perf record: ratio-to-prev event term for auto counter reload
v2 cover perf record: ratio-to-prev event term for auto counter reload
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
-- Event sampling period ("period")
-- acr_mask, which determines which events get reloaded
when the sample period is reached.
For example, in the following command:
perf record -e "{cpu_atom/branch-misses,period=200000,\
acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
acr_mask=0x3/u}" -- ./mispredict
The goal is to limit event sampling to cases when the branch miss rate exceeds 20%. If the branch instructions sample period is exceeded first, both events are reloaded. If branch misses exceed their threshold first, only the second counter is reloaded, and a sample is taken.
To simplify this, provide a new “ratio-to-prev” event term that works alongside the period event option or -c option. This would allow users to specify the desired relative rate between events as a ratio, making configuration more intuitive.
With this enhancement, the equivalent command would be:
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
-- ./mispredict
or
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
-- ./mispredict
[1] https://lore.kernel.org/lkml/[email protected]/
Changes in v2 (mostly suggested by Ian Rogers):
-- Add documentation explaining acr_mask bitmask used by ACR -- Move ACR specific implementation to arch/x86/
-- Provide test cases for event parsing and perf record tests
Thomas Falcon (2):
perf record: Add ratio-to-prev term
perf record: add auto counter reload parse and regression tests
tools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++ tools/perf/Documentation/perf-list.txt | 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/tests/parse-events.c | 54 ++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 ++++++++++++++ tools/perf/util/evsel.c | 76 ++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 12 files changed, 307 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/intel-acr.txt
Signature · 1 line
2.50.1
PATCH RESEND v2 1/2 perf record: Add ratio-to-prev term
Provide ratio-to-prev term which allows the user to
set the event sample period of two events corresponding to a desired ratio. If using on an Intel x86 platform with Auto Counter Reload support, also set corresponding event's config2 attribute with a bitmask which counters to reset and which counters to sample if the desired ratio is met or exceeded. On other platforms, only the sample period is affected by the ratio-to-prev term.
--- tools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++ tools/perf/Documentation/perf-list.txt | 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/util/evsel.c | 76 ++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 10 files changed, 213 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/intel-acr.txt
tools/perf/Documentation/intel-acr.txt new file +53 -0
@@ -0,0 +1,53 @@ +Intel Auto Counter Reload Support +--------------------------------- +Support for Intel Auto Counter Reload in perf tools + +Auto counter reload provides a means for software to specify to hardware +that certain counters, if supported, should be automatically reloaded +upon overflow of chosen counters. By taking a sample only if the rate of +one event exceeds some threshold relative to the rate of another event, +this feature enables software to sample based on the relative rate of +two or more events. To enable this, the user must provide a sample period +term and a bitmask ("acr_mask") for each relevant event specifying the +counters in an event group to reload if the event's specified sample +period is exceeded. + +For example, if the user desires to measure a scenario when IPC > 2, +the event group might look like the one below: + + perf record -e {cpu_atom/instructions,period=200000,acr_mask=0x2/, \ + cpu_atom/cycles,period=100000,acr_mask=0x3/} -- true + +In this case, if the "instructions" counter exceeds the sample period of +200000, the second counter, "cycles", will be reset and a sample will be +taken. If "cycles" is exceeded first, both counters in the group will be +reset. In this way, samples will only be taken for cases where IPC > 2. + +The acr_mask term is a hexadecimal value representing a bitmask of the +events in the group to be reset when the period is exceeded. In the +example above, "instructions" is assigned an acr_mask of 0x2, meaning +only the second event in the group is reloaded and a sample is taken +for the first event. "cycles" is assigned an acr_mask of 0x3, meaning +that both event counters will be reset if the sample period is exceeded +first. + +ratio-to-prev Event Term +------------------------ +To simplify this, an event term "ratio-to-prev" is provided which is used +alongside the sample period term n or the -c/--count option. This would +allow users to specify the desired relative rate between events as a +ratio. Note: Both events compared must belong to the same PMU. + +The command above would then become + + perf record -e {cpu_atom/instructions/, \ + cpu_atom/cycles,period=100000,ratio-to-prev=0.5/} -- true + +ratio-to-prev is the ratio of the event using the term relative +to the previous event in the group, which will always be 1, +for a 1:0.5 or 2:1 ratio. + +To sample for IPC < 2 for example, the events need to be reordered: + + perf record -e {cpu_atom/cycles/, \ + cpu_atom/instructions,period=200000,ratio-to-prev=2.0/} -- true
tools/perf/Documentation/perf-list.txt +2 -0
@@ -392,6 +392,8 @@ Support raw format: . '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of a certain kind of events. +include::intel-acr.txt[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1],
tools/perf/arch/x86/util/evsel.c +53 -0
66 lines not on this page · raw message
tools/perf/util/evsel.c +76 -0
106 lines not on this page · raw message
tools/perf/util/evsel.h +1 -0
@@ -342,6 +342,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);void arch_evsel__set_sample_weight (struct evsel *evsel);void arch__post_evsel_config (struct evsel *evsel,struct perf_event_attr *attr);int arch_evsel__open_strerror (struct evsel *evsel,char *msg,size_t size); +void arch_evsel__apply_ratio_to_prev (struct evsel *evsel,struct perf_event_attr *attr);int evsel__set_filter (struct evsel *evsel,const char *filter);int evsel__append_tp_filter (struct evsel *evsel,const char *filter);
tools/perf/util/evsel_config.h +1 -0
