rtla/timerlat: Introduce enum timerlat_tracing_mode

After the introduction of BPF-based sample collection, rtla-timerlat
effectively runs in one of three modes:

- Pure BPF mode, with tracefs only being used to set up the timerlat
tracer. Sample processing and stop on threshold are handled by BPF.

- tracefs mode. BPF is unsupported or kernel is lacking the necessary
trace event (osnoise:timerlat_sample). Stop on theshold is handled by
timerlat tracer stopping tracing in all instances.

- BPF/tracefs mixed mode - BPF is used for sample collection for top or
histogram, tracefs is used for trace output and/or auto-analysis. Stop
on threshold is handled both through BPF program, which stops sample
collection for top/histogram and wakes up rtla, and by timerlat
tracer, which stops tracing for trace output/auto-analysis instances.

Add enum timerlat_tracing_mode, with three values:

- TRACING_MODE_BPF
- TRACING_MODE_TRACEFS
- TRACING_MODE_MIXED

Those represent the modes described above. A field of this type is added
to struct timerlat_params, named "mode", replacing the no_bpf variable.
params->mode is set in timerlat_{top,hist}_parse_args to
TRACING_MODE_BPF or TRACING_MODE_MIXED based on whether trace output
and/or auto-analysis is requested. timerlat_{top,hist}_main then checks
if BPF is not unavailable or disabled, in that case, it sets
params->mode to TRACING_MODE_TRACEFS.

A condition is added to timerlat_apply_config that skips setting
timerlat tracer thresholds if params->mode is TRACING_MODE_BPF (those
are unnecessary, since they only turn off tracing, which is already
turned off in that case, since BPF is used to collect samples).

Cc: John Kacur <jkacur@redhat.com>
Cc: Luis Goncalves <lgoncalv@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Chang Yin <cyin@redhat.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Cc: Crystal Wood <crwood@redhat.com>
Cc: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lore.kernel.org/20250626123405.1496931-2-tglozar@redhat.com
Signed-off-by: Tomas Glozar <tglozar@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
pull/1320/head
Tomas Glozar 2025-06-26 14:33:57 +02:00 committed by Steven Rostedt (Google)
parent d7b8f8e208
commit 8b6cbcac76
4 changed files with 104 additions and 60 deletions

View File

@ -40,16 +40,22 @@ timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_params *params)
CPU_SET(i, &params->monitored_cpus);
}
retval = osnoise_set_stop_us(tool->context, params->stop_us);
if (retval) {
err_msg("Failed to set stop us\n");
goto out_err;
}
if (params->mode != TRACING_MODE_BPF) {
/*
* In tracefs and mixed mode, timerlat tracer handles stopping
* on threshold
*/
retval = osnoise_set_stop_us(tool->context, params->stop_us);
if (retval) {
err_msg("Failed to set stop us\n");
goto out_err;
}
retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
if (retval) {
err_msg("Failed to set stop total us\n");
goto out_err;
retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
if (retval) {
err_msg("Failed to set stop total us\n");
goto out_err;
}
}

View File

@ -1,6 +1,23 @@
// SPDX-License-Identifier: GPL-2.0
#include "osnoise.h"
/*
* Define timerlat tracing mode.
*
* There are three tracing modes:
* - tracefs-only, used when BPF is unavailable.
* - BPF-only, used when BPF is available and neither trace saving nor
* auto-analysis are enabled.
* - mixed mode, used when BPF is available and either trace saving or
* auto-analysis is enabled (which rely on sample collection through
* tracefs).
*/
enum timerlat_tracing_mode {
TRACING_MODE_BPF,
TRACING_MODE_TRACEFS,
TRACING_MODE_MIXED,
};
struct timerlat_params {
/* Common params */
char *cpus;
@ -30,6 +47,7 @@ struct timerlat_params {
cpu_set_t hk_cpu_set;
struct sched_attr sched_param;
struct trace_events *events;
enum timerlat_tracing_mode mode;
union {
struct {
/* top only */

View File

@ -802,6 +802,9 @@ static struct timerlat_params
params->bucket_size = 1;
params->entries = 256;
/* default to BPF mode */
params->mode = TRACING_MODE_BPF;
while (1) {
static struct option long_options[] = {
{"auto", required_argument, 0, 'a'},
@ -1054,6 +1057,13 @@ static struct timerlat_params
if (params->kernel_workload && params->user_workload)
timerlat_hist_usage("--kernel-threads and --user-threads are mutually exclusive!");
/*
* If auto-analysis or trace output is enabled, switch from BPF mode to
* mixed mode
*/
if (params->mode == TRACING_MODE_BPF && params->trace_output && !params->no_aa)
params->mode = TRACING_MODE_MIXED;
return params;
}
@ -1149,7 +1159,6 @@ int timerlat_hist_main(int argc, char *argv[])
pthread_t timerlat_u;
int retval;
int nr_cpus, i;
bool no_bpf = false;
params = timerlat_hist_parse_args(argc, argv);
if (!params)
@ -1161,12 +1170,6 @@ int timerlat_hist_main(int argc, char *argv[])
goto out_exit;
}
retval = timerlat_hist_apply_config(tool, params);
if (retval) {
err_msg("Could not apply config\n");
goto out_free;
}
trace = &tool->trace;
/*
* Save trace instance into global variable so that SIGINT can stop
@ -1175,24 +1178,30 @@ int timerlat_hist_main(int argc, char *argv[])
*/
hist_inst = trace;
/*
* Try to enable BPF, unless disabled explicitly.
* If BPF enablement fails, fall back to tracefs mode.
*/
if (getenv("RTLA_NO_BPF") && strncmp(getenv("RTLA_NO_BPF"), "1", 2) == 0) {
debug_msg("RTLA_NO_BPF set, disabling BPF\n");
no_bpf = true;
}
if (!no_bpf && !tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
params->mode = TRACING_MODE_TRACEFS;
} else if (!tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
no_bpf = true;
}
if (!no_bpf) {
params->mode = TRACING_MODE_TRACEFS;
} else {
retval = timerlat_bpf_init(params);
if (retval) {
debug_msg("Could not enable BPF\n");
no_bpf = true;
params->mode = TRACING_MODE_TRACEFS;
}
}
retval = timerlat_hist_apply_config(tool, params);
if (retval) {
err_msg("Could not apply config\n");
goto out_free;
}
retval = enable_timerlat(trace);
if (retval) {
err_msg("Failed to enable timerlat tracer\n");
@ -1320,7 +1329,7 @@ int timerlat_hist_main(int argc, char *argv[])
trace_instance_start(&record->trace);
if (!params->no_aa)
trace_instance_start(&aa->trace);
if (no_bpf) {
if (params->mode == TRACING_MODE_TRACEFS) {
trace_instance_start(trace);
} else {
retval = timerlat_bpf_attach();
@ -1333,7 +1342,7 @@ int timerlat_hist_main(int argc, char *argv[])
tool->start_time = time(NULL);
timerlat_hist_set_signals(params);
if (no_bpf) {
if (params->mode == TRACING_MODE_TRACEFS) {
while (!stop_tracing) {
sleep(params->sleep_time);
@ -1362,7 +1371,7 @@ int timerlat_hist_main(int argc, char *argv[])
} else
timerlat_bpf_wait(-1);
if (!no_bpf) {
if (params->mode != TRACING_MODE_TRACEFS) {
timerlat_bpf_detach();
retval = timerlat_hist_bpf_pull_data(tool);
if (retval) {
@ -1409,10 +1418,10 @@ out_free:
osnoise_destroy_tool(aa);
osnoise_destroy_tool(record);
osnoise_destroy_tool(tool);
if (params->mode != TRACING_MODE_TRACEFS)
timerlat_bpf_destroy();
free(params);
free_cpu_idle_disable_states();
if (!no_bpf)
timerlat_bpf_destroy();
out_exit:
exit(return_value);
}

View File

@ -559,6 +559,9 @@ static struct timerlat_params
/* display data in microseconds */
params->output_divisor = 1000;
/* default to BPF mode */
params->mode = TRACING_MODE_BPF;
while (1) {
static struct option long_options[] = {
{"auto", required_argument, 0, 'a'},
@ -790,6 +793,13 @@ static struct timerlat_params
if (params->kernel_workload && params->user_workload)
timerlat_top_usage("--kernel-threads and --user-threads are mutually exclusive!");
/*
* If auto-analysis or trace output is enabled, switch from BPF mode to
* mixed mode
*/
if (params->mode == TRACING_MODE_BPF && params->trace_output && !params->no_aa)
params->mode = TRACING_MODE_MIXED;
return params;
}
@ -994,7 +1004,6 @@ int timerlat_top_main(int argc, char *argv[])
char *max_lat;
int retval;
int nr_cpus, i;
bool no_bpf = false;
params = timerlat_top_parse_args(argc, argv);
if (!params)
@ -1006,38 +1015,38 @@ int timerlat_top_main(int argc, char *argv[])
goto out_exit;
}
trace = &top->trace;
/*
* Save trace instance into global variable so that SIGINT can stop
* the timerlat tracer.
* Otherwise, rtla could loop indefinitely when overloaded.
*/
top_inst = trace;
/*
* Try to enable BPF, unless disabled explicitly.
* If BPF enablement fails, fall back to tracefs mode.
*/
if (getenv("RTLA_NO_BPF") && strncmp(getenv("RTLA_NO_BPF"), "1", 2) == 0) {
debug_msg("RTLA_NO_BPF set, disabling BPF\n");
params->mode = TRACING_MODE_TRACEFS;
} else if (!tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
params->mode = TRACING_MODE_TRACEFS;
} else {
retval = timerlat_bpf_init(params);
if (retval) {
debug_msg("Could not enable BPF\n");
params->mode = TRACING_MODE_TRACEFS;
}
}
retval = timerlat_top_apply_config(top, params);
if (retval) {
err_msg("Could not apply config\n");
goto out_free;
}
trace = &top->trace;
/*
* Save trace instance into global variable so that SIGINT can stop
* the timerlat tracer.
* Otherwise, rtla could loop indefinitely when overloaded.
*/
top_inst = trace;
if (getenv("RTLA_NO_BPF") && strncmp(getenv("RTLA_NO_BPF"), "1", 2) == 0) {
debug_msg("RTLA_NO_BPF set, disabling BPF\n");
no_bpf = true;
}
if (!no_bpf && !tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
no_bpf = true;
}
if (!no_bpf) {
retval = timerlat_bpf_init(params);
if (retval) {
debug_msg("Could not enable BPF\n");
no_bpf = true;
}
}
retval = enable_timerlat(trace);
if (retval) {
err_msg("Failed to enable timerlat tracer\n");
@ -1166,7 +1175,7 @@ int timerlat_top_main(int argc, char *argv[])
trace_instance_start(&record->trace);
if (!params->no_aa)
trace_instance_start(&aa->trace);
if (no_bpf) {
if (params->mode == TRACING_MODE_TRACEFS) {
trace_instance_start(trace);
} else {
retval = timerlat_bpf_attach();
@ -1179,7 +1188,7 @@ int timerlat_top_main(int argc, char *argv[])
top->start_time = time(NULL);
timerlat_top_set_signals(params);
if (no_bpf)
if (params->mode == TRACING_MODE_TRACEFS)
retval = timerlat_top_main_loop(top, record, params, &params_u);
else
retval = timerlat_top_bpf_main_loop(top, record, params, &params_u);
@ -1187,7 +1196,7 @@ int timerlat_top_main(int argc, char *argv[])
if (retval)
goto out_top;
if (!no_bpf)
if (params->mode != TRACING_MODE_TRACEFS)
timerlat_bpf_detach();
if (params->user_workload && !params_u.stopped_running) {
@ -1239,6 +1248,8 @@ out_free:
osnoise_destroy_tool(aa);
osnoise_destroy_tool(record);
osnoise_destroy_tool(top);
if (params->mode != TRACING_MODE_TRACEFS)
timerlat_bpf_destroy();
free(params);
free_cpu_idle_disable_states();
out_exit: