1. 28 11月, 2009 12 次提交
    • A
      perf tools: Consolidate symbol resolving across all tools · 1ed091c4
      Arnaldo Carvalho de Melo 提交于
      Now we have a very high level routine for simple tools to
      process IP sample events:
      
      	int event__preprocess_sample(const event_t *self,
      				     struct addr_location *al,
      				     symbol_filter_t filter)
      
      It receives the event itself and will insert new threads in the
      global threads list and resolve the map and symbol, filling all
      this info into the new addr_location struct, so that tools like
      annotate and report can further process the event by creating
      hist_entries in their specific way (with or without callgraphs,
      etc).
      
      It in turn uses the new next layer function:
      
      	void thread__find_addr_location(struct thread *self, u8 cpumode,
      					enum map_type type, u64 addr,
      					struct addr_location *al,
      					symbol_filter_t filter)
      
      This one will, given a thread (userspace or the kernel kthread
      one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE
      too in the near future) at the given cpumode, taking vdsos into
      account (userspace hit, but kernel symbol) and will fill all
      these details in the addr_location given.
      
      Tools that need a more compact API for plain function
      resolution, like 'kmem', can use this other one:
      
      	struct symbol *thread__find_function(struct thread *self, u64 addr,
      					     symbol_filter_t filter)
      
      So, to resolve a kernel symbol, that is all the 'kmem' tool
      needs, its just a matter of calling:
      
      	sym = thread__find_function(kthread, addr, NULL);
      
      The 'filter' parameter is needed because we do lazy
      parsing/loading of ELF symtabs or /proc/kallsyms.
      
      With this we remove more code duplication all around, which is
      always good, huh? :-)
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: John Kacur <jkacur@redhat.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      1ed091c4
    • A
      perf tools: Reorganize event processing routines, lotsa dups killed · 62daacb5
      Arnaldo Carvalho de Melo 提交于
      While implementing event__preprocess_sample, that will do all of
      the symbol lookup in one convenient function, I noticed that
      util/process_event.[ch] were not being used at all, then started
      looking if there were other functions that could be shared
      and...
      
      All those functions really don't need to receive offset + head,
      the only thing they did was common to all of them, so do it at
      one place instead.
      
      Stats about number of each type of event processed now is done
      in a central place.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: John Kacur <jkacur@redhat.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-11-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      62daacb5
    • A
      perf symbols: When not using modules, discard its symbols · 1de8e245
      Arnaldo Carvalho de Melo 提交于
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-10-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      1de8e245
    • A
      perf symbols: Support multiple symtabs in struct thread · 95011c60
      Arnaldo Carvalho de Melo 提交于
      Making the routines that were so far specific to the kernel maps
      useful for all threads.
      
      This is done by making the kernel maps be contained in a kernel
      "thread".
      
      This gets the kernel specific routines closer to the userspace
      counterparts, which will help in reducing the boilerplate for
      resolving a symbol, as will be demonstrated in the next patches.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-9-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      95011c60
    • A
      perf symbols: Kernel_maps should be an array of MAP__NR_TYPES entries · 23ea4a3f
      Arnaldo Carvalho de Melo 提交于
      So that we can support multiple symbol table types.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-8-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      23ea4a3f
    • A
      perf symbols: Make the kallsyms loading routines part of the dso class · 4e06255f
      Arnaldo Carvalho de Melo 提交于
      So that the kallsyms loading routines are the direct counterpart
      of the vmlinux loading ones, i.e. dso__load_kallsyms is the
      counterpart of dso__load_vmlinux.
      
      In the process make them also use the symbols rb tree indexed by
      map->type, paving the way for supporting other types of symtabs,
      such as the next one to be supported: variables.
      
