rtla: Add -C cgroup support

The -C option sets a cgroup to the tracer's threads. If the -C option is
passed without arguments, the tracer's thread will inherit rtla's
cgroup. Otherwise, the threads will be placed on the cgroup passed
to the option.

Link: https://lkml.kernel.org/r/cb051477331d292f17c08bf1d66f0e0384bbe5a5.1686066600.git.bristot@kernel.org

Cc: William White <chwhite@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This commit is contained in:
Daniel Bristot de Oliveira 2023-06-06 18:12:15 +02:00 committed by Steven Rostedt (Google)
parent 9561de3a55
commit a957cbc025
7 changed files with 286 additions and 9 deletions

View File

@ -42,6 +42,10 @@
- *f:prio* - use SCHED_FIFO with *prio*;
- *d:runtime[us|ms|s]:period[us|ms|s]* - use SCHED_DEADLINE with *runtime* and *period* in nanoseconds.
**-C**, **--cgroup**\[*=cgroup*]
Set a *cgroup* to the tracer's threads. If the **-C** option is passed without arguments, the tracer's thread will inherit **rtla**'s *cgroup*. Otherwise, the threads will be placed on the *cgroup* passed to the option.
**-h**, **--help**
Print help menu.

View File

@ -19,6 +19,7 @@ struct osnoise_hist_params {
char *cpus;
char *monitored_cpus;
char *trace_output;
char *cgroup_name;
unsigned long long runtime;
unsigned long long period;
long long threshold;
@ -28,6 +29,7 @@ struct osnoise_hist_params {
int duration;
int set_sched;
int output_divisor;
int cgroup;
struct sched_attr sched_param;
struct trace_events *events;
@ -433,7 +435,7 @@ static void osnoise_hist_usage(char *usage)
" usage: rtla osnoise hist [-h] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\",
" [-T us] [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] \\",
" [-c cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] [--no-index] \\",
" [--with-zeros]",
" [--with-zeros] [-C[=cgroup_name]]",
"",
" -h/--help: print this menu",
" -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit",
@ -443,6 +445,7 @@ static void osnoise_hist_usage(char *usage)
" -S/--stop-total us: stop trace if the total sample is higher than the argument in us",
" -T/--threshold us: the minimum delta to be considered a noise",
" -c/--cpus cpu-list: list of cpus to run osnoise threads",
" -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited",
" -d/--duration time[s|m|h|d]: duration of the session",
" -D/--debug: print debug info",
" -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]",
@ -501,6 +504,7 @@ static struct osnoise_hist_params
{"bucket-size", required_argument, 0, 'b'},
{"entries", required_argument, 0, 'E'},
{"cpus", required_argument, 0, 'c'},
{"cgroup", optional_argument, 0, 'C'},
{"debug", no_argument, 0, 'D'},
{"duration", required_argument, 0, 'd'},
{"help", no_argument, 0, 'h'},
@ -524,7 +528,7 @@ static struct osnoise_hist_params
/* getopt_long stores the option index here. */
int option_index = 0;
c = getopt_long(argc, argv, "a:c:b:d:e:E:Dhp:P:r:s:S:t::T:01234:5:",
c = getopt_long(argc, argv, "a:c:C::b:d:e:E:Dhp:P:r:s:S:t::T:01234:5:",
long_options, &option_index);
/* detect the end of the options. */
@ -554,6 +558,16 @@ static struct osnoise_hist_params
osnoise_hist_usage("\nInvalid -c cpu list\n");
params->cpus = optarg;
break;
case 'C':
params->cgroup = 1;
if (!optarg) {
/* will inherit this cgroup */
params->cgroup_name = NULL;
} else if (*optarg == '=') {
/* skip the = */
params->cgroup_name = ++optarg;
}
break;
case 'D':
config_debug = 1;
break;
@ -816,6 +830,14 @@ int osnoise_hist_main(int argc, char *argv[])
}
}
if (params->cgroup) {
retval = set_comm_cgroup("timerlat/", params->cgroup_name);
if (!retval) {
err_msg("Failed to move threads to cgroup\n");
goto out_free;
}
}
trace_instance_start(trace);
if (params->trace_output) {

