kernel/tools/perf/util/block-info.c, branch linux-6.2.y

perf report: Fix wrong LBR block sorting

2021-04-07T19:18:49Z

When '--total-cycles' is specified, it supports sorting for all blocks by 'Sampled Cycles%'. This is useful to concentrate on the globally hottest blocks. 'Sampled Cycles%' - block sampled cycles aggregation / total sampled cycles But in current code, it doesn't use the cycles aggregation. Part of 'cycles' counting is possibly dropped for some overlap jumps. But for identifying the hot block, we always need the full cycles. # perf record -b ./triad_loop # perf report --total-cycles --stdio Before: # # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... ............................................................. ................. # 0.81% 793 4.32% 793 [setup-vdso.h:34 -> setup-vdso.h:40] ld-2.27.so 0.49% 480 0.87% 160 [native_write_msr+0 -> native_write_msr+16] [kernel.kallsyms] 0.48% 476 0.52% 95 [native_read_msr+0 -> native_read_msr+29] [kernel.kallsyms] 0.31% 303 1.65% 303 [nmi_restore+0 -> nmi_restore+37] [kernel.kallsyms] 0.26% 255 1.39% 255 [nohz_balance_exit_idle+75 -> nohz_balance_exit_idle+162] [kernel.kallsyms] 0.24% 234 1.28% 234 [end_repeat_nmi+67 -> end_repeat_nmi+83] [kernel.kallsyms] 0.23% 227 1.24% 227 [__irqentry_text_end+96 -> __irqentry_text_end+126] [kernel.kallsyms] 0.20% 194 1.06% 194 [native_set_debugreg+52 -> native_set_debugreg+56] [kernel.kallsyms] 0.11% 106 0.14% 26 [native_sched_clock+0 -> native_sched_clock+98] [kernel.kallsyms] 0.10% 97 0.53% 97 [trigger_load_balance+0 -> trigger_load_balance+67] [kernel.kallsyms] 0.09% 85 0.46% 85 [get-dynamic-info.h:102 -> get-dynamic-info.h:111] ld-2.27.so ... 0.00% 92.7K 0.02% 4 [triad_loop.c:64 -> triad_loop.c:65] triad_loop The hottest block '[triad_loop.c:64 -> triad_loop.c:65]' is not at the top of output. After: # Sampled Cycles% Sampled Cycles Avg Cycles% Avg Cycles [Program Block Range] Shared Object # ............... .............. ........... .......... .............................................................. ................. # 94.35% 92.7K 0.02% 4 [triad_loop.c:64 -> triad_loop.c:65] triad_loop 0.81% 793 4.32% 793 [setup-vdso.h:34 -> setup-vdso.h:40] ld-2.27.so 0.49% 480 0.87% 160 [native_write_msr+0 -> native_write_msr+16] [kernel.kallsyms] 0.48% 476 0.52% 95 [native_read_msr+0 -> native_read_msr+29] [kernel.kallsyms] 0.31% 303 1.65% 303 [nmi_restore+0 -> nmi_restore+37] [kernel.kallsyms] 0.26% 255 1.39% 255 [nohz_balance_exit_idle+75 -> nohz_balance_exit_idle+162] [kernel.kallsyms] 0.24% 234 1.28% 234 [end_repeat_nmi+67 -> end_repeat_nmi+83] [kernel.kallsyms] 0.23% 227 1.24% 227 [__irqentry_text_end+96 -> __irqentry_text_end+126] [kernel.kallsyms] 0.20% 194 1.06% 194 [native_set_debugreg+52 -> native_set_debugreg+56] [kernel.kallsyms] 0.11% 106 0.14% 26 [native_sched_clock+0 -> native_sched_clock+98] [kernel.kallsyms] 0.10% 97 0.53% 97 [trigger_load_balance+0 -> trigger_load_balance+67] [kernel.kallsyms] 0.09% 85 0.46% 85 [get-dynamic-info.h:102 -> get-dynamic-info.h:111] ld-2.27.so 0.08% 82 0.06% 11 [intel_pmu_drain_pebs_nhm+580 -> intel_pmu_drain_pebs_nhm+627] [kernel.kallsyms] 0.08% 77 0.42% 77 [lru_add_drain_cpu+0 -> lru_add_drain_cpu+133] [kernel.kallsyms] 0.08% 74 0.10% 18 [handle_pmi_common+271 -> handle_pmi_common+310] [kernel.kallsyms] 0.08% 74 0.40% 74 [get-dynamic-info.h:131 -> get-dynamic-info.h:157] ld-2.27.so 0.07% 69 0.09% 17 [intel_pmu_drain_pebs_nhm+432 -> intel_pmu_drain_pebs_nhm+468] [kernel.kallsyms] Now the hottest block is reported at the top of output. Fixes: b65a7d372b1a55db ("perf hist: Support block formats with compare/sort/display") Signed-off-by: Jin Yao Reviewed-by: Andi Kleen Cc: Alexander Shishkin Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210407024452.29988-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf block-info: Support color ops to print block percents in color

2020-03-10T00:43:25Z

It would be nice to print the block percents with colors. This patch supports the 'Sampled Cycles%' and 'Avg Cycles%' printed in colors. For example, perf record -b ... perf report --total-cycles or perf report --total-cycles --stdio percent > 5%, colored in red percent > 0.5%, colored in green percent < 0.5%, default color Signed-off-by: Jin Yao Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200202141655.32053-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf block-info: Allow selecting which columns to report and its order

2020-03-10T00:43:25Z

Currently we use a predefined array to set the block info output formats, it's fixed and inflexible. This patch adds two parameters "block_hpps" and "nr_hpps" in block_info__create_report and other static functions, in order to let user decide which columns to report and with specified report ordering. It should be more flexible. Buffers will be allocated to contain the new fmts, of course, we need to release them before perf exits. Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200202141655.32053-4-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf diff: Use __block_info__cmp() to replace block_pair_cmp()

2020-03-10T00:43:25Z

'perf diff' uses block_pair_cmp() to compare two blocks. But block_info__cmp() has the similar functionality and it's a bit more complete. This patch removes block_pair_cmp() and uses __block_info__cmp() instead. __block_info__cmp() is wrapped by block_info__cmp() and it doesn't receives a perf_hpp_fmt parameter. Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200202141655.32053-3-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf block-info: Fix wrong block address comparison in block_info__cmp()

2020-03-10T00:43:25Z

Commit 6041441870ab ("perf block: Cleanup and refactor block info functions") introduces block_info__cmp(), which compares two blocks. But the issues are: 1. It should return the strcmp cmp value only if it's not 0. 2. When symbol names are matched, we need to compare the addresses of blocks further. But it wrongly uses the symbol addresses for comparison. 3. If the syms are both NULL, we can't consider these two blocks are matched. This patch fixes above 3 issues. Fixes: 6041441870ab ("perf block: Cleanup and refactor block info functions") Signed-off-by: Jin Yao Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200202141655.32053-2-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf diff: Fix undefined string comparison spotted by clang's -Wstring-compare

2020-03-04T13:28:08Z

clang warns: util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/map.c:434:15: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if (srcline != SRCLINE_UNKNOWN) ^ ~~~~~~~~~~~~~~~ Reviewer Notes: Looks good to me. Some more context: https://clang.llvm.org/docs/DiagnosticsReference.html#wstring-compare The spec says: J.1 Unspecified behavior The following are unspecified: .. Whether two string literals result in distinct arrays (6.4.5). Signed-off-by: Nick Desaulniers Reviewed-by: Ian Rogers Cc: Alexander Shishkin Cc: Changbin Du Cc: Jin Yao Cc: Jiri Olsa Cc: John Keeping Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/900 Link: http://lore.kernel.org/lkml/20200223193456.25291-1-nick.desaulniers@gmail.com Signed-off-by: Arnaldo Carvalho de Melo

perf report: Jump to symbol source view from total cycles view

2019-11-19T22:37:04Z

This patch supports jumping from tui total cycles view to symbol source view. For example, perf record -b ./div perf report --total-cycles In total cycles view, we can select one entry and press 'a' or press ENTER key to jump to symbol source view. This patch also sets sort_order to NULL in cmd_report() which will use the default branch sort order. The percent value in new annotate view will be consistent with the percent in annotate view switched from perf report (we observed the original percent gap with previous patches). v2: --- Fix the 'make NO_SLANG=1' error. (set __maybe_unused to annotation_opts in block_hists_tui_browse()). Signed-off-by: Jin Yao Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20191118140849.20714-2-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf util: Move block TUI function to ui browsers

2019-11-19T22:33:40Z

It would be nice if we could jump to the assembler/source view (like the normal perf report) from total cycles view. This patch moves the block_hists_tui_browse from block-info.c to ui/browsers/hists.c in order to reuse some browser codes (i.e do_annotate) for implementing new annotation view. v2: --- Fix the 'make NO_SLANG=1' error. (Change 'int block_hists_tui_browse()' to 'static inline int block_hists_tui_browse()') Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20191118140849.20714-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf report: Sort by sampled cycles percent per block for tui

2019-11-07T13:14:48Z

Previous patch has implemented a new option "--total-cycles". But only stdio mode is supported. This patch supports the tui mode and support '--percent-limit'. For example, perf record -b ./div perf report --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 -------------------------------------------------- v7: --- 1. Since we have used use_browser in report__browse_block_hists to support stdio mode, now we also add supporting for tui. 2. Move block tui browser code from ui/browsers/hists.c to block-info.c. v6: --- Create report__tui_browse_block_hists in block-info.c (codes are moved from builtin-report.c). v5: --- Fix a crash issue when running perf report without '--total-cycles'. The issue is because the internal flag is renamed from 'total_cycles' to 'total_cycles_mode' in previous patch but this patch still uses 'total_cycles' to check if the '--total-cycles' option is enabled, which causes the code to be inconsistent. v4: --- Since the block collection is moved out of printing in previous patch, this patch is updated accordingly for tui supporting. v3: --- Minor change since the function name is changed: block_total_cycles_percent -> block_info__total_cycles_percent Signed-off-by: Jin Yao Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20191107074719.26139-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf report: Support --percent-limit for --total-cycles

2019-11-07T13:14:48Z

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 Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20191107074719.26139-7-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo