Add Current (Instant) Socket Power

* Updates:
    - rocm_smi_logger:
      General cleanup &
      Aligned to cpplint rules for usage
    - rocm_smi_monitor:
      Fixed MonitorTypes
      from not displaying properly in logs
      & Added socket power label + current
      socket power MonitorTypes
    - rocm_smi API:
      Added rsmi_dev_current_socket_power_get API
    - rocm_smi CLI:
      General cleanup,
      Concise info now displays device data
      in variable width (see printLogSpacer's
      new field),
      printLogSpacer now as an adjustable
      variable that overrides appWidth,
      Added Socket Power to base rocm-smi +
      --showpower CLI calls,
      --showpower & base rocm-smi CLI defaults
      to printing socket power (if not available,
      displays average power)
    - Cleaned up temp label references
    - power_read gtests:
      Added current socket power to testing

Change-Id: Ica57e6f98ad96e2584e7c7955e188f68d2dab89d
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: f078375350]
This commit is contained in:
Charis Poag
2023-09-24 02:29:07 -05:00
committed by Dmitrii Galantsev
parent e9addd72cc
commit 6e81bbcf16
13 changed files with 387 additions and 195 deletions
+92 -17
View File
@@ -77,7 +77,6 @@
#include "rocm_smi/rocm_smi64Config.h"
#include "rocm_smi/rocm_smi_logger.h"
using namespace ROCmLogging;
using namespace amd::smi;
static const uint32_t kMaxOverdriveLevel = 20;
@@ -2386,21 +2385,22 @@ rsmi_dev_temp_metric_get(uint32_t dv_ind, uint32_t sensor_type,
amd::smi::MonitorTypes mon_type = amd::smi::kMonInvalid;
uint16_t val_ui16;
static const std::map<rsmi_temperature_metric_t, amd::smi::MonitorTypes> kMetricTypeMap = {
{ RSMI_TEMP_CURRENT, amd::smi::kMonTemp },
{ RSMI_TEMP_MAX, amd::smi::kMonTempMax },
{ RSMI_TEMP_MIN, amd::smi::kMonTempMin },
{ RSMI_TEMP_MAX_HYST, amd::smi::kMonTempMaxHyst },
{ RSMI_TEMP_MIN_HYST, amd::smi::kMonTempMinHyst },
{ RSMI_TEMP_CRITICAL, amd::smi::kMonTempCritical },
{ RSMI_TEMP_CRITICAL_HYST, amd::smi::kMonTempCriticalHyst },
{ RSMI_TEMP_EMERGENCY, amd::smi::kMonTempEmergency },
{ RSMI_TEMP_EMERGENCY_HYST, amd::smi::kMonTempEmergencyHyst },
{ RSMI_TEMP_CRIT_MIN, amd::smi::kMonTempCritMin },
{ RSMI_TEMP_CRIT_MIN_HYST, amd::smi::kMonTempCritMinHyst },
{ RSMI_TEMP_OFFSET, amd::smi::kMonTempOffset },
{ RSMI_TEMP_LOWEST, amd::smi::kMonTempLowest },
{ RSMI_TEMP_HIGHEST, amd::smi::kMonTempHighest },
static const std::map<rsmi_temperature_metric_t, amd::smi::MonitorTypes>
kMetricTypeMap = {
{ RSMI_TEMP_CURRENT, amd::smi::kMonTemp },
{ RSMI_TEMP_MAX, amd::smi::kMonTempMax },
{ RSMI_TEMP_MIN, amd::smi::kMonTempMin },
{ RSMI_TEMP_MAX_HYST, amd::smi::kMonTempMaxHyst },