      This also allowed removal of yet another global variable:
      kernel_map__functions.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-7-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      4e06255f
    • A
      perf symbols: Better support for multiple symbol tables per dso · 6a4694a4
      Arnaldo Carvalho de Melo 提交于
      By using an array of rb_roots in struct dso we can, from a
      struct map instance to get the right symbol rb_tree more easily.
      This way we can have just one symbol lookup method for struct
      map instances, map__find_symbol, instead of one per symtab type
      (functions, variables).
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-6-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      6a4694a4
    • A
      perf symbols: Add a 'type' field to struct map · 3610583c
      Arnaldo Carvalho de Melo 提交于
      That way we will be able to check if the right symtab is loaded
      in the underlying DSO.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-5-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      3610583c
    • A
      perf symbols: Unexport kernel_map__functions · 605ca4ba
      Arnaldo Carvalho de Melo 提交于
      perf annotate was the only user, and it doesn't really need it.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-4-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      605ca4ba
    • A
      perf symbols: Split the dsos list into kernel and user parts · b0da954a
      Arnaldo Carvalho de Melo 提交于
      We don't need to look at modules in dsos__findnew because the
      kernel events come only with user DSOs. Also we need a way to
      list just the module DSOs so that we can create multiple sets of
      maps, now that we will support maps for the variables in a
      symtab.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-3-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      b0da954a
    • A
      perf symbols: Rename kernel_mapto kernel_map[s]__functions · 61f37a82
      Arnaldo Carvalho de Melo 提交于
      As we'll have kernel_map[s]__variables too.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-2-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      61f37a82
    • A
      perf symbols: Avoid annoying message about loading symbols · 3f5ee186
      Arnaldo Carvalho de Melo 提交于
      This should be properly fixed when we remove the XXX comment in
      'perf report', function resolve_symbol.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259346563-12568-1-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      3f5ee186
  2. 25 11月, 2009 1 次提交
    • T
      perf tools: Add 'signed' flag setting back into trace-event-parse.c · 0d0bea5e
      Tom Zanussi 提交于
      Commit 13999e59 (perf tools:
      Handle the case with and without the "signed" trace field)
      removed code to set the FIELD_IS_SIGNED flag that was originally
      added by commit 26a50744
      (tracing/events: Add 'signed' field to format files).
      
      This adds it back.
      Signed-off-by: NTom Zanussi <tzanussi@gmail.com>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <1259133299-23594-2-git-send-email-tzanussi@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      0d0bea5e
  3. 24 11月, 2009 17 次提交
    • A
      perf symbols: Rename find_symbol routines to find_function · fcf1203a
      Arnaldo Carvalho de Melo 提交于
      Paving the way for supporting variable in adition to function
      symbols.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259074912-5924-1-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      fcf1203a
    • A
      perf tools: Remove unused wrapper routines · 727dad10
      Arnaldo Carvalho de Melo 提交于
      And also make xrealloc and xmalloc weak symbols so that we don't
      have this problem:
      
       /usr/lib/gcc/x86_64-redhat-linux/4.4.1/../../../../lib64/libiberty.a(xmalloc.o):
       In function `xrealloc':
       (.text+0xc0): multiple definition of `xrealloc'
       libperf.a(wrapper.o):/home/acme_unencrypted/git/linux-2.6-tip/tools/perf/util/wrapper.c:67:
       first defined here
       collect2: ld returned 1 exit status
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259071517-3242-4-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      727dad10
    • A
      perf tools: Introduce zalloc() for the common calloc(1, N) case · 36479484
      Arnaldo Carvalho de Melo 提交于
      This way we type less characters and it looks more like the
      kzalloc kernel counterpart.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259071517-3242-3-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      36479484
    • A
      perf symbols: Simplify symbol machinery setup · b32d133a
      Arnaldo Carvalho de Melo 提交于
      And also express its configuration toggles via a struct.
      
      Now all one has to do is to call symbol__init(NULL) if the
      defaults are OK, or pass a struct symbol_conf pointer with the
      desired configuration.
      
      If a tool uses kernel_maps__find_symbol() to look at the kernel
      and modules mappings for a symbol but didn't call symbol__init()
      first, that will generate a one time warning too, alerting the
      subcommand developer that symbol__init() must be called.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259071517-3242-2-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      b32d133a
    • A
      perf top: Always show the DSO column, even if its all the same · 7cc017ed
      Arnaldo Carvalho de Melo 提交于
      Ingo found it confusing, and I agree with that, for 'perf
      report' its OK because it is static, but for a tool refreshing
      it the eventual switch from column to summary at the top may
      seem confusing.
      Suggested-by: NIngo Molnar <mingo@elte.hu>
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259071517-3242-1-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      7cc017ed
    • J
      perf tools: Use common process_event functions for annotate and report · e74328d3
      John Kacur 提交于
      Prevent bit-rot in perf-annotate by using common functions where
      possible. Here we create process_events.[ch] to hold the common
      functions.
      Signed-off-by: NJohn Kacur <jkacur@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: acme@redhat.com
      LKML-Reference: <1259073301-11506-3-git-send-email-jkacur@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      e74328d3
    • J
      perf tools: Add perf.data to .gitignore · c9c7ccaf
      John Kacur 提交于
      Signed-off-by: NJohn Kacur <jkacur@redhat.com>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: acme@redhat.com
      LKML-Reference: <1259073301-11506-2-git-send-email-jkacur@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      c9c7ccaf
    • L
      perf kmem: Add help file · b23d5767
      Li Zefan 提交于
      Add Documentation/perf-kmem.txt
      Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <4B0B6EAF.80802@cn.fujitsu.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      b23d5767
    • L
      perf kmem: Measure kmalloc/kfree CPU ping-pong call-sites · 079d3f65
      Li Zefan 提交于
      Show statistics for allocations and frees on different cpus:
      
