When callgraph data was included in the perf data file, it may take a
long time to scan all those data and merge them together especially
if the stored callchains are long and the perf data file itself is
large, like a Gbyte or so.
The callchain stack is currently limited to PERF_MAX_STACK_DEPTH (127).
This is a large value. Usually the callgraph data that developers are
most interested in are the first few levels, the rests are usually
not looked at.
This patch adds a new --max-stack option to perf-report to limit the
depth of callchain stack data to look at to reduce the time it takes
for perf-report to finish its processing. It trades the presence of
trailing stack information with faster speed.
The following table shows the elapsed time of doing perf-report on a
perf.data file of size 985,531,828 bytes.
--max_stack Elapsed Time Output data size
----------- ------------ ----------------
not set 88.0s 124,422,651
64 87.5s 116,303,213
32 87.2s 112,023,804
16 86.6s 94,326,380
8 59.9s 33,697,248
4 40.7s 10,116,637
-g none 27.1s 2,555,810
Signed-off-by: Waiman Long <[email protected]>
---
tools/perf/Documentation/perf-report.txt | 8 ++++++++
tools/perf/builtin-report.c | 28 +++++++++++++++++++++++-----
tools/perf/builtin-top.c | 3 ++-
tools/perf/util/machine.c | 14 +++++++++-----
tools/perf/util/machine.h | 3 ++-
tools/perf/util/session.c | 3 ++-
6 files changed, 46 insertions(+), 13 deletions(-)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2b8097e..dc8e956 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -135,6 +135,14 @@ OPTIONS
Default: fractal,0.5,callee,function.
+--max-stack::
+ Set the stack depth limit when parsing the callchain, anything
+ beyond the specified depth will be ignored. This is a trade-off
+ between information loss and faster processing especially for user
+ workloads that can have a very long callchain stack.
+
+ Default: 127
+
-G::
--inverted::
alias for inverted caller based call graph.
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 72eae74..d90d04a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -37,6 +37,12 @@
#include <linux/bitmap.h>
+/*
+ * 2-level stringification macro to enable stringification of macro value
+ * */
+#define __to_string(x) #x
+#define STRINGIFY(x) __to_string(x)
+
struct perf_report {
struct perf_tool tool;
struct perf_session *session;
@@ -47,6 +53,7 @@ struct perf_report {
bool show_threads;
bool inverted_callchain;
bool mem_mode;
+ int max_stack;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
const char *cpu_list;
@@ -88,7 +95,8 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
@@ -179,7 +187,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
@@ -242,18 +251,21 @@ out:
return err;
}
-static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+static int perf_evsel__add_hist_entry(struct perf_tool *tool,
+ struct perf_evsel *evsel,
struct addr_location *al,
struct perf_sample *sample,
struct machine *machine)
{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
struct symbol *parent = NULL;
int err = 0;
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
err = machine__resolve_callchain(machine, evsel, al->thread,
- sample, &parent, al);
+ sample, &parent, al,
+ rep->max_stack);
if (err)
return err;
}
@@ -330,7 +342,8 @@ static int process_sample_event(struct perf_tool *tool,
if (al.map != NULL)
al.map->dso->hit = 1;
- ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine);
+ ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
+ machine);
if (ret < 0)
pr_debug("problem incrementing symbol period, skipping event\n");
}
@@ -757,6 +770,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
.ordered_samples = true,
.ordering_requires_timestamps = true,
},
+ .max_stack = PERF_MAX_STACK_DEPTH,
.pretty_printing_style = "normal",
};
const struct option options[] = {
@@ -797,6 +811,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
"Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
"Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
+ OPT_INTEGER(0, "max-stack", &report.max_stack,
+ "Set the maximum stack depth when parsing the callchain, "
+ "anything beyond the specified depth will be ignored. "
+ "Default: " STRINGIFY(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2122141..2725aca 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -771,7 +771,8 @@ static void perf_event__process_sample(struct perf_tool *tool,
sample->callchain) {
err = machine__resolve_callchain(machine, evsel,
al.thread, sample,
- &parent, &al);
+ &parent, &al,
+ PERF_MAX_STACK_DEPTH);
if (err)
return;
}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6188d28..9617c4a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1267,10 +1267,12 @@ static int machine__resolve_callchain_sample(struct machine *machine,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
u8 cpumode = PERF_RECORD_MISC_USER;
- unsigned int i;
+ int chain_nr = min(max_stack, (int)chain->nr);
+ int i;
int err;
callchain_cursor_reset(&callchain_cursor);
@@ -1280,7 +1282,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
return 0;
}
- for (i = 0; i < chain->nr; i++) {
+ for (i = 0; i < chain_nr; i++) {
u64 ip;
struct addr_location al;
@@ -1352,12 +1354,14 @@ int machine__resolve_callchain(struct machine *machine,
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al)
+ struct addr_location *root_al,
+ int max_stack)
{
int ret;
ret = machine__resolve_callchain_sample(machine, thread,
- sample->callchain, parent, root_al);
+ sample->callchain, parent,
+ root_al, max_stack);
if (ret)
return ret;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 58a6be1..d09cce0 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -91,7 +91,8 @@ int machine__resolve_callchain(struct machine *machine,
struct thread *thread,
struct perf_sample *sample,
struct symbol **parent,
- struct addr_location *root_al);
+ struct addr_location *root_al,
+ int max_stack);
/*
* Default guest kernel is defined by parameter --guestkallsyms
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 568b750..96e5449 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1525,7 +1525,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
if (symbol_conf.use_callchain && sample->callchain) {
if (machine__resolve_callchain(machine, evsel, al.thread,
- sample, NULL, NULL) != 0) {
+ sample, NULL, NULL,
+ PERF_MAX_STACK_DEPTH) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
--
1.7.1
On 10/16/13 1:59 PM, Waiman Long wrote:
> This patch adds a new --max-stack option to perf-report to limit the
> depth of callchain stack data to look at to reduce the time it takes
> for perf-report to finish its processing. It trades the presence of
> trailing stack information with faster speed.
I like the patch. I have a similar option in my perf-sched-timehist
command, and I have a patch somewhere for perf-script.
It would be even better to pass this arg kernel side and limit the stack
depth at data collection time.
---8<---
> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> index 72eae74..d90d04a 100644
> --- a/tools/perf/builtin-report.c
> +++ b/tools/perf/builtin-report.c
> @@ -37,6 +37,12 @@
>
> #include <linux/bitmap.h>
>
> +/*
> + * 2-level stringification macro to enable stringification of macro value
> + * */
> +#define __to_string(x) #x
> +#define STRINGIFY(x) __to_string(x)
These 2 lines should be somewhere else -- like util/util.h
---8<---
> diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
> index 2122141..2725aca 100644
> --- a/tools/perf/builtin-top.c
> +++ b/tools/perf/builtin-top.c
> @@ -771,7 +771,8 @@ static void perf_event__process_sample(struct perf_tool *tool,
> sample->callchain) {
> err = machine__resolve_callchain(machine, evsel,
> al.thread, sample,
> - &parent, &al);
> + &parent, &al,
> + PERF_MAX_STACK_DEPTH);
> if (err)
> return;
> }
Why not add the option to perf-top as well? copy-paste.
David
On 10/16/2013 11:01 PM, David Ahern wrote:
> On 10/16/13 1:59 PM, Waiman Long wrote:
>> This patch adds a new --max-stack option to perf-report to limit the
>> depth of callchain stack data to look at to reduce the time it takes
>> for perf-report to finish its processing. It trades the presence of
>> trailing stack information with faster speed.
>
> I like the patch. I have a similar option in my perf-sched-timehist
> command, and I have a patch somewhere for perf-script.
>
> It would be even better to pass this arg kernel side and limit the
> stack depth at data collection time.
>
That will require option a similar option on the record side. However,
the overhead of collecting more stack ip address isn't as high as that
in the report side.
> ---8<---
>
>> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
>> index 72eae74..d90d04a 100644
>> --- a/tools/perf/builtin-report.c
>> +++ b/tools/perf/builtin-report.c
>> @@ -37,6 +37,12 @@
>>
>> #include <linux/bitmap.h>
>>
>> +/*
>> + * 2-level stringification macro to enable stringification of macro
>> value
>> + * */
>> +#define __to_string(x) #x
>> +#define STRINGIFY(x) __to_string(x)
>
> These 2 lines should be somewhere else -- like util/util.h
I will move that to a common header file.
>
> ---8<---
>
>> diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
>> index 2122141..2725aca 100644
>> --- a/tools/perf/builtin-top.c
>> +++ b/tools/perf/builtin-top.c
>> @@ -771,7 +771,8 @@ static void perf_event__process_sample(struct
>> perf_tool *tool,
>> sample->callchain) {
>> err = machine__resolve_callchain(machine, evsel,
>> al.thread, sample,
>> - &parent, &al);
>> + &parent, &al,
>> + PERF_MAX_STACK_DEPTH);
>> if (err)
>> return;
>> }
>
> Why not add the option to perf-top as well? copy-paste.
I had thought about it, but I decided to wait for feedback before doing
it. I will make that change in the next version.
-Longman