\nInitially this was just to be able to have a printf like method to\nprepare the formatted string and then pass to newtPushHelpLine, but as\nwe already have for ui_progress, etc, its a step in identifying a\nrestricted, highlevel set of widgets we can then have implementations\nfor multiple widget sets (GTK, etc).\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "b09e0190acf88c7fe3b05e3c331e1b2ef5310896", "tree": "260c82190298a9ee1b298679c6457c6b1735541a", "parents": [ "e3174cfd2a1e28fff774681f00a0eef3d31da970" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 11:10:15 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 11 12:43:10 2010 -0300" }, "message": "perf hist: Adopt filter by dso and by thread methods from the newt browser\n\nThose are really not specific to the newt code, can be used by other UI\nfrontends.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "de068ec048f807d4f62b7dda100c23a1365f086f", "tree": "9d7d7be670747628e2e5ea93db5418ddeb7d739a", "parents": [ "722154e4cacf015161efe60009ae9be23d492296" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed May 05 22:07:39 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 11 09:14:24 2010 +0200" }, "message": "perf: Fix static strings treated like dynamic ones\n\nThe raw_field_ptr() helper, used to retrieve the address of a field\ninside a trace event, treats every strings as if they were dynamic\nie: having a secondary level of indirection to retrieve their\ncontents.\n\nFIELD_IS_STRING doesn\u0027t mean FIELD_IS_DYNAMIC, we only need to\ncompute the secondary dereference for the latter case.\n\nThis fixes perf sched segfaults, bad cmdline report and may be\nsome other bugs.\n\nReported-by: Jason Baron \u003cjbaron@redhat.com\u003e\nReported-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\n" }, { "commit": "3824a4e8da9791f4eed99d69bfcdb3b42f440426", "tree": "970679392b4f1372f0d5c8a19c83f96a1101d646", "parents": [ "a3412d9b358d37fce4527fd67ea601635f2b9496" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sun May 09 23:46:57 2010 -0500" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 19:50:59 2010 -0300" }, "message": "perf/trace/scripting: don\u0027t show script start/stop messages by default\n\nOnly print the script start/stop messages in verbose mode - users\nnormally don\u0027t care and it just clutters up the output.\n\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c1273466820-9330-7-git-send-email-tzanussi@gmail.com\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "fefb0b94bbab858be0909a7eb5ef357e0f996a79", "tree": "db46b10241ad338db05e9ee68bb0ee45954d7b8a", "parents": [ "1c02c4d2e92f2097f1bba63ec71560b0e05a7f36" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 13:57:51 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 19:49:08 2010 -0300" }, "message": "perf hist: Calculate max_sym name len and nr_entries\n\nBetter done when we are adding entries, be it initially of when we\u0027re\nre-sorting the histograms.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "1c02c4d2e92f2097f1bba63ec71560b0e05a7f36", "tree": "ad2a722931398ce3cd3ae850c4cfa148558a52ea", "parents": [ "d118f8ba6ac2af2bf11d40cba657c813f0f39ca2" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 13:04:11 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 13:13:49 2010 -0300" }, "message": "perf hist: Introduce hists class and move lots of methods to it\n\nIn cbbc79a we introduced support for multiple events by introducing a\nnew \"event_stat_id\" struct and then made several perf_session methods\nreceive a point to it instead of a pointer to perf_session, and kept the\nevent_stats and hists rb_tree in perf_session.\n\nWhile working on the new newt based browser, I realised that it would be\nbetter to introduce a new class, \"hists\" (short for \"histograms\"),\nrenaming the \"event_stat_id\" struct and the perf_session methods that\nwere really \"hists\" methods, as they manipulate only struct hists\nmembers, not touching anything in the other perf_session members.\n\nOther optimizations, such as calculating the maximum lenght of a symbol\nname present in an hists instance will be possible as we add them,\navoiding a re-traversal just for finding that information.\n\nThe rationale for the name \"hists\" to replace \"event_stat_id\" is that we\nmay have multiple sets of hists for the same event_stat id, as, for\ninstance, the \u0027perf diff\u0027 tool has, so event stat id is not what\ncharacterizes what this struct and the functions that manipulate it do.\n\nCc: Eric B Munson \u003cebmunson@us.ibm.com\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "d118f8ba6ac2af2bf11d40cba657c813f0f39ca2", "tree": "3df771498254ed1e6ed374031cd32e7f4e51e753", "parents": [ "cdd5b75b0cd24c4d6a98b12a219217b1ccfe2586" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 12:51:05 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 12:51:05 2010 -0300" }, "message": "perf session: create_kernel_maps should use -\u003ehost_machine\n\nUsing machines__create_kernel_maps(..., HOST_KERNEL_ID) it would create\nanother machine instance for the host machine, and since 1f626bc we have\nit out of the machines rb_tree.