def sum_values(data):
"""
Interpolate values where missing and sum data across NCPs
Args:
data (dict): attr -> app -> ncp -> timestamp -> value
Returns:
dict: attr -> app -> timestamp -> value
"""
# first compute all times across all data
all_times = set()
for attr, attr_data in data.items():
for app, app_data in attr_data.items():
for node_name, time_data in app_data.items():
all_times.update(time_data.keys())
all_times = list(sorted(all_times))
result = dict()
for attr, attr_data in data.items():
result_attr_data = dict()
for app, app_data in attr_data.items():
values_summed = np.zeros(len(all_times))
for node_name, time_data in app_data.items():
values_ar = map_utils.fill_missing_times(all_times, time_data)
values_summed = np.add(values_summed, values_ar)
result_attr_data[app] = dict(zip(all_times, values_summed))
result[attr] = result_attr_data
return result
def process_file(first_timestamp_ms, output, csv_file):
ncp = csv_file.stem
get_logger().debug("Processing %s ncp: %s", csv_file, ncp)
df = pd.read_csv(csv_file)
df['minutes'] = (df['timestamp'] - first_timestamp_ms) / 1000 / 60
df = df.sort_values(by=['minutes'])
max_minutes = df['minutes'].max()
services = df['service'].unique()
source_regions = df['source region'].unique()
attributes = df['attribute'].unique()
xdata = df['minutes'].unique()
for service in sorted(services):
get_logger().debug("Service: %s", service)
for attr in attributes:
get_logger().debug("attribute: %s", attr)
fig, ax = map_utils.subplots()
ax.set_title(f"Inferred demand for {service} and {attr} on {ncp}")
ax.set_xlabel('time (minutes)')
ax.set_xlim(left=0, right=max_minutes)
ydata = list()
labels = list()
for source_region in sorted(source_regions):
get_logger().debug("source region: %s", source_region)
plot_data = df.loc[(df['service'] == service)
& (df['source region'] == source_region) &
(df['attribute'] == attr)]
label = source_region
time_data = pd.Series(plot_data['value'].values,
index=plot_data['minutes']).to_dict()
yfilled = map_utils.fill_missing_times(xdata, time_data)
get_logger().debug("yseries len: %d", len(yfilled))
ydata.append(yfilled)
labels.append(label)
get_logger().debug("xdata len: %d", len(xdata))
get_logger().debug("ydata len: %d", len(ydata))
ax.stackplot(xdata, ydata, labels=labels)
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles,
labels,
bbox_to_anchor=(1.04, 1),
loc="upper left")
output_name = output / f"{ncp}-{service}-{attr}.png"
fig.savefig(output_name.as_posix(),
format='png',
bbox_extra_artists=(lgd, ),
bbox_inches='tight')
plt.close(fig)
def sum_capacity_values_by_region(data, node_region, container_node):
"""
Interpolate capacity values where missing and sum data per region.
Args:
data (dict): attr -> app -> ncp -> timestamp -> value
node_region (dict): ncp -> region
container_node (dict): container -> ncp
Returns:
dict: region -> attr -> app -> timestamp -> value
"""
# first compute all times across all data
all_times = set()
for attr, attr_data in data.items():
for app, app_data in attr_data.items():
for node_name, time_data in app_data.items():
all_times.update(time_data.keys())
all_times = list(sorted(all_times))
regions = set(node_region.values())
result = dict()
for sum_region in regions:
region_data = dict()
for attr, attr_data in data.items():
result_attr_data = dict()
for app, app_data in attr_data.items():
values_summed = np.zeros(len(all_times))
for container_name, time_data in app_data.items():
ncp = container_node[container_name]
region = node_region[ncp]
if region == sum_region:
values_ar = map_utils.fill_missing_times(all_times, time_data)
values_summed = np.add(values_summed, values_ar)
result_attr_data[app] = dict(zip(all_times, values_summed))
region_data[attr] = result_attr_data
result[sum_region] = region_data
return result
def output_graphs(first_timestamp_ms, output, data, load_name):
all_times = find_all_times(data)
all_times_minutes = [(float(t) - first_timestamp_ms) / 1000.0 / 60.0
for t in all_times]
max_minutes = max(all_times_minutes)
for app, app_values in data.items():
for attr, attr_values in app_values.items():
fig, ax = map_utils.subplots()
ax.set_title(f"{load_name} for service: {app} attribute: {attr}")
ax.set_xlabel('time (minutes)')
ax.set_xlim(left=0, right=max_minutes)
plot_data = dict()
for container_name, time_values in attr_values.items():
time_values_minutes = dict()
for timestamp, value in time_values.items():
time = (float(timestamp) -
first_timestamp_ms) / 1000.0 / 60.0
get_logger().debug("time %s timestamp %s first_time %s",
time, timestamp, first_timestamp_ms)
time_values_minutes[time] = value
