linux/tools/perf/util/block-info.h

87 lines
2.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERF_BLOCK_H
#define __PERF_BLOCK_H
#include <linux/types.h>
#include <linux/refcount.h>
#include "hist.h"
#include "symbol.h"
#include "sort.h"
perf report: Sort by sampled cycles percent per block for stdio 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 hottest blocks. This patch implements a new option "--total-cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is the percent: percent = block sampled cycles aggregation / total sampled cycles Note that, this patch only supports "--stdio" mode. For example, # perf record -b ./div # perf report --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] Committer testing: This should provide material for hours of endless joy, both from looking for suspicious things in the implementation of this patch, such as the top one: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] As well from things that look legit: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] :-) Very short system wide taken branches session: # perf record -h -b Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -b, --branch-any sample any taken branches # # perf record -b ^C[ perf record: Woken up 595 times to write data ] [ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ] # # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY # # perf report --total-cycles --stdio # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 6M of event 'cycles' # Event count (approx.): 6299936 # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ...................................................................... .................... # 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] 1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so 0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux] 0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux] 0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux] 0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux] 0.30% 260.8K 0.07% 564 [clear_page_64.S:47 -> clear_page_64.S:50] [kernel.vmlinux] 0.28% 215.3K 0.05% 369 [traps.c:623 -> traps.c:628] [kernel.vmlinux] 0.23% 178.1K 0.04% 278 [entry_64.S:271 -> entry_64.S:275] [kernel.vmlinux] 0.20% 152.6K 0.09% 706 [paravirt.c:177 -> paravirt.c:179] [kernel.vmlinux] 0.20% 155.8K 0.05% 373 [entry_64.S:153 -> entry_64.S:175] [kernel.vmlinux] 0.18% 136.6K 0.03% 222 [msr.h:105 -> msr.h:166] [kernel.vmlinux] 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] 0.16% 118.3K 0.01% 44 [entry_64.S:632 -> entry_64.S:657] [kernel.vmlinux] 0.14% 104.5K 0.00% 28 [rwsem.c:1541 -> rwsem.c:1544] [kernel.vmlinux] 0.13% 99.2K 0.01% 53 [spinlock.c:150 -> spinlock.c:152] [kernel.vmlinux] 0.13% 95.5K 0.00% 35 [swap.c:456 -> swap.c:471] [kernel.vmlinux] 0.12% 96.2K 0.05% 407 [copy_user_64.S:175 -> copy_user_64.S:209] [kernel.vmlinux] 0.11% 85.9K 0.00% 31 [swap.c:400 -> page-flags.h:188] [kernel.vmlinux] 0.10% 73.0K 0.01% 52 [paravirt.h:763 -> list.h:131] [kernel.vmlinux] 0.07% 56.2K 0.03% 214 [filemap.c:1524 -> filemap.c:1557] [kernel.vmlinux] 0.07% 54.2K 0.02% 145 [memory.c:1032 -> memory.c:1049] [kernel.vmlinux] 0.07% 50.3K 0.00% 39 [mmzone.c:49 -> mmzone.c:69] [kernel.vmlinux] 0.06% 48.3K 0.01% 40 [paravirt.h:768 -> page_alloc.c:3304] [kernel.vmlinux] 0.06% 46.7K 0.02% 155 [memory.c:1032 -> memory.c:1056] [kernel.vmlinux] 0.06% 46.9K 0.01% 103 [swap.c:867 -> swap.c:902] [kernel.vmlinux] 0.06% 47.8K 0.00% 34 [entry_64.S:1201 -> entry_64.S:1202] [kernel.vmlinux] ----------------------------------------------------------- v7: --- Use use_browser in report__browse_block_hists for supporting stdio and potential tui mode. v6: --- Create report__browse_block_hists in block-info.c (codes are moved from builtin-report.c). It's called from perf_evlist__tty_browse_hists. v5: --- 1. Move all block functions to block-info.c 2. Move the code of setting ms in block hist_entry to other patch. v4: --- 1. Use new option '--total-cycles' to replace '-s total_cycles' in v3. 2. Move block info collection out of block info printing. v3: --- 1. Use common function block_info__process_sym to process the blocks per symbol. 2. Remove the nasty hack for skipping calculation of column length 3. Some minor cleanup Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20191107074719.26139-6-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-07 10:47:17 +03:00
#include "ui/ui.h"
struct block_info {
struct symbol *sym;
u64 start;
u64 end;
u64 cycles;
u64 cycles_aggr;
s64 cycles_spark[NUM_SPARKS];
u64 total_cycles;
int num;
int num_aggr;
refcount_t refcnt;
};
struct block_fmt {
struct perf_hpp_fmt fmt;
int idx;
int width;
const char *header;
u64 total_cycles;
u64 block_cycles;
};
enum {
PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
PERF_HPP_REPORT__BLOCK_RANGE,
PERF_HPP_REPORT__BLOCK_DSO,
PERF_HPP_REPORT__BLOCK_MAX_INDEX
};
struct block_report {
struct block_hist hist;
u64 cycles;
struct block_fmt fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX];
int nr_fmts;
};
struct block_hist;
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 hist_entry *left, struct hist_entry *right);
int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right);
int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
u64 *block_cycles_aggr, u64 total_cycles);