{ RSMI_TEMP_MIN_HYST, amd::smi::kMonTempMinHyst },
{ RSMI_TEMP_CRITICAL, amd::smi::kMonTempCritical },
{ RSMI_TEMP_CRITICAL_HYST, amd::smi::kMonTempCriticalHyst },
{ RSMI_TEMP_EMERGENCY, amd::smi::kMonTempEmergency },
{ RSMI_TEMP_EMERGENCY_HYST, amd::smi::kMonTempEmergencyHyst },
{ RSMI_TEMP_CRIT_MIN, amd::smi::kMonTempCritMin },
{ RSMI_TEMP_CRIT_MIN_HYST, amd::smi::kMonTempCritMinHyst },
{ RSMI_TEMP_OFFSET, amd::smi::kMonTempOffset },
{ RSMI_TEMP_LOWEST, amd::smi::kMonTempLowest },
{ RSMI_TEMP_HIGHEST, amd::smi::kMonTempHighest },
};
const auto mon_type_it = kMetricTypeMap.find(metric);
@@ -2485,7 +2485,8 @@ rsmi_dev_temp_metric_get(uint32_t dv_ind, uint32_t sensor_type,
return RSMI_STATUS_NOT_SUPPORTED;
}
*temperature = static_cast<int64_t>(val_ui16) * CENTRIGRADE_TO_MILLI_CENTIGRADE;
*temperature =
static_cast<int64_t>(val_ui16) * CENTRIGRADE_TO_MILLI_CENTIGRADE;
ss << __PRETTY_FUNCTION__ << " | ======= end ======= "
<< " | Success "
@@ -2815,6 +2816,80 @@ rsmi_dev_power_ave_get(uint32_t dv_ind, uint32_t sensor_ind, uint64_t *power) {
CATCH
}
rsmi_status_t
rsmi_dev_current_socket_power_get(uint32_t dv_ind, uint64_t *socket_power) {
TRY
std::ostringstream ss;
rsmi_status_t rsmiReturn = RSMI_STATUS_NOT_SUPPORTED;
std::string val_str;
uint32_t sensor_ind = 1; // socket_power sysfs files have 1-based indices
MonitorTypes mon_type = amd::smi::kMonPowerInput;
ss << __PRETTY_FUNCTION__ << " | ======= start =======, dv_ind="
<< std::to_string(dv_ind);
LOG_TRACE(ss);
if (socket_power == nullptr) {
rsmiReturn = RSMI_STATUS_INVALID_ARGS;
ss << __PRETTY_FUNCTION__
<< " | ======= end ======= "
<< " | Fail "
<< " | Device #: " << dv_ind
<< " | Type: " << monitorTypesToString.at(mon_type)
<< " | Cause: socket_power was a null ptr reference"
<< " | Returning = "
<< getRSMIStatusString(rsmiReturn) << " |";
LOG_ERROR(ss);
return RSMI_STATUS_INVALID_ARGS;
}
CHK_SUPPORT_SUBVAR_ONLY(socket_power, sensor_ind)
DEVICE_MUTEX
if (dev->monitor() == nullptr) {
ss << __PRETTY_FUNCTION__
<< " | ======= end ======= "
<< " | Fail "
<< " | Device #: " << dv_ind
<< " | Type: " << monitorTypesToString.at(mon_type)
<< " | Cause: hwmon monitor was a null ptr reference"
<< " | Returning = "
<< getRSMIStatusString(rsmiReturn) << " |";
LOG_ERROR(ss);
return rsmiReturn;
}
int ret = dev->monitor()->readMonitor(amd::smi::kMonPowerLabel,
sensor_ind, &val_str);
if (ret || val_str != "PPT" || val_str.size() != 3) {
if (ret != 0) {
rsmiReturn = amd::smi::ErrnoToRsmiStatus(ret);
}
ss << __PRETTY_FUNCTION__
<< " | ======= end ======= "
<< " | Fail "
<< " | Device #: " << dv_ind
<< " | Type: " << monitorTypesToString.at(mon_type)
<< " | Cause: readMonitor() returned an error status"
<< " or Socket Power label did not show PPT or size of label data was"
