perf ftrace latency linear buckets
Arnaldo Carvalho de Melo
maintainercover perf ftrace latency linear buckets
From: Arnaldo Carvalho de Melo <[email protected]>
Hi,
Gabriele has been using 'perf ftrace latency' in some
investigations at work and wanted to have an alternative way of populating the buckets, so we came up with this series, please take a look at the examples provided in the changesets.
Thanks,
- Arnaldo
Arnaldo Carvalho de Melo (3):
perf ftrace latency: Pass ftrace pointer to histogram routines to pass more args perf ftrace latency: Introduce --bucket-range to ask for linear bucketing perf ftrace latency: Introduce --min-latency to narrow down into a latency range
Gabriele Monaco (1):
perf ftrace latency: Add --max-latency option
tools/perf/Documentation/perf-ftrace.txt | 11 ++ tools/perf/builtin-ftrace.c | 131 ++++++++++++++++---- tools/perf/util/bpf_ftrace.c | 3 + tools/perf/util/bpf_skel/func_latency.bpf.c | 26 +++- tools/perf/util/ftrace.h | 3 + 5 files changed, 150 insertions(+), 24 deletions(-)
Signature · 1 line
2.47.0
Arnaldo Carvalho de Melo
maintainerPATCH 1/4 perf ftrace latency: Pass ftrace pointer to histogram routines to pass more args
From: Arnaldo Carvalho de Melo <[email protected]>
The ftrace->use_nsec arg is being passed to both make_historgram() and display_histogram(), since another ftrace field will be passed to those functions in a followup patch, make them look like other functions in this codebase that receive the 'struct perf_ftrace' pointer.
No change in logic.
--- tools/perf/builtin-ftrace.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-)
tools/perf/builtin-ftrace.c +8 -7
@@ -726,8 +726,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)return (done && !workload_exec_errno) ?0 :-1 ; } -static void make_histogram (int buckets[],char *buf,size_t len,char *linebuf, -bool use_nsec) +static void make_histogram (struct perf_ftrace *ftrace,int buckets[], +char *buf,size_t len,char *linebuf) {char *p, *q;char *unit;
@@ -774,7 +774,7 @@ static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf,if (!unit ||strncmp (unit," us" ,3 )) goto next; -if (use_nsec) +if (ftrace->use_nsec) num *=1000 ; i =log2 (num);
@@ -794,8 +794,9 @@ static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf,strcat (linebuf, p); } -static void display_histogram (int buckets[],bool use_nsec) +static void display_histogram (struct perf_ftrace *ftrace,int buckets[]) { +bool use_nsec = ftrace->use_nsec;int i;int total =0 ;int bar_total =46 ;/* to fit in 80 column */
@@ -951,7 +952,7 @@ static int __cmd_latency(struct perf_ftrace *ftrace)if (n <0 )break ; -make_histogram (buckets, buf, n, line, ftrace->use_nsec); +make_histogram (ftrace, buckets, buf, n, line); } }
@@ -968,12 +969,12 @@ static int __cmd_latency(struct perf_ftrace *ftrace)int n =read (trace_fd, buf,sizeof (buf) -1 );if (n <=0 )break ; -make_histogram (buckets, buf, n, line, ftrace->use_nsec); +make_histogram (ftrace, buckets, buf, n, line); }read_func_latency (ftrace, buckets); -display_histogram (buckets, ftrace->use_nsec); +display_histogram (ftrace, buckets); out:close (trace_fd);
Signature · 1 line
2.47.0
Arnaldo Carvalho de Melo
maintainerPATCH 2/4 perf ftrace latency: Introduce --bucket-range to ask for linear bucketing
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
In addition to showing it exponentially, using log2() to figure out the histogram index, allow for showing it linearly:
The preexisting more, the default:
# perf ftrace latency --use-nsec --use-bpf \
-T switch_mm_irqs_off -a sleep 2