struct block_report *block_info__create_report(struct evlist *evlist,
u64 total_cycles,
int *block_hpps, int nr_hpps,
int *nr_reps);
void block_info__free_report(struct block_report *reps, int nr_reps);
perf report: Sort by sampled cycles percent per block for stdio 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 hottest blocks. This patch implements a new option "--total-cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is the percent: percent = block sampled cycles aggregation / total sampled cycles Note that, this patch only supports "--stdio" mode. For example, # perf record -b ./div # perf report --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] Committer testing: This should provide material for hours of endless joy, both from looking for suspicious things in the implementation of this patch, such as the top one: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] As well from things that look legit: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] :-) Very short system wide taken branches session: # perf record -h -b Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -b, --branch-any sample any taken branches # # perf record -b ^C[ perf record: Woken up 595 times to write data ] [ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ] # # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY # # perf report --total-cycles --stdio # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 6M of event 'cycles' # Event count (approx.): 6299936 # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ...................................................................... .................... # 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] 1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so 0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux] 0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux] 0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux] 0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux] 0.30% 260.8K 0.07% 564 [clear_page_64.S:47 -> clear_page_64.S:50] [kernel.vmlinux] 0.28% 215.3K 0.05% 369 [traps.c:623 -> traps.c:628] [kernel.vmlinux] 0.23% 178.1K 0.04% 278 [entry_64.S:271 -> entry_64.S:275] [kernel.vmlinux] 0.20% 152.6K 0.09% 706 [paravirt.c:177 -> paravirt.c:179] [kernel.vmlinux] 0.20% 155.8K 0.05% 373 [entry_64.S:153 -> entry_64.S:175] [kernel.vmlinux] 0.18% 136.6K 0.03% 222 [msr.h:105 -> msr.h:166] [kernel.vmlinux] 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] 0.16% 118.3K 0.01% 44 [entry_64.S:632 -> entry_64.S:657] [kernel.vmlinux] 0.14% 104.5K 0.00% 28 [rwsem.c:1541 -> rwsem.c:1544] [kernel.vmlinux] 0.13% 99.2K 0.01% 53 [spinlock.c:150 -> spinlock.c:152] [kernel.vmlinux] 0.13% 95.5K 0.00% 35 [swap.c:456 -> swap.c:471] [kernel.vmlinux] 0.12% 96.2K 0.05% 407 [copy_user_64.S:175 -> copy_user_64.S:209] [kernel.vmlinux] 0.11% 85.9K 0.00% 31 [swap.c:400 -> page-flags.h:188] [kernel.vmlinux] 0.10% 73.0K 0.01% 52 [paravirt.h:763 -> list.h:131] [kernel.vmlinux] 0.07% 56.2K 0.03% 214 [filemap.c:1524 -> filemap.c:1557] [kernel.vmlinux] 0.07% 54.2K 0.02% 145 [memory.c:1032 -> memory.c:1049] [kernel.vmlinux] 0.07% 50.3K 0.00% 39 [mmzone.c:49 -> mmzone.c:69] [kernel.vmlinux] 0.06% 48.3K 0.01% 40 [paravirt.h:768 -> page_alloc.c:3304] [kernel.vmlinux] 0.06% 46.7K 0.02% 155 [memory.c:1032 -> memory.c:1056] [kernel.vmlinux] 0.06% 46.9K 0.01% 103 [swap.c:867 -> swap.c:902] [kernel.vmlinux] 0.06% 47.8K 0.00% 34 [entry_64.S:1201 -> entry_64.S:1202] [kernel.vmlinux] ----------------------------------------------------------- v7: --- Use use_browser in report__browse_block_hists for supporting stdio and potential tui mode. v6: --- Create report__browse_block_hists in block-info.c (codes are moved from builtin-report.c). It's called from perf_evlist__tty_browse_hists. v5: --- 1. Move all block functions to block-info.c 2. Move the code of setting ms in block hist_entry to other patch. v4: --- 1. Use new option '--total-cycles' to replace '-s total_cycles' in v3. 2. Move block info collection out of block info printing. v3: --- 1. Use common function block_info__process_sym to process the blocks per symbol. 2. Remove the nasty hack for skipping calculation of column length 3. Some minor cleanup Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20191107074719.26139-6-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-07 10:47:17 +03:00
int report__browse_block_hists(struct block_hist *bh, float min_percent,
struct evsel *evsel, struct perf_env *env,
struct annotation_options *annotation_opts);
perf report: Sort by sampled cycles percent per block for stdio 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 hottest blocks. This patch implements a new option "--total-cycles" which sorts all blocks by 'Sampled Cycles%'. The 'Sampled Cycles%' is the percent: percent = block sampled cycles aggregation / total sampled cycles Note that, this patch only supports "--stdio" mode. For example, # perf record -b ./div # perf report --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] Committer testing: This should provide material for hours of endless joy, both from looking for suspicious things in the implementation of this patch, such as the top one: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] As well from things that look legit: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] :-) Very