@@ -28,6 +28,7 @@ enum evsel_term_type {EVSEL__CONFIG_TERM_AUX_ACTION ,EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE ,EVSEL__CONFIG_TERM_CFG_CHG , + EVSEL__CONFIG_TERM_RATIO_TO_PREV, }; struct evsel_config_term {
tools/perf/util/parse-events.c +22 -0
@@ -834,6 +834,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", [PARSE_EVENTS__TERM_TYPE_CPU] = "cpu", + [PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV] = "ratio-to-prev", };if ((unsigned int )term_type >= __PARSE_EVENTS__TERM_TYPE_NR)return "unknown term" ;
@@ -884,6 +885,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_ercase PARSE_EVENTS__TERM_TYPE_RAW :case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :if (!err)return false;
@@ -1037,6 +1039,21 @@ do { \perf_cpu_map__put (map);break ; } +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV : +CHECK_TYPE_VAL (STR ); +if (strtod (term->val.str,NULL ) <=0 ) { +parse_events_error__handle (err, term->err_val, +strdup ("zero or negative" ), +NULL ); +return -EINVAL ; + } +if (errno ==ERANGE ) { +parse_events_error__handle (err, term->err_val, +strdup ("too big" ), +NULL ); +return -EINVAL ; + } +break ;case PARSE_EVENTS__TERM_TYPE_DRV_CFG :case PARSE_EVENTS__TERM_TYPE_USER :case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :
@@ -1165,6 +1182,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE :case PARSE_EVENTS__TERM_TYPE_CPU : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :if (err) { parse_events_error__handle(err, term->err_term,
@@ -1289,6 +1307,9 @@ do { \ADD_CONFIG_TERM_VAL (AUX_SAMPLE_SIZE , aux_sample_size, term->val.num, term->weak);break ; +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV : +ADD_CONFIG_TERM_STR (RATIO_TO_PREV , term->val.str, term->weak); +break ;case PARSE_EVENTS__TERM_TYPE_USER :case PARSE_EVENTS__TERM_TYPE_CONFIG :case PARSE_EVENTS__TERM_TYPE_CONFIG1 :
@@ -1355,6 +1376,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *headcase PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE :case PARSE_EVENTS__TERM_TYPE_CPU : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :break ; }
tools/perf/util/parse-events.h +2 -1
@@ -83,7 +83,8 @@ enum parse_events__term_type {PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE ,PARSE_EVENTS__TERM_TYPE_HARDWARE ,PARSE_EVENTS__TERM_TYPE_CPU , -#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_CPU + 1) +PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV , +#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV + 1) }; struct parse_events_term {
tools/perf/util/parse-events.l +1 -0
@@ -336,6 +336,7 @@ aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } cpu { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CPU); } +ratio-to-prev { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV); } cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } stalled-cycles-frontend|idle-cycles-frontend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } stalled-cycles-backend|idle-cycles-backend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
tools/perf/util/pmu.c +2 -1
@@ -1541,7 +1541,7 @@ static int pmu_config_term(const struct perf_pmu *pmu,break ;case PARSE_EVENTS__TERM_TYPE_USER :/* Not hardcoded. */ return -EINVAL ; - case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_CPU: + case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV:/* Skip non-config terms. */ break ;default :
@@ -1930,6 +1930,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call"aux-action=(pause|resume|start-paused)" ,"aux-sample-size=number" ,"cpu=number" , + "ratio-to-prev=string", };struct perf_pmu_format *format;int ret;
Signature · 1 line
2.50.1
Re: [RESEND][PATCH v2 1/2] perf record: Add ratio-to-prev term
Quoted 53 lines · Thomas Falcon
Provide ratio-to-prev term which allows the user to
set the event sample period of two events corresponding to a desired ratio. If using on an Intel x86 platform with Auto Counter Reload support, also set corresponding event's config2 attribute with a bitmask which counters to reset and which counters to sample if the desired ratio is met or exceeded. On other platforms, only the sample period is affected by the ratio-to-prev term.Signed-off-by Thomas Falcon <[email protected]>--- tools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++ tools/perf/Documentation/perf-list.txt | 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/util/evsel.c | 76 ++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 10 files changed, 213 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/intel-acr.txttools/perf/Documentation/intel-acr.txt new file +22
-0@@ -0,0 +1,53 @@ +Intel Auto Counter Reload Support +--------------------------------- +Support for Intel Auto Counter Reload in perf tools + +Auto counter reload provides a means for software to specify to hardware +that certain counters, if supported, should be automatically reloaded +upon overflow of chosen counters. By taking a sample only if the rate of +one event exceeds some threshold relative to the rate of another event, +this feature enables software to sample based on the relative rate of +two or more events. To enable this, the user must provide a sample period +term and a bitmask ("acr_mask") for each relevant event specifying the +counters in an event group to reload if the event's specified sample +period is exceeded. + +For example, if the user desires to measure a scenario when IPC > 2, +the event group might look like the one below: + + perf record -e {cpu_atom/instructions,period=200000,acr_mask=0x2/, \ + cpu_atom/cycles,period=100000,acr_mask=0x3/} -- true + +In this case, if the "instructions" counter exceeds the sample period of +200000, the second counter, "cycles", will be reset and a sample will be
tools/perf/Documentation/intel-acr.txt line 32
Quoted 10 lines
tools/perf/Documentation/intel-acr.txt new file +10
-0+taken. If "cycles" is exceeded first, both counters in the group will be +reset. In this way, samples will only be taken for cases where IPC > 2. + +The acr_mask term is a hexadecimal value representing a bitmask of the +events in the group to be reset when the period is exceeded. In the +example above, "instructions" is assigned an acr_mask of 0x2, meaning +only the second event in the group is reloaded and a sample is taken +for the first event. "cycles" is assigned an acr_mask of 0x3, meaning +that both event counters will be reset if the sample period is exceeded +first.
