linux/tools/perf/util/callchain.c

399 lines
8.7 KiB
C
Raw Normal View History

/*
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
* Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
*
* Handle the callchains from the stream in an ad-hoc radix tree and then
* sort them in an rbtree.
*
* Using a radix for code path provides a fast retrieval and factorizes
* memory use. Also that lets us use the paths in a hierarchical graph view.
*
*/
#include <stdlib.h>
#include <stdio.h>
#include <stdbool.h>
#include <errno.h>
#include <math.h>
#include "callchain.h"
#define chain_for_each_child(child, parent) \
list_for_each_entry(child, &parent->children, brothers)
static void
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct callchain_node *rnode;
u64 chain_cumul = cumul_hits(chain);
while (*p) {
u64 rnode_cumul;
parent = *p;
rnode = rb_entry(parent, struct callchain_node, rb_node);
rnode_cumul = cumul_hits(rnode);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
switch (mode) {
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
case CHAIN_FLAT:
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
if (rnode->hit < chain->hit)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
break;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
case CHAIN_GRAPH_ABS: /* Falldown */
case CHAIN_GRAPH_REL:
if (rnode_cumul < chain_cumul)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
break;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu 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: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 10:26:57 +00:00
case CHAIN_NONE:
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
default:
break;
}
}
rb_link_node(&chain->rb_node, parent, p);
rb_insert_color(&chain->rb_node, root);
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
static void
__sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
u64 min_hit)
{
struct callchain_node *child;
chain_for_each_child(child, node)
__sort_chain_flat(rb_root, child, min_hit);
if (node->hit && node->hit >= min_hit)
rb_insert_callchain(rb_root, node, CHAIN_FLAT);
}
/*
* Once we get every callchains from the stream, we can now
* sort them by hit
*/
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
static void
sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
u64 min_hit, struct callchain_param *param __used)
{
__sort_chain_flat(rb_root, node, min_hit);
}
static void __sort_chain_graph_abs(struct callchain_node *node,
u64 min_hit)
{
struct callchain_node *child;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
node->rb_root = RB_ROOT;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
chain_for_each_child(child, node) {
__sort_chain_graph_abs(child, min_hit);
if (cumul_hits(child) >= min_hit)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_ABS);
}
}
static void
sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_node *chain_root,
u64 min_hit, struct callchain_param *param __used)
{
__sort_chain_graph_abs(chain_root, min_hit);
rb_root->rb_node = chain_root->rb_root.rb_node;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
static void __sort_chain_graph_rel(struct callchain_node *node,
double min_percent)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
{
struct callchain_node *child;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
u64 min_hit;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
node->rb_root = RB_ROOT;
min_hit = ceil(node->children_hit * min_percent);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
chain_for_each_child(child, node) {
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
__sort_chain_graph_rel(child, min_percent);
if (cumul_hits(child) >= min_hit)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_REL);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
}
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
static void
sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
u64 min_hit __used, struct callchain_param *param)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
{
__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
rb_root->rb_node = chain_root->rb_root.rb_node;
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
int register_callchain_param(struct callchain_param *param)
{
switch (param->mode) {
case CHAIN_GRAPH_ABS:
param->sort = sort_chain_graph_abs;
break;
case CHAIN_GRAPH_REL:
param->sort = sort_chain_graph_rel;
break;
case CHAIN_FLAT:
param->sort = sort_chain_flat;
break;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu 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: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 10:26:57 +00:00
case CHAIN_NONE:
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
default:
return -1;
}
return 0;
}
/*
* Create a child for a parent. If inherit_children, then the new child
* will become the new parent of it's parent children
*/
static struct callchain_node *
create_child(struct callchain_node *parent, bool inherit_children)
{
struct callchain_node *new;
new = malloc(sizeof(*new));
if (!new) {
perror("not enough memory to create child for code path tree");
return NULL;
}
new->parent = parent;
INIT_LIST_HEAD(&new->children);
INIT_LIST_HEAD(&new->val);
if (inherit_children) {
struct callchain_node *next;
list_splice(&parent->children, &new->children);
INIT_LIST_HEAD(&parent->children);
chain_for_each_child(next, new)
next->parent = new;
}
list_add_tail(&new->brothers, &parent->children);
return new;
}
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
struct resolved_ip {
u64 ip;
struct symbol *sym;
};
struct resolved_chain {
u64 nr;
struct resolved_ip ips[0];
};
/*
* Fill the node with callchain values
*/
static void
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
{
unsigned int i;
for (i = start; i < chain->nr; i++) {
struct callchain_list *call;
call = malloc(sizeof(*call));
if (!call) {
perror("not enough memory for the code path tree");
return;
}
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
call->ip = chain->ips[i].ip;
call->sym = chain->ips[i].sym;
list_add_tail(&call->list, &node->val);
}
node->val_nr = chain->nr - start;
if (!node->val_nr)
pr_warning("Warning: empty node in callchain tree\n");
}
static void
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
add_child(struct callchain_node *parent, struct resolved_chain *chain,
int start)
{
struct callchain_node *new;
new = create_child(parent, false);
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
fill_node(new, chain, start);
new->children_hit = 0;
new->hit = 1;
}
/*
* Split the parent in two parts (a new child is created) and
* give a part of its callchain to the created child.
* Then create another child to host the given callchain of new branch
*/
static void
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
struct callchain_list *to_split, int idx_parents, int idx_local)
{
struct callchain_node *new;
struct list_head *old_tail;
unsigned int idx_total = idx_parents + idx_local;
/* split */
new = create_child(parent, true);
/* split the callchain and move a part to the new child */
old_tail = parent->val.prev;
list_del_range(&to_split->list, old_tail);
new->val.next = &to_split->list;
new->val.prev = old_tail;
to_split->list.prev = &new->val;
old_tail->next = &new->val;
/* split the hits */
new->hit = parent->hit;
new->children_hit = parent->children_hit;
parent->children_hit = cumul_hits(new);
new->val_nr = parent->val_nr - idx_local;
parent->val_nr = idx_local;
/* create a new child for the new branch if any */
if (idx_total < chain->nr) {
parent->hit = 0;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
add_child(parent, chain, idx_total);
parent->children_hit++;
} else {
parent->hit = 1;
}
}
static int
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
__append_chain(struct callchain_node *root, struct resolved_chain *chain,
unsigned int start);
static void
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
__append_chain_children(struct callchain_node *root,
struct resolved_chain *chain,
unsigned int start)
{
struct callchain_node *rnode;
/* lookup in childrens */
chain_for_each_child(rnode, root) {
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
unsigned int ret = __append_chain(rnode, chain, start);
if (!ret)
goto inc_children_hit;
}
/* nothing in children, add to the current node */
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
add_child(root, chain, start);
inc_children_hit:
root->children_hit++;
}
static int
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
__append_chain(struct callchain_node *root, struct resolved_chain *chain,
unsigned int start)
{
struct callchain_list *cnode;
unsigned int i = start;
bool found = false;
/*
* Lookup in the current node
* If we have a symbol, then compare the start to match
* anywhere inside a function.
*/
list_for_each_entry(cnode, &root->val, list) {
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
struct symbol *sym;
if (i == chain->nr)
break;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
sym = chain->ips[i].sym;
if (cnode->sym && sym) {
if (cnode->sym->start != sym->start)
break;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
} else if (cnode->ip != chain->ips[i].ip)
break;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
if (!found)
found = true;
i++;
}
/* matches not, relay on the parent */
if (!found)
return -1;
/* we match only a part of the node. Split it and add the new chain */
if (i - start < root->val_nr) {
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
split_add_child(root, chain, cnode, start, i - start);
return 0;
}
/* we match 100% of the path, increment the hit */
if (i - start == root->val_nr && i == chain->nr) {
root->hit++;
return 0;
}
/* We match the node and still have a part remaining */
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
__append_chain_children(root, chain, i);
return 0;
}
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
static void
filter_context(struct ip_callchain *old, struct resolved_chain *new,
struct symbol **syms)
{
int i, j = 0;
for (i = 0; i < (int)old->nr; i++) {
if (old->ips[i] >= PERF_CONTEXT_MAX)
continue;
new->ips[j].ip = old->ips[i];
new->ips[j].sym = syms[i];
j++;
}
new->nr = j;
}
int append_chain(struct callchain_node *root, struct ip_callchain *chain,
struct symbol **syms)
{
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
struct resolved_chain *filtered;
if (!chain->nr)
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 16:09:33 +00:00
return 0;
filtered = malloc(sizeof(*filtered) +
chain->nr * sizeof(struct resolved_ip));
if (!filtered)
return -ENOMEM;
filter_context(chain, filtered, syms);
if (!filtered->nr)
goto end;
__append_chain_children(root, filtered, 0);
end:
free(filtered);
return 0;
}