In order to profile app one needs to store significant amount of samples somewhere for an analysis latern on. Since trace library supports storing data in a CTF format lets take adventage of that and add a dedicated PMU tracepoint.
Signed-off-by: Tomasz Duszynski <tduszyn...@marvell.com> --- app/test/test_trace_perf.c | 4 ++ doc/guides/prog_guide/profile_app.rst | 5 ++ doc/guides/prog_guide/trace_lib.rst | 32 +++++++++++ lib/eal/common/eal_common_trace_points.c | 3 + lib/eal/common/rte_pmu.c | 73 +++++++++++++++++++++++- lib/eal/include/rte_eal_trace.h | 10 ++++ lib/eal/version.map | 1 + 7 files changed, 126 insertions(+), 2 deletions(-) diff --git a/app/test/test_trace_perf.c b/app/test/test_trace_perf.c index 46ae7d8074..4851b6852f 100644 --- a/app/test/test_trace_perf.c +++ b/app/test/test_trace_perf.c @@ -114,6 +114,8 @@ worker_fn_##func(void *arg) \ #define GENERIC_DOUBLE rte_eal_trace_generic_double(3.66666) #define GENERIC_STR rte_eal_trace_generic_str("hello world") #define VOID_FP app_dpdk_test_fp() +/* 0 corresponds first event passed via --trace= */ +#define READ_PMU rte_eal_trace_pmu_read(0) WORKER_DEFINE(GENERIC_VOID) WORKER_DEFINE(GENERIC_U64) @@ -122,6 +124,7 @@ WORKER_DEFINE(GENERIC_FLOAT) WORKER_DEFINE(GENERIC_DOUBLE) WORKER_DEFINE(GENERIC_STR) WORKER_DEFINE(VOID_FP) +WORKER_DEFINE(READ_PMU) static void run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz) @@ -174,6 +177,7 @@ test_trace_perf(void) run_test("double", worker_fn_GENERIC_DOUBLE, data, sz); run_test("string", worker_fn_GENERIC_STR, data, sz); run_test("void_fp", worker_fn_VOID_FP, data, sz); + run_test("read_pmu", worker_fn_READ_PMU, data, sz); rte_free(data); return TEST_SUCCESS; diff --git a/doc/guides/prog_guide/profile_app.rst b/doc/guides/prog_guide/profile_app.rst index a8b501fe0c..6a53341c6b 100644 --- a/doc/guides/prog_guide/profile_app.rst +++ b/doc/guides/prog_guide/profile_app.rst @@ -16,6 +16,11 @@ that information, perf being an example here. Though in some scenarios, eg. when isolated (nohz_full) and run dedicated tasks, using perf is less than ideal. In such cases one can read specific events directly from application via ``rte_pmu_read()``. +Alternatively tracing library can be used which offers dedicated tracepoint +``rte_eal_trace_pmu_event()``. + +Refer to :doc:`../prog_guide/trace_lib` for more details. + Profiling on x86 ---------------- diff --git a/doc/guides/prog_guide/trace_lib.rst b/doc/guides/prog_guide/trace_lib.rst index 9a8f38073d..10d5b99084 100644 --- a/doc/guides/prog_guide/trace_lib.rst +++ b/doc/guides/prog_guide/trace_lib.rst @@ -46,6 +46,7 @@ DPDK tracing library features trace format and is compatible with ``LTTng``. For detailed information, refer to `Common Trace Format <https://diamon.org/ctf/>`_. +- Support reading PMU events on ARM64 and x86 (Intel) How to add a tracepoint? ------------------------ @@ -137,6 +138,37 @@ the user must use ``RTE_TRACE_POINT_FP`` instead of ``RTE_TRACE_POINT``. ``RTE_TRACE_POINT_FP`` is compiled out by default and it can be enabled using the ``enable_trace_fp`` option for meson build. +PMU tracepoint +-------------- + +Performance measurement unit (PMU) event values can be read from hardware +registers using predefined ``rte_pmu_read`` tracepoint. + +Tracing is enabled via ``--trace`` EAL option by passing both expression +matching PMU tracepoint name i.e ``lib.eal.pmu.read`` and expression +``e=ev1[,ev2,...]`` matching particular events:: + + --trace='.