yinterp = map_utils.fill_missing_times(all_times_minutes,
time_values_minutes)
plot_data[container_name] = yinterp
series_labels, ydata = zip(*sorted(plot_data.items()))
plt.stackplot(all_times_minutes, ydata, labels=series_labels)
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles,
labels,
bbox_to_anchor=(1.04, 1),
loc="upper left")
output_name = output / f"container-{load_name}-{app}-{attr}.png"
plt.savefig(output_name.as_posix(),
format='png',
bbox_extra_artists=(lgd, ),
bbox_inches='tight')
plt.close(fig)
def output_graphs(first_time, output, data, container_expected_queue_lengths,
load_name, container_queue_length_capacity):
'''
first_time (int): reference time in ms for run
output: output folder for graphs
data: resource report data
container_expected_queue_lengths: estimated queeu lengths from processing latency csv files
container_queue_length_capacity: queue length capacity for containers
'''
_, all_times = find_first_time(data)
all_times_minutes = [(float(t) - first_time) / 1000.0 / 60.0
for t in all_times]
get_logger().debug("First time %s", first_time)
max_minutes = max(all_times_minutes)
for app, app_values in data.items():
container_data = dict()
for attr, attr_values in app_values.items():
if attr == "CPU" or attr == "QueueLength":
for container_name, time_values in attr_values.items():
container_data.setdefault(container_name,
dict())[attr] = time_values
app_total_queue_lengths = 0
app_total_queue_lengths_within_capacity = 0
for container_name, attr_data in container_data.items():
fig, ax = map_utils.subplots()
ax.set_title(
f"{load_name} for service: {app}, container: {container_name}")
ax.set_xlabel('time (minutes)')
ax.set_xlim(left=0, right=max_minutes)
queue_lengths = 0
queue_lengths_within_capacity = 0
if container_queue_length_capacity:
ax.set_ylim(top=2.0)
for attr, time_values in attr_data.items():
time_values_minutes = dict()
for timestamp, value in time_values.items():
time = (float(timestamp) - first_time) / 1000.0 / 60.0
get_logger().debug("time %s timestamp %s first_time %s",
time, timestamp, first_time)
if attr == "QueueLength" and container_queue_length_capacity != None:
queue_lengths += value
queue_lengths_within_capacity += min(
value, container_queue_length_capacity)
time_values_minutes[
time] = value / container_queue_length_capacity
else:
time_values_minutes[time] = value
yinterp = map_utils.fill_missing_times(all_times_minutes,
time_values_minutes)
times = sorted(list(time_values_minutes.keys()))
values = list()
for time in times:
values.append(time_values_minutes[time])
if attr == "QueueLength":
#plt.scatter(times, values, label=attr, color='red', marker='o')
plt.plot(all_times_minutes,
yinterp,
label=attr,
color='red')
else:
#plt.scatter(times, values, label=attr, marker='o')
plt.plot(all_times_minutes, yinterp, label=attr)
get_logger().debug(
f'container_expected_queue_lengths.keys(): {container_expected_queue_lengths.keys()}'
)
# plot estimated queue lengthss
if app in container_expected_queue_lengths.keys():
times = sorted(
list(container_expected_queue_lengths[app]
[container_name].keys()))
times_minutes = [(float(time) - first_time) / 1000.0 / 60.0
for time in times]
if container_queue_length_capacity != None:
queue_lengths = [
container_expected_queue_lengths[app][container_name]
[time] / container_queue_length_capacity
for time in times
]
else:
queue_lengths = [
container_expected_queue_lengths[app][container_name]
[time] for time in times
]
plt.plot(times_minutes,
queue_lengths,
label='Estimated queue length',
color='black')
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles,
labels,
bbox_to_anchor=(1.04, 1),
loc="upper left")
output_name = output / f"container-{load_name}-{app}-{container_name}-CPU_QueueLength.png"
plt.savefig(output_name.as_posix(),
format='png',
bbox_extra_artists=(lgd, ),
bbox_inches='tight')
plt.close(fig)
get_logger().info(
f'container {container_name}: queue_lengths: {queue_lengths}, queue_lengths_within_capacity: {queue_lengths_within_capacity}, percent queue lengths within capacity: {[queue_lengths_within_capacity / queue_lengths if queue_lengths > 0 else float("NaN")]}'
)
app_total_queue_lengths += queue_lengths
app_total_queue_lengths_within_capacity += queue_lengths_within_capacity
get_logger().info(
f'app {app}: queue_lengths: {app_total_queue_lengths}, queue_lengths_within_capacity: {app_total_queue_lengths_within_capacity}, percent queue lengths within capacity: {app_total_queue_lengths_within_capacity / app_total_queue_lengths}'
)
def output_graphs_per_region(first_timestamp, output, capacity, data, label):
"""
Create a graph per node attribute.
