perf report: Support sorting all blocks by cycles
cover perf report: Support sorting all blocks by cycles
It would be useful to support sorting for all blocks by the sampled cycles percent per block. This is useful to concentrate on the globally busiest/slowest blocks.
This patch series implements a new sort option "total_cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is block sampled cycles aggregation / total sampled cycles
For example,
perf record -b ./div
perf report -s total_cycles --stdio
# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
# ............... .............. ........... .......... ................................................................. ....................
#
26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div
15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so
5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div
4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so
4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div
3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div
3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so
3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so
2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so
2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so
2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so
2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div
1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div
1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so......
This patch series supports both stdio and tui. And also with the supporting of --percent-limit.
Jin Yao (5):
perf util: Create new block.h/block.c for block related functions perf util: Count the total cycles of all samples
perf report: Sort by sampled cycles percent per block for stdio perf report: Support --percent-limit for total_cycles perf report: Sort by sampled cycles percent per block for tui
tools/perf/Documentation/perf-report.txt | 10 + tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-diff.c | 41 +-- tools/perf/builtin-report.c | 445 ++++++++++++++++++++++- tools/perf/builtin-top.c | 3 +- tools/perf/ui/browsers/hists.c | 62 +++- tools/perf/ui/browsers/hists.h | 2 + tools/perf/ui/stdio/hist.c | 29 +- tools/perf/util/Build | 1 + tools/perf/util/block.c | 73 ++++ tools/perf/util/block.h | 39 ++ tools/perf/util/hist.c | 11 +- tools/perf/util/hist.h | 15 +- tools/perf/util/sort.c | 5 + tools/perf/util/sort.h | 1 + tools/perf/util/symbol.c | 22 -- tools/perf/util/symbol.h | 23 -- tools/perf/util/symbol_conf.h | 1 + 18 files changed, 693 insertions(+), 92 deletions(-) create mode 100644 tools/perf/util/block.c create mode 100644 tools/perf/util/block.h
Signature · 1 line
2.17.1
PATCH 1/5 perf util: Create new block.h/block.c for block related functions
We have already implemented some block related functions. Now it's time to do some cleanup, and move the functions and structures to the new block.h/block.c.
--- tools/perf/builtin-diff.c | 38 ++--------------------- tools/perf/util/Build | 1 + tools/perf/util/block.c | 63 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/block.h | 36 ++++++++++++++++++++++ tools/perf/util/hist.c | 1 + tools/perf/util/symbol.c | 22 -------------- tools/perf/util/symbol.h | 23 -------------- 7 files changed, 103 insertions(+), 81 deletions(-) create mode 100644 tools/perf/util/block.c create mode 100644 tools/perf/util/block.h
tools/perf/builtin-diff.c +2 -36
@@ -23,6 +23,7 @@#include "util/time-utils.h" #include "util/annotate.h" #include "util/map.h" +#include "util/block.h" #include <linux/err.h> #include <linux/zalloc.h> #include <subcmd/pager.h>