\n\nFix it by using machine__create_kernel_maps(\u0026self-\u003ehost_machine)\ndirectly.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "cdd5b75b0cd24c4d6a98b12a219217b1ccfe2586", "tree": "540a54641d6d236b6159c4e3721000dcf403ba15", "parents": [ "7f8264539c62378cccbdf9b598927b034bef4a92" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 10:56:50 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 10:57:39 2010 -0300" }, "message": "perf callchains: Use zalloc to allocate objects\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "7f8264539c62378cccbdf9b598927b034bef4a92", "tree": "d8ffc9d666e306b78f5023b5b4ded3d6174583d8", "parents": [ "1f0ac7183f4d270bd9ce511254ba5d931d4f29c9" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 10:51:25 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 10 10:51:25 2010 -0300" }, "message": "perf newt: Use newtAddComponent()\n\nInstead of newtAddComponents(just-one-entry, NULL), that is not needed\nif, like in this browser, we\u0027re adding just one component at a time.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "1f0ac7183f4d270bd9ce511254ba5d931d4f29c9", "tree": "124b2682a249b0393f29e929537aa76ab299bb5f", "parents": [ "232a5c948da5e23dff27e48180abf4a4238f7602", "76ba7e846fcc89d9d4b25b89e303c9058de96d60" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 10 08:20:19 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 10 08:20:19 2010 +0200" }, "message": "Merge branch \u0027perf/test\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core\n" }, { "commit": "232a5c948da5e23dff27e48180abf4a4238f7602", "tree": "bf17e2e428a77b656946e798e3b099dc09c658be", "parents": [ "1f626bc36847ac8dd192f055aed0f9678a781313" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 20:28:10 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 21:15:35 2010 -0300" }, "message": "perf report: Allow limiting the number of entries to print in callchains\n\nWorks by adding a third parameter to the \u0027-g\u0027 argument, after the graph\ntype and minimum percentage, for example:\n\n[root@doppio linux-2.6-tip]# perf report -g fractal,0.5,2\n\nWill show only the first two symbols where at least 0.5% of the samples\ntook place.\n\nAll the other symbols that don\u0027t fall outside these constraints will be\nput together in the last entry, prefixed with \"[...]\" and the total\npercentage for them.\n\nSuggested-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nAcked-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nCc: Arjan van de Ven \u003carjan@linux.intel.com\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "1f626bc36847ac8dd192f055aed0f9678a781313", "tree": "d96b43c56217fb1ec7adaf4a9e12e11a61d0ce44", "parents": [ "4cc4945844fe2cf493f1783b6ce938ba1617d5c2" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 19:57:08 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 21:14:52 2010 -0300" }, "message": "perf session: Embed the host machine data on perf_session\n\nWe have just one host on a given session, and that is the most common\nsetup right now, so embed a -\u003ehost_machine struct machine instance\ndirectly in the perf_session class, check if we\u0027re looking for it before\ngoing to the rb_tree.\n\nThis also fixes a problem found when we try to process old perf.data\nfiles where we didn\u0027t have MMAP events for the kernel and modules and\nthus don\u0027t create the kernel maps, do it in event__preprocess_sample if\nit wasn\u0027t already.\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Zhang, Yanmin \u003cyanmin_zhang@linux.intel.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "4cc4945844fe2cf493f1783b6ce938ba1617d5c2", "tree": "d4d94f2f4447acf93473ec47de1ef5851fca9f00", "parents": [ "3ceb0d4438876a65606c258e5d69e03e57460dd6" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 21:14:07 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 21:14:07 2010 -0300" }, "message": "perf symbols: Check if a struct machine instance was found\n\nWhich can happen when processing old files that had no fake kernel MMAP,\nevents.\n\nThat shouldn\u0027t result in perf_session__create_kernel_maps not being\ncalled, this will be fixed in a followup patch, for now do these checks\nto avoid segfaulting.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "3ceb0d4438876a65606c258e5d69e03e57460dd6", "tree": "cfc37034c00e7806c8bbae99d2dbf9e0f4982d87", "parents": [ "28e2a106d16046ca792722795f809e3f80a5af80" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 16:07:01 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 18:32:32 2010 -0300" }, "message": "perf symbols: Consider unresolved DSOs in the dso__col_widt calculation\n\nBy using BITS_PER_LONG / 4, that is the number of chars that will be\nused in such cases as the DSO \"name\".