Sched-tools May 2015

sched-tools@lists.linaro.org

8 participants
9 discussions

[RFC PATCH] idlestat: Support energy modeling of idle consumption at different OPPs

by Xunlei Pang

From: Xunlei Pang <pang.xunlei(a)linaro.org> BACKGROUND Overview: Currently idlestat only handles a energy model with a single value for energy savings when going to WFI. IOW, idlestat does not know what OPP (frequency, voltage) is this WFI energy savings calculated at. Add funtionality to allow a table of OPP and energy saving values to be listed so that the savings at various frequencies can be modeled correctly. As an example, a platform may have different power consumption when idled at different OPPs, as follow: @1989 MHz: single core in WFI consumes about 120 mW @1001 MHz: single core in WFI consumes about 45 mW @ 507 MHz: single core in WFI consumes about 30 mW This data is useful to optimise a platform's idle policy. MODIFICATION METHOD Now we want to modify the format of idlestat's energy model to accomodate the different C-states energy data at different OPPs. Let's take a simple example to explicate the way: Assuming different C-States energy data below: 1200Mhz: WFI 80 10 1200Mhz: cluster-sleep-b 30 5 1000Mhz: WFI 70 0 1000Mhz: cluster-sleep-b 25 0 Before modification: clusterA: 2 cap states 2 C states P-states: 1200 15200 6997 1000 8446 3846 C-states: WFI 70 0 cluster-sleep-b 25 0 After modification: clusterA: 2 cap states 2 C states P-state C-states pair 1: 1200 15200 6997 WFI 80 10 cluster-sleep-b 30 5 P-state C-states pair 2: 1000 8446 3846 WFI 70 0 cluster-sleep-b 25 0 In this way, we ensure P-states and C-States always appear in pairs. Signed-off-by: Xunlei Pang <pang.xunlei(a)linaro.org> --- energy_model.c | 104 ++++++++++++++++++++++----------------------------- idlestat.c | 64 +++++++++++++++++++++++++++++-- idlestat.h | 10 +++++ trace_ops.h | 1 - tracefile_idlestat.c | 4 ++ 5 files changed, 120 insertions(+), 63 deletions(-) diff --git a/energy_model.c b/energy_model.c index 2ea6fdd..3932c23 100644 --- a/energy_model.c +++ b/energy_model.c @@ -75,7 +75,7 @@ static int make_energy_model_template(struct program_options *options) list_for_each_entry(s_phy, &cpu_topo->physical_head, list_physical) { unsigned int num_cap_states = 0; unsigned int num_c_states = 0; - int i; + int i, j; s_core = list_entry((&s_phy->core_head)->prev, struct cpu_core, list_core); s_cpu = list_entry((&s_core->cpu_head)->prev, struct cpu_cpu, list_cpu); @@ -89,27 +89,23 @@ static int make_energy_model_template(struct program_options *options) num_cap_states++; } - fprintf(f, "\nC-states:\n"); - fprintf(f, "cluster%c: %d cap states %d C states\n\n", cluster_number + 'A', num_cap_states, num_c_states); - fprintf(f, "P-states:\n"); - fprintf(f, "# speed, cluster power, core power\n"); - for (i = 0; i < s_cpu->pstates->max; i++) { struct cpufreq_pstate *p = &s_cpu->pstates->pstate[i]; if (p->freq == 0) continue; + fprintf(f, "P-state C-states pair %d:\n", i + 1); + fprintf(f, "# P-state: speed, cluster power, core power\n"); fprintf(f, "%d\t\t?\t?\n", p->freq/1000); - } - fprintf(f, "\nC-states:\n"); - fprintf(f, "# name, cluster power, core power\n"); - for (i = 0; i < s_cpu->cstates->cstate_max + 1; i++) { - struct cpuidle_cstate *c = &s_cpu->cstates->cstate[i]; + fprintf(f, "# C-states: name, cluster power, core power\n"); + for (j = 0; j < s_cpu->cstates->cstate_max + 1; j++) { + struct cpuidle_cstate *c = &s_cpu->cstates->cstate[j]; - fprintf(f, "%s\t\t?\t?\n", c->name); + fprintf(f, "%s\t\t?\t?\n", c->name); + } } fprintf(f, "\n"); cluster_number++; @@ -130,8 +126,8 @@ int parse_energy_model(struct program_options *options) struct cluster_energy_info *clustp = NULL; unsigned int number_cap_states, number_c_states; int current_cluster = -1; - unsigned int current_pstate = 0; - unsigned int current_cstate = 0; + unsigned int current_pstate, speed; + unsigned int current_cstate; unsigned int clust_p, core_p; char buffer[BUFSIZE]; char *path = options->energy_model_filename; @@ -196,12 +192,13 @@ int parse_energy_model(struct program_options *options) clustp->number_c_states = number_c_states; clustp->p_energy = calloc(number_cap_states, sizeof(struct pstate_energy_info)); - clustp->c_energy = calloc(number_c_states, + clustp->c_energy = calloc(number_c_states*number_cap_states, sizeof(struct cstate_energy_info)); clustp->state = parsed_cluster_info; + current_pstate = 0; continue; } - if (strstr(buffer, "P-states")) { + if (strstr(buffer, "P-state C-states pair")) { if (current_cluster == -1) { fprintf(stderr, "%s: unknown cluster (cap states) in %s\n", __func__, path); @@ -214,27 +211,9 @@ int parse_energy_model(struct program_options *options) fclose(f); return -1; } - current_pstate = 0; clustp->state = parsing_cap_states; continue; } - if (strstr(buffer, "C-states")) { - if (current_cluster == -1) { - fprintf(stderr, "%s: unknown cluster (c states) in %s\n", - __func__, path); - fclose(f); - return -1; - } - if (clustp->state < parsed_cluster_info) { - fprintf(stderr, "%s: number of c states for cluster%c not specified in %s\n", - __func__, current_cluster, path); - fclose(f); - return -1; - } - current_cstate = 0; - clustp->state = parsing_c_states; - continue; - } if (strstr(buffer, "wakeup")) { unsigned int clust_w, core_w; @@ -254,10 +233,9 @@ int parse_energy_model(struct program_options *options) __func__, path); fclose(f); return -1; - } + } if (clustp->state == parsing_cap_states) { struct pstate_energy_info *pp; - unsigned int speed; if (sscanf(buffer, "%d %d %d", &speed, &clust_p, &core_p) != 3) { fprintf(stderr, "%s: expected P state (speed cluster core) for cluster%c in %s\n", @@ -276,6 +254,8 @@ int parse_energy_model(struct program_options *options) pp->speed = speed; pp->cluster_power = clust_p; pp->core_power = core_p; + clustp->state = parsing_c_states; + current_cstate = 0; continue; } if (clustp->state == parsing_c_states) { @@ -295,8 +275,9 @@ int parse_energy_model(struct program_options *options) fclose(f); return -1; } - cp = &clustp->c_energy[current_cstate++]; + cp = &clustp->c_energy[(current_pstate - 1) * clustp->number_c_states + current_cstate++]; strncpy(cp->cstate_name, name, NAMELEN); + cp->speed = speed; cp->cluster_idle_power = clust_p; cp->core_idle_power = core_p; continue; @@ -309,7 +290,7 @@ int parse_energy_model(struct program_options *options) return 0; } -static struct cstate_energy_info *find_cstate_energy_info(const unsigned int cluster, const char *name) +static struct cstate_energy_info *find_cstate_energy_info(const unsigned int cluster, unsigned int speed, const char *name) { struct cluster_energy_info *clustp; struct cstate_energy_info *cp; @@ -317,8 +298,8 @@ static struct cstate_energy_info *find_cstate_energy_info(const unsigned int clu clustp = cluster_energy_table + cluster; cp = &clustp->c_energy[0]; - for (i = 0; i < clustp->number_c_states; i++, cp++) { - if (!strcmp(cp->cstate_name, name)) return cp; + for (i = 0; i < clustp->number_c_states * clustp->number_cap_states; i++, cp++) { + if (cp->speed == speed && !strcmp(cp->cstate_name, name)) return cp; } return NULL; } @@ -377,6 +358,7 @@ void calculate_energy_consumption(struct cpu_topology *cpu_topo) for (j = 0; j < s_phy->cstates->cstate_max + 1; j++) { struct cpuidle_cstate *c = &s_phy->cstates->cstate[j]; + struct duration_opp *opps = c->duration_opps; if (c->nrdata == 0) { verbose_fprintf(stderr, 2, @@ -385,19 +367,20 @@ void calculate_energy_consumption(struct cpu_topology *cpu_topo) continue; } - cp = find_cstate_energy_info(current_cluster, c->name); - if (!cp) { - verbose_fprintf(stderr, 2, " C%-2d no energy model for [%s] (%d hits, %f duration)\n", - j, c->name, c->nrdata, c->duration); - continue; - } + for (i = 0; i < c->nropp; i++) { + cp = find_cstate_energy_info(current_cluster, opps[i].speed/1000, c->name); + if (!cp) { + verbose_fprintf(stderr, 2, " C%-2d no energy model for [%s] (%d hits, %f duration) %d