@@ -530,41 +531,6 @@ static void hists__baseline_only(struct hists *hists) } } -static int64_t block_cmp (struct perf_hpp_fmt *fmt__maybe_unused , -struct hist_entry *left,struct hist_entry *right) -{ -struct block_info *bi_l = left->block_info; -struct block_info *bi_r = right->block_info; -int cmp; - -if (!bi_l->sym || !bi_r->sym) { -if (!bi_l->sym && !bi_r->sym) -return 0 ; -else if (!bi_l->sym) -return -1 ; -else -return 1 ; - } - -if (bi_l->sym == bi_r->sym) { -if (bi_l->start == bi_r->start) { -if (bi_l->end == bi_r->end) -return 0 ; -else -return (int64_t )(bi_r->end - bi_l->end); - }else -return (int64_t )(bi_r->start - bi_l->start); - }else { - cmp =strcmp (bi_l->sym->name, bi_r->sym->name); -return cmp; - } - -if (bi_l->sym->start != bi_r->sym->start) -return (int64_t )(bi_r->sym->start - bi_l->sym->start); - -return (int64_t )(bi_r->sym->end - bi_l->sym->end); -} -static int64_t block_cycles_diff_cmp (struct hist_entry *left,struct hist_entry *right) {
@@ -593,7 +559,7 @@ static void init_block_hist(struct block_hist *bh)INIT_LIST_HEAD (&bh->block_fmt.list);INIT_LIST_HEAD (&bh->block_fmt.sort_list); - bh->block_fmt.cmp = block_cmp; + bh->block_fmt.cmp = block_info__cmp; bh->block_fmt.sort = block_sort;perf_hpp_list__register_sort_field (&bh->block_list, &bh->block_fmt);
tools/perf/util/Build +1 -0
@@ -1,4 +1,5 @@ perf-y += annotate.o +perf-y += block.o perf-y += block-range.o perf-y += build-id.o perf-y += cacheline.o
tools/perf/util/block.c new file +63 -0
63 lines not on this page · raw message
tools/perf/util/block.h new file +36 -0
@@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_BLOCK_H +#define __PERF_BLOCK_H + +#include <linux/types.h> +#include <linux/refcount.h> +#include "util/hist.h" +#include "util/symbol.h" + +struct block_info { +struct symbol *sym; +u64 start; +u64 end; +u64 cycles; +u64 cycles_aggr; +int num; +int num_aggr; +refcount_t refcnt; +}; + +struct block_info *block_info__new (void ); +struct block_info *block_info__get (struct block_info *bi); +void block_info__put (struct block_info *bi); + +static inline void __block_info__zput (struct block_info **bi) +{ +block_info__put (*bi); + *bi =NULL ; +} + +#define block_info__zput (bi) __block_info__zput(&bi) + +int64_t block_info__cmp (struct perf_hpp_fmt *fmt__maybe_unused , +struct hist_entry *left,struct hist_entry *right); + +#endif /* __PERF_BLOCK_H */
tools/perf/util/hist.c +1 -0
@@ -18,6 +18,7 @@#include "srcline.h" #include "symbol.h" #include "thread.h" +#include "block.h" #include "ui/progress.h" #include <errno.h> #include <math.h>
tools/perf/util/symbol.c +0 -22
@@ -2371,25 +2371,3 @@ struct mem_info *mem_info__new(void)refcount_set (&mi->refcnt,1 );return mi; } - -struct block_info *block_info__get (struct block_info *bi) -{ -if (bi) -refcount_inc (&bi->refcnt); -return bi; -} - -void block_info__put (struct block_info *bi) -{ -if (bi &&refcount_dec_and_test (&bi->refcnt)) -free (bi); -} - -struct block_info *block_info__new (void ) -{ -struct block_info *bi =zalloc (sizeof (*bi)); - -if (bi) -refcount_set (&bi->refcnt,1 ); -return bi; -}
tools/perf/util/symbol.h +0 -23
@@ -105,17 +105,6 @@ struct ref_reloc_sym {u64 unrelocated_addr; }; -struct block_info { -struct symbol *sym; -u64 start; -u64 end; -u64 cycles; -u64 cycles_aggr; -int num; -int num_aggr; -refcount_t refcnt; -}; -struct addr_location {struct machine *machine;struct thread *thread;
@@ -289,16 +278,4 @@ static inline void __mem_info__zput(struct mem_info **mi)#define mem_info__zput (mi) __mem_info__zput(&mi) -struct block_info *block_info__new (void ); -struct block_info *block_info__get (struct block_info *bi); -void block_info__put (struct block_info *bi); - -static inline void __block_info__zput (struct block_info **bi) -{ -block_info__put (*bi); - *bi =NULL ; -} - -#define block_info__zput (bi) __block_info__zput(&bi) -#endif /* __PERF_SYMBOL */
Signature · 1 line
2.17.1
PATCH 2/5 perf util: Count the total cycles of all samples
In reply to Jin YaoWe can get the per sample cycles by hist__account_cycles(). It's also useful to know the total cycles of all samples in order to get the cycles coverage for a single program block in further. For example,
coverage = per block sampled cycles / total sampled cycles
This patch creates a new argument 'total_cycles' in hist__account_cycles(), which will be added with the cycles of each sample.
--- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-diff.c | 3 ++- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 3 ++- tools/perf/util/hist.c | 6 +++++- tools/perf/util/hist.h | 3 ++- 6 files changed, 13 insertions(+), 6 deletions(-)
tools/perf/builtin-annotate.c +1 -1
@@ -201,7 +201,7 @@ static int process_branch_callback(struct evsel *evsel,if (a.map !=NULL ) a.map->dso->hit =1 ; -hist__account_cycles (sample->branch_stack, al, sample, false); +hist__account_cycles (sample->branch_stack, al, sample, false,NULL ); ret =hist_entry_iter__add (&iter, &a,PERF_MAX_STACK_DEPTH , ann);return ret;
tools/perf/builtin-diff.c +2 -1
@@ -421,7 +421,8 @@ static int diff__process_sample_event(struct perf_tool *tool, goto out_put; } -hist__account_cycles (sample->branch_stack, &al, sample, false); +hist__account_cycles (sample->branch_stack, &al, sample, false, +NULL ); }/*
tools/perf/builtin-report.c +1 -1
@@ -292,7 +292,7 @@ static int process_sample_event(struct perf_tool *tool,if (ui__has_annotation () || rep->symbol_ipc) {hist__account_cycles (sample->branch_stack, &al, sample, - rep->nonany_branch_mode); + rep->nonany_branch_mode,NULL ); } ret =hist_entry_iter__add (&iter, &al, rep->max_stack, rep);
tools/perf/builtin-top.c +2 -1
@@ -724,7 +724,8 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,perf_top__record_precise_ip (top, he, iter->sample, evsel, al->addr);hist__account_cycles (iter->sample->branch_stack, al, iter->sample, - !(top->record_opts.branch_stack &PERF_SAMPLE_BRANCH_ANY )); + !(top->record_opts.branch_stack &PERF_SAMPLE_BRANCH_ANY ), +NULL );return 0 ; }
tools/perf/util/hist.c +5 -1
@@ -2570,7 +2570,8 @@ int hists__unlink(struct hists *hists) }void hist__account_cycles (struct branch_stack *bs,struct addr_location *al, -struct perf_sample *sample,bool nonany_branch_mode) +struct perf_sample *sample,bool nonany_branch_mode, +u64 *total_cycles) {struct branch_info *bi;
@@ -2597,6 +2598,9 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, nonany_branch_mode ?NULL : prev, bi[i].flags.cycles); prev = &bi[i].to; + +if (total_cycles) + *total_cycles += bi[i].flags.cycles; }free (bi); }
tools/perf/util/hist.h +2 -1
@@ -527,7 +527,8 @@ unsigned int hists__sort_list_width(struct hists *hists);unsigned int hists__overhead_width (struct hists *hists);void hist__account_cycles (struct branch_stack *bs,struct addr_location *al, -struct perf_sample *sample,bool nonany_branch_mode); +struct perf_sample *sample,bool nonany_branch_mode, +u64 *total_cycles);struct option ;int parse_filter_percentage (const struct option *opt,const char *arg,int unset);
Signature · 1 line
2.17.1
PATCH 3/5 perf report: Sort by sampled cycles percent per block for stdio
In reply to Jin YaoIt would be useful to support sorting for all blocks by the sampled cycles percent per block. This is useful to concentrate on the globally busiest/slowest blocks.
This patch implements a new sort option "total_cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is block sampled cycles aggregation / total sampled cycles
Note that, this patch only supports "--stdio" mode.