\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "28e2a106d16046ca792722795f809e3f80a5af80", "tree": "c84149ddf45d02044187fe4511cead93d009b6ee", "parents": [ "39d1e1b1e26dc84d40bf2792287d0d61e44b57df" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 13:02:23 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 13:10:39 2010 -0300" }, "message": "perf hist: Simplify the insertion of new hist_entry instances\n\nAnd with that fix at least one bug:\n\nThe first hit for an entry, the one that calls malloc to create a new\ninstance in __perf_session__add_hist_entry, wasn\u0027t adding the count to\nthe per cpumode (PERF_RECORD_MISC_USER, etc) total variable.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "139633c6a43781cd44798165b0472a34bf53a1e8", "tree": "17c2412ccb2993846488153e8dcc2c7015d260d1", "parents": [ "e157eb8341e7885ff2d9f1620155e3da6e0c8f56" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 11:47:13 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 09 13:07:05 2010 -0300" }, "message": "perf callchain: Move validate_callchain to callchain lib\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "794e43b56c18b95fc9776c914a2659e7d558a352", "tree": "4c31bcb7ed0e7e23b5da02a4b4f6d2c218236463", "parents": [ "2c193c736803ceb547daec725e5c5d992d039f20" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Wed May 05 00:27:40 2010 -0500" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun May 09 13:49:52 2010 +0200" }, "message": "perf/live-mode: Handle payload-less events\n\nSome events, such as the PERF_RECORD_FINISHED_ROUND event consist of\nonly an event header and no data. In this case, a 0-length payload\nwill be read, and the 0 return value will be wrongly interpreted as an\n\u0027unexpected end of event stream\u0027.\n\nThis patch allows for proper handling of data-less events by skipping\n0-length reads.\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nLKML-Reference: \u003c1273038527.6383.51.camel@tropicana\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "d6b17bebd79dae2e3577f2ea27a832af4991a5e6", "tree": "3b7f253ccd54ef9355706224a055dc79e59d954a", "parents": [ "984028075794c00cbf4fb1e94bb6233e8be08875" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon May 03 15:14:33 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun May 09 13:43:42 2010 +0200" }, "message": "perf: Provide a new deterministic events reordering algorithm\n\nThe current events reordering algorithm is based on a heuristic that\ngets broken once we deal with a very fast flow of events.\n\nIndeed the time period based flushing is not suitable anymore\nin the following case, assuming we have a flush period of two\nseconds.\n\n CPU 0 | CPU 1\n |\n cnt1 timestamps | cnt1 timestamps\n |\n 0 | 0\n 1 | 1\n 2 | 2\n 3 | 3\n [...] | [...]\n 4 seconds later\n\nIf we spend too much time to read the buffers (case of a lot of\nevents to record in each buffers or when we have a lot of CPU buffers\nto read), in the next pass the CPU 0 buffer could contain a slice\nof several seconds of events. We\u0027ll read them all and notice we\u0027ve\nreached the period to flush. In the above example we flush the first\nhalf of the CPU 0 buffer, then we read the CPU 1 buffer where we\nhave events that were on the flush slice and then the reordering\nfails.\n\nIt\u0027s simple to reproduce with:\n\n\tperf lock record perf bench sched messaging\n\nTo solve this, we use a new solution that doesn\u0027t rely on an\nheuristical time slice period anymore but on a deterministic basis\nbased on how perf record does its job.\n\nperf record saves the buffers through passes. A pass is a tour\non every buffers from every CPUs. This is made in order: for\neach CPU we read the buffers of every counters. So the more\nbuffers we visit, the later will be the timstamps of their events.\n\nWhen perf record finishes a pass it records a\nPERF_RECORD_FINISHED_ROUND pseudo event.\nWe record the max timestamp t found in the pass n. Assuming these\ntimestamps are monotonic across cpus, we know that if a buffer\nstill has events with timestamps below t, they will be all available\nand then read in the pass n + 1.\nHence when we start to read the pass n + 2, we can safely flush every\nevents with timestamps below t.\n\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d PASS n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n CPU 0 | CPU 1\n |\n cnt1 timestamps | cnt2 timestamps\n 1 | 2\n 2 | 3\n - | 4 \u003c--- max recorded\n\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d PASS n + 1 \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n CPU 0 | CPU 1\n |\n cnt1 timestamps | cnt2 timestamps\n 3 | 5\n 4 | 6\n 5 | 7 \u003c---- max recorded\n\n Flush every events below timestamp 4\n\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d PASS n + 2 \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n CPU 0 | CPU 1\n |\n cnt1 timestamps | cnt2 timestamps\n 6 | 8\n 7 | 9\n - | 10\n\n Flush every events below timestamp 7\n etc...\n\nIt also works on perf.data versions that don\u0027t have\nPERF_RECORD_FINISHED_ROUND pseudo events. The difference is that\nthe events will be only flushed in the end of the perf.data\nprocessing. It will then consume more memory and scale less with\nlarge perf.data files.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\n" }, { "commit": "984028075794c00cbf4fb1e94bb6233e8be08875", "tree": "80c925f948cce8132dde8ec9307854365d363aff", "parents": [ "e157eb8341e7885ff2d9f1620155e3da6e0c8f56" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun May 02 22:05:29 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun May 09 13:43:42 2010 +0200" }, "message": "perf: Introduce a new \"round of buffers read\" pseudo event\n\nIn order to provide a more rubust and deterministic reordering\nalgorithm, we need to know when we reach a point where we just\ndid a pass through over every counter buffers to read every thing\nthey had.\n\nThis patch introduces a new PERF_RECORD_FINISHED_ROUND pseudo event\nthat only consist in an event header and doesn\u0027t need to contain\nanything.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\n" }, { "commit": "ed82702155b6343727ee732f7eae6d72e8b453fe", "tree": "c0925890e9b917d456d0fec38f0d64dad8a99b93", "parents": [ "4d1c52b02d977d884abb21d0bbaba6b5d6bc8374", "1cf4a0632c24ea61162ed819bde358bc94c55510" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat May 08 10:02:57 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat May 08 10:02:57 2010 +0200" }, "message": "Merge branch \u0027perf\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core\n" }, { "commit": "1cf4a0632c24ea61162ed819bde358bc94c55510", "tree": "ba5cfceb0bd6b48f15e2993706876035f4a174a4", "parents": [ "4778e0e8c64f683a71632dba1cff1f85f76f83c4" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 07 14:07:05 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri May 07 14:07:05 2010 -0300" }, "message": "perf list: Improve the raw hw event descriptor documentation\n\nIt was x86 specific and imcomplete at that, improve the situation by\nmaking it clear where the example provided applies and by adding the\nURLs for the Intel and AMD manuals where this is discussed in depth.\n\nAcked-by: Robert Richter \u003crobert.richter@amd.com\u003e\nCc: Cyrill Gorcunov \u003cgorcunov@gmail.com\u003e\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Robert Richter \u003crobert.richter@amd.com\u003e\nReported-by: Robert Richter \u003crobert.richter@amd.com\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "ab608344bcbde4f55ec4cd911b686b0ce3eae076", "tree": "ebd38efabfaab59d6de11a24143d70e1eec36fae", "parents": [ "2b0b5c6fe9b383f3cf35a0a6371c9d577bd523ff" ], "author": { "name": "Peter Zijlstra", "email": "peterz@infradead.org", "time": "Thu Apr 08 23:03:20 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 07 11:31:02 2010 +0200" }, "message": "perf, x86: Improve the PEBS ABI\n\nRename perf_event_attr::precise to perf_event_attr::precise_ip and\nwiden it to 2 bits. This new field describes the required precision of\nthe PERF_SAMPLE_IP field:\n\n 0 - SAMPLE_IP can have arbitrary skid\n 1 - SAMPLE_IP must have constant skid\n 2 - SAMPLE_IP requested to have 0 skid\n 3 - SAMPLE_IP must have 0 skid\n\nAnd modify the Intel PEBS code accordingly. The PEBS implementation\nnow supports up to precise_ip \u003d\u003d 2, where we perform the IP fixup.\n\nAlso s/PERF_RECORD_MISC_EXACT/\u0026_IP/ to clarify its meaning, this bit\nshould be set for each PERF_SAMPLE_IP field known to match the actual\ninstruction triggering the event.\n\nThis new scheme allows for a PEBS mode that uses the buffer for more\nthan a single event.\n\nSigned-off-by: 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: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9e32a3cb0661a6a30e0fd2b77ce85293805e6337", "tree": "b576e0ccd70d8c563f6340f6f2b71c433b9223b3", "parents": [ "db620b1c2fb172346dc54eb62bba9b4a117d173b" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 05 11:20:05 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 05 11:20:05 2010 -0300" }, "message": "perf list: Add explanation about raw hardware event descriptors\n\nUsing explanation given by Ingo Molnar in the oprofile mailing list.\n\nSuggested-by: Nick Black \u003cdank@qemfd.net\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Nick Black \u003cdank@qemfd.net\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\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": "db620b1c2fb172346dc54eb62bba9b4a117d173b", "tree": "6580f89ea495b4e623c4a23aed8754beb428a389", "parents": [ "9890948d857c2120c234b0ca91a80416e8f747fb" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Tue May 04 22:20:16 2010 -0500" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 05 11:12:53 2010 -0300" }, "message": "perf/record: simplify TRACE_INFO tracepoint check\n\nFix a couple of inefficiencies and redundancies related to\nhave_tracepoints() and its use when checking whether to write\nTRACE_INFO.\n\nFirst, there\u0027s no need to use get_tracepoints_path() in\nhave_tracepoints() - we really just want the part that checks whether\nany attributes correspondo to tracepoints.\n\nSecond, we really don\u0027t care about raw_samples per se - tracepoints\nare always raw_samples. In any case, the have_tracepoints() check\nshould be sufficient to decide whether or not to write TRACE_INFO.\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 \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1273030770.6383.6.camel@tropicana\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "9890948d857c2120c234b0ca91a80416e8f747fb", "tree": "b3ac857ff1b3dc2248db23eb93b8a14e5e0f2d4d", "parents": [ "c4f3b5a2d70eae4abb8bcaaf8dc3f067ff1714e8" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 04 20:58:51 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Wed May 05 09:49:48 2010 -0300" }, "message": "perf report: Make dso__calc_col_width agree with hist_entry__dso_snprintf\n\nThe first was always using the -\u003elong_name, while the later used\n-\u003eshort_name if verbose was not set, resulting in the dso column to be\nmuch wider than needed most of the time.\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: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c4f3b5a2d70eae4abb8bcaaf8dc3f067ff1714e8", "tree": "54b857fc96f423ee3fcd4b8752169024ad8ebdb1", "parents": [ "777d0411cd1e384115985dac5ccd42031e3eee2b", "02bf60aad7d5912dfcdbe0154f1bd67ea7a8301e" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 04 18:31:47 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 04 18:31:47 2010 +0200" }, "message": "Merge branch \u0027perf\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core\n" }, { "commit": "02bf60aad7d5912dfcdbe0154f1bd67ea7a8301e", "tree": "4d0c009e30079b127e0d7b01cdd30d8375e44c7c", "parents": [ "11d232ec285b07860670277c8ab3f6076f7bce1e" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Tue May 04 21:19:15 2010 +1000" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue May 04 10:54:09 2010 -0300" }, "message": "perf: Fix performance issue with perf report\n\nOn a large machine we spend a lot of time in perf_header__find_attr when\nrunning perf report.\n\nIf we are parsing a file without PERF_SAMPLE_ID then for each sample we call\nperf_header__find_attr and loop through all counter IDs, never finding a match.\nAs the machine gets larger there are more per cpu counters and we spend an\nawful lot of time in there.\n\nThe patch below initialises each sample id to -1ULL and checks for this in\nperf_header__find_attr. We may need to do something more intelligent eventually\n(eg a hash lookup from counter id to attr) but this at least fixes the most\ncommon usage of perf report.\n\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nAcked-by: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nLKML-Reference: \u003c20100504111915.GB14636@kryten\u003e\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\n--\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "63e0c7715aab6085faa487d498889f4361dc6542", "tree": "3d6923589ed744abeca4e3bb1a6fa512e6e3952b", "parents": [ "090f7204dfdb5d7f18208ea81dfdba845897cedd" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Mon May 03 00:14:48 2010 -0500" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon May 03 10:31:48 2010 -0300" }, "message": "perf: record TRACE_INFO only if using tracepoints and SAMPLE_RAW\n\nThe current perf code implicitly assumes SAMPLE_RAW means tracepoints\nare being used, but doesn\u0027t check for that. It happily records the\nTRACE_INFO even if SAMPLE_RAW is used without tracepoints, but when the\nperf data is read it won\u0027t go any further when it finds TRACE_INFO but\nno tracepoints, and displays misleading errors.\n\nThis adds a check for both in perf-record, and won\u0027t record TRACE_INFO\nunless both are true. This at least allows perf report -D to dump raw\nevents, and avoids triggering a misleading error condition in perf\ntrace. It doesn\u0027t actually enable the non-tracepoint raw events to be\ndisplayed in perf trace, since perf trace currently only deals with\ntracepoint events.