<< " unexpected"
<< " | Returning = "
<< getRSMIStatusString(rsmiReturn) << " |";
LOG_ERROR(ss);
return rsmiReturn;
}
rsmiReturn = get_dev_mon_value(mon_type, dv_ind, sensor_ind,
socket_power);
ss << __PRETTY_FUNCTION__
<< " | ======= end ======= "
<< " | Success "
<< " | Device #: " << dv_ind
<< " | Type: " << monitorTypesToString.at(mon_type)
<< " | Data: " << *socket_power
<< " | Returning = "
<< getRSMIStatusString(rsmiReturn) << " |";
LOG_TRACE(ss);
return rsmiReturn;
CATCH
}
rsmi_status_t
rsmi_dev_energy_count_get(uint32_t dv_ind, uint64_t *power,
float *counter_resolution, uint64_t *timestamp) {
-2
View File
@@ -68,8 +68,6 @@
#include "rocm_smi/rocm_smi_logger.h"
#include "shared_mutex.h" // NOLINT
using namespace ROCmLogging;
namespace amd {
namespace smi {
@@ -61,7 +61,6 @@
#include "rocm_smi/rocm_smi_exception.h"
#include "rocm_smi/rocm_smi_logger.h"
using namespace ROCmLogging;
using namespace amd::smi;
#define TRY try {
+56 -55
View File
@@ -71,9 +71,8 @@
#include "rocm_smi/rocm_smi_logger.h"
#include "rocm_smi/rocm_smi_main.h"
using namespace ROCmLogging;
Logger* Logger::m_Instance = nullptr;
ROCmLogging::Logger *ROCmLogging::Logger::m_Instance = nullptr;
// Log file name
// WARNING: File name should be changed here and
@@ -81,39 +80,39 @@ Logger* Logger::m_Instance = nullptr;
// in one place will cause a mismatch in these scripts,
// files may not have proper permissions, and logrotate
// would not function properly.
const std::string logPath = "/var/log/rocm_smi_lib/";
const std::string logBaseFName = "ROCm-SMI-lib";
const std::string logExtension = ".log";
const std::string logFileName = logPath + logBaseFName + logExtension;
#define LOGPATH "/var/log/rocm_smi_lib/"
#define LOGBASE_FNAME "ROCm-SMI-lib"
#define LOGEXTENSION ".log"
const char *logFileName = LOGPATH LOGBASE_FNAME LOGEXTENSION;
Logger::Logger() {
ROCmLogging::Logger::Logger() {
initialize_resources();
}
Logger::~Logger() {
ROCmLogging::Logger::~Logger() {
if (m_loggingIsOn) {
destroy_resources();
}
}
Logger* Logger::getInstance() throw() {
ROCmLogging::Logger* ROCmLogging::Logger::getInstance() throw() {
if (m_Instance == nullptr) {
m_Instance = new Logger();
m_Instance = new ROCmLogging::Logger();
}
return m_Instance;
}
void Logger::lock() {
void ROCmLogging::Logger::lock() {
m_Lock.lock();
}
void Logger::unlock() {
void ROCmLogging::Logger::unlock() {
m_Lock.unlock();
}
void Logger::logIntoFile(std::string& data) {
void ROCmLogging::Logger::logIntoFile(std::string& data) {
lock();
if(!m_File.is_open()) {
if (!m_File.is_open()) {
initialize_resources();
if (!m_File.is_open()) {
std::cout << "WARNING: re-initializing resources was unsuccessful."