# DURATION | COUNT | GRAPH |
0 - 1 ns | 0 | |
1 - 2 ns | 0 | |
2 - 4 ns | 0 | |
4 - 8 ns | 0 | |
8 - 16 ns | 0 | |
16 - 32 ns | 0 | |
32 - 64 ns | 0 | |
64 - 128 ns | 238 | # |
128 - 256 ns | 1704 | ########## |
256 - 512 ns | 672 | ### |
512 - 1024 ns | 4458 | ########################## |
1 - 2 us | 677 | #### |
2 - 4 us | 5 | |
4 - 8 us | 0 | |
8 - 16 us | 0 | |
16 - 32 us | 0 | |
32 - 64 us | 0 | |
64 - 128 us | 0 | |
128 - 256 us | 0 | |
256 - 512 us | 0 | |
512 - 1024 us | 0 | |
1 - ... ms | 0 | |
#The new histogram mode:
# perf ftrace latency --bucket-range=150 --use-nsec --use-bpf \
-T switch_mm_irqs_off -a sleep 2
# DURATION | COUNT | GRAPH |
0 - 1 ns | 0 | |
1 - 151 ns | 265 | # |
151 - 301 ns | 1797 | ########### |
301 - 451 ns | 258 | # |
451 - 601 ns | 289 | # |
601 - 751 ns | 2049 | ############# |
751 - 901 ns | 967 | ###### |
901 - 1051 ns | 513 | ### |
1.05 - 1.20 us | 114 | |
1.20 - 1.35 us | 559 | ### |
1.35 - 1.50 us | 189 | # |
1.50 - 1.65 us | 137 | |
1.65 - 1.80 us | 32 | |
1.80 - 1.95 us | 2 | |
1.95 - 2.10 us | 0 | |
2.10 - 2.25 us | 1 | |
2.25 - 2.40 us | 1 | |
2.40 - 2.55 us | 0 | |
2.55 - 2.70 us | 0 | |
2.70 - 2.85 us | 0 | |
2.85 - 3.00 us | 1 | |
3.00 - ... us | 4 | |
#--- tools/perf/Documentation/perf-ftrace.txt | 3 + tools/perf/builtin-ftrace.c | 66 +++++++++++++++++---- tools/perf/util/bpf_ftrace.c | 2 + tools/perf/util/bpf_skel/func_latency.bpf.c | 14 +++++ tools/perf/util/ftrace.h | 1 + 5 files changed, 73 insertions(+), 13 deletions(-)
tools/perf/Documentation/perf-ftrace.txt +3 -0
@@ -148,6 +148,9 @@ OPTIONS for 'perf ftrace latency' --use-nsec:: Use nano-second instead of micro-second as a base unit of the histogram. +--bucket-range=:: + Bucket range in ms or ns (according to -n/--use-nsec), default is log2() mode. + OPTIONS for 'perf ftrace profile' ---------------------------------
tools/perf/builtin-ftrace.c +53 -13
96 lines not on this page · raw message
tools/perf/util/bpf_ftrace.c +2 -0
@@ -36,6 +36,8 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)return -1 ; } + skel->rodata->bucket_range = ftrace->bucket_range; +/* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { ncpus =perf_cpu_map__nr (ftrace->evlist->core.user_requested_cpus);
tools/perf/util/bpf_skel/func_latency.bpf.c +14 -0
@@ -41,6 +41,7 @@ int enabled = 0;const volatile int has_cpu =0 ;const volatile int has_task =0 ;const volatile int use_nsec =0 ; +const volatile unsigned int bucket_range; SEC("kprobe/func")int BPF_PROG (func_begin )
@@ -100,12 +101,25 @@ int BPF_PROG(func_end)if (delta <0 )return 0 ; +if (bucket_range !=0 ) { + delta /= cmp_base; +// Less than 1 unit (ms or ns), or, in the future, +// than the min latency desired. + key =0 ; +if (delta >0 ) {// 1st entry: [ 1 unit .. bucket_range units ) + key = delta / bucket_range +1 ; +if (key >=NUM_BUCKET ) + key =NUM_BUCKET -1 ; + } + goto do_lookup; + }// calculate index using delta for (key =0 ; key < (NUM_BUCKET -1 ); key++) {if (delta < (cmp_base << key))break ; } +do_lookup: hist =bpf_map_lookup_elem (&latency, &key);if (!hist)return 0 ;
tools/perf/util/ftrace.h +1 -0
@@ -20,6 +20,7 @@ struct perf_ftrace {unsigned long percpu_buffer_size;bool inherit;bool use_nsec; +unsigned int bucket_range;int graph_depth;int func_stack_trace;int func_irq_info;
Signature · 1 line
2.47.0
Arnaldo Carvalho de Melo
maintainerPATCH 3/4 perf ftrace latency: Introduce --min-latency to narrow down into a latency range
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
Things below and over will be in the first and last, outlier, buckets.