speed\n", + j, c->name, c->nrdata, opps[i].duration, opps[i].speed); + continue; + } - cluster_idl += c->duration * cp->cluster_idle_power; + cluster_idl += opps[i].duration * cp->cluster_idle_power; + } - verbose_fprintf(stderr, 1, " C%-2d +%7d hits for [%15s] | %13.0f | %7d | %7s | %12s | %12.0f | %12s |\n", + verbose_fprintf(stderr, 1, " C%-2d +%7d hits for [%15s] | %13.0f | %7s | %12s | %12.0f | %12s |\n", j, c->nrdata, c->name, c->duration, - cp->cluster_idle_power, "", "", cluster_idl, ""); @@ -415,7 +398,7 @@ void calculate_energy_consumption(struct cpu_topology *cpu_topo) pp = find_pstate_energy_info(current_cluster, p->freq/1000); if (!pp) { - verbose_fprintf(stderr, 2, "Cluster %c frequency %u MHz no energy model for [%d] (%d hits, %f duration)\n", + verbose_fprintf(stderr, 1, "Cluster %c frequency %u MHz no energy model for [%d] (%d hits, %f duration)\n", s_phy->physical_id + 'A', p->freq/1000, p->count, p->duration); continue; @@ -442,25 +425,28 @@ void calculate_energy_consumption(struct cpu_topology *cpu_topo) for (i = 0; i < s_cpu->cstates->cstate_max + 1; i++) { struct cpuidle_cstate *c = &s_cpu->cstates->cstate[i]; + struct duration_opp *opps = c->duration_opps; + if (c->nrdata == 0) { verbose_fprintf(stderr, 2, "Cpu%d C%-2d no hits for [%15s] | 0 | 0 | | | 0 | |\n", s_cpu->cpu_id, i, c->name); continue; } - cp = find_cstate_energy_info(current_cluster, c->name); - if (!cp) { - verbose_fprintf(stderr, 2, "Cpu%d C%-2d no energy model for [%s] (%d hits, %f duration)\n", - s_cpu->cpu_id, i, c->name, - c->nrdata, c->duration); - continue; + for (j = 0; j < c->nropp; j++) { + cp = find_cstate_energy_info(current_cluster, opps[j].speed/100, c->name); + if (!cp) { + verbose_fprintf(stderr, 2, "Cpu%d C%-2d no energy model for [%s] (%d hits, %f duration, %d speed)\n", + s_cpu->cpu_id, i, c->name, + c->nrdata, opps[j].duration, opps[j].speed); + continue; + } + cluster_idl += opps[j].duration * cp->core_idle_power; } - cluster_idl += c->duration * cp->core_idle_power; - verbose_fprintf(stderr, 1, "Cpu%d C%-2d +%7d hits for [%15s] | %13.0f | %7d | %7s | %12s | %12.0f | %12s |\n", + verbose_fprintf(stderr, 2, "Cpu%d C%-2d +%7d hits for [%15s] | %13.0f | %7s | %12s | %12.0f | %12s |\n", s_cpu->cpu_id, i, c->nrdata, c->name, c->duration, - cp->core_idle_power, "", "", cluster_idl, ""); diff --git a/idlestat.c b/idlestat.c index 4d773f4..75ac1fc 100644 --- a/idlestat.c +++ b/idlestat.c @@ -335,9 +335,10 @@ struct cpuidle_cstates *build_cstate_info(int nrcpus) c->avg_time = 0.; c->max_time = 0.; c->min_time = DBL_MAX; - c->duration = 0.; c->target_residency = cpuidle_get_target_residency(cpu, i); + c->duration_opps = NULL; + c->nropp = 0; } } return cstates; @@ -739,6 +740,7 @@ static int cstate_begin(double time, int state, struct cpuidle_cstates *cstates) memset(data + nrdata, 0, sizeof(*data)); data[nrdata].begin = time; + data[nrdata].speed = cstates->current_speed; cstate->data = data; cstates->cstate_max = MAX(cstates->cstate_max, state); @@ -747,7 +749,34 @@ static int cstate_begin(double time, int state, struct cpuidle_cstates *cstates) return 0; } -static void cstate_end(double time, struct cpuidle_cstates *cstates) +static int update_duration_opp(struct cpuidle_cstate *cstate, unsigned int freq, double duration) +{ + struct duration_opp *opps = cstate->duration_opps; + int i; + + for (i = 0; i < cstate->nropp; i++) { + if (opps[i].speed == freq) { + opps[i].duration += duration; + return 0; + } + } + + opps = realloc(cstate->duration_opps, sizeof(*opps) * (cstate->nropp + 1)); + if (!opps) { + free(cstate->duration_opps); + return error(__func__); + } + + cstate->duration_opps = opps; + memset(opps + cstate->nropp, 0, sizeof(*opps)); + opps[cstate->nropp].speed = freq; + opps[cstate->nropp].duration += duration; + cstate->nropp++; + + return 0; +} + +static int cstate_end(double time, struct cpuidle_cstates *cstates) { int last_cstate = cstates->current_cstate; struct cpuidle_cstate *cstate = &cstates->cstate[last_cstate]; @@ -792,12 +821,17 @@ static void cstate_end(double time, struct cpuidle_cstates *cstates) cstate->max_time = MAX(cstate->max_time, data->duration); cstate->avg_time = AVG(cstate->avg_time, data->duration, cstate->nrdata + 1); + + if (update_duration_opp(cstate, data->speed, data->duration) < 0) + return error(__func__); + cstate->duration += data->duration; cstate->nrdata++; skip_entry: /* CPU is no longer idle */ cstates->current_cstate = -1; + return 0; } int record_cstate_event(struct cpuidle_cstates *cstates, @@ -810,13 +844,35 @@ int record_cstate_event(struct cpuidle_cstates *cstates, return 0; if (cstates->current_cstate != -1) - cstate_end(time, cstates); + ret = cstate_end(time, cstates); if (state != -1) ret = cstate_begin(time, state, cstates); return ret; } +static void core_update_current_speed(struct cpu_core *core) +{ + struct cpu_cpu *cpu; + unsigned int max_speed = 0; + + core_for_each_cpu(cpu, core) + max_speed = MAX(max_speed, cpu->cstates->current_speed); + + core->cstates->current_speed = max_speed; +} + +static void cluster_update_current_speed(struct cpu_physical *clust) +{ + struct cpu_cpu *cpu; + unsigned int max_speed = 0; + + cluster_for_each_cpu(cpu, clust) + max_speed = MAX(max_speed, cpu->cstates->current_speed); + + clust->cstates->current_speed = max_speed; +} + int store_data(double time, int state, int cpu, struct cpuidle_datas *datas) { @@ -843,11 +899,13 @@ int store_data(double time, int state, int cpu, /* Update core and cluster */ aff_core = cpu_to_core(cpu, datas->topo); state = core_get_least_cstate(aff_core); + core_update_current_speed(aff_core); if (record_cstate_event(aff_core->cstates, time, state) == -1) return -1; aff_cluster = cpu_to_cluster(cpu, datas->topo); state = cluster_get_least_cstate(aff_cluster); + cluster_update_current_speed(aff_cluster); if (record_cstate_event(aff_cluster->cstates, time,state) == -1) return -1; diff --git a/idlestat.h b/idlestat.h index e030f6a..2eef6c9 100644 --- a/idlestat.h +++ b/idlestat.h @@ -48,11 +48,17 @@ "/sys/devices/system/cpu/cpu%d/cpufreq/cpuinfo_cur_freq" struct cpuidle_data { + unsigned int speed; double begin; double end; double duration; }; +struct duration_opp { + unsigned int speed; + double duration; +}; + struct cpuidle_cstate { char *name; struct cpuidle_data *data; @@ -62,7 +68,9 @@ struct cpuidle_cstate { double avg_time; double max_time; double min_time; + struct duration_opp *duration_opps; double duration; + int nropp; int target_residency; /* -1 if not available */ }; @@ -83,6 +91,7 @@ struct cpuidle_cstates { struct cpuidle_cstate cstate[MAXCSTATE]; struct wakeup_info wakeinfo; int current_cstate; + unsigned int current_speed; int cstate_max; struct wakeup_irq *wakeirq; enum {as_expected, too_long, too_short} actual_residency; @@ -157,6 +166,7 @@ struct pstate_energy_info { struct cstate_energy_info { char cstate_name[NAMELEN]; + unsigned int speed; unsigned int cluster_idle_power; unsigned int core_idle_power; double cluster_duration; diff --git a/trace_ops.h b/trace_ops.h index 6d097ff..41258b6 100644 --- a/trace_ops.h +++ b/trace_ops.h @@ -46,5 +46,4 @@ extern void load_text_data_lines(FILE *f, char *buffer, struct cpuidle_datas *da * tracetype_name ## _trace_ptr = &tracetype_name##_trace_ops extern const struct trace_ops *trace_ops_head; - #endif diff --git a/tracefile_idlestat.c b/tracefile_idlestat.c index 3430693..79f8578 100644 --- a/tracefile_idlestat.c +++ b/tracefile_idlestat.c @@ -108,6 +108,8 @@ static struct cpuidle_cstates *load_and_build_cstate_info(FILE* f, char *buffer, c->max_time = 0.; c->min_time = DBL_MAX; c->duration = 0.; + c->duration_opps = NULL; + c->nropp = 0; c->target_residency = residency; } fgets(buffer, BUFSIZE, f); @@ -146,6 +148,8 @@ int load_text_data_line(char *buffer, struct cpuidle_datas *datas, char *format, "be wrong.\n"); return -1; } + + datas->cstates[cpu].current_speed = freq; return cpu_change_pstate(datas, cpu, freq, time); } -- 1.9.1

