cc2c4e26ec
It is possible to optimize metrics when all SMT threads (CPUs) on a core are measuring events in system wide mode. For example, TMA metrics defines CORE_CLKS for Sandybrdige as: if SMT is disabled: CPU_CLK_UNHALTED.THREAD if SMT is enabled and recording on all SMT threads: CPU_CLK_UNHALTED.THREAD_ANY / 2 if SMT is enabled and not recording on all SMT threads: (CPU_CLK_UNHALTED.THREAD/2)* (1+CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE/CPU_CLK_UNHALTED.REF_XCLK ) That is two more events are necessary when not gathering counts on all SMT threads. To distinguish all SMT threads on a core vs system wide (all CPUs) call the new property core wide. Add a core wide test that determines the property from user requested CPUs, the topology and system wide. System wide is required as other processes running on a SMT thread will change the counts. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.garry@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220831174926.579643-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
38 lines
916 B
C
38 lines
916 B
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
#include <string.h>
|
|
#include "api/fs/fs.h"
|
|
#include "cputopo.h"
|
|
#include "smt.h"
|
|
|
|
bool smt_on(const struct cpu_topology *topology)
|
|
{
|
|
static bool cached;
|
|
static bool cached_result;
|
|
int fs_value;
|
|
|
|
if (cached)
|
|
return cached_result;
|
|
|
|
if (sysfs__read_int("devices/system/cpu/smt/active", &fs_value) >= 0)
|
|
cached_result = (fs_value == 1);
|
|
else
|
|
cached_result = cpu_topology__smt_on(topology);
|
|
|
|
cached = true;
|
|
return cached_result;
|
|
}
|
|
|
|
bool core_wide(bool system_wide, const char *user_requested_cpu_list,
|
|
const struct cpu_topology *topology)
|
|
{
|
|
/* If not everything running on a core is being recorded then we can't use core_wide. */
|
|
if (!system_wide)
|
|
return false;
|
|
|
|
/* Cheap case that SMT is disabled and therefore we're inherently core_wide. */
|
|
if (!smt_on(topology))
|
|
return true;
|
|
|
|
return cpu_topology__core_wide(topology, user_requested_cpu_list);
|
|
}
|