linux/tools/perf/builtin-report.c

377 lines
10 KiB
C
Raw Normal View History

/*
* builtin-report.c
*
* Builtin report command: Analyze the perf.data input file,
* look up and read DSOs and symbol information and display
* a histogram of results, along various sorting keys.
*/
#include "builtin.h"
#include "util/util.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/string.h"
#include "util/callchain.h"
#include "util/strlist.h"
#include "util/values.h"
#include "perf.h"
#include "util/debug.h"
#include "util/header.h"
#include "util/session.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
static char const *input_name = "perf.data";
static int force;
static int show_threads;
static struct perf_read_values show_threads_values;
static char default_pretty_printing_style[] = "normal";
static char *pretty_printing_style = default_pretty_printing_style;
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 char callchain_default_opt[] = "fractal,0.5";
static int perf_session__add_hist_entry(struct perf_session *self,
struct addr_location *al,
struct ip_callchain *chain, u64 count)
{
struct symbol **syms = NULL, *parent = NULL;
bool hit;
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && chain)
syms = perf_session__resolve_callchain(self, al->thread,
chain, &parent);
he = __perf_session__add_hist_entry(self, al, parent, count, &hit);
if (he == NULL)
return -ENOMEM;
if (hit)
he->count += count;
if (symbol_conf.use_callchain) {
if (!hit)
callchain_init(&he->callchain);
append_chain(&he->callchain, chain, syms);
free(syms);
}
return 0;
}
static int validate_chain(struct ip_callchain *chain, event_t *event)
{
unsigned int chain_size;
chain_size = event->header.size;
chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
if (chain->nr*sizeof(u64) > chain_size)
return -1;
return 0;
}
static int process_sample_event(event_t *event, struct perf_session *session)
{
struct sample_data data = { .period = 1, };
perf tools: Consolidate symbol resolving across all tools 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: Arnaldo 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: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
struct addr_location al;
event__parse_sample(event, session->sample_type, &data);
dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
event->header.misc,
data.pid, data.tid,
(void *)(long)data.ip,
(long long)data.period);
if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
unsigned int i;
dump_printf("... chain: nr:%Lu\n", data.callchain->nr);
if (validate_chain(data.callchain, event) < 0) {
pr_debug("call-chain problem with event, "
"skipping it.\n");
return 0;
}
if (dump_trace) {
for (i = 0; i < data.callchain->nr; i++)
dump_printf("..... %2d: %016Lx\n",
i, data.callchain->ips[i]);
}
}
if (event__preprocess_sample(event, session, &al, NULL) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
if (al.filtered)
return 0;
if (perf_session__add_hist_entry(session, &al, data.callchain, data.period)) {
pr_debug("problem incrementing symbol count, skipping event\n");
return -1;
}
session->events_stats.total += data.period;
return 0;
}
static int process_read_event(event_t *event, struct perf_session *session __used)
{
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
struct perf_event_attr *attr;
attr = perf_header__find_attr(event->read.id, &session->header);
if (show_threads) {
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
const char *name = attr ? __event_name(attr->type, attr->config)
: "unknown";
perf_read_values_add_value(&show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
name,
event->read.value);
}
dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid,
attr ? __event_name(attr->type, attr->config) : "FAIL",
event->read.value);
return 0;
}
static int perf_session__setup_sample_type(struct perf_session *self)
{
if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
fprintf(stderr, "selected --sort parent, but no"
" callchain data. Did you call"
" perf record without -g?\n");
return -EINVAL;
}
if (symbol_conf.use_callchain) {
fprintf(stderr, "selected -g but no callchain data."