This is great! Thank you for adding it.
Quoted 66 lines
tools/perf/Documentation/intel-acr.txt new file +21
-0+ +ratio-to-prev Event Term +------------------------ +To simplify this, an event term "ratio-to-prev" is provided which is used +alongside the sample period term n or the -c/--count option. This would +allow users to specify the desired relative rate between events as a +ratio. Note: Both events compared must belong to the same PMU. + +The command above would then become + + perf record -e {cpu_atom/instructions/, \ + cpu_atom/cycles,period=100000,ratio-to-prev=0.5/} -- true + +ratio-to-prev is the ratio of the event using the term relative +to the previous event in the group, which will always be 1, +for a 1:0.5 or 2:1 ratio. + +To sample for IPC < 2 for example, the events need to be reordered: + + perf record -e {cpu_atom/cycles/, \ + cpu_atom/instructions,period=200000,ratio-to-prev=2.0/} -- truetools/perf/Documentation/perf-list.txt +2
-0@@ -392,6 +392,8 @@ Support raw format: . '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of a certain kind of events. +include::intel-acr.txt[] + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1],tools/perf/arch/x86/util/evsel.c +16
-0@@ -1,7 +1,9 @@// SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <stdlib.h> +#include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_config.h" #include "util/env.h" #include "util/pmu.h" #include "util/pmus.h" @@ -67,6 +69,57 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) event_name); } +void arch_evsel__apply_ratio_to_prev (struct evsel *evsel, +struct perf_event_attr *attr) +{ +struct perf_event_attr *prev_attr =NULL ; +struct evsel *evsel_prev =NULL ; +const char *name ="acr_mask" ; +int evsel_idx =0 ; +__u64 ev_mask, pr_ev_mask; + +if (!perf_pmu__has_format (evsel->pmu, name)) { +pr_err ("'%s' does not have acr_mask format support\n" , evsel->pmu->name); +return ; + } + if (perf_pmu__format_type(evsel->pmu, name) !=
tools/perf/arch/x86/util/evsel.c int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) · line 95
Quoted 10 lines
tools/perf/arch/x86/util/evsel.c +10
-0+ PERF_PMU_FORMAT_VALUE_CONFIG2) { +pr_err ("'%s' does not have config2 format support\n" , evsel->pmu->name); +return ; + } + + evsel_prev =evsel__prev (evsel); +if (!evsel_prev) { +pr_err ("Previous event does not exist.\n" ); +return ; + }
Nit: you should probably check that the leader of both events is the same, this means the events are in the same group.
Quoted 48 lines
tools/perf/arch/x86/util/evsel.c +27
-0+ + prev_attr = &evsel_prev->core.attr; + +if (prev_attr->config2) { +pr_err ("'%s' has set config2 (acr_mask?) already, configuration not supported\n" , evsel_prev->name); +return ; + } + +/* +* acr_mask (config2) is calculated using the event's index in +* the event group. The first event will use the index of the +* second event as its mask (e.g., 0x2), indicating that the +* second event counter will be reset and a sample taken for +* the first event if its counter overflows. The second event +* will use the mask consisting of the first and second bits +* (e.g., 0x3), meaning both counters will be reset if the +* second event counter overflows. +*/ + + evsel_idx =evsel__group_idx (evsel); + ev_mask =1ull << evsel_idx; + pr_ev_mask =1ull << (evsel_idx -1 ); + + prev_attr->config2 = ev_mask; + attr->config2 = ev_mask | pr_ev_mask; +} +static void ibs_l3miss_warn (void ) { pr_warning(tools/perf/util/evsel.c +10
-0@@ -1091,6 +1091,71 @@ static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param * } } +static void evsel__apply_ratio_to_prev (struct evsel *evsel, +struct perf_event_attr *attr, +struct record_opts *opts, +const char *buf) +{ +struct perf_event_attr *prev_attr =NULL ; +struct evsel *evsel_prev =NULL ; +u64 type = evsel->core.attr.sample_type; +u64 prev_type =0 ; +double rtp;
tools/perf/util/evsel.c static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param * · line 1113
Quoted 10 lines
tools/perf/util/evsel.c +10
-0+ + rtp =strtod (buf,NULL ); +if (rtp <=0 ) { +pr_err ("Invalid ratio-to-prev value %lf\n" , rtp); +return ; + } +if (evsel ==evsel__leader (evsel)) { +pr_err ("Invalid use of ratio-to-prev term without preceding element in group\n" ); +return ; + }
Ah, it is done here.