Without it:
# perf ftrace latency --use-nsec --use-bpf \
--bucket-range=200 \
-T switch_mm_irqs_off -a sleep 2
# DURATION | COUNT | GRAPH |
0 - 200 ns | 0 | |
200 - 400 ns | 44 | |
400 - 600 ns | 291 | # |
600 - 800 ns | 506 | ## |
800 - 1000 ns | 148 | |
1.00 - 1.20 us | 581 | ## |
1.20 - 1.40 us | 2199 | ########## |
1.40 - 1.60 us | 1048 | #### |
1.60 - 1.80 us | 1448 | ###### |
1.80 - 2.00 us | 1091 | ##### |
2.00 - 2.20 us | 517 | ## |
2.20 - 2.40 us | 318 | # |
2.40 - 2.60 us | 370 | # |
2.60 - 2.80 us | 271 | # |
2.80 - 3.00 us | 150 | |
3.00 - 3.20 us | 85 | |
3.20 - 3.40 us | 48 | |
3.40 - 3.60 us | 40 | |
3.60 - 3.80 us | 22 | |
3.80 - 4.00 us | 13 | |
4.00 - 4.20 us | 14 | |
4.20 - ... us | 626 | ## |
#
# perf ftrace latency --use-nsec --use-bpf \
--bucket-range=20 --min-latency=1200 \
-T switch_mm_irqs_off -a sleep 2
# DURATION | COUNT | GRAPH |
0 - 1200 ns | 1243 | ##### |
1.20 - 1.22 us | 141 | |
1.22 - 1.24 us | 202 | |
1.24 - 1.26 us | 209 | |
1.26 - 1.28 us | 219 | |
1.28 - 1.30 us | 208 | |
1.30 - 1.32 us | 245 | # |
1.32 - 1.34 us | 246 | # |
1.34 - 1.36 us | 224 | # |
1.36 - 1.38 us | 219 | |
1.38 - 1.40 us | 206 | |
1.40 - 1.42 us | 190 | |
1.42 - 1.44 us | 190 | |
1.44 - 1.46 us | 146 | |
1.46 - 1.48 us | 140 | |
1.48 - 1.50 us | 125 | |
1.50 - 1.52 us | 115 | |
1.52 - 1.54 us | 102 | |
1.54 - 1.56 us | 87 | |
1.56 - 1.58 us | 90 | |
1.58 - 1.60 us | 85 | |
1.60 - ... us | 5487 | ######################## |
#Now we want focus on the latencies starting at 1.2us, with a finer grained range of 20ns:
This is all on a live system, so statistically interesting, but not narrowing down on the same numbers, so a 'perf ftrace latency record' seems interesting to then use all on the same snapshot of latencies.
A --max-latency counterpart should come next, at first limiting the max-latency to 20 * bucket-size, as we have a fixed buckets array with 20 + 2 entries (+ for the outliers) and thus would need to make it larger for higher latencies.
We also may need a way to ask for not considering the out of range values (first and last buckets) when drawing the buckets bars.