8 years, 10 months

[PATCH rt-app v2 00/20] fixes of rt-app

by pi-cheng.chen

This patchset includes fixes/changes that have been done. These patches mainly fixed some typos or moves code but should not change the behavior of rt-app. changes from v1: - split style fix patches in smaller ones - clarify some changelogs - remove patches not suitable for this patchset Those patches are also found in the branch: https://git.linaro.org/people/picheng.chen/rt-app.git fixes_v2 Chris Muller (1): Update thread name Vincent Guittot (10): fix deadline print format consolidate trace and debug point update .gitignore fix inconsistency in delay unit fix cpu affinity string info deadline: set deadline field to deadline parameter reorder the start sequence of threads remove the yaml example as we don't support it remove useless json_object_put rt-app: remove use of deprecated json interface pi-cheng.chen (9): remove useless space and add blank lines to make the code more readable fix some comments align parameters and indents some style fixes Rename variable to improve readability do not sleep if we have run longer than expected fix debugfs path remove unused function add missed code snip to get deadline parameter .gitignore | 8 ++ doc/taskset.yml | 53 ------------- src/rt-app.c | 195 +++++++++++++++++++++++++++------------------- src/rt-app_args.c | 57 +++++++------- src/rt-app_parse_config.c | 49 +++++++----- src/rt-app_utils.c | 3 + 6 files changed, 185 insertions(+), 180 deletions(-) delete mode 100644 doc/taskset.yml -- 1.9.1