*pmu.read\|e=cpu_cycles,l1d_cache' + +Event names are available under ``/sys/bus/event_source/devices/PMU/events`` +directory, where ``PMU`` is a placeholder for either a ``cpu`` or a directory +containing ``cpus``. + +In contrary to other tracepoints this does not need any extra variables +added to source files. Instead, caller passes index which follows the order of +events specified via ``--trace`` parameter. In the following example index ``0`` +corresponds to ``cpu_cyclces`` while index ``1`` corresponds to ``l1d_cache``. + +.. code-block:: c + + ... + rte_eal_trace_pmu_read(0); + rte_eal_trace_pmu_read(1); + ... + +PMU tracing support must be explicitly enabled using the ``enable_trace_fp`` +option for meson build. + Event record mode ----------------- diff --git a/lib/eal/common/eal_common_trace_points.c b/lib/eal/common/eal_common_trace_points.c index 0b0b254615..de918ca618 100644 --- a/lib/eal/common/eal_common_trace_points.c +++ b/lib/eal/common/eal_common_trace_points.c @@ -75,3 +75,6 @@ RTE_TRACE_POINT_REGISTER(rte_eal_trace_intr_enable, lib.eal.intr.enable) RTE_TRACE_POINT_REGISTER(rte_eal_trace_intr_disable, lib.eal.intr.disable) + +RTE_TRACE_POINT_REGISTER(rte_eal_trace_pmu_read, + lib.eal.pmu.read) diff --git a/lib/eal/common/rte_pmu.c b/lib/eal/common/rte_pmu.c index 67e8ffefb2..fd0df3b756 100644 --- a/lib/eal/common/rte_pmu.c +++ b/lib/eal/common/rte_pmu.c @@ -19,6 +19,7 @@ #include <rte_tailq.h> #include "pmu_private.h" +#include "eal_trace.h" #define EVENT_SOURCE_DEVICES_PATH "/sys/bus/event_source/devices" @@ -361,6 +362,12 @@ rte_pmu_add_event(const char *name) struct rte_pmu_event *event; char path[PATH_MAX]; + if (rte_pmu.name == NULL) + return -ENODEV; + + if (rte_pmu.num_group_events + 1 >= MAX_NUM_GROUP_EVENTS) + return -ENOSPC; + snprintf(path, sizeof(path), EVENT_SOURCE_DEVICES_PATH "/%s/events/%s", rte_pmu.name, name); if (access(path, R_OK)) return -ENODEV; @@ -372,11 +379,11 @@ rte_pmu_add_event(const char *name) } event = calloc(1, sizeof(*event)); - if (!event) + if (event == NULL) return -ENOMEM; event->name = strdup(name); - if (!event->name) { + if (event->name == NULL) { free(event); return -ENOMEM; @@ -390,11 +397,70 @@ rte_pmu_add_event(const char *name) return event->index; } +static void +add_events(const char *pattern) +{ + char *token, *copy; + int ret; + + copy = strdup(pattern); + if (copy == NULL) + return; + + token = strtok(copy, ","); + while (token) { + ret = rte_pmu_add_event(token); + if (ret < 0) + RTE_LOG(ERR, EAL, "failed to add %s event\n", token); + + token = strtok(NULL, ","); + } + + free(copy); +} + +static void +add_events_by_pattern(const char *pattern) +{ + regmatch_t rmatch; + char buf[BUFSIZ]; + unsigned int num; + regex_t reg; + + /* events are matched against occurrences of e=ev1[,ev2,..] pattern */ + if (regcomp(®, "e=([_[:alnum:]-],?)+", REG_EXTENDED)) + return; + + for (;;) { + if (regexec(®, pattern, 1, &rmatch, 0)) + break; + + num = rmatch.rm_eo - rmatch.rm_so; + if (num > sizeof(buf)) + num = sizeof(buf); + + /* skip e= pattern prefix */ + memcpy(buf, pattern + rmatch.rm_so + 2, num - 2); + buf[num] = '\0'; + add_events(buf); + + pattern += rmatch.rm_eo; + } + + regfree(®); +} + void eal_pmu_init(void) { + struct trace_arg *arg; + struct trace *trace; int ret; + trace = trace_obj_get(); + if (trace == NULL) + RTE_LOG(WARNING, EAL, "tracing not initialized\n"); + TAILQ_INIT(&rte_pmu.event_list); ret = scan_pmus(); @@ -409,6 +475,9 @@ eal_pmu_init(void) goto out; } + STAILQ_FOREACH(arg, &trace->args, next) + add_events_by_pattern(arg->val); + return; out: free(rte_pmu.name); diff --git a/lib/eal/include/rte_eal_trace.h b/lib/eal/include/rte_eal_trace.h index 5ef4398230..9b35af75d5 100644 --- a/lib/eal/include/rte_eal_trace.h +++ b/lib/eal/include/rte_eal_trace.h @@ -17,6 +17,7 @@ extern "C" { #include <rte_alarm.h> #include <rte_interrupts.h> +#include <rte_pmu.h> #include <rte_trace_point.h> #include "eal_interrupts.h" @@ -279,6 +280,15 @@ RTE_TRACE_POINT( rte_trace_point_emit_string(cpuset); ) +/* PMU */ +RTE_TRACE_POINT_FP( + rte_eal_trace_pmu_read, + RTE_TRACE_POINT_ARGS(unsigned int index), + uint64_t val; + val = rte_pmu_read(index); + rte_trace_point_emit_u64(val); +) + #ifdef __cplusplus } #endif diff --git a/lib/eal/version.map b/lib/eal/version.map index 1717b221b4..d87a867e5b 100644 --- a/lib/eal/version.map +++ b/lib/eal/version.map @@ -442,6 +442,7 @@ EXPERIMENTAL { rte_thread_join; # added in 23.03 + __rte_eal_trace_pmu_read; # WINDOWS_NO_EXPORT rte_pmu; # WINDOWS_NO_EXPORT rte_pmu_add_event; # WINDOWS_NO_EXPORT rte_pmu_read; # WINDOWS_NO_EXPORT -- 2.34.1