Quoted 76 lines
tools/perf/util/evsel.c +51
-0+if (!evsel->pmu->is_core) { +pr_err ("Event using ratio-to-prev term must have a core PMU\n" ); +return ; + } + + evsel_prev =evsel__prev (evsel); +if (!evsel_prev) { +pr_err ("Previous event does not exist.\n" ); +return ; + } + +if (evsel_prev->pmu->type != evsel->pmu->type) { +pr_err ("Compared events (\"%s\", \"%s\") must have same PMU\n" , + evsel->name, evsel_prev->name); +return ; + } + + prev_attr = &evsel_prev->core.attr; + prev_type = evsel_prev->core.attr.sample_type; + +if (!(prev_type &PERF_SAMPLE_PERIOD )) { + attr->sample_period = prev_attr->sample_period * rtp; + attr->freq =0 ; +evsel__reset_sample_bit (evsel,PERIOD ); + }else if (!(type &PERF_SAMPLE_PERIOD )) { + prev_attr->sample_period = attr->sample_period / rtp; + prev_attr->freq =0 ; +evsel__reset_sample_bit (evsel_prev,PERIOD ); + }else { +if (opts->user_interval !=ULLONG_MAX ) { + prev_attr->sample_period = opts->user_interval; + attr->sample_period = prev_attr->sample_period * rtp; + prev_attr->freq =0 ; + attr->freq =0 ; +evsel__reset_sample_bit (evsel_prev,PERIOD ); +evsel__reset_sample_bit (evsel,PERIOD ); + }else { +pr_err ("Event period term or count (-c) must be set when using ratio-to-prev term.\n" ); +return ; + } + } + +arch_evsel__apply_ratio_to_prev (evsel, attr); +} +static void evsel__apply_config_terms (struct evsel *evsel,struct record_opts *opts,bool track) {@@ -1104,6 +1169,7 @@ static void evsel__apply_config_terms(struct evsel *evsel,u32 dump_size =0 ;int max_stack =0 ;const char *callgraph_buf =NULL ; +const char *rtp_buf =NULL ;list_for_each_entry (term, config_terms, list) {switch (term->type) {@@ -1174,6 +1240,9 @@ static void evsel__apply_config_terms(struct evsel *evsel,break ;case EVSEL__CONFIG_TERM_CFG_CHG :break ; +case EVSEL__CONFIG_TERM_RATIO_TO_PREV : + rtp_buf = term->val.str; +break ;default :break ; }@@ -1225,6 +1294,8 @@ static void evsel__apply_config_terms(struct evsel *evsel,evsel__config_callchain (evsel, opts, ¶m); } } +if (rtp_buf) +evsel__apply_ratio_to_prev (evsel, attr, opts, rtp_buf); }struct evsel_config_term *__evsel__get_config_term (struct evsel *evsel,enum evsel_term_type type)
tools/perf/util/evsel.c void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, · line 1327
Quoted 8 lines
tools/perf/util/evsel.c +5
-0@@ -1249,6 +1320,11 @@ void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, { } +void __weak arch_evsel__apply_ratio_to_prev (struct evsel *evsel__maybe_unused , +struct perf_event_attr *attr__maybe_unused ) +{ +} +
I'm not a fan of weak functions as they introduce subtle bugs, but I can see why you have this organization.
Thanks,
Ian
Quoted 145 lines
tools/perf/util/evsel.c +0
-0static void evsel__set_default_freq_period (struct record_opts *opts,struct perf_event_attr *attr) {tools/perf/util/evsel.h +1
-0@@ -342,6 +342,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);void arch_evsel__set_sample_weight (struct evsel *evsel);void arch__post_evsel_config (struct evsel *evsel,struct perf_event_attr *attr);int arch_evsel__open_strerror (struct evsel *evsel,char *msg,size_t size); +void arch_evsel__apply_ratio_to_prev (struct evsel *evsel,struct perf_event_attr *attr);int evsel__set_filter (struct evsel *evsel,const char *filter);int evsel__append_tp_filter (struct evsel *evsel,const char *filter);tools/perf/util/evsel_config.h +1
-0@@ -28,6 +28,7 @@ enum evsel_term_type {EVSEL__CONFIG_TERM_AUX_ACTION ,EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE ,EVSEL__CONFIG_TERM_CFG_CHG , + EVSEL__CONFIG_TERM_RATIO_TO_PREV, }; struct evsel_config_term {tools/perf/util/parse-events.c +22
-0@@ -834,6 +834,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", [PARSE_EVENTS__TERM_TYPE_CPU] = "cpu", + [PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV] = "ratio-to-prev", };if ((unsigned int )term_type >= __PARSE_EVENTS__TERM_TYPE_NR)return "unknown term" ;@@ -884,6 +885,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_ercase PARSE_EVENTS__TERM_TYPE_RAW :case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :if (!err)return false;@@ -1037,6 +1039,21 @@ do { \perf_cpu_map__put (map);break ; } +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV : +CHECK_TYPE_VAL (STR ); +if (strtod (term->val.str,NULL ) <=0 ) { +parse_events_error__handle (err, term->err_val, +strdup ("zero or negative" ), +NULL ); +return -EINVAL ; + } +if (errno ==ERANGE ) { +parse_events_error__handle (err, term->err_val, +strdup ("too big" ), +NULL ); +return -EINVAL ; + } +break ;case PARSE_EVENTS__TERM_TYPE_DRV_CFG :case PARSE_EVENTS__TERM_TYPE_USER :case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :@@ -1165,6 +1182,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE :case PARSE_EVENTS__TERM_TYPE_CPU : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :if (err) { parse_events_error__handle(err, term->err_term,@@ -1289,6 +1307,9 @@ do { \ADD_CONFIG_TERM_VAL (AUX_SAMPLE_SIZE , aux_sample_size, term->val.num, term->weak);break ; +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV : +ADD_CONFIG_TERM_STR (RATIO_TO_PREV , term->val.str, term->weak); +break ;case PARSE_EVENTS__TERM_TYPE_USER :case PARSE_EVENTS__TERM_TYPE_CONFIG :case PARSE_EVENTS__TERM_TYPE_CONFIG1 :@@ -1355,6 +1376,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *headcase PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE :case PARSE_EVENTS__TERM_TYPE_HARDWARE :case PARSE_EVENTS__TERM_TYPE_CPU : +case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV :default :break ; }tools/perf/util/parse-events.h +2
-1@@ -83,7 +83,8 @@ enum parse_events__term_type {PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE ,PARSE_EVENTS__TERM_TYPE_HARDWARE ,PARSE_EVENTS__TERM_TYPE_CPU , -#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_CPU + 1) +PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV , +#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV + 1) }; struct parse_events_term {tools/perf/util/parse-events.l +1
-0@@ -336,6 +336,7 @@ aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } cpu { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CPU); } +ratio-to-prev { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV); } cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } stalled-cycles-frontend|idle-cycles-frontend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } stalled-cycles-backend|idle-cycles-backend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }tools/perf/util/pmu.c +2
-2@@ -1541,7 +1541,7 @@ static int pmu_config_term(const struct perf_pmu *pmu,break ;case PARSE_EVENTS__TERM_TYPE_USER :/* Not hardcoded. */ return -EINVAL ; - case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_CPU: + case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV:/* Skip non-config terms. */ break ;default :@@ -1930,6 +1930,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call"aux-action=(pause|resume|start-paused)" ,"aux-sample-size=number" ,"cpu=number" , + "ratio-to-prev=string", };struct perf_pmu_format *format;int ret; --2.50.1
PATCH RESEND v2 2/2 perf record: Add auto counter reload parse and regression tests
In reply to Thomas FalconInclude event parsing and regression tests for auto counter reload and ratio-to-prev event term.