" Did you call perf record without"
" -g?\n");
return -1;
}
} else if (callchain_param.mode != CHAIN_NONE && !symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
if (register_callchain_param(&callchain_param) < 0) {
fprintf(stderr, "Can't register callchain"
" params\n");
return -EINVAL;
}
}
return 0;
}
static struct perf_event_ops event_ops = {
.process_sample_event = process_sample_event,
.process_mmap_event = event__process_mmap,
.process_comm_event = event__process_comm,
.process_exit_event = event__process_task,
.process_fork_event = event__process_task,
.process_lost_event = event__process_lost,
.process_read_event = process_read_event,
};
static int __cmd_report(void)
{
int ret = -EINVAL;
struct perf_session *session;
session = perf_session__new(input_name, O_RDONLY, force);
if (session == NULL)
return -ENOMEM;
if (show_threads)
perf_read_values_init(&show_threads_values);
ret = perf_session__setup_sample_type(session);
if (ret)
goto out_delete;
ret = perf_session__process_events(session, &event_ops);
if (ret)
goto out_delete;
if (dump_trace) {
event__print_totals();
goto out_delete;
}
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
dsos__fprintf(stdout);
perf_session__collapse_resort(session);
perf_session__output_resort(session, session->events_stats.total);
fprintf(stdout, "# Samples: %Ld\n#\n", session->events_stats.total);
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
perf_session__fprintf_hists(session, NULL, false, stdout);
if (sort_order == default_sort_order &&
parent_pattern == default_parent_pattern)
fprintf(stdout, "#\n# (For a higher level overview, try: perf report --sort comm,dso)\n#\n");
if (show_threads) {
bool raw_printing_style = !strcmp(pretty_printing_style, "raw");
perf_read_values_display(stdout, &show_threads_values,
raw_printing_style);
perf_read_values_destroy(&show_threads_values);
}
out_delete:
perf_session__delete(session);
return ret;
}
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
static int
parse_callchain_opt(const struct option *opt __used, const char *arg,
int unset __used)
{
2009-07-02 18:14:33 +00:00
char *tok;
char *endptr;
symbol_conf.use_callchain = true;
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 (!arg)
return 0;
2009-07-02 18:14:33 +00:00
tok = strtok((char *)arg, ",");
if (!tok)
return -1;
/* get the output mode */
if (!strncmp(tok, "graph", strlen(arg)))
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
callchain_param.mode = CHAIN_GRAPH_ABS;
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
2009-07-02 18:14:33 +00:00
else if (!strncmp(tok, "flat", strlen(arg)))
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
callchain_param.mode = CHAIN_FLAT;
else if (!strncmp(tok, "fractal", strlen(arg)))
callchain_param.mode = CHAIN_GRAPH_REL;
else if (!strncmp(tok, "none", strlen(arg))) {
callchain_param.mode = CHAIN_NONE;
symbol_conf.use_callchain = true;
return 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
else
return -1;
2009-07-02 18:14:33 +00:00
/* get the min percentage */
tok = strtok(NULL, ",");
if (!tok)
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
goto setup;
2009-07-02 18:14:33 +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
callchain_param.min_percent = strtod(tok, &endptr);
2009-07-02 18:14:33 +00:00
if (tok == endptr)
return -1;
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
setup:
if (register_callchain_param(&callchain_param) < 0) {
fprintf(stderr, "Can't register callchain params\n");
return -1;
}
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
return 0;
}
static const char * const report_usage[] = {
"perf report [<options>] <command>",
NULL
};
static const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
OPT_BOOLEAN('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
OPT_BOOLEAN('T', "threads", &show_threads,
"Show per-thread event counters"),
OPT_STRING(0, "pretty", &pretty_printing_style, "key",
"pretty printing style key: normal raw"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
"Don't shorten the pathnames taking into account the cwd"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
"regex filter to identify parent, see: '--sort parent'"),
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
2009-07-02 18:14:33 +00:00
"Display callchains using output_type and min percent threshold. "
"Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic 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: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"width[,width...]",
"don't try to adjust column width, use these fixed values"),
OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic 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: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
OPT_END()
};
int cmd_report(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, report_usage, 0);
setup_pager();
if (symbol__init() < 0)
return -1;
setup_sorting(report_usage, options);
if (parent_pattern != default_parent_pattern) {
sort_dimension__add("parent");
sort_parent.elide = 1;
} else
symbol_conf.exclude_other = false;
/*
* Any (unrecognized) arguments left?
*/
if (argc)
usage_with_options(report_usage, options);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
return __cmd_report();
}