8 years, 10 months

[PATCH] [PATCH] measure the efficiency of cpufreq governors

by Xunlei Pang

From: Xunlei Pang <pang.xunlei(a)linaro.org> DVFS adds a latency in the execution of task because of the time to decide to move at max freq. We need to measure this latency and check that the governor stays in an acceptable range. When workgen runs a json file, a log file is created for each thread. This log file records the number of loop that has been executed and the duration for executing these loops (per phase). We can use these figures to evaluate to latency that is added by a cpufreq governor and its "performance efficiency". We use the run+sleep patten to do the measurement, for the run time per loop, the performance governor should run the expected duration as the CPU stays a max freq. At the opposite, the powersave governor will give use the longest duration (as it stays at lowest OPP). Other governor will be somewhere between the 2 previous duration as they will use several OPP and will go back to max frequency after a defined duration which depends on its monitoring period. The formula: duration of powersave gov - duration of the gov -------------------------------------------------------- x 100% duration of powersave gov - duration of performance gov will give the efficiency of the governor. 100% means as efficient as the perf governor and 0% means as efficient as the powersave governor. This patch offers json files and shell scripts to do the measurement, Usage: ./test.sh <cpus> <runtime> <sleeptime> cpus: number of cpus in the CPU0's frequency domain runtime: running time in ms per loop of the workload pattern sleeptime: sleeping time in ms per loop of the workload patten Example: "./test.sh 4 100 1000" means CPU0~CPU3 sharing frequency, "100ms run + 1000ms sleep" workload pattern. test result on my machine: ~#./test.sh 4 100 1000 Frequency domain CPU0~CPU3, run 100ms, sleep 1000ms: conservative efficiency: 28% ondemand efficiency: 95% NOTE: Make sure there are "sed", "cut", "grep", "rt-app" tools on your test machine, and run the script under root privilege. Signed-off-by: Xunlei Pang <pang.xunlei(a)linaro.org> --- .../cpufreq_governor_efficiency/calibration.json | 27 ++++++++ .../cpufreq_governor_efficiency/calibration.sh | 9 +++ doc/examples/cpufreq_governor_efficiency/dvfs.json | 27 ++++++++ doc/examples/cpufreq_governor_efficiency/dvfs.sh | 38 ++++++++++++ doc/examples/cpufreq_governor_efficiency/test.sh | 71 ++++++++++++++++++++++ 5 files changed, 172 insertions(+) create mode 100644 doc/examples/cpufreq_governor_efficiency/calibration.json create mode 100755 doc/examples/cpufreq_governor_efficiency/calibration.sh create mode 100644 doc/examples/cpufreq_governor_efficiency/dvfs.json create mode 100755 doc/examples/cpufreq_governor_efficiency/dvfs.sh create mode 100755 doc/examples/cpufreq_governor_efficiency/test.sh diff --git a/doc/examples/cpufreq_governor_efficiency/calibration.json b/doc/examples/cpufreq_governor_efficiency/calibration.json new file mode 100644 index 0000000..4377990 --- /dev/null +++ b/doc/examples/cpufreq_governor_efficiency/calibration.json @@ -0,0 +1,27 @@ +{ + "tasks" : { + "thread" : { + "instance" : 1, + "cpus" : [0], + "loop" : 1, + "phases" : { + "run" : { + "loop" : 1, + "run" : 200000, + }, + "sleep" : { + "loop" : 1, + "sleep" : 200000, + } + } + } + }, + "global" : { + "default_policy" : "SCHED_FIFO", + "calibration" : "CPU0", + "lock_pages" : true, + "ftrace" : true, + "logdir" : "./", + } +} + diff --git a/doc/examples/cpufreq_governor_efficiency/calibration.sh b/doc/examples/cpufreq_governor_efficiency/calibration.sh new file mode 100755 index 0000000..89fe5de --- /dev/null +++ b/doc/examples/cpufreq_governor_efficiency/calibration.sh @@ -0,0 +1,9 @@ +# !/bin/bash + +echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor + +sleep 1 + +pLoad=`rt-app calibration.json 2>&1 |grep pLoad |sed 's/.*= $.*$ns.*/\1/'` +sed 's/"calibration" : .*,/"calibration" : '$pLoad',/' -i dvfs.json + diff --git a/doc/examples/cpufreq_governor_efficiency/dvfs.json b/doc/examples/cpufreq_governor_efficiency/dvfs.json new file mode 100644 index 0000000..b413156 --- /dev/null +++ b/doc/examples/cpufreq_governor_efficiency/dvfs.json @@ -0,0 +1,27 @@ +{ + "tasks" : { + "thread" : { + "instance" : 1, + "cpus" : [0], + "loop" : 5, + "phases" : { + "running" : { + "loop" : 1, + "run" : 100000, + }, + "sleeping" : { + "loop" : 1, + "sleep" : 1000000, + } + } + } + }, + "global" : { + "default_policy" : "SCHED_OTHER", + "calibration" : 90, + "lock_pages" : true, + "ftrace" : true, + "logdir" : "./", + } +} + diff --git a/doc/examples/cpufreq_governor_efficiency/dvfs.sh b/doc/examples/cpufreq_governor_efficiency/dvfs.sh new file mode 100755 index 0000000..1772041 --- /dev/null +++ b/doc/examples/cpufreq_governor_efficiency/dvfs.sh @@ -0,0 +1,38 @@ +# !/bin/bash + +#echo $1 $2 $3 + +if [ $1 ] && [ $2 ] ; then + for i in `seq 0 1 $[$2-1]` + do + echo $1 > /sys/devices/system/cpu/cpu$i/cpufreq/scaling_governor + #cat /sys/devices/system/cpu/cpu$i/cpufreq/scaling_governor + done + + sleep 3 +fi + +if [ $3 ] ; then + sed 's/"run" : .*,/"run" : '$3',/' -i dvfs.json +fi + +if [ $4 ] ; then + sed 's/"sleep" : .*,/"sleep" : '$4',/' -i dvfs.json +fi + +#cat dvfs.json + +rt-app dvfs.json 2> /dev/null + +if [ $1 ] ; then + mv rt-app-thread-0.log rt-app_$1_run$3us_sleep$4us.log + + declare -i sum + sum=0 + for i in `cat rt-app_$1_run$3us_sleep$4us.log | sed '1~2!d' | sed '1d' |cut -d " " -f 3`; + do sum=sum+$i + done + sum=sum/5 + echo $sum +fi + diff --git a/doc/examples/cpufreq_governor_efficiency/test.sh b/doc/examples/cpufreq_governor_efficiency/test.sh new file mode 100755 index 0000000..6f41a1b --- /dev/null +++ b/doc/examples/cpufreq_governor_efficiency/test.sh @@ -0,0 +1,71 @@ +# !/bin/bash + +function set_calibration +{ + calibration.sh +} + +function test_efficiency +{ + declare -i performance + declare -i powersave + declare -i conservative + declare -i ondemand + declare -i denominator + declare -i numerator + + FILENAME="results_$RANDOM$$.txt" + + dvfs.sh performance $1 $2 $3> $FILENAME + dvfs.sh powersave $1 $2 $3 >> $FILENAME + dvfs.sh conservative $1 $2 $3 >> $FILENAME + dvfs.sh ondemand $1 $2 $3 >> $FILENAME + + performance=`cat $FILENAME |sed -n '1p'` + powersave=`cat $FILENAME |sed -n '2p'` + conservative=`cat $FILENAME |sed -n '3p'` + ondemand=`cat $FILENAME |sed -n '4p'` + + rm -f $FILENAME + + denominator=$powersave-$performance + numerator=($powersave-$conservative)*100 + + if [ $denominator -le 0 ] ; then + echo "Probably not input all the cpus in the same frequncy domain" + exit + fi + + if [ $numerator -lt 0 ] ; then + numerator=0 + fi + + conservative=$numerator/$denominator + echo "conservative efficiency: $conservative%" + + numerator=($powersave-$ondemand)*100 + if [ $numerator -lt 0 ] ; then + numerator=0 + fi + + ondemand=$numerator/$denominator + echo -e "ondemand efficiency: $ondemand%\n" +} + +if [ $# -lt 3 ]; then + echo "Usage: ./test.sh <cpus> <runtime> <sleeptime>" + echo "cpus: number of cpus in the CPU0's frequency domain" + echo "runtime: running time in ms per loop of the workload pattern" + echo "sleeptime: sleeping time in ms per loop of the workload patten" + echo -e "\nExample: \n\"./test.sh 4 100 1000\" means\nCPU0~CPU3 sharing frequency, \"100ms run + 1000ms sleep\" workload pattern.\n" + exit +fi + +echo "Frequency domain CPU0~CPU$[$1-1], run $2ms, sleep $3ms:" + +PATH=$PATH:. +set_calibration +test_efficiency $1 $[$2*1000] $[$3*1000] + +sleep 5 + -- 1.9.1

