perf/core improvements and fixes
hi Ingo,
please consider pulling
thanks,
jirka
The following changes since commit 37b6cb475a6d74bc047c53bc323d6eb3113e27a4:
Merge branch 'uprobes/core' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc into perf/core (2014-04-18 09:49:14 +0200)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git tags/perf-core-for-mingo
for you to fetch changes up to a651d9357f936a19ae811a29d031224cdb8c2f1f:
perf callchain: Add generic report parse callchain callback function (2014-04-18 11:56:59 +0200)
----------------------------------------------------------------
perf/core improvements and fixes:
Developer stuff:
. Making some code (cpu node map and report parse callchain callback) global
to be usable by upcomming changes (Don Zickus)
. Fix pmu object compilation error (Jiri Olsa)
----------------------------------------------------------------
Don Zickus (4):
perf tools: Allow ability to map cpus to nodes easily perf tools: Use cpu/possible instead of cpu/kernel_max perf kmem: Utilize the new generic cpunode_map
perf callchain: Add generic report parse callchain callback function
Jiri Olsa (1):
perf tools: Fix pmu object compilation error
tools/perf/builtin-kmem.c | 78 +---------------------- tools/perf/builtin-report.c | 81 +----------------------- tools/perf/util/callchain.c | 82 ++++++++++++++++++++++++ tools/perf/util/callchain.h | 1 + tools/perf/util/cpumap.c | 147 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/cpumap.h | 35 +++++++++++ tools/perf/util/pmu.c | 6 +- 7 files changed, 274 insertions(+), 156 deletions(-)
PATCH 1/5 perf tools: Fix pmu object compilation error
After applying some patches got another shadowing error:
CC util/pmu.outil/pmu.c: In function ‘pmu_alias_terms’:util/pmu.c:287:35: error: declaration of ‘clone’ shadows a global declaration [-Werror=shadow]
Renaming clone to cloned.
--- tools/perf/util/pmu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
tools/perf/util/pmu.c +3 -3
@@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head)static int pmu_alias_terms (struct perf_pmu_alias *alias,struct list_head *terms) { -struct parse_events_term *term, *clone; +struct parse_events_term *term, *cloned;LIST_HEAD (list);int ret;list_for_each_entry (term, &alias->terms, list) { - ret =parse_events_term__clone (&clone, term); + ret =parse_events_term__clone (&cloned, term);if (ret) {parse_events__free_terms (&list);return ret; } -list_add_tail (&clone->list, &list); +list_add_tail (&cloned->list, &list); }list_splice (&list, terms);return 0 ;
Signature · 1 line
1.8.3.1
PATCH 2/5 perf tools: Allow ability to map cpus to nodes easily
In reply to Jiri OlsaFrom: Don Zickus <[email protected]>
This patch figures out the max number of cpus and nodes that are on the system and creates a map of cpu to node. This allows us to provide a cpu and quickly get the node associated with it.
It was mostly copied from builtin-kmem.c and tweaked slightly to use less memory (use possible cpus instead of max). It also calculates the max number of nodes.
V6: use original kernel_max reference
V5: use sysfs_mountpoint and filename__read_str
V4: fix typos, rename get_max_num
V3: simplify function names
--- tools/perf/util/cpumap.c | 147 +++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/cpumap.h | 35 +++++++++++ 2 files changed, 182 insertions(+)
tools/perf/util/cpumap.c +147 -0
@@ -317,3 +317,150 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) {return cpu_map__build_map (cpus, corep, cpu_map__get_core); } + +/* setup simple routines to easily access node numbers given a cpu number */ +static int get_max_num (char *path,int *max) +{ +size_t num; +char *buf; +int err =0 ; + +if (filename__read_str (path, &buf, &num)) +return -1 ; + + buf[num] ='\0' ; + +/* start on the right, to find highest node num */ +while (--num) { +if ((buf[num] ==',' ) || (buf[num] =='-' )) { + num++; +break ; + } + } +if (sscanf (&buf[num],"%d" , max) <1 ) { + err =-1 ; + goto out; + } + +/* convert from 0-based to 1-based */ + (*max)++; + +out: +free (buf); +return err; +} + +/* Determine highest possible cpu in the system for sparse allocation */ +static void set_max_cpu_num (void ) +{ +const char *mnt; +char path[PATH_MAX ]; +int ret =-1 ; + +/* set up default */ + max_cpu_num =4096 ; + + mnt =sysfs__mountpoint (); +if (!mnt) + goto out; + +/* get the highest possible cpu number for a sparse allocation */ +snprintf (path,PATH_MAX ,"%s/devices/system/cpu/kernel_max" , mnt); + + ret =get_max_num (path, &max_cpu_num); + +out: +if (ret) +pr_err ("Failed to read max cpus, using default of %d\n" , + max_cpu_num); +return ; +} + +/* Determine highest possible node in the system for sparse allocation */ +static void set_max_node_num (void ) +{ +const char *mnt; +char path[PATH_MAX ]; +int ret =-1 ; + +/* set up default */ + max_node_num =8 ; + + mnt =sysfs__mountpoint (); +if (!mnt) + goto out; + +/* get the highest possible cpu number for a sparse allocation */ +snprintf (path,PATH_MAX ,"%s/devices/system/node/possible" , mnt); + + ret =get_max_num (path, &max_node_num); + +out: +if (ret) +pr_err ("Failed to read max nodes, using default of %d\n" , + max_node_num); +return ; +} + +static int init_cpunode_map (void ) +{ +int i; + +set_max_cpu_num (); +set_max_node_num (); + + cpunode_map =calloc (max_cpu_num,sizeof (int )); +if (!cpunode_map) { +pr_err ("%s: calloc failed\n" , __func__); +return -1 ; + } + +for (i =0 ; i < max_cpu_num; i++) + cpunode_map[i] =-1 ; + +return 0 ; +} + +int cpu__setup_cpunode_map (void ) +{ +struct dirent *dent1, *dent2; +DIR *dir1, *dir2; +unsigned int cpu, mem; +char buf[PATH_MAX ]; +char path[PATH_MAX ]; +const char *mnt; + +/* initialize globals */ +if (init_cpunode_map ()) +return -1 ; + + mnt =sysfs__mountpoint (); +if (!mnt) +return 0 ; + +snprintf (path,PATH_MAX ,"%s/devices/system/node" , mnt); + dir1 =opendir (path); +if (!dir1) +return 0 ; + +/* walk tree and setup map */ +while ((dent1 =readdir (dir1)) !=NULL ) { +if (dent1->d_type !=DT_DIR || +sscanf (dent1->d_name,"node%u" , &mem) <1 ) +continue ; + +snprintf (buf,PATH_MAX ,"%s/%s" , path, dent1->d_name); + dir2 =opendir (buf); +if (!dir2) +continue ; +while ((dent2 =readdir (dir2)) !=NULL ) { +if (dent2->d_type !=DT_LNK || +sscanf (dent2->d_name,"cpu%u" , &cpu) <1 ) +continue ; + cpunode_map[cpu] = mem; + } +closedir (dir2); + } +closedir (dir1); +return 0 ; +}
tools/perf/util/cpumap.h +35 -0
@@ -4,6 +4,9 @@#include <stdio.h> #include <stdbool.h> +#include "perf.h" +#include "util/debug.h" +struct cpu_map {int nr;int map[];
@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } +int max_cpu_num; +int max_node_num; +int *cpunode_map; + +int cpu__setup_cpunode_map (void ); + +static inline int cpu__max_node (void ) +{ +if (unlikely (!max_node_num)) +pr_debug ("cpu_map not initialized\n" ); + +return max_node_num; +} + +static inline int cpu__max_cpu (void ) +{ +if (unlikely (!max_cpu_num)) +pr_debug ("cpu_map not initialized\n" ); + +return max_cpu_num; +} + +static inline int cpu__get_node (int cpu) +{ +if (unlikely (cpunode_map ==NULL )) { +pr_debug ("cpu_map not initialized\n" ); +return -1 ; + } + +return cpunode_map[cpu]; +} +#endif /* __PERF_CPUMAP_H */
Signature · 1 line
1.8.3.1
PATCH 3/5 perf tools: Use cpu/possible instead of cpu/kernel_max
In reply to Jiri OlsaFrom: Don Zickus <[email protected]>
The system's max configuration is represented by cpu/possible and cpu/kernel_max can be huge (4096 vs. 128), so save space by keeping smaller structures.