For example,
perf record -b ./div
perf report -s total_cycles --stdio
# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
# ............... .............. ........... .......... ................................................................. ....................
#
26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div
15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so
5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div
4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so
4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div
3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div
3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so
3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so
2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so
2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so
2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so
2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div
1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div
1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so
0.25% 182.5K 0.02% 1 [random_r.c:388 -> random_r.c:391] libc-2.27.so
0.00% 48 1.07% 48 [x86_pmu_enable+284 -> x86_pmu_enable+298] [kernel.kallsyms]
0.00% 74 1.64% 74 [vm_mmap_pgoff+0 -> vm_mmap_pgoff+92] [kernel.kallsyms]
0.00% 73 1.62% 73 [vm_mmap+0 -> vm_mmap+48] [kernel.kallsyms]
0.00% 63 0.69% 31 [up_write+0 -> up_write+34] [kernel.kallsyms]
0.00% 13 0.29% 13 [setup_arg_pages+396 -> setup_arg_pages+413] [kernel.kallsyms]
0.00% 3 0.07% 3 [setup_arg_pages+418 -> setup_arg_pages+450] [kernel.kallsyms]
0.00% 616 6.84% 308 [security_mmap_file+0 -> security_mmap_file+72] [kernel.kallsyms]
0.00% 23 0.51% 23 [security_mmap_file+77 -> security_mmap_file+87] [kernel.kallsyms]
0.00% 4 0.02% 1 [sched_clock+0 -> sched_clock+4] [kernel.kallsyms]
0.00% 4 0.02% 1 [sched_clock+9 -> sched_clock+12] [kernel.kallsyms]
0.00% 1 0.02% 1 [rcu_nmi_exit+0 -> rcu_nmi_exit+9] [kernel.kallsyms]
0.00% 1 0.02% 1 [rcu_nmi_exit+14 -> rcu_nmi_exit+15] [kernel.kallsyms]
0.00% 5 0.11% 5 [rcu_irq_exit+0 -> rcu_irq_exit+79] [kernel.kallsyms]
0.00% 2 0.04% 2 [printk_nmi_exit+0 -> printk_nmi_exit+16] [kernel.kallsyms]
0.00% 3 0.07% 3 [perf_sample_event_took+0 -> perf_sample_event_took+56] [kernel.kallsyms]
0.00% 1 0.02% 1 [perf_sample_event_took+184 -> perf_sample_event_took+185] [kernel.kallsyms]
0.00% 72 1.60% 72 [perf_iterate_ctx+0 -> perf_iterate_ctx+50] [kernel.kallsyms]
0.00% 1 0.02% 1 [perf_event_nmi_handler+50 -> perf_event_nmi_handler+52] [kernel.kallsyms]
0.00% 1 0.02% 1 [perf_event_nmi_handler+57 -> perf_event_nmi_handler+63] [kernel.kallsyms]
0.00% 1 0.02% 1 [perf_event_nmi_handler+68 -> perf_event_nmi_handler+74] [kernel.kallsyms]--- tools/perf/Documentation/perf-report.txt | 10 + tools/perf/builtin-report.c | 423 ++++++++++++++++++++++- tools/perf/ui/stdio/hist.c | 22 ++ tools/perf/util/block.h | 1 + tools/perf/util/hist.c | 4 + tools/perf/util/sort.c | 5 + tools/perf/util/sort.h | 1 + tools/perf/util/symbol_conf.h | 1 + 8 files changed, 463 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-report.txt +10 -0
@@ -124,6 +124,7 @@ OPTIONS - in_tx: branch in TSX transaction - abort: TSX transaction abort. - cycles: Cycles in basic block + - total_cycles: sort all blocks by the 'Sampled Cycles%'. And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'.