--- tools/perf/tests/parse-events.c | 54 ++++++++++++++++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 +++++++++++++++++++++++ 2 files changed, 94 insertions(+)
tools/perf/tests/parse-events.c +54 -0
@@ -1736,6 +1736,53 @@ static int test__intel_pt(struct evlist *evlist)return TEST_OK ; } +static bool test__acr_valid (void ) +{ +struct perf_pmu *pmu =NULL ; + +while ((pmu =perf_pmus__scan_core (pmu)) !=NULL ) { +if (perf_pmu__has_format (pmu,"acr_mask" )) +return true; + } + +return false; +} + +static int test__ratio_to_prev (struct evlist *evlist) +{ +struct evsel *evsel; +int ret; + +TEST_ASSERT_VAL ("wrong number of entries" ,2 *perf_pmus__num_core_pmus () == evlist->core.nr_entries); + +evlist__for_each_entry (evlist, evsel) { +if (!perf_pmu__has_format (evsel->pmu,"acr_mask" )) +return TEST_OK ; + +if (evsel ==evlist__first (evlist)) { +TEST_ASSERT_VAL ("wrong config2" ,0 == evsel->core.attr.config2); +TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong core.nr_members" , evsel->core.nr_members ==2 ); +TEST_ASSERT_VAL ("wrong group_idx" ,evsel__group_idx (evsel) ==0 ); + ret =assert_hw (&evsel->core,PERF_COUNT_HW_CPU_CYCLES ,"cycles" ); + }else { +TEST_ASSERT_VAL ("wrong config2" ,0 == evsel->core.attr.config2); +TEST_ASSERT_VAL ("wrong leader" , !evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong core.nr_members" , evsel->core.nr_members ==0 ); +TEST_ASSERT_VAL ("wrong group_idx" ,evsel__group_idx (evsel) ==1 ); + ret =assert_hw (&evsel->core,PERF_COUNT_HW_INSTRUCTIONS ,"instructions" ); + } +if (ret) +return ret; +/* +* The period value gets configured within evlist__config, +* while this test executes only parse events method. +*/ +TEST_ASSERT_VAL ("wrong period" ,0 == evsel->core.attr.sample_period); + } +return TEST_OK ; +} +static int test__checkevent_complex_name (struct evlist *evlist) {struct evsel *evsel =evlist__first (evlist);
@@ -2249,6 +2296,13 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint, /* 4 */ }, + { + .name = "{cycles,instructions/period=200000,ratio-to-prev=2.0/}", + .valid = test__acr_valid, + .check = test__ratio_to_prev, + /* 5 */ + }, + };static const struct evlist_test test__events_pmu[] = {
tools/perf/tests/shell/record.sh +40 -0
@@ -388,6 +388,45 @@ test_callgraph() { echo "Callgraph test [Success]" } +test_ratio_to_prev() { + echo "ratio-to-prev test" + if ! perf record -o /dev/null -e "{instructions, cycles/period=100000,ratio-to-prev=0.5/}" \ + true 2> /dev/null + then + echo "ratio-to-prev [Skipped not supported]" + return + fi + if ! perf record -o /dev/null -e "instructions, cycles/period=100000,ratio-to-prev=0.5/" \ + true |& grep -q 'Invalid use of ratio-to-prev term without preceding element in group' + then + echo "ratio-to-prev test [Failed elements must be in same group]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{instructions,dummy,cycles/period=100000,ratio-to-prev=0.5/}" \ + true |& grep -q 'must have same PMU' + then + echo "ratio-to-prev test [Failed elements must have same PMU]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{instructions,cycles/ratio-to-prev=0.5/}" \ + true |& grep -q 'Event period term or count (-c) must be set when using ratio-to-prev term.' + then + echo "ratio-to-prev test [Failed period must be set]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{cycles/ratio-to-prev=0.5/}" \ + true |& grep -q 'Invalid use of ratio-to-prev term without preceding element in group' + then + echo "ratio-to-prev test [Failed need 2+ events]" + err=1 + return + fi + echo "Basic ratio-to-prev record test [Success]" +} + # raise the limit of file descriptors to minimum if [[ $default_fd_limit -lt $min_fd_limit ]]; then ulimit -Sn $min_fd_limit
@@ -404,6 +443,7 @@ test_leader_sampling test_topdown_leader_sampling test_precise_max test_callgraph +test_ratio_to_prev # restore the default value ulimit -Sn $default_fd_limit
Signature · 1 line
2.50.1
Re: [RESEND][PATCH v2 2/2] perf record: Add auto counter reload parse and regression tests
Quoted 5 lines · Thomas Falcon
Include event parsing and regression tests for auto counter reload and ratio-to-prev event term.
