def _get_trace_metrics(self, trace_path):
"""
Parse a trace (or used cached results) and extract extra metrics from it
Returns a DataFrame with columns:
metric,value,units
"""
cache_path = os.path.join(os.path.dirname(trace_path), 'lisa_trace_metrics.csv')
if self.use_cached_trace_metrics and os.path.exists(cache_path):
return pd.read_csv(cache_path)
# I wonder if this should go in LISA itself? Probably.
metrics = []
events = ['irq_handler_entry', 'cpu_frequency', 'nohz_kick', 'sched_switch',
'sched_load_cfs_rq', 'sched_load_avg_task', 'thermal_temperature']
trace = Trace(self.platform, trace_path, events)
metrics.append(('cpu_wakeup_count', len(trace.data_frame.cpu_wakeups()), None))
# Helper to get area under curve of multiple CPU active signals
def get_cpu_time(trace, cpus):
df = pd.DataFrame([trace.getCPUActiveSignal(cpu) for cpu in cpus])
return df.sum(axis=1).sum(axis=0)
clusters = trace.platform.get('clusters')
if clusters:
for cluster in clusters.values():
name = '-'.join(str(c) for c in cluster)
df = trace.data_frame.cluster_frequency_residency(cluster)
if df is None or df.empty:
self._log.warning("Can't get cluster freq residency from %s",
trace.data_dir)
else:
df = df.reset_index()
avg_freq = (df.frequency * df.time).sum() / df.time.sum()
metric = 'avg_freq_cluster_{}'.format(name)
metrics.append((metric, avg_freq, 'MHz'))
df = trace.data_frame.trace_event('cpu_frequency')
df = df[df.cpu == cluster[0]]
metrics.append(('freq_transition_count_{}'.format(name), len(df), None))
active_time = area_under_curve(trace.getClusterActiveSignal(cluster))
metrics.append(('active_time_cluster_{}'.format(name),
active_time, 'seconds'))
metrics.append(('cpu_time_cluster_{}'.format(name),
get_cpu_time(trace, cluster), 'cpu-seconds'))
metrics.append(('cpu_time_total',
get_cpu_time(trace, range(trace.platform['cpus_count'])),
'cpu-seconds'))
event = None
if trace.hasEvents('sched_load_cfs_rq'):
event = 'sched_load_cfs_rq'
row_filter = lambda r: r.path == '/'
column = 'util'
elif trace.hasEvents('sched_load_avg_cpu'):
event = 'sched_load_avg_cpu'
row_filter = lambda r: True
column = 'util_avg'
if event:
df = trace.data_frame.trace_event(event)
util_sum = (handle_duplicate_index(df)[row_filter]
.pivot(columns='cpu')[column].ffill().sum(axis=1))
avg_util_sum = area_under_curve(util_sum) / (util_sum.index[-1] - util_sum.index[0])
metrics.append(('avg_util_sum', avg_util_sum, None))
if trace.hasEvents('thermal_temperature'):
df = trace.data_frame.trace_event('thermal_temperature')
for zone, zone_df in df.groupby('thermal_zone'):
metrics.append(('tz_{}_start_temp'.format(zone),
zone_df.iloc[0]['temp_prev'],
'milliCelcius'))
if len(zone_df == 1): # Avoid division by 0
avg_tmp = zone_df['temp'].iloc[0]
else:
avg_tmp = (area_under_curve(zone_df['temp'])
/ (zone_df.index[-1] - zone_df.index[0]))
metrics.append(('tz_{}_avg_temp'.format(zone),
avg_tmp,
'milliCelcius'))
ret = pd.DataFrame(metrics, columns=['metric', 'value', 'units'])
ret.to_csv(cache_path, index=False)
return ret
def _get_trace_metrics(self, trace_path):
"""
Parse a trace (or used cached results) and extract extra metrics from it
Returns a DataFrame with columns:
metric,value,units
"""
cache_path = os.path.join(os.path.dirname(trace_path),
'lisa_trace_metrics.csv')
if self.use_cached_trace_metrics and os.path.exists(cache_path):
return pd.read_csv(cache_path)