View File

@ -26,6 +26,7 @@ struct osnoise_top_params {
char *cpus;
char *monitored_cpus;
char *trace_output;
char *cgroup_name;
unsigned long long runtime;
unsigned long long period;
long long threshold;
@ -35,6 +36,7 @@ struct osnoise_top_params {
int duration;
int quiet;
int set_sched;
int cgroup;
struct sched_attr sched_param;
struct trace_events *events;
enum osnoise_mode mode;
@ -276,7 +278,7 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
static const char * const msg[] = {
" [-h] [-q] [-D] [-d s] [-a us] [-p us] [-r us] [-s us] [-S us] \\",
" [-T us] [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] \\",
" [-c cpu-list] [-P priority]",
" [-c cpu-list] [-P priority] [-C[=cgroup_name]]",
"",
" -h/--help: print this menu",
" -a/--auto: set automatic trace mode, stopping the session if argument in us sample is hit",
@ -286,6 +288,7 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
" -S/--stop-total us: stop trace if the total sample is higher than the argument in us",
" -T/--threshold us: the minimum delta to be considered a noise",
" -c/--cpus cpu-list: list of cpus to run osnoise threads",
" -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited",
" -d/--duration time[s|m|h|d]: duration of the session",
" -D/--debug: print debug info",
" -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]",
@ -347,6 +350,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv)
static struct option long_options[] = {
{"auto", required_argument, 0, 'a'},
{"cpus", required_argument, 0, 'c'},
{"cgroup", optional_argument, 0, 'C'},
{"debug", no_argument, 0, 'D'},
{"duration", required_argument, 0, 'd'},
{"event", required_argument, 0, 'e'},
@ -367,7 +371,7 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv)
/* getopt_long stores the option index here. */
int option_index = 0;
c = getopt_long(argc, argv, "a:c:d:De:hp:P:qr:s:S:t::T:0:1:",
c = getopt_long(argc, argv, "a:c:C::d:De:hp:P:qr:s:S:t::T:0:1:",
long_options, &option_index);
/* Detect the end of the options. */
@ -392,6 +396,16 @@ struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv)
osnoise_top_usage(params, "\nInvalid -c cpu list\n");
params->cpus = optarg;
break;
case 'C':
params->cgroup = 1;
if (!optarg) {
/* will inherit this cgroup */
params->cgroup_name = NULL;
} else if (*optarg == '=') {
/* skip the = */
params->cgroup_name = ++optarg;
}
break;
case 'D':
config_debug = 1;
break;
@ -643,6 +657,14 @@ int osnoise_top_main(int argc, char **argv)
}
}
if (params->cgroup) {
retval = set_comm_cgroup("osnoise/", params->cgroup_name);
if (!retval) {
err_msg("Failed to move threads to cgroup\n");
goto out_free;
}
}
trace_instance_start(trace);
if (params->trace_output) {

View File

@ -19,6 +19,7 @@ struct timerlat_hist_params {
char *cpus;
char *monitored_cpus;
char *trace_output;
char *cgroup_name;
unsigned long long runtime;
long long stop_us;
long long stop_total_us;
@ -29,9 +30,9 @@ struct timerlat_hist_params {
int duration;
int set_sched;
int dma_latency;
int cgroup;
struct sched_attr sched_param;
struct trace_events *events;
char no_irq;
char no_thread;
char no_header;
@ -433,7 +434,7 @@ static void timerlat_hist_usage(char *usage)
" usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-a us] [-p us] [-i us] [-T us] [-s us] \\",
" [-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] \\",
" [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\",
" [--no-index] [--with-zeros] [--dma-latency us]",
" [--no-index] [--with-zeros] [--dma-latency us] [-C[=cgroup_name]]",
"",
" -h/--help: print this menu",
" -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit",
@ -442,6 +443,7 @@ static void timerlat_hist_usage(char *usage)
" -T/--thread us: stop trace if the thread latency is higher than the argument in us",
" -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us",
" -c/--cpus cpus: run the tracer only on the given cpus",
" -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited",
" -d/--duration time[m|h|d]: duration of the session in seconds",
" -D/--debug: print debug info",
" -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]",
@ -506,6 +508,7 @@ static struct timerlat_hist_params
static struct option long_options[] = {
{"auto", required_argument, 0, 'a'},
{"cpus", required_argument, 0, 'c'},
{"cgroup", optional_argument, 0, 'C'},
{"bucket-size", required_argument, 0, 'b'},
{"debug", no_argument, 0, 'D'},
{"entries", required_argument, 0, 'E'},
@ -534,7 +537,7 @@ static struct timerlat_hist_params
/* getopt_long stores the option index here. */
int option_index = 0;
c = getopt_long(argc, argv, "a:c:b:d:e:E:Dhi:np:P:s:t::T:0123456:7:8:",
c = getopt_long(argc, argv, "a:c:C::b:d:e:E:Dhi:np:P:s:t::T:0123456:7:8:",
long_options, &option_index);
/* detect the end of the options. */
@ -561,6 +564,16 @@ static struct timerlat_hist_params
timerlat_hist_usage("\nInvalid -c cpu list\n");
params->cpus = optarg;
break;
case 'C':
params->cgroup = 1;
if (!optarg) {
/* will inherit this cgroup */
params->cgroup_name = NULL;
} else if (*optarg == '=') {
/* skip the = */
params->cgroup_name = ++optarg;
}
break;
case 'b':
params->bucket_size = get_llong_from_str(optarg);
if ((params->bucket_size == 0) || (params->bucket_size >= 1000000))
@ -840,6 +853,14 @@ int timerlat_hist_main(int argc, char *argv[])
}
}
if (params->cgroup) {
retval = set_comm_cgroup("timerlat/", params->cgroup_name);
if (!retval) {
err_msg("Failed to move threads to cgroup\n");
goto out_free;
}
}
if (params->dma_latency >= 0) {
dma_latency_fd = set_cpu_dma_latency(params->dma_latency);
if (dma_latency_fd < 0) {