--- tools/perf/Documentation/perf-ftrace.txt | 4 +++ tools/perf/builtin-ftrace.c | 32 +++++++++++++++++---- tools/perf/util/bpf_ftrace.c | 1 + tools/perf/util/bpf_skel/func_latency.bpf.c | 12 ++++++-- tools/perf/util/ftrace.h | 1 + 5 files changed, 43 insertions(+), 7 deletions(-)
tools/perf/Documentation/perf-ftrace.txt +4 -0
@@ -151,6 +151,10 @@ OPTIONS for 'perf ftrace latency' --bucket-range=:: Bucket range in ms or ns (according to -n/--use-nsec), default is log2() mode. +--min-latency=:: + Minimum latency for the start of the first bucket, in ms or ns (according to + -n/--use-nsec). + OPTIONS for 'perf ftrace profile' ---------------------------------
tools/perf/builtin-ftrace.c +27 -5
@@ -729,6 +729,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)static void make_histogram (struct perf_ftrace *ftrace,int buckets[],char *buf,size_t len,char *linebuf) { +int min_latency = ftrace->min_latency;char *p, *q;char *unit;double num;
@@ -777,6 +778,12 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[],if (ftrace->use_nsec) num *=1000 ; + i =0 ; +if (num < min_latency) + goto do_inc; + + num -= min_latency; +if (!ftrace->bucket_range) { i =log2 (num);if (i <0 )
@@ -784,13 +791,13 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], }else {// Less than 1 unit (ms or ns), or, in the future, // than the min latency desired. - i =0 ;if (num >0 )// 1st entry: [ 1 unit .. bucket_range units ] i = num / ftrace->bucket_range +1 ; }if (i >=NUM_BUCKET ) i =NUM_BUCKET -1 ; +do_inc: buckets[i]++; next:
@@ -804,6 +811,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[],static void display_histogram (struct perf_ftrace *ftrace,int buckets[]) { +int min_latency = ftrace->min_latency;bool use_nsec = ftrace->use_nsec;int i;int total =0 ;
@@ -825,7 +833,8 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) bar_len = buckets[0 ] * bar_total / total;printf (" %4d - %4d %s | %10d | %.*s%*s |\n" , -0 ,1 , use_nsec ?"ns" :"us" , buckets[0 ], bar_len, bar, bar_total - bar_len,"" ); +0 , min_latency, use_nsec ?"ns" :"us" , + buckets[0 ], bar_len, bar, bar_total - bar_len,"" );for (i =1 ; i <NUM_BUCKET -1 ; i++) {int start, stop;
@@ -841,8 +850,8 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) unit = use_nsec ?"us" :"ms" ; } }else { - start = (i -1 ) * ftrace->bucket_range +1 ; - stop = i * ftrace->bucket_range +1 ; + start = (i -1 ) * ftrace->bucket_range + min_latency; + stop = i * ftrace->bucket_range + min_latency;if (start >=1000 ) { double dstart = start / 1000.0,
@@ -864,7 +873,7 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[])if (!ftrace->bucket_range) {printf (" %4d - %-4s %s" ,1 ,"..." , use_nsec ?"ms" :"s " ); }else { -int upper_outlier = (NUM_BUCKET -2 ) * ftrace->bucket_range; +int upper_outlier = (NUM_BUCKET -2 ) * ftrace->bucket_range + min_latency;if (upper_outlier >=1000 ) {double dstart = upper_outlier /1000.0 ;
@@ -1598,6 +1607,8 @@ int cmd_ftrace(int argc, const char **argv) "Use nano-second histogram"),OPT_UINTEGER (0 ,"bucket-range" , &ftrace.bucket_range,"Bucket range in ms or ns (-n/--use-nsec), default is log2() mode" ), +OPT_UINTEGER (0 ,"min-latency" , &ftrace.min_latency, +"Minimum latency (1st bucket). Works only with --bucket-range." ), OPT_PARENT(common_options), }; const struct option profile_options[] = {
@@ -1693,6 +1704,17 @@ int cmd_ftrace(int argc, const char **argv) ret = -EINVAL ; goto out_delete_filters; } +if (!ftrace.bucket_range && ftrace.min_latency) { +pr_err ("--min-latency works only with --bucket-range\n" ); +parse_options_usage (ftrace_usage, options, +"min-latency" ,/*short_opt=*/ false); + ret = -EINVAL ; + goto out_delete_filters; + } +if (!ftrace.min_latency) { +/* default min latency should be the bucket range */ + ftrace.min_latency = ftrace.bucket_range; + } cmd_func = __cmd_latency;break ;case PERF_FTRACE_PROFILE :
tools/perf/util/bpf_ftrace.c +1 -0