\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: \u003c1272865861.7932.16.camel@tropicana\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "0806ebd974590ab24ab357d5d87db744e56bfe13", "tree": "baf96726e3d9f8c2316e509e0a4cbc99ba5fe67a", "parents": [ "090f7204dfdb5d7f18208ea81dfdba845897cedd", "feef47d0cb530e8419dfa0b48141b538b89b1b1a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 03 08:29:35 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 03 08:29:35 2010 +0200" }, "message": "Merge branch \u0027perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core\n" }, { "commit": "454c407ec17a0c63e4023ac0877d687945a7df4a", "tree": "1271299a59a89419c0dd4dcbf29b4492b63555ca", "parents": [ "789688faef5b3ba78065beaf2f3d6f1c839f74a3" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sat May 01 01:41:20 2010 -0500" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 02 13:36:56 2010 -0300" }, "message": "perf: add perf-inject builtin\n\nCurrently, perf \u0027live mode\u0027 writes build-ids at the end of the\nsession, which isn\u0027t actually useful for processing live mode events.\n\nWhat would be better would be to have the build-ids sent before any of\nthe samples that reference them, which can be done by processing the\nevent stream and retrieving the build-ids on the first hit. Doing\nthat in perf-record itself, however, is off-limits.\n\nThis patch introduces perf-inject, which does the same job while\nleaving perf-record untouched. Normal mode perf still records the\nbuild-ids at the end of the session as it should, but for live mode,\nperf-inject can be injected in between the record and report steps\ne.g.:\n\nperf record -o - ./hackbench 10 | perf inject -v -b | perf report -v -i -\n\nperf-inject reads a perf-record event stream and repipes it to stdout.\nAt any point the processing code can inject other events into the\nevent stream - in this case build-ids (-b option) are read and\ninjected as needed into the event stream.\n\nBuild-ids are just the first user of perf-inject - potentially\nanything that needs userspace processing to augment the trace stream\nwith additional information could make use of this facility.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1272696080-16435-3-git-send-email-tzanussi@gmail.com\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "789688faef5b3ba78065beaf2f3d6f1c839f74a3", "tree": "4d4bf78c420cbb0a135a10c602f49566dce1dcd4", "parents": [ "fb72014d98afd51e85aab9c061344ef32d615606" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sat May 01 01:41:19 2010 -0500" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 02 12:04:05 2010 -0300" }, "message": "perf/live: don\u0027t synthesize build ids at the end of a live mode trace\n\nIt doesn\u0027t really make sense to record the build ids at the end of a\nlive mode session - live mode samples need that information during the\ntrace rather than at the end.\n\nLeave event__synthesize_build_id() in place, however; we\u0027ll still be\nusing that to synthesize build ids in a more timely fashion in a\nfuture patch.\n\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1272696080-16435-2-git-send-email-tzanussi@gmail.com\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "fb72014d98afd51e85aab9c061344ef32d615606", "tree": "18713d4d1084870c604b512396b893944a2bbdab", "parents": [ "bc4b473f1aa2ef785ccfd890a24a1de5a6660f98" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Apr 30 19:31:12 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Sun May 02 12:00:44 2010 -0300" }, "message": "perf tools: Don\u0027t use code surrounded by __KERNEL__\n\nWe need to refactor code to be explicitely shared by the kernel and at\nleast the tools/ userspace programs, so, till we do that, copy the bare\nminimum bitmap/bitops code needed by tools/perf.\n\nReported-by: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\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" }, { "commit": "d00a47cce569a3e660a8c9de5d57af28d6a9f0f7", "tree": "0993bc6584d8726a7a921f9a13ce11f7c560cdb0", "parents": [ "e5a5f1f015cf435eb3d2f5712ba51ffdbb92cbef" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat May 01 03:08:46 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat May 01 04:31:48 2010 +0200" }, "message": "perf: Fix warning while reading ring buffer headers\n\ncommit e9e94e3bd862d31777335722e747e97d9821bc1d\n\"perf trace: Ignore \"overwrite\" field if present in\n/events/header_page\" makes perf trace launching spurious warnings\nabout unexpected tokens read:\n\n\tWarning: Error: expected type 6 but read 4\n\nThis change tries to handle the overcommit field in the header_page\nfile whenever this field is present or not.\n\nThe problem is that if this field is not present, we try to find it\nand give up in the middle of the line when we realize we are actually\ndealing with another field, which is the \"data\" one. And this failure\nabandons the file pointer in the middle of the \"data\" description\nline:\n\n\tfield: u64 timestamp;\toffset:0;\tsize:8;\tsigned:0;\n\tfield: local_t commit;\toffset:8;\tsize:8;\tsigned:1;\n\tfield: char data;\toffset:16;\tsize:4080;\tsigned:1;\n ^^^\n Here\n\nWhat happens next is that we want to read this line to parse the data\nfield, but we fail because the pointer is not in the beginning of the\nline.