@@ -136,6 +137,15 @@ OPTIONS executed, such as a memory access bottleneck. If a function has high overhead and low IPC, it's worth further analyzing it to optimize its performance. + When the total_cycles is specified, it supports sorting for all blocks by the + 'Sampled Cycles%'. This is useful to concentrate on the globally slowest blocks. + In output, there are some new columns: + 'Sampled Cycles%' - block sampled cycles aggregation / total sampled cycles + 'Sampled Cycles' - block sampled cycles aggregation + 'Avg Cycles%' - block average sampled cycles / sum of total block average + sampled cycles + 'Avg Cycles' - block average sampled cycles + If the --mem-mode option is used, the following sort keys are also available (incompatible with --branch-stack): symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
tools/perf/builtin-report.c +419 -4
476 lines not on this page · raw message
tools/perf/ui/stdio/hist.c +22 -0
@@ -558,6 +558,25 @@ static int hist_entry__block_fprintf(struct hist_entry *he,return ret; } +static int hist_entry__individual_block_fprintf (struct hist_entry *he, +char *bf,size_t size, +FILE *fp) +{ +int ret =0 ; + +struct perf_hpp hpp = { + .buf = bf, + .size = size, + .skip = false, + }; + +hist_entry__snprintf (he, &hpp); +if (!hpp.skip) + ret +=fprintf (fp,"%s\n" , bf); + +return ret; +} +static int hist_entry__fprintf (struct hist_entry *he,size_t size,char *bf,size_t bfsz,FILE *fp,bool ignore_callchains)
@@ -580,6 +599,9 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,if (symbol_conf.report_block)return hist_entry__block_fprintf (he, bf, size, fp); +if (symbol_conf.report_individual_block) +return hist_entry__individual_block_fprintf (he, bf, size, fp); +hist_entry__snprintf (he, &hpp); ret =fprintf (fp,"%s\n" , bf);
tools/perf/util/block.h +1 -0
@@ -13,6 +13,7 @@ struct block_info {u64 end;u64 cycles;u64 cycles_aggr; +u64 total_cycles;int num;int num_aggr;refcount_t refcnt;
tools/perf/util/hist.c +4 -0
@@ -756,6 +756,10 @@ struct hist_entry *hists__add_entry_block(struct hists *hists,struct hist_entry entry = { .block_info = block_info, .hists = hists, + .ms = { + .map = al->map, + .sym = al->sym, + }, }, *he =hists__findnew_entry (hists, &entry, al, false);return he;
tools/perf/util/sort.c +5 -0
@@ -492,6 +492,10 @@ struct sort_entry sort_sym_ipc_null = { .se_width_idx = HISTC_SYMBOL_IPC, }; +struct sort_entry sort_block_cycles = { + .se_cmp = sort__sym_cmp, +}; +/* --sort srcfile */ static char no_srcfile[1 ];
@@ -1695,6 +1699,7 @@ static struct sort_dimension bstack_sort_dimensions[] = {DIM (SORT_SRCLINE_FROM ,"srcline_from" , sort_srcline_from),DIM (SORT_SRCLINE_TO ,"srcline_to" , sort_srcline_to),DIM (SORT_SYM_IPC ,"ipc_lbr" , sort_sym_ipc), + DIM(SORT_BLOCK_CYCLES, "total_cycles", sort_block_cycles), };#undef DIM
tools/perf/util/sort.h +1 -0
@@ -235,6 +235,7 @@ enum sort_type {SORT_SRCLINE_FROM ,SORT_SRCLINE_TO ,SORT_SYM_IPC , +SORT_BLOCK_CYCLES ,/* memory mode specific sort keys */ __SORT_MEMORY_MODE,
tools/perf/util/symbol_conf.h +1 -0
@@ -40,6 +40,7 @@ struct symbol_conf { raw_trace, report_hierarchy, report_block, + report_individual_block, inline_name, disable_add2line_warn; const char *vmlinux_name,
Signature · 1 line
2.17.1
PATCH 4/5 perf report: Support --percent-limit for total_cycles
In reply to Jin YaoWe have already supported the 'total_cycles' option in previous patch. It's also useful to show entries only above a threshold percent.