Signed-off-by Thomas Falcon <[email protected]>
There will be conflicts with:
https://lore.kernel.org/linux-perf-users/[email protected]/
as I refactored parts of the parse-events test. I wouldn't be holding my breath waiting for those patches to land, so I guess I'll deal with the issues when they pop up.
Thanks,
Ian
Quoted 138 lines
--- tools/perf/tests/parse-events.c | 54 ++++++++++++++++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 +++++++++++++++++++++++ 2 files changed, 94 insertions(+)tools/perf/tests/parse-events.c +54
-0@@ -1736,6 +1736,53 @@ static int test__intel_pt(struct evlist *evlist)return TEST_OK ; } +static bool test__acr_valid (void ) +{ +struct perf_pmu *pmu =NULL ; + +while ((pmu =perf_pmus__scan_core (pmu)) !=NULL ) { +if (perf_pmu__has_format (pmu,"acr_mask" )) +return true; + } + +return false; +} + +static int test__ratio_to_prev (struct evlist *evlist) +{ +struct evsel *evsel; +int ret; + +TEST_ASSERT_VAL ("wrong number of entries" ,2 *perf_pmus__num_core_pmus () == evlist->core.nr_entries); + +evlist__for_each_entry (evlist, evsel) { +if (!perf_pmu__has_format (evsel->pmu,"acr_mask" )) +return TEST_OK ; + +if (evsel ==evlist__first (evlist)) { +TEST_ASSERT_VAL ("wrong config2" ,0 == evsel->core.attr.config2); +TEST_ASSERT_VAL ("wrong leader" ,evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong core.nr_members" , evsel->core.nr_members ==2 ); +TEST_ASSERT_VAL ("wrong group_idx" ,evsel__group_idx (evsel) ==0 ); + ret =assert_hw (&evsel->core,PERF_COUNT_HW_CPU_CYCLES ,"cycles" ); + }else { +TEST_ASSERT_VAL ("wrong config2" ,0 == evsel->core.attr.config2); +TEST_ASSERT_VAL ("wrong leader" , !evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong core.nr_members" , evsel->core.nr_members ==0 ); +TEST_ASSERT_VAL ("wrong group_idx" ,evsel__group_idx (evsel) ==1 ); + ret =assert_hw (&evsel->core,PERF_COUNT_HW_INSTRUCTIONS ,"instructions" ); + } +if (ret) +return ret; +/* +* The period value gets configured within evlist__config, +* while this test executes only parse events method. +*/ +TEST_ASSERT_VAL ("wrong period" ,0 == evsel->core.attr.sample_period); + } +return TEST_OK ; +} +static int test__checkevent_complex_name (struct evlist *evlist) {struct evsel *evsel =evlist__first (evlist);@@ -2249,6 +2296,13 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint, /* 4 */ }, + { + .name = "{cycles,instructions/period=200000,ratio-to-prev=2.0/}", + .valid = test__acr_valid, + .check = test__ratio_to_prev, + /* 5 */ + }, + };static const struct evlist_test test__events_pmu[] = {tools/perf/tests/shell/record.sh +40
-1@@ -388,6 +388,45 @@ test_callgraph() { echo "Callgraph test [Success]" } +test_ratio_to_prev() { + echo "ratio-to-prev test" + if ! perf record -o /dev/null -e "{instructions, cycles/period=100000,ratio-to-prev=0.5/}" \ + true 2> /dev/null + then + echo "ratio-to-prev [Skipped not supported]" + return + fi + if ! perf record -o /dev/null -e "instructions, cycles/period=100000,ratio-to-prev=0.5/" \ + true |& grep -q 'Invalid use of ratio-to-prev term without preceding element in group' + then + echo "ratio-to-prev test [Failed elements must be in same group]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{instructions,dummy,cycles/period=100000,ratio-to-prev=0.5/}" \ + true |& grep -q 'must have same PMU' + then + echo "ratio-to-prev test [Failed elements must have same PMU]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{instructions,cycles/ratio-to-prev=0.5/}" \ + true |& grep -q 'Event period term or count (-c) must be set when using ratio-to-prev term.' + then + echo "ratio-to-prev test [Failed period must be set]" + err=1 + return + fi + if ! perf record -o /dev/null -e "{cycles/ratio-to-prev=0.5/}" \ + true |& grep -q 'Invalid use of ratio-to-prev term without preceding element in group' + then + echo "ratio-to-prev test [Failed need 2+ events]" + err=1 + return + fi + echo "Basic ratio-to-prev record test [Success]" +} + # raise the limit of file descriptors to minimum if [[ $default_fd_limit -lt $min_fd_limit ]]; then ulimit -Sn $min_fd_limit@@ -404,6 +443,7 @@ test_leader_sampling test_topdown_leader_sampling test_precise_max test_callgraph +test_ratio_to_prev # restore the default value ulimit -Sn $default_fd_limit --2.50.1
Quoted 5 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
Ping.
Thanks,
Tom
Quoted 63 lines
-- Event sampling period ("period")
--acr_mask, which determines which events get reloaded when the sample period is reached.For example, in the following command:
perf record -e "{cpu_atom/branch-misses,period=200000,\
acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
acr_mask=0x3/u}" -- ./mispredictThe goal is to limit event sampling to cases when the branch miss rate exceeds 20%. If the branch instructions sample period is exceeded first, both events are reloaded. If branch misses exceed their threshold first, only the second counter is reloaded, and a sample is taken.
To simplify this, provide a new “ratio-to-prev” event term that works alongside the period event option or -c option. This would allow users to specify the desired relative rate between events as a ratio, making configuration more intuitive.