View File

@ -21,6 +21,7 @@ struct timerlat_top_params {
char *cpus;
char *monitored_cpus;
char *trace_output;
char *cgroup_name;
unsigned long long runtime;
long long stop_us;
long long stop_total_us;
@ -35,6 +36,7 @@ struct timerlat_top_params {
int no_aa;
int aa_only;
int dump_tasks;
int cgroup;
struct sched_attr sched_param;
struct trace_events *events;
};
@ -285,7 +287,7 @@ static void timerlat_top_usage(char *usage)
"",
" usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\",
" [[-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] \\",
" [-P priority] [--dma-latency us] [--aa-only us]",
" [-P priority] [--dma-latency us] [--aa-only us] [-C[=cgroup_name]]",
"",
" -h/--help: print this menu",
" -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit",
@ -295,6 +297,7 @@ static void timerlat_top_usage(char *usage)
" -T/--thread us: stop trace if the thread latency is higher than the argument in us",
" -s/--stack us: save the stack trace at the IRQ if a thread latency is higher than the argument in us",
" -c/--cpus cpus: run the tracer only on the given cpus",
" -C/--cgroup[=cgroup_name]: set cgroup, if no cgroup_name is passed, the rtla's cgroup will be inherited",
" -d/--duration time[m|h|d]: duration of the session in seconds",
" -D/--debug: print debug info",
" --dump-tasks: prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)",
@ -352,6 +355,7 @@ static struct timerlat_top_params
static struct option long_options[] = {
{"auto", required_argument, 0, 'a'},
{"cpus", required_argument, 0, 'c'},
{"cgroup", optional_argument, 0, 'C'},
{"debug", no_argument, 0, 'D'},
{"duration", required_argument, 0, 'd'},
{"event", required_argument, 0, 'e'},
@ -376,7 +380,7 @@ static struct timerlat_top_params
/* getopt_long stores the option index here. */
int option_index = 0;
c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:345:",
c = getopt_long(argc, argv, "a:c:C::d:De:hi:np:P:qs:t::T:0:1:2:345:",
long_options, &option_index);
/* detect the end of the options. */
@ -417,6 +421,16 @@ static struct timerlat_top_params
timerlat_top_usage("\nInvalid -c cpu list\n");
params->cpus = optarg;
break;
case 'C':
params->cgroup = 1;
if (!optarg) {
/* will inherit this cgroup */
params->cgroup_name = NULL;
} else if (*optarg == '=') {
/* skip the = */
params->cgroup_name = ++optarg;
}
break;
case 'D':
config_debug = 1;
break;
@ -694,6 +708,14 @@ int timerlat_top_main(int argc, char *argv[])
}
}
if (params->cgroup) {
retval = set_comm_cgroup("timerlat/", params->cgroup_name);
if (!retval) {
err_msg("Failed to move threads to cgroup\n");
goto out_free;
}
}
if (params->dma_latency >= 0) {
dma_latency_fd = set_cpu_dma_latency(params->dma_latency);
if (dma_latency_fd < 0) {

View File

@ -529,3 +529,188 @@ int set_cpu_dma_latency(int32_t latency)
return fd;
}
#define _STR(x) #x
#define STR(x) _STR(x)
/*
* find_mount - find a the mount point of a given fs
*
* Returns 0 if mount is not found, otherwise return 1 and fill mp
* with the mount point.
*/
static const int find_mount(const char *fs, char *mp, int sizeof_mp)
{
char mount_point[MAX_PATH];
char type[100];
int found;
FILE *fp;
fp = fopen("/proc/mounts", "r");
if (!fp)
return 0;
while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n", mount_point, type) == 2) {
if (strcmp(type, fs) == 0) {
found = 1;
break;
}
}
fclose(fp);
if (!found)
return 0;
memset(mp, 0, sizeof_mp);
strncpy(mp, mount_point, sizeof_mp - 1);
debug_msg("Fs %s found at %s\n", fs, mp);
return 1;
}
/*
* get_self_cgroup - get the current thread cgroup path
*
* Parse /proc/$$/cgroup file to get the thread's cgroup. As an example of line to parse:
*
* 0::/user.slice/user-0.slice/session-3.scope'\n'
*
* This function is interested in the content after the second : and before the '\n'.
*
* Returns 1 if a string was found, 0 otherwise.
*/
static int get_self_cgroup(char *self_cg, int sizeof_self_cg)
{
char path[MAX_PATH], *start;
int fd, retval;
snprintf(path, MAX_PATH, "/proc/%d/cgroup", getpid());
fd = open(path, O_RDONLY);
if (fd < 0)
return 0;
retval = read(fd, path, MAX_PATH);
close(fd);
if (retval <= 0)
return 0;
start = path;
start = strstr(start, ":");
if (!start)
return 0;
/* skip ":" */
start++;
start = strstr(start, ":");
if (!start)
return 0;
/* skip ":" */
start++;
if (strlen(start) >= sizeof_self_cg)
return 0;
snprintf(self_cg, sizeof_self_cg, "%s", start);
/* Swap '\n' with '\0' */
start = strstr(self_cg, "\n");
/* there must be '\n' */
if (!start)
return 0;
/* ok, it found a string after the second : and before the \n */
*start = '\0';
return 1;
}
/**
* set_comm_cgroup - Set cgroup to threads starting with char *comm_prefix
*
* If cgroup argument is not NULL, the threads will move to the given cgroup.
* Otherwise, the cgroup of the calling, i.e., rtla, thread will be used.
*
* Supports cgroup v2.
*
* Returns 1 on success, 0 otherwise.
*/
int set_comm_cgroup(const char *comm_prefix, const char *cgroup)
{
char cgroup_path[MAX_PATH - strlen("/cgroup.procs")];
char cgroup_procs[MAX_PATH];
struct dirent *proc_entry;
DIR *procfs;
int retval;
int cg_fd;
if (strlen(comm_prefix) >= MAX_PATH) {
err_msg("Command prefix is too long: %d < strlen(%s)\n",
MAX_PATH, comm_prefix);
return 0;
}
retval = find_mount("cgroup2", cgroup_path, sizeof(cgroup_path));
if (!retval) {
err_msg("Did not find cgroupv2 mount point\n");
return 0;
}
if (!cgroup) {
retval = get_self_cgroup(&cgroup_path[strlen(cgroup_path)],
sizeof(cgroup_path) - strlen(cgroup_path));
if (!retval) {
err_msg("Did not find self cgroup\n");
return 0;
}
} else {
snprintf(&cgroup_path[strlen(cgroup_path)],
sizeof(cgroup_path) - strlen(cgroup_path), "%s/", cgroup);
}
snprintf(cgroup_procs, MAX_PATH, "%s/cgroup.procs", cgroup_path);
debug_msg("Using cgroup path at: %s\n", cgroup_procs);
cg_fd = open(cgroup_procs, O_RDWR);
if (cg_fd < 0)
return 0;
procfs = opendir("/proc");
if (!procfs) {
err_msg("Could not open procfs\n");
goto out_cg;
}
while ((proc_entry = readdir(procfs))) {
retval = procfs_is_workload_pid(comm_prefix, proc_entry);
if (!retval)
continue;
retval = write(cg_fd, proc_entry->d_name, strlen(proc_entry->d_name));
if (retval < 0) {
err_msg("Error setting cgroup attributes for pid:%s - %s\n",
proc_entry->d_name, strerror(errno));
goto out_procfs;
}
debug_msg("Set cgroup attributes for pid:%s\n", proc_entry->d_name);
}
closedir(procfs);
close(cg_fd);
return 1;
out_procfs:
closedir(procfs);
out_cg:
close(cg_fd);
return 0;
}

View File

@ -55,6 +55,7 @@ struct sched_attr {
int parse_prio(char *arg, struct sched_attr *sched_param);
int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr);
int set_comm_cgroup(const char *comm_prefix, const char *cgroup);
int set_cpu_dma_latency(int32_t latency);
#define ns_to_usf(x) (((double)x/1000))