8 years, 10 months

[PATCH] rt-app: add a template file

by Vincent Guittot

add a template.json file that can be used by tune_json.py to create use cases with various type a load Signed-off-by: Vincent Guittot <vincent.guittot(a)linaro.org> --- doc/examples/template.json | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 doc/examples/template.json diff --git a/doc/examples/template.json b/doc/examples/template.json new file mode 100644 index 0000000..5ed3215 --- /dev/null +++ b/doc/examples/template.json @@ -0,0 +1,28 @@ +{ + /* + * Simple use case which creates 10% load + * for 6 seconds. + * A "sleep" : 0 has been added so the file can be used by tune_json.py to + * use a sleep event instead of the timer. In this latter case, you need + * to set the timer's period to 0 + */ + "tasks" : { + "thread0" : { + "instance" : 1, + "loop" : -1, + "run" : 10000, + "sleep" : 0, + "timer" : { "ref" : "unique", "period" : 100000 } + } + }, + "global" : { + "duration" : 6, + "calibration" : "CPU0", + "default_policy" : "SCHED_OTHER", + "pi_enabled" : false, + "lock_pages" : false, + "logdir" : "./", + "log_basename" : "rt-app2", + "gnuplot" : true + } +} -- 1.9.1

8 years, 10 months

Re: [Sched-tools] [PATCH v2] rt-app: Add IO-bounded and memory-bounded events.

by Vincent Guittot

with the new list @ On 29 May 2015 at 11:19, Vincent Guittot <vincent.guittot(a)linaro.org> wrote: > Hi Pi-cheng, > > On 16 December 2014 at 04:57, pi-cheng.chen <pi-cheng.chen(a)linaro.org> wrote: >> Add 2 new kind of event for running a memory or a io bounded load. >> "mem" name for a load is memory bounded, and "iorun" name for a load is io >> bounded. The default file to be written to create the load is /dev/null and >> the device/file could be specified with "io_device" key in "global" section. >> The size of per-thread memory buffer to create IO/memory load could also be >> specified with "mem_buffer_size" in the same section. >> >> E.g. >> "tasks" : { >> "thread0" : >> { "sleep" : 1000, "run" : 100, "mem" : 1000, "sleep" 10000, "iorun" : 1000 } >> }, >> "global" : { "io_device" : "/dev/ttyS0", "mem_buffer_size" : 1048576 } >> >> changes v1 to v2: >> Allocate per-thread memory buffer. Add "mem_buffer_size" in global section to >> set the size of memory buffer to be allocated. And fix possible buffer overrun >> when creating IO-bounded load. >> >> Signed-off-by: pi-cheng.chen <pi-cheng.chen(a)linaro.org> >> --- >> src/rt-app.c | 104 +++++++++++++++++++++++++++++++++++++++++++++- >> src/rt-app_parse_config.c | 27 ++++++++++++ >> src/rt-app_types.h | 11 +++++ >> 3 files changed, 140 insertions(+), 2 deletions(-) >> >> diff --git a/src/rt-app.c b/src/rt-app.c >> index 3cd601d..16bbe48 100644 >> --- a/src/rt-app.c >> +++ b/src/rt-app.c >> @@ -33,7 +33,9 @@ static volatile int continue_running; >> static pthread_t *threads; >> static int nthreads; >> static int p_load; >> +static int io_fd; >> rtapp_options_t opts; >> +static iomem_buf_t *iomem_buf; > > You should better create a iomem_buf_t iomem_buf field into the thread > struct so you don't have to allocate additionnal array beside > >> >> static ftrace_data_t ft_data = { >> .debugfs = "/sys/kernel/debug", >> @@ -110,8 +112,57 @@ static inline loadwait(unsigned long exec) >> return load_count; >> } >> >> +static void ioload(unsigned long count, iomem_buf_t *iomem) >> +{ >> + ssize_t ret; >> + >> + while (count != 0) { >> + unsigned long size; >> + >> + if (count > iomem->size) >> + size = iomem->size; >> + else >> + size = count; > > Why can't we loop on the buffer and write more than it's size in the io ? > >> + >> + if (size > (iomem->size - iomem->pos)) >> + size = iomem->size - iomem->pos; >> + >> + ret = write(io_fd, iomem->buf + iomem->pos, size); >> + if (ret == -1) { >> + perror("write"); >> + return; >> + } >> + count -= ret; >> + iomem->pos += ret; >> + if (iomem->pos >= iomem->size) >> + iomem->pos -= iomem->size; >> + } >> +} >> + >> +static void memload(unsigned long count, iomem_buf_t *iomem) >> +{ >> + while (count > 0) { >> + unsigned long size; >> + >> + if (count > iomem->size) >> + size = iomem->size; >> + else >> + size = count; > > same question as for io > >> + >> + if (size > (iomem->size - iomem->pos)) >> + size = iomem->size - iomem->pos; >> + >> + memset(iomem->buf + iomem->pos, 0, size); >> + count -= size; >> + iomem->pos += size; >> + if (iomem->pos >= iomem->size) >> + iomem->pos -= iomem->size; >> + } >> +} >> + >> static int run_event(event_data_t *event, int dry_run, >> - unsigned long *perf, unsigned long *duration, rtapp_resource_t *resources) >> + unsigned long *perf, unsigned long *duration, >> + rtapp_resource_t *resources, int ind) >> { >> rtapp_resource_t *rdata = &(resources[event->res]); >> rtapp_resource_t *ddata = &(resources[event->dep]); >> @@ -196,6 +247,18 @@ static int run_event(event_data_t *event, int dry_run, >> pthread_mutex_unlock(&(ddata->res.mtx.obj)); >> break; >> } >> + case rtapp_mem: >> + { >> + log_debug("mem %d", event->count); >> + memload(event->count, &iomem_buf[ind]); >> + } >> + break; >> + case rtapp_iorun: >> + { >> + log_debug("iorun %d", event->count); >> + ioload(event->count, &iomem_buf[ind]); >> + } >> + break; >> } >> >> return lock; >> @@ -218,7 +281,8 @@ int run(int ind, event_data_t *events, >> log_ftrace(ft_data.marker_fd, >> "[%d] locking %d", >> ind, events[i].type); >> - lock += run_event(&events[i], !continue_running, &perf, duration, resources); >> + lock += run_event(&events[i], !continue_running, &perf, >> + duration, resources, ind); >> } >> >> return perf; >> @@ -488,6 +552,35 @@ int main(int argc, char* argv[]) >> >> parse_command_line(argc, argv, &opts); >> >> + /* >> + * allocate per-thread memory buffers for memory-bound and IO-bound >> + * busy loops >> + */ >> + iomem_buf = malloc(sizeof(iomem_buf_t) * opts.nthreads); >> + if (!iomem_buf) { >> + log_error("Cannot allocate memory for IO/memory buffer struct"); >> + exit(EXIT_FAILURE); >> + } >> + for (i = 0; i < opts.nthreads; i++) { >> + iomem_buf_t *iomem = &iomem_buf[i]; >> + >> + iomem->size = opts.mem_buffer_size; >> + iomem->buf = malloc(iomem->size); >> + if (!iomem->buf) { >> + log_error("Cannot allocate memory for memory-bounded" >> + "and IO-bounded busy loops"); >> + exit(EXIT_FAILURE); >> + } >> + iomem->pos = 0; >> + } >> + >> + /* open file for IO-bound busy loops */ >> + io_fd = open(opts.io_device, O_CREAT | O_WRONLY, 0644); >> + if (io_fd < 0) { >> + log_error("Cannot open io_device file %s", opts.io_device); >> + exit(EXIT_FAILURE); >> + } >> + >> /* allocated threads */ >> nthreads = opts.nthreads; >> threads = malloc(nthreads * sizeof(pthread_t)); >> @@ -713,6 +806,13 @@ int main(int argc, char* argv[]) >> close(ft_data.trace_fd); >> close(ft_data.marker_fd); >> } >> + >> + close(io_fd); >> + >> + for (i = 0; i < nthreads; i++) >> + free(iomem_buf[i].buf); >> + free(iomem_buf); >> + >> exit(EXIT_SUCCESS); >> >> >> diff --git a/src/rt-app_parse_config.c b/src/rt-app_parse_config.c >> index e062f79..9bdf38a 100644 >> --- a/src/rt-app_parse_config.c >> +++ b/src/rt-app_parse_config.c >> @@ -27,6 +27,7 @@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. >> #define PIN2 PIN" " >> #define PIN3 PIN2" " >> #define JSON_FILE_BUF_SIZE 4096 >> +#define DEFAULT_MEM_BUF_SIZE (4 * 1024 * 1024) >> >> /* redefine foreach as in <json/json_object.h> but to be ANSI >> * compatible */ >> @@ -320,6 +321,22 @@ parse_thread_event_data(char *name, struct json_object *obj, >> return; >> } >> >> + if (!strncmp(name, "mem", strlen("mem")) || >> + !strncmp(name, "iorun", strlen("iorun"))) { >> + if (!json_object_is_type(obj, json_type_int)) >> + goto unknown_event; >> + >> + data->count = json_object_get_int(obj); >> + >> + if (!strncmp(name, "mem", strlen("mem"))) >> + data->type = rtapp_mem; >> + else >> + data->type = rtapp_iorun; >> + >> + log_info(PIN2 "type %d count %d", data->type, data->count); >> + return; >> + } >> + >> if (!strncmp(name, "lock", strlen("lock")) || >> !strncmp(name, "unlock", strlen("unlock"))) { >> >> @@ -493,6 +510,10 @@ obj_is_event(char *name) >> return rtapp_suspend; >> if (!strncmp(name, "resume", strlen("resume"))) >> return rtapp_resume; >> + if (!strncmp(name, "mem", strlen("mem"))) >> + return rtapp_mem; >> + if (!strncmp(name, "iorun", strlen("iorun"))) >> + return rtapp_iorun; >> >> return 0; >> } >> @@ -677,6 +698,8 @@ parse_global(struct json_object *global, rtapp_options_t *opts) >> opts->logbasename = strdup("rt-app"); >> opts->ftrace = 0; >> opts->pi_enabled = 0; >> + opts->io_device = strdup("/dev/null"); >> + opts->mem_buffer_size = DEFAULT_MEM_BUF_SIZE; >> return; >> } >> >> @@ -719,6 +742,10 @@ parse_global(struct json_object *global, rtapp_options_t *opts) >> TRUE, "rt-app"); >> opts->ftrace = get_bool_value_from(global, "ftrace", TRUE, 0); >> opts->pi_enabled = get_bool_value_from(global, "pi_enabled", TRUE, 0); >> + opts->io_device = get_string_value_from(global, "io_device", TRUE, >> + "/dev/null"); >> + opts->mem_buffer_size = get_int_value_from(global, "mem_buffer_size", >> + TRUE, DEFAULT_MEM_BUF_SIZE); >> >> } >> >> diff --git a/src/rt-app_types.h b/src/rt-app_types.h >> index cefb3a6..d230d45 100644 >> --- a/src/rt-app_types.h >> +++ b/src/rt-app_types.h >> @@ -65,6 +65,8 @@ typedef enum resource_t >> rtapp_timer, >> rtapp_suspend, >> rtapp_resume, >> + rtapp_mem, >> + rtapp_iorun, >> } resource_t; >> >> struct _rtapp_mutex { >> @@ -103,6 +105,7 @@ typedef struct _event_data_t { >> int res; >> int dep; >> int duration; >> + int count; >> } event_data_t; >> >> typedef struct _phase_data_t { >> @@ -165,6 +168,8 @@ typedef struct _rtapp_options_t { >> >> int ftrace; >> int die_on_dmiss; >> + char *io_device; >> + int mem_buffer_size; >> } rtapp_options_t; >> >> typedef struct _timing_point_t { >> @@ -177,4 +182,10 @@ typedef struct _timing_point_t { >> __u64 rel_start_time; >> } timing_point_t; >> >> +typedef struct { >> + char *buf; >> + int pos; >> + int size; >> +} iomem_buf_t; >> + >> #endif // _RTAPP_TYPES_H_ >> -- >> 1.9.1 >>