With this enhancement, the equivalent command would be:
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
-- ./mispredictor
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
-- ./mispredict[1]
https://lore.kernel.org/lkml/[email protected]/Changes in v2 (mostly suggested by Ian Rogers):
-- Add documentation explaining
acr_maskbitmask used by ACR -- Move ACR specific implementation toarch/x86/
-- Provide test cases for event parsing and perf record testsThomas Falcon (2):
perf record: Add ratio-to-prev term
perf record: add auto counter reload parse and regression teststools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++
tools/perf/Documentation/perf-list.txt| 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/tests/parse-events.c | 54 ++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 ++++++++++++++ tools/perf/util/evsel.c | 76
++++++++++++++++++++++++++
tools/perf/util/evsel.h | 1 +tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 12 files changed, 307 insertions(+), 2 deletions(-)create mode 100644
tools/perf/Documentation/intel-acr.txt
Quoted 27 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
-- Event sampling period ("period")
--acr_mask, which determines which events get reloaded
when the sample period is reached.For example, in the following command:
perf record -e "{cpu_atom/branch-misses,period=200000,\
acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
acr_mask=0x3/u}" -- ./mispredictThe goal is to limit event sampling to cases when the branch miss rate exceeds 20%. If the branch instructions sample period is exceeded first, both events are reloaded. If branch misses exceed their threshold first, only the second counter is reloaded, and a sample is taken.
To simplify this, provide a new “ratio-to-prev” event term that works alongside the period event option or -c option. This would allow users to specify the desired relative rate between events as a ratio, making configuration more intuitive.
Quoted 5 lines
With this enhancement, the equivalent command would be:
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
-- ./mispredict
Hi Tom,
Does this "ratio-to-prev" option support 3 and more events in ACR group?
If not, should we consider to support the cases there are 3 and more events in the ACR group? (If I remember correct, the PMU driver should support it).
e.g.,
perf record -e "{cpu_atom/branch-misses,period=200000,acr_mask=0x6/p,cpu_atom/branches,period=1000000,acr_mask=0x7/,cpu_atom/branches,period=1000000,acr_mask=0x7/}" -- sleep 1
Of course, this is just an example that indicates the cases are supported, it doesn't mean the command is meaningful. But we can't exclude that users have such real requirements.
If we want to support 3 and more events in ACR group (if not already), we'd better rename the "ratio-to-prev" option to "ratio-to-head" and only allow the group leader can be set the sampling period explicitly with "period" option and the sampling period of all other group members can only be calculated base on the sampling period of group leader and
the "ratio-to-head", maybe like this.
perf record -e "{cpu_atom/branch-misses,period=200000/p,cpu_atom/branches,ratio-to-head=5/,cpu_atom/branches,ratio-to-head=5/}" -- sleep 1
Thanks.
Quoted 34 lines
or
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
-- ./mispredict[1] https://lore.kernel.org/lkml/[email protected]/
Changes in v2 (mostly suggested by Ian Rogers):
-- Add documentation explaining
acr_maskbitmask used by ACR -- Move ACR specific implementation toarch/x86/
-- Provide test cases for event parsing and perf record testsThomas Falcon (2):
perf record: Add ratio-to-prev term
perf record: add auto counter reload parse and regression teststools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++ tools/perf/Documentation/perf-list.txt | 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/tests/parse-events.c | 54 ++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 ++++++++++++++ tools/perf/util/evsel.c | 76 ++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 12 files changed, 307 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/intel-acr.txt
Quoted 31 lines · Dapeng
Quoted 29 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
-- Event sampling period ("period")
--acr_mask, which determines which events get reloaded when the sample period is reached.For example, in the following command:
perf record -e "{cpu_atom/branch-misses,period=200000,\
acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
acr_mask=0x3/u}" -- ./mispredictThe goal is to limit event sampling to cases when the branch miss rate exceeds 20%. If the branch instructions sample period is exceeded first, both events are reloaded. If branch misses exceed their threshold first, only the second counter is reloaded, and a sample is taken.
To simplify this, provide a new “ratio-to-prev” event term that works alongside the period event option or -c option. This would allow users to specify the desired relative rate between events as a ratio, making configuration more intuitive.
With this enhancement, the equivalent command would be:
Quoted 9 lines
Quoted 3 lines
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
-- ./mispredictHi Tom,
Does this "ratio-to-prev" option support 3 and more events in ACR group?
Hi Dapeng,
The 'ratio-to-prev' option only supports groups with two events at this time. For larger event groups, the "acr_mask" term is available.
Quoted 5 lines
If not, should we consider to support the cases there are 3 and more events
in the ACR group? (If I remember correct, the PMU driver should support it).
Correct.
Quoted 24 lines
e.g.,
perf record -e
"{cpu_atom/branch- misses,period=200000,acr_mask=0x6/p,cpu_atom/branches,period=1000000, acr_mask=0x7/,cpu_atom/branches,period=1000000,acr_mask=0x7/}" -- sleep 1Of course, this is just an example that indicates the cases are supported,
it doesn't mean the command is meaningful. But we can't exclude that users
have such real requirements.If we want to support 3 and more events in ACR group (if not already), we'd
better rename the "ratio-to-prev" option to "ratio-to-head" and only allow
the group leader can be set the sampling period explicitly with "period"
option and the sampling period of all other group members can only be calculated base on the sampling period of group leader and the "ratio-to-head", maybe like this.
Quoted 8 lines
perf record -e "{cpu_atom/branch-misses,period=200000/p,cpu_atom/branches,ratio-to- head=5/,cpu_atom/branches,ratio-to-head=5/}"
-- sleep 1Thanks.
Thanks, those are good suggestions, but the goal of the feature was to provide users a way to utilize ACR to make simple comparisons without needing to use the "acr_mask" field. For tests comparing larger event groups, the acr_mask field may be used instead.