This patch enables '--percent-limit' for not showing entries under that percent.
For example,
perf report -s total_cycles --stdio --percent-limit 1
# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
#
# Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
# ............... .............. ........... .......... ................................................................. ....................
#
26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div
15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so
5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div
4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so
4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div
3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div
3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so
3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so
2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so
2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so
2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so
2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div
1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div
1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.soIt only shows the entries which 'Sampled Cycles%' > 1%.
--- tools/perf/builtin-report.c | 2 +- tools/perf/ui/stdio/hist.c | 7 ++++++- tools/perf/util/block.c | 10 ++++++++++ tools/perf/util/block.h | 2 ++ 4 files changed, 19 insertions(+), 2 deletions(-)
tools/perf/builtin-report.c +1 -1
@@ -867,7 +867,7 @@ static int hists__fprintf_all_blocks(struct hists *hists, struct report *rep)get_block_hists (hists, bh, rep); symbol_conf.report_individual_block = true; -hists__fprintf (&bh->block_hists, true,0 ,0 ,0 , +hists__fprintf (&bh->block_hists, true,0 ,0 , rep->min_percent, stdout, true);hists__delete_entries (&bh->block_hists);return 0 ;
tools/perf/ui/stdio/hist.c +6 -1
@@ -15,6 +15,7 @@#include "../../util/srcline.h" #include "../../util/string2.h" #include "../../util/thread.h" +#include "../../util/block.h" #include <linux/ctype.h> #include <linux/zalloc.h>
@@ -856,7 +857,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,if (h->filtered)continue ; - percent =hist_entry__get_percent_limit (h); +if (symbol_conf.report_individual_block) + percent =block_total_cycles_percent (h); +else + percent =hist_entry__get_percent_limit (h); +if (percent < min_pcnt)continue ;
tools/perf/util/block.c +10 -0
@@ -61,3 +61,13 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,return (int64_t )(bi_r->sym->end - bi_l->sym->end); } + +float block_total_cycles_percent (struct hist_entry *he) +{ +struct block_info *bi = he->block_info; + +if (bi->total_cycles) +return bi->cycles *100.0 / bi->total_cycles; + +return 0.0 ; +}
tools/perf/util/block.h +2 -0
@@ -34,4 +34,6 @@ static inline void __block_info__zput(struct block_info **bi)int64_t block_info__cmp (struct perf_hpp_fmt *fmt__maybe_unused ,struct hist_entry *left,struct hist_entry *right); +float block_total_cycles_percent (struct hist_entry *he); +#endif /* __PERF_BLOCK_H */
Signature · 1 line
2.17.1
PATCH 5/5 perf report: Sort by sampled cycles percent per block for tui
In reply to Jin YaoPrevious patch has implemented a new sort option "total_cycles". But there was only stdio mode supported.
This patch supports the tui mode and support '--percent-limit' as well.
For example,
perf record -b ./div
perf report -s total_cycles --percent-limit 1
# Samples: 2753248 of event 'cycles'
Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object
26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div
15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so
5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div
4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so
4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div
3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div
3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so
3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so
2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so
2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so
2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so
2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so
2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div
1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so
1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div
1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so--- tools/perf/builtin-report.c | 30 +++++++++++++--- tools/perf/ui/browsers/hists.c | 62 +++++++++++++++++++++++++++++++++- tools/perf/ui/browsers/hists.h | 2 ++ tools/perf/util/hist.h | 12 +++++++ 4 files changed, 101 insertions(+), 5 deletions(-)
tools/perf/builtin-report.c +26 -4
@@ -873,6 +873,27 @@ static int hists__fprintf_all_blocks(struct hists *hists, struct report *rep)return 0 ; } +static int perf_evlist__tui_block_hists_browse (struct evlist *evlist, +struct report *rep) +{ +struct block_hist *bh = &rep->block_hist; +struct evsel *pos; +int ret; + +evlist__for_each_entry (evlist, pos) { +struct hists *hists =evsel__hists (pos); + +get_block_hists (hists, bh, rep); + symbol_conf.report_individual_block = true; + ret =block_hists_tui_browse (bh, pos, rep->min_percent); +hists__delete_entries (&bh->block_hists); +if (ret !=0 ) +return ret; + } + +return ret; +} +static int perf_evlist__tty_browse_hists (struct evlist *evlist,struct report *rep,const char *help)
@@ -981,6 +1002,11 @@ static int report__browse_hists(struct report *rep)switch (use_browser) {case 1 : +if (rep->total_cycles) { + ret =perf_evlist__tui_block_hists_browse (evlist, rep); +break ; + } + ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, &session->header.env,
@@ -1775,10 +1801,6 @@ int cmd_report(int argc, const char **argv)if (sort_order &&strstr (sort_order,"total_cycles" ) && (sort__mode ==SORT_MODE__BRANCH )) { report.total_cycles = true; -if (!report.use_stdio) { -pr_err ("Error: -s total_cycles can be only used together with --stdio\n" ); - goto error; - } }if (strcmp (input_name,"-" ) !=0 )
tools/perf/ui/browsers/hists.c +61 -1
77 lines not on this page · raw message
tools/perf/ui/browsers/hists.h +2 -0
@@ -5,6 +5,7 @@#include "ui/browser.h" struct annotation_options ; +struct evsel ;struct hist_browser {struct ui_browser b;
@@ -15,6 +16,7 @@ struct hist_browser {struct pstack *pstack;struct perf_env *env;struct annotation_options *annotation_opts; +struct evsel *block_evsel;int print_seq;bool show_dso;bool show_headers;
tools/perf/util/hist.h +12 -0
@@ -449,6 +449,8 @@ enum rstype { A_SOURCE }; +struct block_hist ; +#ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" void attr_to_script (char *buf,struct perf_event_attr *attr);
@@ -474,6 +476,9 @@ void run_script(char *cmd);int res_sample_browse (struct res_sample *res_samples,int num_res,struct evsel *evsel,enum rstype rstype);void res_sample_init (void ); + +int block_hists_tui_browse (struct block_hist *bh,struct evsel *evsel, +float min_percent);#else static inline int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
@@ -516,6 +521,13 @@ static inline int res_sample_browse(struct res_sample *res_samples __maybe_unusereturn 0 ; } +static inline int block_hists_tui_browse (struct block_hist *bh__maybe_unused , +struct evsel *evsel__maybe_unused , +float min_percent) +{ +return 0 ; +} +static inline void res_sample_init (void ) {}#define K_LEFT -1000
Signature · 1 line
2.17.1
Quoted 46 lines · Jin Yao
It would be useful to support sorting for all blocks by the sampled cycles percent per block. This is useful to concentrate on the globally busiest/slowest blocks.
This patch series implements a new sort option "
total_cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is block sampled cycles aggregation / total sampled cyclesFor example,
perf record -b ./div
perf report -stotal_cycles--stdio# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
## Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ................................................................. .................... # 26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div 15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so 5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div 4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so 4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div 3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div 3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so 3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so 2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so 2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so 2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so 2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div 1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so 1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div 1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so......
This patch series supports both stdio and tui. And also with the supporting of --percent-limit.
Quoted 6 lines
Jin Yao (5):
perf util: Create newblock.h/block.cfor block related functions perf util: Count the total cycles of all samples
perf report: Sort by sampled cycles percent per block for stdio perf report: Support --percent-limit fortotal_cyclesperf report: Sort by sampled cycles percent per block for tui
sry for delay, but I can no longer apply this
could you please rebase?
thanks,
jirka
Quoted 54 lines · Jiri Olsa
Quoted 46 lines · Jin Yao
It would be useful to support sorting for all blocks by the sampled cycles percent per block. This is useful to concentrate on the globally busiest/slowest blocks.
This patch series implements a new sort option "
total_cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is block sampled cycles aggregation / total sampled cyclesFor example,
perf record -b ./div
perf report -stotal_cycles--stdio# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
## Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ................................................................. .................... # 26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div 15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so 5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div 4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so 4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div 3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div 3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so 3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so 2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so 2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so 2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so 2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div 1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so 1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div 1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so......
This patch series supports both stdio and tui. And also with the supporting of --percent-limit.
Quoted 6 lines
Jin Yao (5):
perf util: Create newblock.h/block.cfor block related functions perf util: Count the total cycles of all samples
perf report: Sort by sampled cycles percent per block for stdio perf report: Support --percent-limit fortotal_cyclesperf report: Sort by sampled cycles percent per block for tui
Quoted 3 lines
sry for delay, but I can no longer apply this
could you please rebase?
Sure, I'd like to rebase to latest perf/core branch. I will send v2 soon. :)
Thanks
Jin Yao
Quoted 3 lines
thanks,
jirka
Quoted 54 lines · Jiri Olsa
Quoted 46 lines · Jin Yao
It would be useful to support sorting for all blocks by the sampled cycles percent per block. This is useful to concentrate on the globally busiest/slowest blocks.
This patch series implements a new sort option "
total_cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is block sampled cycles aggregation / total sampled cyclesFor example,
perf record -b ./div
perf report -stotal_cycles--stdio# To display the perf.data header info, please use --header/--header-only options. #
#
# Total Lost Samples: 0
#
# Samples: 2M of event 'cycles'
# Event count (approx.): 2753248
## Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ................................................................. .................... # 26.04% 2.8M 0.40% 18 [div.c:42 -> div.c:39] div 15.17% 1.2M 0.16% 7 [random_r.c:357 -> random_r.c:380] libc-2.27.so 5.11% 402.0K 0.04% 2 [div.c:27 -> div.c:28] div 4.87% 381.6K 0.04% 2 [random.c:288 -> random.c:291] libc-2.27.so 4.53% 381.0K 0.04% 2 [div.c:40 -> div.c:40] div 3.85% 300.9K 0.02% 1 [div.c:22 -> div.c:25] div 3.08% 241.1K 0.02% 1 [rand.c:26 -> rand.c:27] libc-2.27.so 3.06% 240.0K 0.02% 1 [random.c:291 -> random.c:291] libc-2.27.so 2.78% 215.7K 0.02% 1 [random.c:298 -> random.c:298] libc-2.27.so 2.52% 198.3K 0.02% 1 [random.c:293 -> random.c:293] libc-2.27.so 2.36% 184.8K 0.02% 1 [rand.c:28 -> rand.c:28] libc-2.27.so 2.33% 180.5K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.28% 176.7K 0.02% 1 [random.c:295 -> random.c:295] libc-2.27.so 2.20% 168.8K 0.02% 1 [rand@plt+0 -> rand@plt+0] div 1.98% 158.2K 0.02% 1 [random_r.c:388 -> random_r.c:388] libc-2.27.so 1.57% 123.3K 0.02% 1 [div.c:42 -> div.c:44] div 1.44% 116.0K 0.42% 19 [random_r.c:357 -> random_r.c:394] libc-2.27.so......
This patch series supports both stdio and tui. And also with the supporting of --percent-limit.
Quoted 6 lines
Jin Yao (5):
perf util: Create newblock.h/block.cfor block related functions perf util: Count the total cycles of all samples
perf report: Sort by sampled cycles percent per block for stdio perf report: Support --percent-limit fortotal_cyclesperf report: Sort by sampled cycles percent per block for tui
Quoted 6 lines
sry for delay, but I can no longer apply this
could you please rebase?thanks,
jirka
Hi Jiri,
Thanks a lot for reviewing the patch. I just sent out the v2 which had been rebased to perf/core branch.
Thanks
Jin Yao