8 years, 10 months

[PATCH] rt-app: fix calibration issue on mt8173

by Vincent Guittot

Calibration sequence fails to get the right ns per loop value when the calibration is done on the A57 cluster of the mt8173evb. A new calibration has been added that adds a sleep period between each each calibration loop. This idle phase enable rt-app to get the to get the right ns per loop value for such kind of HW. The calibration sequence finally uses the lowest value of the calibration methods which match with the highest compute capacity Reported-by: Koan-Sin Tan <freedom.tan(a)linaro.org> Signed-off-by: Vincent Guittot <vincent.guittot(a)linaro.org> --- src/rt-app.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 75 insertions(+), 5 deletions(-) diff --git a/src/rt-app.c b/src/rt-app.c index 97aee0f..37e9892 100644 --- a/src/rt-app.c +++ b/src/rt-app.c @@ -62,12 +62,14 @@ void waste_cpu_cycles(int load_loops) } /* -* calibrate_cpu_cycles() -* collects the time that waste_cycles runs. +* calibrate_cpu_cycles_1() +* 1st method to calibrate the ns per loop value +* We alternate idle period and run period in order to not trig some hw +* protection mechanism like thermal mitgation */ -int calibrate_cpu_cycles(int clock) +int calibrate_cpu_cycles_1(int clock) { - struct timespec start, stop; + struct timespec start, stop, sleep; int max_load_loop = 10000; unsigned int diff; int nsec_per_loop, avg_per_loop = 0; @@ -75,6 +77,10 @@ int calibrate_cpu_cycles(int clock) while (cal_trial) { cal_trial--; + sleep.tv_sec = 1; + sleep.tv_nsec = 0; + + clock_nanosleep(CLOCK_MONOTONIC, 0, &sleep, NULL); clock_gettime(clock, &start); waste_cpu_cycles(max_load_loop); @@ -100,6 +106,69 @@ int calibrate_cpu_cycles(int clock) return 0; } +/* +* calibrate_cpu_cycles_2() +* 2nd method to calibrate the ns per loop value +* We continously runs something to ensure that CPU is set to max freq by the +* governor +*/ +int calibrate_cpu_cycles_2(int clock) +{ + struct timespec start, stop, sleep; + int max_load_loop = 10000; + unsigned int diff; + int nsec_per_loop, avg_per_loop = 0; + int ret, cal_trial = 1000; + + while (cal_trial) { + cal_trial--; + + clock_gettime(clock, &start); + waste_cpu_cycles(max_load_loop); + clock_gettime(clock, &stop); + + diff = (int)timespec_sub_to_ns(&stop, &start); + nsec_per_loop = diff / max_load_loop; + avg_per_loop = (avg_per_loop + nsec_per_loop) >> 1; + + /* collect a critical mass of samples.*/ + if ((abs(nsec_per_loop - avg_per_loop) * 50) < avg_per_loop) + return avg_per_loop; + + /* + * use several loop duration in order to be sure to not + * fall into a specific platform loop duration + *(like the cpufreq period) + */ + /*randomize the number of loops and recheck 1000 times*/ + max_load_loop += 33333; + max_load_loop %= 1000000; + } + return 0; +} + +/* +* calibrate_cpu_cycles() +* Use several methods to calibrate the ns per loop and get the min value which +* correspond to the highest achievable compute capacity. +*/ +int calibrate_cpu_cycles(int clock) +{ + int calib1, calib2; + + /* Run 1st method */ + calib1 = calibrate_cpu_cycles_1(clock); + + /* Run 2nd method */ + calib2 = calibrate_cpu_cycles_2(clock); + + if (calib1 < calib2) + return calib1; + else + return calib2; + +} + static inline loadwait(unsigned long exec) { unsigned long load_count; @@ -531,13 +600,14 @@ int main(int argc, char* argv[]) /* Needs to calibrate 'calib_cpu' core */ if (opts.calib_ns_per_loop == 0) { + log_notice("Calibrate ns per loop"); cpu_set_t calib_set; CPU_ZERO(&calib_set); CPU_SET(opts.calib_cpu, &calib_set); sched_getaffinity(0, sizeof(cpu_set_t), &orig_set); sched_setaffinity(0, sizeof(cpu_set_t), &calib_set); - p_load = calibrate_cpu_cycles(CLOCK_THREAD_CPUTIME_ID); + p_load = calibrate_cpu_cycles(CLOCK_MONOTONIC); sched_setaffinity(0, sizeof(cpu_set_t), &orig_set); log_notice("pLoad = %dns : calib_cpu %d", p_load, opts.calib_cpu); } else { -- 1.9.1

8 years, 11 months

[PATCH] Add a script to tune parameters in json file.

by pi-cheng.chen

This scripts strips all comments in the input JSON file, modifies the parameters according to commnad line arguments, and write the content to a new JSON file. Signed-off-by: pi-cheng.chen <pi-cheng.chen(a)linaro.org> --- doc/tune_json.py | 131 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) create mode 100755 doc/tune_json.py diff --git a/doc/tune_json.py b/doc/tune_json.py new file mode 100755 index 0000000..7e2ca82 --- /dev/null +++ b/doc/tune_json.py @@ -0,0 +1,131 @@ +#!/usr/bin/env python + +import argparse +import collections +import json +import os +import re +import shutil +import sys +import tempfile + + +def find_dict_by_key(doc, key): + if key in doc and type(doc[key]) is collections.OrderedDict: + return doc[key] + + for k in doc: + if type(doc[k]) is collections.OrderedDict: + return find_dict_by_key(doc[k], key) + + +def dict_find_and_replace_value(dic, key, val): + for k in dic: + if type(dic[k]) is collections.OrderedDict: + dict_find_and_replace_value(dic[k], key, val) + if k == key: + dic[k] = val + + +def dict_of_loading(dic): + if not 'run' in dic: + return False, None + + for k in dic: + if 'timer' in k and 'period' in dic[k]: + return True, k + else: + return False, None + + +def calculate_and_update_loading(dic, loading): + of_loading, timer_id = dict_of_loading(dic) + + if of_loading: + period = dic[timer_id]['period'] + run = period * loading / 100 + dic['run'] = run + + for k in dic: + if type(dic[k]) is collections.OrderedDict: + calculate_and_update_loading(dic[k], loading) + + +# strip comments in json file and load the file as a dict +def load_json_file(filename): + try: + f = open(filename, 'r') + except: + print 'ERROR: Unable to open %s' %filename + sys.exit(2) + + comment_re = re.compile( + '(^)?[^\S\n]*/(?:\*(.*?)\*/[^\S\n]*|/[^\n]*)($)?', + re.DOTALL | re.MULTILINE) + + content = ''.join(f.readlines()) + f.close() + + match = comment_re.search(content) + while match: + content = content[:match.start()] + content[match.end():] + match = comment_re.search(content) + + return json.JSONDecoder(object_pairs_hook=collections.OrderedDict).decode(content) + + +def dump_json_file(doc, outfile): + tmp = tempfile.NamedTemporaryFile(delete=False) + json.dump(doc, tmp, indent=4, sort_keys=False) + tmp.close() + + shutil.move(tmp.name, outfile) + + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + + parser.add_argument('-f', '--file', dest='infile', default='', help='input json filename') + parser.add_argument('-o', '--out', dest='outfile', default='workload.json', help='output json filename'); + parser.add_argument('--instance', default=0, type=int, help='number of thread instance') + parser.add_argument('--period', default=0, type=int, help='period of each thread/phase (ms)') + parser.add_argument('--run', default=0, type=int, help='run time of each thread/phase (ms)') + parser.add_argument('--sleep', default=0, type=int, help='sleep time of each thread/phase (ms)') + parser.add_argument('--loop', default=0,type=int, help='loop count of each thread/phase (-1 as infinite loop)') + parser.add_argument('--loading', default=0, type=int, help='loading of each thread (%%)') + parser.add_argument('--key', type=str, help='the key id of thread/phase in which the parameters will be changed') + + args = parser.parse_args() + + if not os.path.isfile(args.infile): + print 'ERROR: input file %s does not exist\n' %args.infile + parser.print_help() + sys.exit(2) + + doc = target = load_json_file(args.infile) + + if args.key: + target = find_dict_by_key(doc, args.key) + if not target: + print 'ERROR: key id %s is not found' %args.key + sys.exit(2) + + if args.instance > 0: + dict_find_and_replace_value(target, 'instance', args.instance) + + if args.period > 0: + dict_find_and_replace_value(target, 'period', args.period * 1000) + + if args.run > 0: + dict_find_and_replace_value(target, 'run', args.run * 1000) + + if args.sleep > 0: + dict_find_and_replace_value(target, 'sleep', args.sleep * 1000) + + if args.loop > 0 or args.loop == -1: + dict_find_and_replace_value(target, 'loop', args.loop) + + if args.loading > 0: + calculate_and_update_loading(target, args.loading); + + dump_json_file(doc, args.outfile) -- 1.9.1