# I wonder if this should go in LISA itself? Probably.
metrics = []
events = [
'irq_handler_entry', 'cpu_frequency', 'nohz_kick', 'sched_switch',
'sched_load_cfs_rq', 'sched_load_avg_task', 'thermal_temperature'
]
trace = Trace(self.platform, trace_path, events)
metrics.append(
('cpu_wakeup_count', len(trace.data_frame.cpu_wakeups()), None))
# Helper to get area under curve of multiple CPU active signals
def get_cpu_time(trace, cpus):
df = pd.DataFrame([trace.getCPUActiveSignal(cpu) for cpu in cpus])
return df.sum(axis=1).sum(axis=0)
clusters = trace.platform.get('clusters')
if clusters:
for cluster in clusters.values():
name = '-'.join(str(c) for c in cluster)
df = trace.data_frame.cluster_frequency_residency(cluster)
if df is None or df.empty:
self._log.warning(
"Can't get cluster freq residency from %s",
trace.data_dir)
else:
df = df.reset_index()
avg_freq = (df.frequency * df.time).sum() / df.time.sum()
metric = 'avg_freq_cluster_{}'.format(name)
metrics.append((metric, avg_freq, 'MHz'))
df = trace.data_frame.trace_event('cpu_frequency')
df = df[df.cpu == cluster[0]]
metrics.append(
('freq_transition_count_{}'.format(name), len(df), None))
active_time = area_under_curve(
trace.getClusterActiveSignal(cluster))
metrics.append(('active_time_cluster_{}'.format(name),
active_time, 'seconds'))
metrics.append(('cpu_time_cluster_{}'.format(name),
get_cpu_time(trace, cluster), 'cpu-seconds'))
metrics.append(
('cpu_time_total',
get_cpu_time(trace,
range(trace.platform['cpus_count'])), 'cpu-seconds'))
event = None
if trace.hasEvents('sched_load_cfs_rq'):
event = 'sched_load_cfs_rq'
row_filter = lambda r: r.path == '/'
column = 'util'
elif trace.hasEvents('sched_load_avg_cpu'):
event = 'sched_load_avg_cpu'
row_filter = lambda r: True
column = 'util_avg'
if event:
df = trace.data_frame.trace_event(event)
util_sum = (handle_duplicate_index(df)[row_filter].pivot(
columns='cpu')[column].ffill().sum(axis=1))
avg_util_sum = area_under_curve(util_sum) / (util_sum.index[-1] -
util_sum.index[0])
metrics.append(('avg_util_sum', avg_util_sum, None))
if trace.hasEvents('thermal_temperature'):
df = trace.data_frame.trace_event('thermal_temperature')
for zone, zone_df in df.groupby('thermal_zone'):
metrics.append(('tz_{}_start_temp'.format(zone),
zone_df.iloc[0]['temp_prev'], 'milliCelcius'))
if len(zone_df == 1): # Avoid division by 0
avg_tmp = zone_df['temp'].iloc[0]
else:
avg_tmp = (area_under_curve(zone_df['temp']) /
(zone_df.index[-1] - zone_df.index[0]))
metrics.append(
('tz_{}_avg_temp'.format(zone), avg_tmp, 'milliCelcius'))
ret = pd.DataFrame(metrics, columns=['metric', 'value', 'units'])
ret.to_csv(cache_path, index=False)
return ret
def get_trace_metrics(self, trace_path):
cache_path = os.path.join(os.path.dirname(trace_path),
'lisa_trace_metrics.csv')
if self.use_cached_trace_metrics and os.path.exists(cache_path):
return pd.read_csv(cache_path)
# I wonder if this should go in LISA itself? Probably.
metrics = []
events = [
'irq_handler_entry', 'cpu_frequency', 'nohz_kick', 'sched_switch',
'sched_load_cfs_rq', 'sched_load_avg_task'
]
trace = Trace(self.platform, trace_path, events)
if hasattr(trace.data_frame, 'cpu_wakeups'): # Not merged in LISA yet
metrics.append(('cpu_wakeup_count',
len(trace.data_frame.cpu_wakeups()), None))
# Helper to get area under curve of multiple CPU active signals
def get_cpu_time(trace, cpus):
df = pd.DataFrame([trace.getCPUActiveSignal(cpu) for cpu in cpus])
return df.sum(axis=1).sum(axis=0)
clusters = trace.platform.get('clusters')
if clusters:
for cluster in clusters.values():
name = '-'.join(str(c) for c in cluster)
df = trace.data_frame.cluster_frequency_residency(cluster)
if df is None or df.empty:
print "Can't get cluster freq residency from {}".format(
trace.data_dir)
else:
df = df.reset_index()
avg_freq = (df.frequency * df.time).sum() / df.time.sum()
metric = 'avg_freq_cluster_{}'.format(name)
metrics.append((metric, avg_freq, 'MHz'))
df = trace.data_frame.trace_event('cpu_frequency')
df = df[df.cpu == cluster[0]]
metrics.append(
('freq_transition_count_{}'.format(name), len(df), None))
active_time = area_under_curve(
trace.getClusterActiveSignal(cluster))
metrics.append(('active_time_cluster_{}'.format(name),
active_time, 'seconds'))
metrics.append(('cpu_time_cluster_{}'.format(name),
get_cpu_time(trace, cluster), 'cpu-seconds'))
metrics.append(
('cpu_time_total',
get_cpu_time(trace,
range(trace.platform['cpus_count'])), 'cpu-seconds'))
event = None
if trace.hasEvents('sched_load_cfs_rq'):
event = 'sched_load_cfs_rq'
row_filter = lambda r: r.path == '/'
column = 'util'
elif trace.hasEvents('sched_load_avg_cpu'):
event = 'sched_load_avg_cpu'
row_filter = lambda r: True
column = 'util_avg'
if event:
df = trace.data_frame.trace_event(event)
util_sum = (handle_duplicate_index(df)[row_filter].pivot(
columns='cpu')[column].ffill().sum(axis=1))
avg_util_sum = area_under_curve(util_sum) / (util_sum.index[-1] -
util_sum.index[0])
metrics.append(('avg_util_sum', avg_util_sum, None))
if trace.hasEvents('nohz_kick'):
metrics.append(
('nohz_kick_count',
len(trace.data_frame.trace_event('nohz_kick')), None))
ret = pd.DataFrame(metrics, columns=['metric', 'value', 'units'])
if self.use_cached_trace_metrics:
ret.to_csv(cache_path)
return ret