\n\nWe could probably fix that by rewinding the pointer. But in fact we\ndon\u0027t care much about these headers that only concern the ftrace\nring-buffer. We don\u0027t use them from perf.\n\nJust skip this part of perf.data, but don\u0027t remove it from recording\nto stay compatible with olders perf.data\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Stephane Eranian \u003ceranian@google.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5c0541d53ef3897494768decb09eb8f1087953a5", "tree": "38b8eab8e45a2d2265db64b131320e6baa43b984", "parents": [ "18acde52b83bd1c8e1d007db519f46d344aa13ed" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Apr 29 15:25:23 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Apr 29 15:25:23 2010 -0300" }, "message": "perf symbols: Add machine helper routines\n\nCreated when writing the first \u0027perf test\u0027 regression testing routine.\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" }, { "commit": "cbf6968098f89d3216d074f06544b5032b344da4", "tree": "842750b609ec0ad6f246be03fc39f7614c98316f", "parents": [ "d28c62232e50eab202bcd3f19b5c7a25b8b900b6" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:22:44 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:22:44 2010 -0300" }, "message": "perf machines: Make the machines class adopt the dsos__fprintf methods\n\nNow those methods don\u0027t operate on a global list of dsos, but on lists\nof machines, so make this clear by renaming the functions.\n\nCc: Avi Kivity \u003cavi@redhat.com\u003e\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: Zhang, Yanmin \u003cyanmin_zhang@linux.intel.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "d28c62232e50eab202bcd3f19b5c7a25b8b900b6", "tree": "544aca2fe1c7a6c813cf2bf319a8ceb4d212b649", "parents": [ "48ea8f5470aa6f35244d1b218316705ea88c0259" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:20:43 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:21:18 2010 -0300" }, "message": "perf machine: Adopt some map_groups functions\n\nThose functions operated on members now grouped in \u0027struct machine\u0027, so\nmove those methods to this new class.\n\nThe changes made to \u0027perf probe\u0027 shows that using this abstraction\ninserting probes on guests almost got supported for free.\n\nCc: Avi Kivity \u003cavi@redhat.com\u003e\nCc: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.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: Zhang, Yanmin \u003cyanmin_zhang@linux.intel.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "48ea8f5470aa6f35244d1b218316705ea88c0259", "tree": "b4e9a2d1cc227be96f2c3de815b5b2b4c12e3cb5", "parents": [ "23346f21b277e3aae5e9989e711a11cbe8133a45" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:19:05 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:19:05 2010 -0300" }, "message": "perf machine: Pass buffer size to machine__mmap_name\n\nDon\u0027t blindly assume that the size of the buffer is enough, use\nsnprintf.\n\nCc: Avi Kivity \u003cavi@redhat.com\u003e\nCc: Frédéric 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: Zhang, Yanmin \u003cyanmin_zhang@linux.intel.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "23346f21b277e3aae5e9989e711a11cbe8133a45", "tree": "21f11a72cf21d4eb3d824f46e274dc8f9815d749", "parents": [ "462b04e28a7ec1339c892117c3f20a40e55d0e83" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:17:50 2010 -0300" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Tue Apr 27 21:17:50 2010 -0300" }, "message": "perf tools: Rename \"kernel_info\" to \"machine\"\n\nstruct kernel_info and kerninfo__ are too vague, what they really\ndescribe are machines, virtual ones or hosts.\n\nThere are more changes to introduce helpers to shorten function calls\nand to make more clear what is really being done, but I left that for\nsubsequent patches.\n\nCc: Avi Kivity \u003cavi@redhat.com\u003e\nCc: Frédéric 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: Zhang, Yanmin \u003cyanmin_zhang@linux.intel.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "462b04e28a7ec1339c892117c3f20a40e55d0e83", "tree": "5ea38f3227c761fa936b293afa52c26a660bd6c7", "parents": [ "cfadf9d4ac4be940595ab73d3def24c23c8b875f", "f93830fbb06b67848c762f2177c06cc3cbb97deb" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Apr 27 11:16:54 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Apr 27 11:16:54 2010 +0200" }, "message": "Merge branch \u0027perf\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/core\n" }, { "commit": "ef4a356574426877d569f8b6579325537eb7909b", "tree": "0416c4ab1740a5ff6a07c01eee3e371128881110", "parents": [ "5d1ee0413c8e2e0aa48510b1edfb3c4d2d43455b" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Wed Apr 21 15:56:40 2010 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Apr 26 15:35:20 2010 -0300" }, "message": "perf probe: Add --max-probes option\n\nAdd --max-probes option to change the maximum limit of\nfindable probe points per event, since inlined function can be\nexpanded into thousands of probe points. Default value is 128.