8 years, 11 months

[PATCH v2] idlestat: add regression test functions for idlestat

by Zhaoyang Huang

This commit add regression test for idlestat and add mmap function for mapping the trace file to process memory.Please find bellowing message for how to use. eg: import the mytrace file and compare it with previous mytrace_old file to see if they match each other make reg_trace eg: import mytrace file and export the report file as myreport_new. compare the myreport_new with myreport_old to see if they match with each other make reg_output eg: set the store format of ftrace as bin and mmap it to userspace ./idlestat --trace -f ./mytrace -t 10 -m --- Makefile | 5 ++ idlestat.c | 211 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- idlestat.h | 7 +- topology.c | 19 ++++++ topology.h | 1 + trace.h | 1 + utils.c | 12 ++++ utils.h | 1 + 8 files changed, 255 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 42f16d7..1eb8f68 100644 --- a/Makefile +++ b/Makefile @@ -47,5 +47,10 @@ install: idlestat idlestat.1 install -D -t /usr/local/bin idlestat install -D -t /usr/local/man/man1 idlestat.1 +reg_trace: idlestat + ./idlestat --regression -f ./mytrace -b ./mytrace_old -T +reg_output: idlestat + ./idlestat --regression -f ./mytrace -p -c -w -o ./myreport_new -b ./myreport_old -O + rm ./myreport_new clean: rm -f $(OBJS) idlestat diff --git a/idlestat.c b/idlestat.c index 4d773f4..d84fae5 100644 --- a/idlestat.c +++ b/idlestat.c @@ -41,6 +41,13 @@ #ifdef ANDROID #include <libgen.h> #endif +#include <sys/mman.h> /* for mmap and munmap */ +#include <sys/types.h> /* for open */ +#include <sys/stat.h> /* for open */ +#include <fcntl.h> /* for open */ +#include <unistd.h> /* for lseek and write */ +#include <stdio.h> +#include <string.h> /* for memcpy */ #include "idlestat.h" #include "utils.h" @@ -1074,6 +1081,7 @@ int getoptions(int argc, char *argv[], struct program_options *options) struct option long_options[] = { { "trace", no_argument, &options->mode, TRACE }, { "import", no_argument, &options->mode, IMPORT }, + { "regression", no_argument, &options->mode, REGRESSION }, { "baseline-trace", required_argument, NULL, 'b' }, { "idle", no_argument, NULL, 'c' }, { "energy-model-file", required_argument, NULL, 'e' }, @@ -1090,6 +1098,9 @@ int getoptions(int argc, char *argv[], struct program_options *options) { "poll-interval", required_argument, NULL, 'I' }, { "buffer-size", required_argument, NULL, 'S' }, { "version", no_argument, NULL, 'V' }, + { "mmap", optional_argument, NULL, 'm' }, + { "trace file compare", no_argument, NULL, 'T' }, + { "output file compare", no_argument, NULL, 'O' }, { 0, 0, 0, 0 } }; int c; @@ -1103,7 +1114,7 @@ int getoptions(int argc, char *argv[], struct program_options *options) int optindex = 0; - c = getopt_long(argc, argv, ":b:ce:f:ho:pr:t:vwBCI:S:V", + c = getopt_long(argc, argv, ":b:ce:f:ho:pr:t:vwBCI:S:VmTO", long_options, &optindex); if (c == -1) break; @@ -1174,6 +1185,15 @@ int getoptions(int argc, char *argv[], struct program_options *options) case 'S': options->tbs.percpu_buffer_size = atoi(optarg); break; + case 'm': + options->mmap_flag = true; + break; + case 'T': + options->tracefile_comp_flag = true; + break; + case 'O': + options->output_comp_flag = true; + break; case 0: /* getopt_long() set a variable, just keep going */ break; case ':': /* missing option argument */ @@ -1197,6 +1217,21 @@ int getoptions(int argc, char *argv[], struct program_options *options) return -1; } + if (options->mode == REGRESSION) { + if ((options->filename == NULL) + &&(options->outfilename == NULL)) { + fprintf(stderr, "expected file name for regression test\n"); + return -1; + } + if (options->filename && bad_filename(options->filename)) + return -1; + + if (options->outfilename && bad_filename(options->outfilename)) + return -1; + + return optind; + } + if (NULL == options->filename) { fprintf(stderr, "expected -f <trace filename>\n"); return -1; @@ -1401,6 +1436,136 @@ static int execute(int argc, char *argv[], char *const envp[], return -1; } +int binary_compare(struct program_options * options,char *const envp[]) +{ + char * argv[4]; + int ret = 0; + + argv[0] = "diff"; + argv[1] = options->filename; + argv[2] = options->baseline_filename; + argv[3] = "-s"; + + ret = execvpe(argv[0], argv, envp); + if(ret){ + perror("execvpe"); + printf("binary compare error\n"); + } + +} + +int output_compare(struct program_options * options,char *const envp[]) +{ + struct report_ops *output_handler = NULL; + void *report_data = NULL; + struct cpu_topology *cpu_topo = NULL; + struct cpuidle_datas *datas; + char * tmp_filename; + int ret = 0; + /* Load the idle states information */ + datas = idlestat_load(options->filename); + + if (is_err(datas)) + return 1; + + cpu_topo = datas->topo; + + output_handler = get_report_ops(options->report_type_name); + if (is_err(output_handler)) + return 1; + + if (output_handler->open_report_file(options->outfilename, report_data)) + return 1; + + if (options->display & IDLE_DISPLAY) { + output_handler->cstate_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_cstates, cpu_topo, 1); + output_handler->cstate_table_footer(report_data); + } + + if (options->display & FREQUENCY_DISPLAY) { + output_handler->pstate_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_pstates, cpu_topo, 0); + output_handler->pstate_table_footer(report_data); + } + + if (options->display & WAKEUP_DISPLAY) { + output_handler->wakeup_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_wakeup, cpu_topo, 1); + output_handler->wakeup_table_footer(report_data); + } + + restore_stdout(); + + /*backup the filename*/ + tmp_filename = options->filename; + + /*compare the new output file with the old one*/ + options->filename = options->outfilename; + ret = binary_compare(options,envp); + + if(ret) + printf("output file comparsion of %s and %s failed\n",options->filename,options->baseline_filename); + else + printf("[IDLE_STAT REGRESSION TEST] <output_compare success>\n"); + /*restore the file name*/ + options->filename = tmp_filename; + + + return ret; + +} + +int regression(struct program_options * options,char *const envp[]) +{ + struct cpuidle_datas *datas; + struct cpu_topology *cpu_topo = NULL; + struct report_ops *output_handler = NULL; + int ret = 0; + + char topo_info[512]; + + output_handler = get_report_ops(options->report_type_name); + if (is_err(output_handler)) + return 1; + + if (output_handler->check_options && + output_handler->check_options(options) < 0) + return 1; + + /* Load the idle states information */ + datas = idlestat_load(options->filename); + + if (is_err(datas)){ + fprintf(stderr, "[IDLE_STAT REGRESSION TEST] <trace file import failed>\n"); + ret = -1; + } + else + printf("[IDLE_STAT REGRESSION TEST] <trace file import success>\n"); + + cpu_topo = read_sysfs_cpu_topo(); + if (is_err(cpu_topo)) { + fprintf(stderr, "Failed to read CPU topology info from" + " sysfs.\n"); + ret = -1; + } + else{ + outstr_topo_info(topo_info,cpu_topo); + printf("%s",topo_info); + printf("[IDLE_STAT REGRESSION TEST] <CPU topology info read success>\n"); + } + + if(options->tracefile_comp_flag) + ret = binary_compare(options, envp); + if(options->output_comp_flag) + ret = output_compare(options, envp); + + return ret; +} + int main(int argc, char *argv[], char *const envp[]) { struct cpuidle_datas *datas; @@ -1414,10 +1579,24 @@ int main(int argc, char *argv[], char *const envp[]) struct trace_options *saved_trace_options = NULL; void *report_data = NULL; + int fd; + int flength; + struct stat statbuff; + args = getoptions(argc, argv, &options); if (args <= 0) return 1; + if (options.mode == REGRESSION){ + if (regression(&options,envp)){ + printf("regression failed\n"); + } + else{ + printf("regression success\n"); + } + return 0; + } + /* Tracing requires manipulation of some files only accessible * to root */ if ((options.mode == TRACE) && getuid()) { @@ -1497,6 +1676,16 @@ int main(int argc, char *argv[], char *const envp[]) initp = build_init_pstates(cpu_topo); + /* + set the trace file format to bin + */ + if(options.mmap_flag){ + FILE * file; + file = fopen(TRACE_OPTIONS, "r+"); + perror(__func__); + printf("%s open %p\n",TRACE_OPTIONS,file); + store_line("bin",(void *)file); + } /* Start the recording */ if (idlestat_trace_enable(true)) goto err_restore_trace_options; @@ -1532,6 +1721,26 @@ int main(int argc, char *argv[], char *const envp[]) initp, cpu_topo)) goto err_restore_trace_options; + if(options.mmap_flag){ + fd = open(options.filename, O_RDONLY); + if((fd == -1) || fstat(fd, &statbuff)){ + perror(__func__); + printf("[idlestat] file length get failed\n"); + close(fd); + return 1; + } + flength = statbuff.st_size; + printf("[idlestat]: mmaped file is %s fd %x length %d\n",options.filename,fd,flength); + options.mapped_mem = mmap(NULL, flength, PROT_READ,MAP_PRIVATE,fd,0); + if((int)(void *)options.mapped_mem == (int)-1){ + perror(__func__); + close(fd); + return 1; + } + //printf("%s\n", options.mapped_mem); + close(fd); + } + /* Restore original kernel ftrace options */ if (idlestat_restore_trace_options(saved_trace_options)) return 1; diff --git a/idlestat.h b/idlestat.h index e030f6a..1ca9748 100644 --- a/idlestat.h +++ b/idlestat.h @@ -121,7 +121,8 @@ struct cpuidle_datas { enum modes { TRACE = 0, - IMPORT + IMPORT, + REGRESSION }; struct trace_buffer_settings { @@ -140,6 +141,10 @@ struct program_options { int verbose; char *energy_model_filename; char *report_type_name; + bool mmap_flag; + bool tracefile_comp_flag; + bool output_comp_flag; + char * mapped_mem; }; #define IDLE_DISPLAY 0x1 diff --git a/topology.c b/topology.c index 39b07bd..ee00bfe 100644 --- a/topology.c +++ b/topology.c @@ -280,6 +280,25 @@ int outfile_topo_info(FILE *f, struct cpu_topology *topo_list) return 0; } +int outstr_topo_info(char *s, struct cpu_topology *topo_list) +{ + struct cpu_physical *s_phy; + struct cpu_core *s_core; + struct cpu_cpu *s_cpu; + + list_for_each_entry(s_phy, &topo_list->physical_head, list_physical) { + sprintf(s, "cluster%c:\n", s_phy->physical_id + 'A'); + list_for_each_entry(s_core, &s_phy->core_head, list_core) { + sprintf(s, "\tcore%d\n", s_core->core_id); + list_for_each_entry(s_cpu, &s_core->cpu_head, list_cpu){ + sprintf(s, "\t\tcpu%d\n", s_cpu->cpu_id); + } + } + } + + return 0; +} + struct cpu_cpu *find_cpu_point(struct cpu_topology *topo_list, int cpuid) { struct cpu_physical *s_phy; diff --git a/topology.h b/topology.h index 84e5bc1..4c7964e 100644 --- a/topology.h +++ b/topology.h @@ -115,5 +115,6 @@ extern int core_get_highest_freq(struct cpu_core *core); core_get_highest_freq(cpu_to_core(cpuid, topo)) extern int setup_topo_states(struct cpuidle_datas *datas); +extern int outstr_topo_info(char *s, struct cpu_topology *topo_list); #endif diff --git a/trace.h b/trace.h index a2f5867..29b4d93 100644 --- a/trace.h +++ b/trace.h @@ -34,6 +34,7 @@ #define TRACE_FREE TRACE_PATH "/free_buffer" #define TRACE_FILE TRACE_PATH "/trace" #define TRACE_STAT_FILE TRACE_PATH "/per_cpu/cpu0/stats" +#define TRACE_OPTIONS TRACE_PATH "/trace_options" #define TRACE_IDLE_NRHITS_PER_SEC 10000 #define TRACE_IDLE_LENGTH 196 #define TRACE_CPUFREQ_NRHITS_PER_SEC 100 diff --git a/utils.c b/utils.c index 48be965..931829b 100644 --- a/utils.c +++ b/utils.c @@ -210,14 +210,17 @@ out_free: return ret; } +int std_fd; int redirect_stdout_to_file(const char *path) { int ret = 0; int fd; if (path) { + std_fd = dup(STDOUT_FILENO); fd = open(path, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR | S_IRGRP |S_IROTH); + if (fd < 0) { fprintf(stderr, "%s: failed to open '%s'\n", __func__, path); return -1; @@ -237,6 +240,15 @@ int redirect_stdout_to_file(const char *path) return 0; } +int restore_stdout() +{ + int ret = -1; + if(std_fd != NULL) + ret = dup2(std_fd,STDOUT_FILENO); + printf("%s %d \n",__func__,ret); + return ret; +} + void display_factored_time(double time, int align) { char buffer[128]; diff --git a/utils.h b/utils.h index ee7a9a2..6b8808c 100644 --- a/utils.h +++ b/utils.h @@ -49,5 +49,6 @@ extern int check_window_size(void); extern int error(const char *str); extern void *ptrerror(const char *str); extern int is_err(const void *ptr); +extern int restore_stdout(); #endif -- 1.7.9.5

8 years, 11 months

[PATCH] idlestat: add regression test functions for idlestat

by Zhaoyang Huang

This commit add regression test for idlestat.Please find bellowing message for how to use. eg: import the mytrace file and compare it with previous mytrace_old file to see if they match each other ./idlestat --regression -f ./mytrace -t 10 -p -c -w -b ./mytrace_old -T eg: import mytrace file and export the report file as myreport_new. compare the myreport_new with myreport_old to see if they match with each other ./idlestat --regression -f ./mytrace -t 10 -p -c -w -o ./myreport_new -b ./myreport_old -O eg: set the store format of ftrace as bin and mmap it to userspace ./idlestat --trace -f ./mytrace -t 10 -m Signed-off-by: Zhaoyang Huang <zhaoyang.huang(a)linaro.org> --- idlestat.c | 233 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- idlestat.h | 7 +- topology.c | 19 +++++ topology.h | 1 + trace.h | 1 + utils.c | 10 +++ utils.h | 1 + 7 files changed, 270 insertions(+), 2 deletions(-) diff --git a/idlestat.c b/idlestat.c index 4d773f4..cb481c9 100644 --- a/idlestat.c +++ b/idlestat.c @@ -41,6 +41,13 @@ #ifdef ANDROID #include <libgen.h> #endif +#include <sys/mman.h> /* for mmap and munmap */ +#include <sys/types.h> /* for open */ +#include <sys/stat.h> /* for open */ +#include <fcntl.h> /* for open */ +#include <unistd.h> /* for lseek and write */ +#include <stdio.h> +#include <string.h> /* for memcpy */ #include "idlestat.h" #include "utils.h" @@ -1074,6 +1081,7 @@ int getoptions(int argc, char *argv[], struct program_options *options) struct option long_options[] = { { "trace", no_argument, &options->mode, TRACE }, { "import", no_argument, &options->mode, IMPORT }, + { "regression", no_argument, &options->mode, REGRESSION }, { "baseline-trace", required_argument, NULL, 'b' }, { "idle", no_argument, NULL, 'c' }, { "energy-model-file", required_argument, NULL, 'e' }, @@ -1090,6 +1098,9 @@ int getoptions(int argc, char *argv[], struct program_options *options) { "poll-interval", required_argument, NULL, 'I' }, { "buffer-size", required_argument, NULL, 'S' }, { "version", no_argument, NULL, 'V' }, + { "mmap", optional_argument, NULL, 'm' }, + { "trace file compare", no_argument, NULL, 'T' }, + { "output file compare", no_argument, NULL, 'O' }, { 0, 0, 0, 0 } }; int c; @@ -1103,7 +1114,7 @@ int getoptions(int argc, char *argv[], struct program_options *options) int optindex = 0; - c = getopt_long(argc, argv, ":b:ce:f:ho:pr:t:vwBCI:S:V", + c = getopt_long(argc, argv, ":b:ce:f:ho:pr:t:vwBCI:S:VmTO", long_options, &optindex); if (c == -1) break; @@ -1174,6 +1185,15 @@ int getoptions(int argc, char *argv[], struct program_options *options) case 'S': options->tbs.percpu_buffer_size = atoi(optarg); break; + case 'm': + options->mmap_flag = true; + break; + case 'T': + options->tracefile_comp_flag = true; + break; + case 'O': + options->output_comp_flag = true; + break; case 0: /* getopt_long() set a variable, just keep going */ break; case ':': /* missing option argument */ @@ -1197,6 +1217,21 @@ int getoptions(int argc, char *argv[], struct program_options *options) return -1; } + if (options->mode == REGRESSION) { + if ((options->filename == NULL) + &&(options->outfilename == NULL)) { + fprintf(stderr, "expected file name for regression test\n"); + return -1; + } + if (options->filename && bad_filename(options->filename)) + return -1; + + if (options->outfilename && bad_filename(options->outfilename)) + return -1; + + return optind; + } + if (NULL == options->filename) { fprintf(stderr, "expected -f <trace filename>\n"); return -1; @@ -1401,6 +1436,158 @@ static int execute(int argc, char *argv[], char *const envp[], return -1; } +int binary_compare(struct program_options * options) +{ + FILE * fp; + FILE * fp_baseline; + char * file; + char * file_baseline; + int file_size; + int ret; + + printf("running binary_compare\n"); + fp = fopen(options->filename,"r"); + fseek( fp , 0 , SEEK_END ); + file_size = ftell( fp ); + printf( "%s %d\n" ,options->filename, file_size ); + fseek( fp , 0 , SEEK_SET); + file = (char *)malloc( file_size * sizeof( char ) ); + fread( file , file_size , sizeof(char) , fp); + + fp_baseline = fopen(options->baseline_filename,"r"); + fseek( fp_baseline , 0 , SEEK_END ); + file_size = ftell(fp_baseline); + printf( "%s %d\n" ,options->baseline_filename, file_size ); + fseek( fp_baseline , 0 , SEEK_SET); + file_baseline = (char *)malloc( file_size * sizeof( char ) ); + fread( file_baseline , file_size , sizeof(char) , fp_baseline); + + ret = strcmp(file,file_baseline); + if(ret) + fprintf(stderr, "[IDLE_STAT REGRESSION TEST] <binary_compare failed>\n"); + else + printf( "[IDLE_STAT REGRESSION TEST] <binary_compare success>\n"); + + fclose(fp); + fclose(fp_baseline); + free(file); + free(file_baseline); + return ret; +} + +int output_compare(struct program_options * options) +{ + struct report_ops *output_handler = NULL; + void *report_data = NULL; + struct cpu_topology *cpu_topo = NULL; + struct cpuidle_datas *datas; + char * tmp_filename; + int ret = 0; + /* Load the idle states information */ + datas = idlestat_load(options->filename); + + if (is_err(datas)) + return 1; + + cpu_topo = datas->topo; + + output_handler = get_report_ops(options->report_type_name); + if (is_err(output_handler)) + return 1; + + if (output_handler->open_report_file(options->outfilename, report_data)) + return 1; + + if (options->display & IDLE_DISPLAY) { + output_handler->cstate_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_cstates, cpu_topo, 1); + output_handler->cstate_table_footer(report_data); + } + + if (options->display & FREQUENCY_DISPLAY) { + output_handler->pstate_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_pstates, cpu_topo, 0); + output_handler->pstate_table_footer(report_data); + } + + if (options->display & WAKEUP_DISPLAY) { + output_handler->wakeup_table_header(report_data); + dump_cpu_topo_info(output_handler, report_data, + display_wakeup, cpu_topo, 1); + output_handler->wakeup_table_footer(report_data); + } + + restore_stdout(); + + /*backup the filename*/ + tmp_filename = options->filename; + + /*compare the new output file with the old one*/ + options->filename = options->outfilename; + ret = binary_compare(options); + + if(ret) + printf("output file comparsion of %s and %s failed\n",options->filename,options->baseline_filename); + else + printf("[IDLE_STAT REGRESSION TEST] <output_compare success>\n"); + /*restore the file name*/ + options->filename = tmp_filename; + + + return ret; + +} + +int regression(struct program_options * options) +{ + struct cpuidle_datas *datas; + struct cpu_topology *cpu_topo = NULL; + struct report_ops *output_handler = NULL; + int ret = 0; + + char topo_info[512]; + + output_handler = get_report_ops(options->report_type_name); + if (is_err(output_handler)) + return 1; + + if (output_handler->check_options && + output_handler->check_options(options) < 0) + return 1; + + /* Load the idle states information */ + datas = idlestat_load(options->filename); + + if (is_err(datas)){ + fprintf(stderr, "[IDLE_STAT REGRESSION TEST] <trace file import failed>\n"); + ret = -1; + } + else + printf("[IDLE_STAT REGRESSION TEST] <trace file import success>\n"); + + cpu_topo = read_sysfs_cpu_topo(); + if (is_err(cpu_topo)) { + fprintf(stderr, "Failed to read CPU topology info from" + " sysfs.\n"); + ret = -1; + } + else{ + outstr_topo_info(topo_info,cpu_topo); + printf("%s",topo_info); + printf("[IDLE_STAT REGRESSION TEST] <CPU topology info read success>\n"); + } + + if(options->tracefile_comp_flag) + ret = binary_compare(options); + + if(options->output_comp_flag) + ret = output_compare(options); + + return ret; +} + int main(int argc, char *argv[], char *const envp[]) { struct cpuidle_datas *datas; @@ -1414,10 +1601,24 @@ int main(int argc, char *argv[], char *const envp[]) struct trace_options *saved_trace_options = NULL; void *report_data = NULL; + int fd; + int flength; + struct stat statbuff; + args = getoptions(argc, argv, &options); if (args <= 0) return 1; + if (options.mode == REGRESSION){ + if (regression(&options)){ + printf("regression failed\n"); + } + else{ + printf("regression success\n"); + } + return 0; + } + /* Tracing requires manipulation of some files only accessible * to root */ if ((options.mode == TRACE) && getuid()) { @@ -1497,6 +1698,16 @@ int main(int argc, char *argv[], char *const envp[]) initp = build_init_pstates(cpu_topo); + /* + set the trace file format to bin + */ + if(options.mmap_flag){ + FILE * file; + file = fopen(TRACE_OPTIONS, "r+"); + perror(__func__); + printf("%s open %p\n",TRACE_OPTIONS,file); + store_line("bin",(void *)file); + } /* Start the recording */ if (idlestat_trace_enable(true)) goto err_restore_trace_options; @@ -1532,6 +1743,26 @@ int main(int argc, char *argv[], char *const envp[]) initp, cpu_topo)) goto err_restore_trace_options; + if(options.mmap_flag){ + fd = open(options.filename, O_RDONLY); + if((fd == -1) || fstat(fd, &statbuff)){ + perror(__func__); + printf("[idlestat] file length get failed\n"); + close(fd); + return 1; + } + flength = statbuff.st_size; + printf("[idlestat]: mmaped file is %s fd %x length %d\n",options.filename,fd,flength); + options.mapped_mem = mmap(NULL, flength, PROT_READ,MAP_PRIVATE,fd,0); + if((int)(void *)options.mapped_mem == (int)-1){ + perror(__func__); + close(fd); + return 1; + } + //printf("%s\n", options.mapped_mem); + close(fd); + } + /* Restore original kernel ftrace options */ if (idlestat_restore_trace_options(saved_trace_options)) return 1; diff --git a/idlestat.h b/idlestat.h index e030f6a..1ca9748 100644 --- a/idlestat.h +++ b/idlestat.h @@ -121,7 +121,8 @@ struct cpuidle_datas { enum modes { TRACE = 0, - IMPORT + IMPORT, + REGRESSION }; struct trace_buffer_settings { @@ -140,6 +141,10 @@ struct program_options { int verbose; char *energy_model_filename; char *report_type_name; + bool mmap_flag; + bool tracefile_comp_flag; + bool output_comp_flag; + char * mapped_mem; }; #define IDLE_DISPLAY 0x1 diff --git a/topology.c b/topology.c index 39b07bd..ee00bfe 100644 --- a/topology.c +++ b/topology.c @@ -280,6 +280,25 @@ int outfile_topo_info(FILE *f, struct cpu_topology *topo_list) return 0; } +int outstr_topo_info(char *s, struct cpu_topology *topo_list) +{ + struct cpu_physical *s_phy; + struct cpu_core *s_core; + struct cpu_cpu *s_cpu; + + list_for_each_entry(s_phy, &topo_list->physical_head, list_physical) { + sprintf(s, "cluster%c:\n", s_phy->physical_id + 'A'); + list_for_each_entry(s_core, &s_phy->core_head, list_core) { + sprintf(s, "\tcore%d\n", s_core->core_id); + list_for_each_entry(s_cpu, &s_core->cpu_head, list_cpu){ + sprintf(s, "\t\tcpu%d\n", s_cpu->cpu_id); + } + } + } + + return 0; +} + struct cpu_cpu *find_cpu_point(struct cpu_topology *topo_list, int cpuid) { struct cpu_physical *s_phy; diff --git a/topology.h b/topology.h index 84e5bc1..4c7964e 100644 --- a/topology.h +++ b/topology.h @@ -115,5 +115,6 @@ extern int core_get_highest_freq(struct cpu_core *core); core_get_highest_freq(cpu_to_core(cpuid, topo)) extern int setup_topo_states(struct cpuidle_datas *datas); +extern int outstr_topo_info(char *s, struct cpu_topology *topo_list); #endif diff --git a/trace.h b/trace.h index a2f5867..29b4d93 100644 --- a/trace.h +++ b/trace.h @@ -34,6 +34,7 @@ #define TRACE_FREE TRACE_PATH "/free_buffer" #define TRACE_FILE TRACE_PATH "/trace" #define TRACE_STAT_FILE TRACE_PATH "/per_cpu/cpu0/stats" +#define TRACE_OPTIONS TRACE_PATH "/trace_options" #define TRACE_IDLE_NRHITS_PER_SEC 10000 #define TRACE_IDLE_LENGTH 196 #define TRACE_CPUFREQ_NRHITS_PER_SEC 100 diff --git a/utils.c b/utils.c index 48be965..1c6bc96 100644 --- a/utils.c +++ b/utils.c @@ -210,14 +210,17 @@ out_free: return ret; } +int std_fd; int redirect_stdout_to_file(const char *path) { int ret = 0; int fd; if (path) { + std_fd = dup(STDOUT_FILENO); fd = open(path, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR | S_IRGRP |S_IROTH); + if (fd < 0) { fprintf(stderr, "%s: failed to open '%s'\n", __func__, path); return -1; @@ -237,6 +240,13 @@ int redirect_stdout_to_file(const char *path) return 0; } +int restore_stdout() +{ + int ret = 0; + ret = dup2(std_fd,STDOUT_FILENO); + printf("%s %d \n",__func__,ret); +} + void display_factored_time(double time, int align) { char buffer[128]; diff --git a/utils.h b/utils.h index ee7a9a2..6b8808c 100644 --- a/utils.h +++ b/utils.h @@ -49,5 +49,6 @@ extern int check_window_size(void); extern int error(const char *str); extern void *ptrerror(const char *str); extern int is_err(const void *ptr); +extern int restore_stdout(); #endif -- 1.7.9.5

8 years, 11 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

Sched-tools May 2015