      ------------------------------------------------------------------------------------------------------
      Callsite                           | Total_alloc/Per | Total_req/Per   | Hit   | Ping-pong | Frag
      ------------------------------------------------------------------------------------------------------
       perf_event_alloc.clone.0+0         |      7504/682   |      7128/648   |     11 |        0 |  5.011%
       alloc_buffer_head+16               |       288/57    |       280/56    |      5 |        0 |  2.778%
       radix_tree_preload+51              |       296/296   |       288/288   |      1 |        0 |  2.703%
       tracepoint_add_probe+32e           |       157/31    |       154/30    |      5 |        0 |  1.911%
       do_maps_open+0                     |       796/12    |       792/12    |     66 |        0 |  0.503%
       sock_alloc_send_pskb+16e           |     23780/495   |     23744/494   |     48 |       38 |  0.151%
       anon_vma_prepare+9a                |      3744/44    |      3740/44    |     85 |        0 |  0.107%
       d_alloc+21                         |     64948/164   |     64944/164   |    396 |        0 |  0.006%
       proc_alloc_inode+23                |    262292/676   |    262288/676   |    388 |        0 |  0.002%
       create_object+28                   |    459600/200   |    459600/200   |   2298 |       71 |  0.000%
       journal_start+67                   |     14440/40    |     14440/40    |    361 |        0 |  0.000%
       get_empty_filp+df                  |     53504/256   |     53504/256   |    209 |        0 |  0.000%
       getname+2a                         |    823296/4096  |    823296/4096  |    201 |        0 |  0.000%
       seq_read+2b0                       |    544768/4096  |    544768/4096  |    133 |        0 |  0.000%
       seq_open+6d                        |     17024/128   |     17024/128   |    133 |        0 |  0.000%
       mmap_region+2e6                    |     11704/88    |     11704/88    |    133 |        0 |  0.000%
       single_open+0                      |      1072/16    |      1072/16    |     67 |        0 |  0.000%
       __alloc_skb+2e                     |     12544/256   |     12544/256   |     49 |       38 |  0.000%
       __sigqueue_alloc+4a                |      1296/144   |      1296/144   |      9 |        8 |  0.000%
       tracepoint_add_probe+6f            |        80/16    |        80/16    |      5 |        0 |  0.000%
      ------------------------------------------------------------------------------------------------------
      ...
      Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <4B0B6E9F.6020309@cn.fujitsu.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      079d3f65
    • L
      perf kmem: Collect cross node allocation statistics · 7d0d3945
      Li Zefan 提交于
      Show cross node memory allocations:
      
       # ./perf kmem
      
       SUMMARY
       =======
       ...
       Cross node allocations: 0/3633
      Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <4B0B6E87.10906@cn.fujitsu.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      7d0d3945
    • L
      perf kmem: Default to sort by fragmentation · 29b3e152
      Li Zefan 提交于
      Make the output sort by fragmentation by default.
      
      Also make the usage of "--sort" option consistent with other
      perf tools. That is, we support multi keys: "--sort
      key1[,key2]...".
      
       # ./perf kmem --stat caller
       ------------------------------------------------------------------------------
       Callsite                    |Total_alloc/Per | Total_req/Per | Hit  | Frag
       ------------------------------------------------------------------------------
       __netdev_alloc_skb+23       |    5048/1682   |    4564/1521  |     3|   9.588%
       perf_event_alloc.clone.0+0  |    7504/682    |    7128/648   |    11|   5.011%
       tracepoint_add_probe+32e    |     157/31     |     154/30    |     5|   1.911%
       alloc_buffer_head+16        |     456/57     |     448/56    |     8|   1.754%
       radix_tree_preload+51       |     584/292    |     576/288   |     2|   1.370%
       ...
      