Thanks,
Tom
Quoted 36 lines
Quoted 36 lines
or
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
-- ./mispredict[1]
https://lore.kernel.org/lkml/[email protected]/Changes in v2 (mostly suggested by Ian Rogers):
-- Add documentation explaining
acr_maskbitmask used by ACR -- Move ACR specific implementation toarch/x86/
-- Provide test cases for event parsing and perf record testsThomas Falcon (2):
perf record: Add ratio-to-prev term
perf record: add auto counter reload parse and regression teststools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++
tools/perf/Documentation/perf-list.txt| 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/tests/parse-events.c | 54 ++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 ++++++++++++++ tools/perf/util/evsel.c | 76
++++++++++++++++++++++++++
tools/perf/util/evsel.h | 1 +tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 12 files changed, 307 insertions(+), 2 deletions(-)create mode 100644
tools/perf/Documentation/intel-acr.txt
Quoted 80 lines · Thomas
Quoted 30 lines · Dapeng
Quoted 29 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
-- Event sampling period ("period")
--acr_mask, which determines which events get reloaded when the sample period is reached.For example, in the following command:
perf record -e "{cpu_atom/branch-misses,period=200000,\
acr_mask=0x2/ppu,cpu_atom/branch-instructions,period=1000000,\
acr_mask=0x3/u}" -- ./mispredictThe goal is to limit event sampling to cases when the branch miss rate exceeds 20%. If the branch instructions sample period is exceeded first, both events are reloaded. If branch misses exceed their threshold first, only the second counter is reloaded, and a sample is taken.
To simplify this, provide a new “ratio-to-prev” event term that works alongside the period event option or -c option. This would allow users to specify the desired relative rate between events as a ratio, making configuration more intuitive.
With this enhancement, the equivalent command would be:
Quoted 8 lines
Quoted 3 lines
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,period=1000000,ratio_to_prev=5/u}" \
-- ./mispredictHi Tom,
Does this "ratio-to-prev" option support 3 and more events in ACR group?
Hi Dapeng,
The 'ratio-to-prev' option only supports groups with two events at this time. For larger event groups, the "
acr_mask" term is available.Quoted 5 lines
If not, should we consider to support the cases there are 3 and more events
in the ACR group? (If I remember correct, the PMU driver should support it).Correct.
Quoted 29 lines
e.g.,
perf record -e
"{cpu_atom/branch- misses,period=200000,acr_mask=0x6/p,cpu_atom/branches,period=1000000, acr_mask=0x7/,cpu_atom/branches,period=1000000,acr_mask=0x7/}" -- sleep 1Of course, this is just an example that indicates the cases are supported,
it doesn't mean the command is meaningful. But we can't exclude that users
have such real requirements.If we want to support 3 and more events in ACR group (if not already), we'd
better rename the "ratio-to-prev" option to "ratio-to-head" and only allow
the group leader can be set the sampling period explicitly with "period"
option and the sampling period of all other group members can only be calculated base on the sampling period of group leader and the "ratio-to-head", maybe like this.perf record -e "{cpu_atom/branch-misses,period=200000/p,cpu_atom/branches,ratio-to- head=5/,cpu_atom/branches,ratio-to-head=5/}"
-- sleep 1
Quoted 7 lines
Quoted 3 lines
Thanks.
Thanks, those are good suggestions, but the goal of the feature was to provide users a way to utilize ACR to make simple comparisons without needing to use the "
acr_mask" field. For tests comparing larger event groups, theacr_maskfield may be used instead.
Yeah, I understand the intent is to get a new simple option for using the ACR feature. But we already support 2 events for the ACR group, why not we make it more generic and can support more events?
Quoted 39 lines
Thanks,
TomQuoted 35 lines
Quoted 35 lines
or
perf record -e "{cpu_atom/branch-misses/ppu,\
cpu_atom/branch-instructions,ratio-to-prev=5/u}" -c 1000000 \
-- ./mispredict[1]
https://lore.kernel.org/lkml/[email protected]/Changes in v2 (mostly suggested by Ian Rogers):
-- Add documentation explaining
acr_maskbitmask used by ACR -- Move ACR specific implementation toarch/x86/
-- Provide test cases for event parsing and perf record testsThomas Falcon (2):
perf record: Add ratio-to-prev term
perf record: add auto counter reload parse and regression teststools/perf/Documentation/intel-acr.txt | 53 ++++++++++++++++++
tools/perf/Documentation/perf-list.txt| 2 + tools/perf/arch/x86/util/evsel.c | 53 ++++++++++++++++++ tools/perf/tests/parse-events.c | 54 ++++++++++++++++++ tools/perf/tests/shell/record.sh | 40 ++++++++++++++ tools/perf/util/evsel.c | 76
++++++++++++++++++++++++++
tools/perf/util/evsel.h | 1 +tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 22 ++++++++ tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +- 12 files changed, 307 insertions(+), 2 deletions(-)create mode 100644
tools/perf/Documentation/intel-acr.txt
Arnaldo Carvalho de Melo
maintainerQuoted 5 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
Can you please try to rebase to what is in tmp.perf-tools-next now?
- Arnaldo
Quoted 8 lines · Arnaldo Carvalho de Melo
Quoted 5 lines · Thomas Falcon
The Auto Counter Reload (ACR)[1] feature is used to track the relative rates of two or more perf events, only sampling when a given threshold is exceeded. This helps reduce overhead and unnecessary samples. However, enabling this feature currently requires setting two parameters:
Can you please try to rebase to what is in tmp.perf-tools-next now?
Ok, I will send it ASAP.
thanks,
Tom
Quoted 2 lines
- Arnaldo