@@ -127,24 +126,24 @@ void Logger::logIntoFile(std::string& data) {
unlock();
}
void Logger::logOnConsole(std::string& data) {
void ROCmLogging::Logger::logOnConsole(std::string& data) {
std::cout << getCurrentTime() << " " << data << std::endl;
}
// Returns: In string format, YY-MM-DD HH:MM:SS.microseconds
std::string Logger::getCurrentTime(void) {
using namespace std::chrono;
std::string ROCmLogging::Logger::getCurrentTime(void) {
std::string currentTime;
// get current time
auto now = system_clock::now();
auto now = std::chrono::system_clock::now();
// get number of milliseconds for the current second
// (remainder after division into seconds)
auto ms = duration_cast<microseconds>(now.time_since_epoch()) % 1000000;
auto ms = std::chrono::duration_cast<std::chrono::microseconds>(
now.time_since_epoch()) % 1000000;
// convert to std::time_t in order to convert to std::tm (broken time)
auto timer = system_clock::to_time_t(now);
auto timer = std::chrono::system_clock::to_time_t(now);
// convert to broken time
std::tm bt = *std::localtime(&timer);
@@ -159,7 +158,7 @@ std::string Logger::getCurrentTime(void) {
}
// Interface for Error Log
void Logger::error(const char* text) throw() {
void ROCmLogging::Logger::error(const char* text) throw() {
// By default, logging is disabled
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -182,18 +181,18 @@ void Logger::error(const char* text) throw() {
}
}
void Logger::error(std::string& text) throw() {
void ROCmLogging::Logger::error(std::string& text) throw() {
error(text.data());
}
void Logger::error(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::error(std::ostringstream& stream) throw() {
std::string text = stream.str();
error(text.data());
stream.str("");
}
// Interface for Alarm Log
void Logger::alarm(const char* text) throw() {
void ROCmLogging::Logger::alarm(const char* text) throw() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -216,18 +215,18 @@ void Logger::alarm(const char* text) throw() {
}
}
void Logger::alarm(std::string& text) throw() {
void ROCmLogging::Logger::alarm(std::string& text) throw() {
alarm(text.data());
}
void Logger::alarm(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::alarm(std::ostringstream& stream) throw() {
std::string text = stream.str();
alarm(text.data());
stream.str("");
}
// Interface for Always Log
void Logger::always(const char* text) throw() {
void ROCmLogging::Logger::always(const char* text) throw() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -250,18 +249,18 @@ void Logger::always(const char* text) throw() {
}
}
void Logger::always(std::string& text) throw() {
void ROCmLogging::Logger::always(std::string& text) throw() {
always(text.data());
}
void Logger::always(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::always(std::ostringstream& stream) throw() {
std::string text = stream.str();
always(text.data());
stream.str("");
}
// Interface for Buffer Log
void Logger::buffer(const char* text) throw() {
void ROCmLogging::Logger::buffer(const char* text) throw() {
// Buffer is the special case. So don't add log level
// and timestamp in the buffer message. Just log the raw bytes.
if ((m_LogType == FILE_LOG) && (m_LogLevel >= LOG_LEVEL_BUFFER)) {
@@ -284,18 +283,18 @@ void Logger::buffer(const char* text) throw() {
}
}
void Logger::buffer(std::string& text) throw() {
void ROCmLogging::Logger::buffer(std::string& text) throw() {
buffer(text.data());
}
void Logger::buffer(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::buffer(std::ostringstream& stream) throw() {
std::string text = stream.str();
buffer(text.data());
stream.str("");
}
// Interface for Info Log