      TODO:
      - Extract duplicate code in builtin-kmem.c and builtin-sched.c
        into util/sort.c.
      Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <4B0B6E72.7010200@cn.fujitsu.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      29b3e152
    • L
      perf kmem: Add new option to show raw ip · 7707b6b6
      Li Zefan 提交于
      Add option "--raw-ip" to show raw ip instead of symbols:
      
       # ./perf kmem --stat caller --raw-ip
       ------------------------------------------------------------------------------
       Callsite                    |Total_alloc/Per | Total_req/Per | Hit  | Frag
       ------------------------------------------------------------------------------
       0xc05301aa                  |  733184/4096   |  733184/4096  |   179|   0.000%
       0xc0542ba0                  |  483328/4096   |  483328/4096  |   118|   0.000%
       ...
      
      Also show symbols with format sym+offset instead of sym/offset.
      Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <4B0B6E5C.4080900@cn.fujitsu.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      7707b6b6
    • P
      perf tools: Fix compilation on powerpc · ee3d2504
      Paul Mackerras 提交于
      Currently, perf fails to compile on powerpc with this error:
      
           CC util/header.o
       In file included from util/../perf.h:17,
                        from util/header.c:9:
       util/../../../arch/powerpc/include/asm/unistd.h:360:27: error:
       linux/linkage.h: No such file or directory make: ***
       [util/header.o] Error 1
      
      The reason is that we still have a #define __KERNEL__ in effect
      at the point where <asm/unistd.h> gets included, which means we
      get extra stuff that we don't need or want.
      
      This fixes the problem by undefining __KERNEL__ once we have
      included the file for which we need __KERNEL__ defined.
      Signed-off-by: NPaul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
      Cc: Peter Zijlstra <peterz@infradead.org>
      LKML-Reference: <19211.24287.453183.78836@cargo.ozlabs.ibm.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      ee3d2504
    • A
      perf kmem: Resolve symbols · 1b145ae5
      Arnaldo Carvalho de Melo 提交于
      E.g.:
      
        [root@doppio linux-2.6-tip]# perf kmem record sleep 3s
        [ perf record: Woken up 2 times to write data ]
        [ perf record: Captured and wrote 0.804 MB perf.data (~35105 samples) ]
      
        [root@doppio linux-2.6-tip]# perf kmem --stat caller | head -10
        ------------------------------------------------------------------------------
        Callsite                    |Total_alloc/Per | Total_req/Per | Hit  | Frag
        ------------------------------------------------------------------------------
        getname/40                  | 1519616/4096   | 1519616/4096  |   371|   0.000%
        seq_read/a2                 |  987136/4096   |  987136/4096  |   241|   0.000%
        __netdev_alloc_skb/43       |  260368/1049   |  259968/1048  |   248|   0.154%
        __alloc_skb/5a              |   77312/256    |   77312/256   |   302|   0.000%
        proc_alloc_inode/33         |   76480/632    |   76472/632   |   121|   0.010%
        get_empty_filp/8d           |   70272/192    |   70272/192   |   366|   0.000%
        split_vma/8e                |   42064/176    |   42064/176   |   239|   0.000%
        [root@doppio linux-2.6-tip]#
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Acked-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      Cc: Li Zefan <lizf@cn.fujitsu.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      LKML-Reference: <1259005869-13487-2-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      1b145ae5
    • A
      perf tools: Move graph_line and graph_dotted_line from top · 2890284b
      Arnaldo Carvalho de Melo 提交于
      So that they can be used in other tools.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259005869-13487-1-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      2890284b
    • A
      perf symbols: Look for vmlinux in more places · cc612d81
      Arnaldo Carvalho de Melo 提交于
      Now that we can check the buildid to see if it really matches,
      this can be done safely:
      
        vmlinux
        /boot/vmlinux
        /boot/vmlinux-<uts.release>
        /lib/modules/<uts.release>/build/vmlinux
        /usr/lib/debug/lib/modules/%s/vmlinux
      
      More can be added - if you know about distros that put the
      vmlinux somewhere else please let us know.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1259001550-8194-1-git-send-email-acme@infradead.org>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      cc612d81
    • F
      perf tools: Add support for breakpoint events in perf tools · 1b290d67
      Frederic Weisbecker 提交于
      Add the breakpoint events support with this new sysnopsis:
      
        mem:addr[:access]
      
      Where addr is a raw addr value in the kernel and access can be
      either [r][w][x]
      
      Example to profile tasklist_lock:
      
      	$ grep tasklist_lock /proc/kallsyms
      	ffffffff8189c000 D tasklist_lock
      
      	$ perf record -e mem:0xffffffff8189c000:rw -a -f -c 1
      	$ perf report
      
      	# Samples: 62
      	#
      	# Overhead          Command  Shared Object  Symbol
      	# ........  ...............  .............  ......
      	#
      	    29.03%          swapper  [kernel]       [k] _raw_read_trylock
      	    29.03%          swapper  [kernel]       [k] _raw_read_unlock
      	    19.35%             init  [kernel]       [k] _raw_read_trylock
      	    19.35%             init  [kernel]       [k] _raw_read_unlock
      	     1.61%         events/0  [kernel]       [k] _raw_read_trylock
      	     1.61%         events/0  [kernel]       [k] _raw_read_unlock
      
      Coming soon:
      
       - Support for symbols in the event definition.
      
       - Default period to 1 for breakpoint events because these are
         not high frequency events. The same thing is needed for trace
         events.
      Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Prasad <prasad@linux.vnet.ibm.com>
      LKML-Reference: <1258987355-8751-4-git-send-email-fweisbec@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Prasad <prasad@linux.vnet.ibm.com>
      1b290d67
  4. 23 11月, 2009 4 次提交
  5. 22 11月, 2009 6 次提交
    • M
      perf tools: Suggest static libraries as well · b197c7ef
      Michael S. Tsirkin 提交于
      On error, suggest installing static libraries
      along with shared libraries.
      Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <20091122131311.GA24318@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      b197c7ef
    • M
      perf tools: Add V=2 option to help debug config issues · 7baed9af
      Michael S. Tsirkin 提交于
      Make standard error show up on console when V=2 is set.
      Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <20091122112726.GC13644@redhat.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      7baed9af
    • P
      perf symbols: Fix ELF header errors during "perf kmem record" · e57cfcda
      Pekka Enberg 提交于
      The write_event() function in builtin-record.c writes out all
      mmap()'d DSOs including non-ELF files like GNOME resource files
      and such.
      
      Therefore, check for ELF_K_ELF in filename__read_build_id()
      before attempting to read the ELF header with gelf_getehdr().
      
      Fixes the following error messages when running "perf kmem
      record":
      
        penberg@penberg-laptop:~/src/linux/tools/perf$ perf kmem record
        ^C[ perf record: Woken up 2 times to write data ]
        [ perf record: Captured and wrote 0.753 MB perf.data (~32885 samples) ]
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
        filename__read_build_id: cannot get elf header.
      Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Li Zefan <lizf@cn.fujitsu.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      LKML-Reference: <1258885784-11709-1-git-send-email-penberg@cs.helsinki.fi>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      e57cfcda
    • P
      perf kmem: Add --sort hit and --sort frag · f3ced7cd
      Pekka Enberg 提交于
      This patch adds support for "--sort hit" and "--sort frag" to
      the "perf kmem" tool. The former was already mentioned in the
      help text and the latter is useful for finding call-sites that
      exhibit worst case behavior for SLAB allocators.
      Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>
      Cc: Li Zefan <lizf@cn.fujitsu.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
      Cc: linux-mm@kvack.org <linux-mm@kvack.org>
      LKML-Reference: <1258883880-7149-1-git-send-email-penberg@cs.helsinki.fi>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      f3ced7cd
    • H
      perf bench: Make the mem/memcpy tests more user-friendly · 12eac0bf
      Hitoshi Mitake 提交于
      mem-memcpy.c uses perf event system calls to obtain CPU clocks.
      And it suddenly dies with BUG_ON() when it running on Linux
      doesn't support perf event.
      
      Also fail at calloc() can occur easily when too large
      length is passed. Fail of calloc() causes sudden death
      with assert().
      
      These behaviours are not friendly. So I fixed the treating of
      errors.
      Signed-off-by: NHitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Frederic Weisbecker <fweisbec@gmail.com>
      LKML-Reference: <1258688237-3797-1-git-send-email-mitake@dcl.info.waseda.ac.jp>
      [ v2: improved a few small details ]
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      12eac0bf
    • A
      perf trace: Read_tracing_data should die() another day · e2561368
      Arnaldo Carvalho de Melo 提交于
      It better propagate errors, also if we do a simple:
      
      [root@doppio linux-2.6-tip]# perf record -R -a -f sleep 3s ;
      perf trace [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 0.182 MB perf.data (~7972 samples) ]
      Fatal: not an trace data file
      [root@doppio linux-2.6-tip]#
      
      That is what is expected, right? I.e. as we didn't specify any
      tracepoint event via -e, it should gracefully bail out and not
      SEGFAULT.
      Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      Cc: Steven Rostedt <rostedt@goodmis.org>
      Cc: Frédéric Weisbecker <fweisbec@gmail.com>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Paul Mackerras <paulus@samba.org>
      LKML-Reference: <1258821086-11521-3-git-send-email-acme@infradead.org>
      [ Fixed the error messages some more ]
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      e2561368