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSuggested-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c20100421195640.24664.62984.stgit@localhost6.localdomain6\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "5d1ee0413c8e2e0aa48510b1edfb3c4d2d43455b", "tree": "bd0dbf0fd4ac13b8b5bc0f5504e658861a7fbdc2", "parents": [ "15eca306ec95e164d05457f9f27c722f69af6d18" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Wed Apr 21 15:56:32 2010 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Apr 26 15:33:08 2010 -0300" }, "message": "perf probe: Fix to exit callback soon after finding too many probe points\n\nFix to exit callback soon after finding too many probe points.\nDon\u0027t try to continue searching because it already failed.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nReported-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c20100421195632.24664.42598.stgit@localhost6.localdomain6\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "15eca306ec95e164d05457f9f27c722f69af6d18", "tree": "2a5a40956d5927202fedc983a51dcee1e5028f25", "parents": [ "0ab061cd523a7f2dbf1b59aab0542cb0ab2e4633" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Wed Apr 21 15:56:24 2010 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Apr 26 15:32:37 2010 -0300" }, "message": "perf probe: Fix to use symtab only if no debuginfo\n\nFix perf probe to use symtab only if there is no debuginfo, because debuginfo\nhas more information than symtab.\n\nIf we can\u0027t find a function in debuginfo, we never find it in symtab.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nReported-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c20100421195624.24664.46214.stgit@localhost6.localdomain6\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "0ab061cd523a7f2dbf1b59aab0542cb0ab2e4633", "tree": "5f7fac5772d3fa7afaa8e66a57736c25a2783d7c", "parents": [ "4093b150e52e6da20e9496df8aa007423952ae42" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Wed Apr 21 15:56:16 2010 -0400" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Mon Apr 26 15:31:32 2010 -0300" }, "message": "perf tools: Initialize dso-\u003enode member in dso__new\n\nIf dso-\u003enode member is not initialized, it causes a segmentation fault when\nadding to other lists.\n\nIt should be initilized in dso__new().\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: : \u003c20100421195616.24664.89980.stgit@localhost6.localdomain6\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\n" }, { "commit": "c61e52ee705f938596d307625dce00cc4345aaf0", "tree": "6bb8a1d2662790c6b5ee8d09e0b94d91c97d1da0", "parents": [ "5710fcad7c367adefe5634dc998f1f88780a8457" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Apr 24 00:04:12 2010 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Apr 24 03:49:58 2010 +0200" }, "message": "perf: Generalize perf lock\u0027s sample event reordering to the session layer\n\nThe sample events recorded by perf record are not time ordered\nbecause we have one buffer per cpu for each event (even demultiplexed\nper task/per cpu for task bound events). But when we read trace events\nwe want them to be ordered by time because many state machines are\ninvolved.\n\nThere are currently two ways perf tools deal with that:\n\n- use -M to multiplex every buffers (perf sched, perf kmem)\n But this creates a lot of contention in SMP machines on\n record time.\n\n- use a post-processing time reordering (perf timechart, perf lock)\n The reordering used by timechart is simple but doesn\u0027t scale well\n with huge flow of events, in terms of performance and memory use\n (unusable with perf lock for example).\n Perf lock has its own samples reordering that flushes its memory\n use in a regular basis and that uses a sorting based on the\n previous event queued (a new event to be queued is close to the\n previous one most of the time).\n\nThis patch proposes to export perf lock\u0027s samples reordering facility\nto the session layer that reads the events. So if a tool wants to\nget ordered sample events, it needs to set its\nstruct perf_event_ops::ordered_samples to true and that\u0027s it.\n\nThis prepares tracing based perf tools to get rid of the need to\nuse buffers multiplexing (-M) or to implement their own\nreordering.\n\nAlso lower the flush period to 2 as it\u0027s sufficient already.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Hitoshi Mitake \u003cmitake@dcl.info.waseda.ac.jp\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\n" } ], "next": "5710fcad7c367adefe5634dc998f1f88780a8457" }