--- tools/perf/util/cpumap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/cpumap.c +1 -1
@@ -365,7 +365,7 @@ static void set_max_cpu_num(void) goto out;/* get the highest possible cpu number for a sparse allocation */ -snprintf (path,PATH_MAX ,"%s/devices/system/cpu/kernel_max" , mnt); +snprintf (path,PATH_MAX ,"%s/devices/system/cpu/possible" , mnt); ret =get_max_num (path, &max_cpu_num);
Signature · 1 line
1.8.3.1
PATCH 4/5 perf kmem: Utilize the new generic cpunode_map
In reply to Jiri OlsaFrom: Don Zickus <[email protected]>
Use the previous patch implementation of cpunode_map for builtin-kmem.c Should not be any functional difference.
--- tools/perf/builtin-kmem.c | 78 ++--------------------------------------------- 1 file changed, 3 insertions(+), 75 deletions(-)
tools/perf/builtin-kmem.c +3 -75
@@ -14,6 +14,7 @@#include "util/parse-options.h" #include "util/trace-event.h" #include "util/data.h" +#include "util/cpumap.h" #include "util/debug.h"
@@ -31,9 +32,6 @@ static int caller_lines = -1;static bool raw_ip; -static int *cpunode_map; -static int max_cpu_num; -struct alloc_stat {u64 call_site;u64 ptr;
@@ -55,76 +53,6 @@ static struct rb_root root_caller_sorted;static unsigned long total_requested, total_allocated;static unsigned long nr_allocs, nr_cross_allocs; -#define PATH_SYS_NODE "/sys/devices/system/node" - -static int init_cpunode_map (void ) -{ -FILE *fp; -int i, err =-1 ; - - fp =fopen ("/sys/devices/system/cpu/kernel_max" ,"r" ); -if (!fp) { - max_cpu_num =4096 ; -return 0 ; - } - -if (fscanf (fp,"%d" , &max_cpu_num) <1 ) { -pr_err ("Failed to read 'kernel_max' from sysfs" ); - goto out_close; - } - - max_cpu_num++; - - cpunode_map =calloc (max_cpu_num,sizeof (int )); -if (!cpunode_map) { -pr_err ("%s: calloc failed\n" , __func__); - goto out_close; - } - -for (i =0 ; i < max_cpu_num; i++) - cpunode_map[i] =-1 ; - - err =0 ; -out_close: -fclose (fp); -return err; -} - -static int setup_cpunode_map (void ) -{ -struct dirent *dent1, *dent2; -DIR *dir1, *dir2; -unsigned int cpu, mem; -char buf[PATH_MAX ]; - -if (init_cpunode_map ()) -return -1 ; - - dir1 =opendir (PATH_SYS_NODE ); -if (!dir1) -return 0 ; - -while ((dent1 =readdir (dir1)) !=NULL ) { -if (dent1->d_type !=DT_DIR || -sscanf (dent1->d_name,"node%u" , &mem) <1 ) -continue ; - -snprintf (buf,PATH_MAX ,"%s/%s" ,PATH_SYS_NODE , dent1->d_name); - dir2 =opendir (buf); -if (!dir2) -continue ; -while ((dent2 =readdir (dir2)) !=NULL ) { -if (dent2->d_type !=DT_LNK || -sscanf (dent2->d_name,"cpu%u" , &cpu) <1 ) -continue ; - cpunode_map[cpu] = mem; - } -closedir (dir2); - } -closedir (dir1); -return 0 ; -} -static int insert_alloc_stat (unsigned long call_site,unsigned long ptr,int bytes_req,int bytes_alloc,int cpu) {
@@ -235,7 +163,7 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,int ret =perf_evsel__process_alloc_event (evsel, sample);if (!ret) { -int node1 = cpunode_map[sample->cpu], +int node1 =cpu__get_node (sample->cpu), node2 =perf_evsel__intval (evsel, sample,"node" );if (node1 != node2)
@@ -772,7 +700,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)if (!strncmp (argv[0 ],"rec" ,3 )) {return __cmd_record (argc, argv); }else if (!strcmp (argv[0 ],"stat" )) { -if (setup_cpunode_map ()) +if (cpu__setup_cpunode_map ())return -1 ;if (list_empty (&caller_sort))
Signature · 1 line
1.8.3.1
PATCH 5/5 perf callchain: Add generic report parse callchain callback function
In reply to Jiri OlsaFrom: Don Zickus <[email protected]>
This takes the parse_callchain_opt function and copies it into the callchain.c file. Now the c2c tool can use it too without duplicating.