@@ -37,6 +37,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) } skel->rodata->bucket_range = ftrace->bucket_range; + skel->rodata->min_latency = ftrace->min_latency;/* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) {
tools/perf/util/bpf_skel/func_latency.bpf.c +10 -2
@@ -42,6 +42,7 @@ const volatile int has_cpu = 0;const volatile int has_task =0 ;const volatile int use_nsec =0 ;const volatile unsigned int bucket_range; +const volatile unsigned int min_latency; SEC("kprobe/func")int BPF_PROG (func_begin )
@@ -93,7 +94,7 @@ int BPF_PROG(func_end) start =bpf_map_lookup_elem (&functime, &tid);if (start) {__s64 delta =bpf_ktime_get_ns () - *start; -__u32 key; +__u32 key =0 ;__u64 *hist;bpf_map_delete_elem (&functime, &tid);
@@ -103,9 +104,16 @@ int BPF_PROG(func_end)if (bucket_range !=0 ) { delta /= cmp_base; + +if (min_latency >0 ) { +if (delta > min_latency) + delta -= min_latency; +else + goto do_lookup; + } +// Less than 1 unit (ms or ns), or, in the future, // than the min latency desired. - key =0 ;if (delta >0 ) {// 1st entry: [ 1 unit .. bucket_range units ) key = delta / bucket_range +1 ;if (key >=NUM_BUCKET )
tools/perf/util/ftrace.h +1 -0
@@ -21,6 +21,7 @@ struct perf_ftrace {bool inherit;bool use_nsec;unsigned int bucket_range; +unsigned int min_latency;int graph_depth;int func_stack_trace;int func_irq_info;
Signature · 1 line
2.47.0
Arnaldo Carvalho de Melo
maintainerPATCH 4/4 perf ftrace latency: Add --max-latency option
In reply to Arnaldo Carvalho de MeloFrom: Gabriele Monaco <[email protected]>
This patch adds a max-latency option as discussed, in case the number of buckets is more than 22, we don't observe the setting (for now, let's say).
By default or if 0 is passed, the value is automatically determined based on the number of buckets, range and minimum, so that we fill all available buffers (equivalent to the behaviour before this patch).
We now get something like this:
# perf ftrace latency --bucket-range=20 \
--min-latency 10 \
--max-latency=100 \
-T switch_mm_irqs_off -a sleep 2
# DURATION | COUNT | GRAPH |
0 - 10 us | 1731 | ################ |
10 - 30 us | 1 | |
30 - 50 us | 0 | |
50 - 70 us | 0 | |
70 - 90 us | 0 | |
90 - 100 us | 0 | |
100 - ... us | 0 | |Note the maximum is observed also if it doesn't cover completely a full range (the second to last range is 10us long to let the last start at 100 sharp), this looks to me more sensible and eases the computations, since we don't need to account for the range while filling the buckets.
--- tools/perf/Documentation/perf-ftrace.txt | 4 +++ tools/perf/builtin-ftrace.c | 28 ++++++++++++++++++--- tools/perf/util/bpf_skel/func_latency.bpf.c | 4 ++- tools/perf/util/ftrace.h | 1 + 4 files changed, 33 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-ftrace.txt +4 -0
@@ -155,6 +155,10 @@ OPTIONS for 'perf ftrace latency' Minimum latency for the start of the first bucket, in ms or ns (according to -n/--use-nsec). +--max-latency=:: + Maximum latency for the start of the last bucket, in ms or ns (according to + -n/--use-nsec). The setting is ignored if the value results in more than + 22 buckets. OPTIONS for 'perf ftrace profile' ---------------------------------
tools/perf/builtin-ftrace.c +25 -3
@@ -730,6 +730,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], char *buf, size_t len, char *linebuf) { int min_latency = ftrace->min_latency; +int max_latency = ftrace->max_latency;char *p, *q;char *unit;double num;
@@ -794,7 +795,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[],if (num >0 )// 1st entry: [ 1 unit .. bucket_range units ] i = num / ftrace->bucket_range +1 ; } -if (i >=NUM_BUCKET ) +if (i >=NUM_BUCKET || num >= max_latency - min_latency) i =NUM_BUCKET -1 ; do_inc:
@@ -837,7 +838,7 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) buckets[0], bar_len, bar, bar_total - bar_len, "");for (i =1 ; i <NUM_BUCKET -1 ; i++) { -int start, stop; +unsigned int start, stop;const char *unit = use_nsec ?"ns" :"us" ;if (!ftrace->bucket_range) {