void Logger::info(const char* text) throw() {
void ROCmLogging::Logger::info(const char* text) throw() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -318,18 +317,18 @@ void Logger::info(const char* text) throw() {
}
}
void Logger::info(std::string& text) throw() {
void ROCmLogging::Logger::info(std::string& text) throw() {
info(text.data());
}
void Logger::info(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::info(std::ostringstream& stream) throw() {
std::string text = stream.str();
info(text.data());
stream.str("");
}
// Interface for Trace Log
void Logger::trace(const char* text) throw() {
void ROCmLogging::Logger::trace(const char* text) throw() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -352,18 +351,18 @@ void Logger::trace(const char* text) throw() {
}
}
void Logger::trace(std::string& text) throw() {
void ROCmLogging::Logger::trace(std::string& text) throw() {
trace(text.data());
}
void Logger::trace(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::trace(std::ostringstream& stream) throw() {
std::string text = stream.str();
trace(text.data());
stream.str("");
}
// Interface for Debug Log
void Logger::debug(const char* text) throw() {
void ROCmLogging::Logger::debug(const char* text) throw() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -386,51 +385,53 @@ void Logger::debug(const char* text) throw() {
}
}
void Logger::debug(std::string& text) throw() {
void ROCmLogging::Logger::debug(std::string& text) throw() {
debug(text.data());
}
void Logger::debug(std::ostringstream& stream) throw() {
void ROCmLogging::Logger::debug(std::ostringstream& stream) throw() {
std::string text = stream.str();
debug(text.data());
stream.str("");
}
// Interfaces to control log levels
void Logger::updateLogLevel(LogLevel logLevel) {
void ROCmLogging::Logger::updateLogLevel(LogLevel logLevel) {
m_LogLevel = logLevel;
}
void Logger::enableAllLogLevels() {
void ROCmLogging::Logger::enableAllLogLevels() {
m_LogLevel = ENABLE_LOG;
}
// Disable all log levels, except error and alarm
void Logger::disableLog() {
void ROCmLogging::Logger::disableLog() {
m_LogLevel = DISABLE_LOG;
}
// Interfaces to control log Types
void Logger::updateLogType(LogType logType) {
void ROCmLogging::Logger::updateLogType(LogType logType) {
m_LogType = logType;
}
void Logger::enableConsoleLogging() {
void ROCmLogging::Logger::enableConsoleLogging() {
m_LogType = CONSOLE;
}
void Logger::enableFileLogging() {
void ROCmLogging::Logger::enableFileLogging() {
m_LogType = FILE_LOG;
}
// Returns a string of details on current log settings
std::string Logger::getLogSettings() {
std::string ROCmLogging::Logger::getLogSettings() {
std::string logSettings;
if (m_File.is_open()) {
logSettings += "OpenStatus = File (" + logFileName + ") is open";
logSettings += "OpenStatus = File (" + std::string(logFileName)
+ ") is open";
} else {
logSettings += "OpenStatus = File (" + logFileName + ") is not open";
logSettings += "OpenStatus = File (" + std::string(logFileName)
+ ") is not open";
}
logSettings += ", ";
@@ -480,11 +481,11 @@ std::string Logger::getLogSettings() {
// Returns current reported enabled logging state. State is controlled by
// user's environment variable RSMI_LOGGING.
bool Logger::isLoggerEnabled() {
bool ROCmLogging::Logger::isLoggerEnabled() {
return m_loggingIsOn;
}
void Logger::initialize_resources() {
void ROCmLogging::Logger::initialize_resources() {
// By default, logging is disabled (ie. no RSMI_LOGGING)
// The check below allows us to toggle logging through RSMI_LOGGING
// set or unset
@@ -492,7 +493,7 @@ void Logger::initialize_resources() {
if (!m_loggingIsOn) {
return;
}
m_File.open(logFileName.c_str(), std::ios::out | std::ios::app);
m_File.open(logFileName, std::ios::out | std::ios::app);
m_LogLevel = LOG_LEVEL_TRACE;
// RSMI_LOGGING = 1, output to logs only
// RSMI_LOGGING = 2, output to console only
@@ -521,9 +522,9 @@ void Logger::initialize_resources() {
if (m_File.fail()) {
std::cout << "WARNING: Failed opening log file." << std::endl;
}
chmod(logFileName.c_str(), S_IRUSR|S_IRGRP|S_IROTH|S_IWUSR|S_IWGRP|S_IWOTH);
chmod(logFileName, S_IRUSR|S_IRGRP|S_IROTH|S_IWUSR|S_IWGRP|S_IWOTH);
}
void Logger::destroy_resources() {
void ROCmLogging::Logger::destroy_resources() {
m_File.close();
}
+2 -3
View File
@@ -68,7 +68,6 @@
#include "rocm_smi/rocm_smi_kfd.h"
#include "rocm_smi/rocm_smi_logger.h"
using namespace ROCmLogging;
static const char *kPathDRMRoot = "/sys/class/drm";
static const char *kPathHWMonRoot = "/sys/class/hwmon";
@@ -314,12 +313,12 @@ RocmSMI::Initialize(uint64_t flags) {
int i_ret;
LOG_ALWAYS("=============== ROCM SMI initialize ================");
Logger::getInstance()->enableAllLogLevels();
ROCmLogging::Logger::getInstance()->enableAllLogLevels();
// Leaving below to allow developers to check current log settings
// std::string logSettings = Logger::getInstance()->getLogSettings();
// std::cout << "Current log settings:\n" << logSettings << std::endl;
if (Logger::getInstance()->isLoggerEnabled()) {
if (ROCmLogging::Logger::getInstance()->isLoggerEnabled()) {
logSystemDetails();
}
+8 -5
View File
@@ -3,7 +3,7 @@
* The University of Illinois/NCSA
* Open Source License (NCSA)
*
* Copyright (c) 2017, Advanced Micro Devices, Inc.
* Copyright (c) 2017-2023, Advanced Micro Devices, Inc.
* All rights reserved.
*
* Developed by:
@@ -58,8 +58,6 @@
#include "rocm_smi/rocm_smi_exception.h"
#include "rocm_smi/rocm_smi_logger.h"
using namespace ROCmLogging;
namespace amd {
namespace smi {
@@ -80,6 +78,8 @@ static const char *kMonPowerCapName = "power#_cap";
static const char *kMonPowerCapMaxName = "power#_cap_max";
static const char *kMonPowerCapMinName = "power#_cap_min";
static const char *kMonPowerAveName = "power#_average";
static const char *kMonPowerInputName = "power#_input";
static const char *kMonPowerLabelName = "power#_label";
static const char *kMonTempMaxName = "temp#_max";
static const char *kMonTempMinName = "temp#_min";
static const char *kMonTempMaxHystName = "temp#_max_hyst";
@@ -135,6 +135,8 @@ static const std::map<MonitorTypes, const char *> kMonitorNameMap = {
{kMonPowerCapMax, kMonPowerCapMaxName},
{kMonPowerCapMin, kMonPowerCapMinName},
{kMonPowerAve, kMonPowerAveName},
{kMonPowerInput, kMonPowerInputName},
{kMonPowerLabel, kMonPowerLabelName},
{kMonTempMax, kMonTempMaxName},
{kMonTempMin, kMonTempMinName},
{kMonTempMaxHyst, kMonTempMaxHystName},
@@ -202,7 +204,8 @@ static const std::map<const char *, monitor_depends_t> kMonFuncDependsMap = {
.variants = {kMonInvalid},
}
},
{"rsmi_dev_power_cap_default_get", { .mandatory_depends = {kMonPowerCapDefaultName},
{"rsmi_dev_power_cap_default_get", { .mandatory_depends =
{kMonPowerCapDefaultName},
.variants = {kMonInvalid},
}
},
@@ -613,7 +616,7 @@ void Monitor::fillSupportedFuncs(SupportedFuncMap *supported_funcs) {
supported_monitors = intersect;
}
if (!supported_monitors.empty()) {
for (unsigned long & supported_monitor : supported_monitors) {
for (uint64_t &supported_monitor : supported_monitors) {
if (m_type == eDefaultMonitor) {
assert(supported_monitor > 0);
supported_monitor |=
-1
View File
@@ -73,7 +73,6 @@
#include "rocm_smi/rocm_smi_device.h"
#include "rocm_smi/rocm_smi_logger.h"
using namespace ROCmLogging;
namespace amd {
namespace smi {