Update perf-report to use the new routine too.
V3: rename function
V2: remove commented code, combine with perf-report change
--- tools/perf/builtin-report.c | 81 ++------------------------------------------ tools/perf/util/callchain.c | 82 +++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/callchain.h | 1 + 3 files changed, 86 insertions(+), 78 deletions(-)
tools/perf/builtin-report.c +3 -78
@@ -589,11 +589,9 @@ static int __cmd_report(struct report *rep) }static int -parse_callchain_opt (const struct option *opt,const char *arg,int unset) +report_parse_callchain_opt (const struct option *opt,const char *arg,int unset) {struct report *rep = (struct report *)opt->value; -char *tok, *tok2; -char *endptr;/* * --no-call-graph
@@ -603,80 +601,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)return 0 ; } - symbol_conf.use_callchain = true; - -if (!arg) -return 0 ; - - tok =strtok ((char *)arg,"," ); -if (!tok) -return -1 ; - -/* get the output mode */ -if (!strncmp (tok,"graph" ,strlen (arg))) - callchain_param.mode =CHAIN_GRAPH_ABS ; - -else if (!strncmp (tok,"flat" ,strlen (arg))) - 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 = false; - -return 0 ; - } - -else -return -1 ; - -/* get the min percentage */ - tok =strtok (NULL ,"," ); -if (!tok) - goto setup; - - callchain_param.min_percent =strtod (tok, &endptr); -if (tok == endptr) -return -1 ; - -/* get the print limit */ - tok2 =strtok (NULL ,"," ); -if (!tok2) - goto setup; - -if (tok2[0 ] !='c' ) { - callchain_param.print_limit =strtoul (tok2, &endptr,0 ); - tok2 =strtok (NULL ,"," ); -if (!tok2) - goto setup; - } - -/* get the call chain order */ -if (!strncmp (tok2,"caller" ,strlen ("caller" ))) - callchain_param.order =ORDER_CALLER ; -else if (!strncmp (tok2,"callee" ,strlen ("callee" ))) - callchain_param.order =ORDER_CALLEE ; -else -return -1 ; - -/* Get the sort key */ - tok2 =strtok (NULL ,"," ); -if (!tok2) - goto setup; -if (!strncmp (tok2,"function" ,strlen ("function" ))) - callchain_param.key =CCKEY_FUNCTION ; -else if (!strncmp (tok2,"address" ,strlen ("address" ))) - callchain_param.key =CCKEY_ADDRESS ; -else -return -1 ; -setup: -if (callchain_register_param (&callchain_param) <0 ) { -pr_err ("Can't register callchain params\n" ); -return -1 ; - } -return 0 ; +return parse_callchain_report_opt (arg); }int
@@ -788,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Only display entries with parent-match"),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), +"Default: fractal,0.5,callee,function" , &report_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. "
tools/perf/util/callchain.c +82 -0
88 lines not on this page · raw message
tools/perf/util/callchain.h +1 -0
@@ -157,4 +157,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parentint hist_entry__append_callchain (struct hist_entry *he,struct perf_sample *sample);extern const char record_callchain_help[]; +int parse_callchain_report_opt (const char *arg);#endif /* __PERF_CALLCHAIN_H */
Signature · 1 line
1.8.3.1