@@ -853,6 +854,11 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) start = (i -1 ) * ftrace->bucket_range + min_latency; stop = i * ftrace->bucket_range + min_latency; +if (start >= ftrace->max_latency) +break ; +if (stop > ftrace->max_latency) + stop = ftrace->max_latency; +if (start >=1000 ) {double dstart = start /1000.0 , dstop = stop /1000.0 ;
@@ -873,7 +879,9 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[])if (!ftrace->bucket_range) {printf (" %4d - %-4s %s" ,1 ,"..." , use_nsec ?"ms" :"s " ); }else { -int upper_outlier = (NUM_BUCKET -2 ) * ftrace->bucket_range + min_latency; +unsigned int upper_outlier = (NUM_BUCKET -2 ) * ftrace->bucket_range + min_latency; +if (upper_outlier > ftrace->max_latency) + upper_outlier = ftrace->max_latency;if (upper_outlier >=1000 ) {double dstart = upper_outlier /1000.0 ;
@@ -1609,6 +1617,8 @@ int cmd_ftrace(int argc, const char **argv) "Bucket range in ms or ns (-n/--use-nsec), default is log2() mode"),OPT_UINTEGER (0 ,"min-latency" , &ftrace.min_latency,"Minimum latency (1st bucket). Works only with --bucket-range." ), +OPT_UINTEGER (0 ,"max-latency" , &ftrace.max_latency, +"Maximum latency (last bucket). Works only with --bucket-range and total buckets less than 22." ), OPT_PARENT(common_options), }; const struct option profile_options[] = {
@@ -1715,6 +1725,18 @@ int cmd_ftrace(int argc, const char **argv)/* default min latency should be the bucket range */ ftrace.min_latency = ftrace.bucket_range; } +if (!ftrace.bucket_range && ftrace.max_latency) { +pr_err ("--max-latency works only with --bucket-range\n" ); +parse_options_usage (ftrace_usage, options, +"max-latency" ,/*short_opt=*/ false); + ret = -EINVAL ; + goto out_delete_filters; + } +if (!ftrace.max_latency) { +/* default max latency should depend on bucket range and num_buckets */ + ftrace.max_latency = (NUM_BUCKET -2 ) * ftrace.bucket_range + + ftrace.min_latency; + } cmd_func = __cmd_latency;break ;case PERF_FTRACE_PROFILE :
tools/perf/util/bpf_skel/func_latency.bpf.c +3 -1
@@ -43,6 +43,7 @@ const volatile int has_task = 0;const volatile int use_nsec =0 ;const volatile unsigned int bucket_range;const volatile unsigned int min_latency; +const volatile unsigned int max_latency; SEC("kprobe/func")int BPF_PROG (func_begin )
@@ -116,7 +117,8 @@ int BPF_PROG(func_end)// than the min latency desired. if (delta >0 ) {// 1st entry: [ 1 unit .. bucket_range units ) key = delta / bucket_range +1 ; -if (key >=NUM_BUCKET ) +if (key >=NUM_BUCKET || + delta >= max_latency - min_latency) key =NUM_BUCKET -1 ; } goto do_lookup;
tools/perf/util/ftrace.h +1 -0
@@ -22,6 +22,7 @@ struct perf_ftrace {bool use_nsec;unsigned int bucket_range;unsigned int min_latency; +unsigned int max_latency;int graph_depth;int func_stack_trace;int func_irq_info;
Signature · 1 line
2.47.0
Quoted 10 lines · Arnaldo Carvalho de Melo
From: Arnaldo Carvalho de Melo <[email protected]>
Hi,
Gabriele has been using 'perf ftrace latency' in some
investigations at work and wanted to have an alternative way of populating the buckets, so we came up with this series, please take a look at the examples provided in the changesets.Thanks,
Applied to perf-tools-next,
- Arnaldo
Quoted 5 lines · Arnaldo Carvalho de Melo
Quoted 4 lines · Arnaldo Carvalho de Melo
From: Arnaldo Carvalho de Melo <[email protected]>
Hi,
Quoted 8 lines
Quoted 6 lines
Gabriele has been using 'perf ftrace latency' in some
investigations at work and wanted to have an alternative way of populating the buckets, so we came up with this series, please take a look at the examples provided in the changesets.Thanks,
Applied to perf-tools-next,
Sorry for the late reply, I forgot about this. I have a couple of issues but they can be handled later.
Thanks,
Namhyung