short system wide taken branches session: # perf record -h -b Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -b, --branch-any sample any taken branches # # perf record -b ^C[ perf record: Woken up 595 times to write data ] [ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ] # # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY # # perf report --total-cycles --stdio # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 6M of event 'cycles' # Event count (approx.): 6299936 # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ...................................................................... .................... # 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] 1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so 0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux] 0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux] 0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux] 0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux] 0.30% 260.8K 0.07% 564 [clear_page_64.S:47 -> clear_page_64.S:50] [kernel.vmlinux] 0.28% 215.3K 0.05% 369 [traps.c:623 -> traps.c:628] [kernel.vmlinux] 0.23% 178.1K 0.04% 278 [entry_64.S:271 -> entry_64.S:275] [kernel.vmlinux] 0.20% 152.6K 0.09% 706 [paravirt.c:177 -> paravirt.c:179] [kernel.vmlinux] 0.20% 155.8K 0.05% 373 [entry_64.S:153 -> entry_64.S:175] [kernel.vmlinux] 0.18% 136.6K 0.03% 222 [msr.h:105 -> msr.h:166] [kernel.vmlinux] 0.16% 123.0K 0.60% 4.7K [nospec-branch.h:265 -> nospec-branch.h:278] [kernel.vmlinux] 0.16% 118.3K 0.01% 44 [entry_64.S:632 -> entry_64.S:657] [kernel.vmlinux] 0.14% 104.5K 0.00% 28 [rwsem.c:1541 -> rwsem.c:1544] [kernel.vmlinux] 0.13% 99.2K 0.01% 53 [spinlock.c:150 -> spinlock.c:152] [kernel.vmlinux] 0.13% 95.5K 0.00% 35 [swap.c:456 -> swap.c:471] [kernel.vmlinux] 0.12% 96.2K 0.05% 407 [copy_user_64.S:175 -> copy_user_64.S:209] [kernel.vmlinux] 0.11% 85.9K 0.00% 31 [swap.c:400 -> page-flags.h:188] [kernel.vmlinux] 0.10% 73.0K 0.01% 52 [paravirt.h:763 -> list.h:131] [kernel.vmlinux] 0.07% 56.2K 0.03% 214 [filemap.c:1524 -> filemap.c:1557] [kernel.vmlinux] 0.07% 54.2K 0.02% 145 [memory.c:1032 -> memory.c:1049] [kernel.vmlinux] 0.07% 50.3K 0.00% 39 [mmzone.c:49 -> mmzone.c:69] [kernel.vmlinux] 0.06% 48.3K 0.01% 40 [paravirt.h:768 -> page_alloc.c:3304] [kernel.vmlinux] 0.06% 46.7K 0.02% 155 [memory.c:1032 -> memory.c:1056] [kernel.vmlinux] 0.06% 46.9K 0.01% 103 [swap.c:867 -> swap.c:902] [kernel.vmlinux] 0.06% 47.8K 0.00% 34 [entry_64.S:1201 -> entry_64.S:1202] [kernel.vmlinux] ----------------------------------------------------------- v7: --- Use use_browser in report__browse_block_hists for supporting stdio and potential tui mode. v6: --- Create report__browse_block_hists in block-info.c (codes are moved from builtin-report.c). It's called from perf_evlist__tty_browse_hists. v5: --- 1. Move all block functions to block-info.c 2. Move the code of setting ms in block hist_entry to other patch. v4: --- 1. Use new option '--total-cycles' to replace '-s total_cycles' in v3. 2. Move block info collection out of block info printing. v3: --- 1. Use common function block_info__process_sym to process the blocks per symbol. 2. Remove the nasty hack for skipping calculation of column length 3. Some minor cleanup Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20191107074719.26139-6-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-07 10:47:17 +03:00
perf report: Support --percent-limit for --total-cycles We 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 --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.so Committer testing: From second exapmple onwards slightly edited for brevity: # perf report --total-cycles --percent-limit 2 --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6M of event 'cycles' # Event count (approx.): 6299936 # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ...................................................................... .................... # 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] # # (Tip: Create an archive with symtabs to analyse on other machine: perf archive) # # perf report --total-cycles --percent-limit 1 --stdio # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] 1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so # # perf report --total-cycles --percent-limit 0.7 --stdio # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object 2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux] 1.75% 1.3M 8.34% 65.5K [memset-vec-unaligned-erms.S:147 -> memset-vec-unaligned-erms.S:151] libc-2.29.so 0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux] # ------------------------------------------- It only shows the entries which 'Sampled Cycles%' > 1%. v7: --- No functional change. Only fix the conflict issue because previous patches are changed. v6: --- No functional change. Only fix the conflict issue because previous patches are changed. v5: --- No functional change. Only fix the conflict issue because previous patches are changed. v4: --- No functional change. Only fix the build issue because previous patches are changed. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20191107074719.26139-7-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-07 10:47:18 +03:00
float block_info__total_cycles_percent(struct hist_entry *he);
#endif /* __PERF_BLOCK_H */