Creates files with names <label>-<attribute>-<region>.png
Args:
first_timestamp(datetime.datetime): when the simulation started
output (Path): output directory
data (dict): region -> attr -> app -> timestamp -> value
label (str): used to label the graph and generate the filenames
capacity: region -> attr -> app -> timestamp -> value
"""
first_timestamp_ms = first_timestamp.timestamp() * 1000
max_minutes = 0
try:
for region, region_data in data.items():
capacity_region = capacity[region]
for attr, attr_data in region_data.items():
frames = list()
fig, ax = map_utils.subplots()
ax.set_title(f"{attr} {label} in {region}")
ax.set_xlabel("Time (minutes)")
stack_xs = None
stack_ys = list()
stack_labels = list()
total_capacity = None
if attr in capacity_region and 'QueueLength' != attr:
for app, app_data in sorted(capacity_region[attr].items()):
if len(app_data) > 0:
pairs = sorted(app_data.items())
timestamps, values = zip(*pairs)
times = [map_utils.timestamp_to_minutes(float(t) - first_timestamp_ms) for t in timestamps]
max_minutes = max(max_minutes, max(times))
series_label=f"{app} capacity"
frames.append(pd.DataFrame(list(values), index=list(times), columns=[series_label]))
ax.plot(times, values, label=series_label)
if total_capacity is None:
total_capacity = app_data.copy()
else:
total_capacity = {k: total_capacity.get(k, 0) + app_data.get(k, 0) for k in set(total_capacity) | set(app_data)}
app_timestamps = None
for app, app_data in sorted(attr_data.items()):
if len(app_data) > 0:
pairs = sorted(app_data.items())
timestamps, values = zip(*pairs)
times = [map_utils.timestamp_to_minutes(float(t) - first_timestamp_ms) for t in timestamps]
max_minutes = max(max_minutes, max(times))
if app_timestamps is None:
app_timestamps = timestamps
frames.append(pd.DataFrame(list(values), index=list(times), columns=[app]))
ax.plot(times, values, label=app)
if stack_xs is None:
stack_xs = times
stack_ys.append(values)
stack_labels.append(app)
ax.set_xlim(left=0, right=max_minutes)
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles, labels, bbox_to_anchor=(1.04, 1), loc="upper left")
output_name = output / f"{label}-{attr}-{region}.png"
fig.savefig(output_name.as_posix(), format='png', bbox_extra_artists=(lgd,), bbox_inches='tight')
plt.close(fig)
# write out CSV of the plot data
df = pd.concat(frames, axis=1)
df.to_csv(output / f"{label}-{attr}-{region}.csv", index_label="relative minutes")
if app_timestamps is not None and total_capacity is not None:
# create stacked plot
fig, ax = map_utils.subplots()
ax.set_title(f"{attr} {label} in {region}")
ax.set_xlabel("Time (minutes)")
ax.set_xlim(left=0, right=max_minutes)
ax.stackplot(stack_xs, stack_ys, labels=stack_labels)
total_capacity = map_utils.fill_missing_times(app_timestamps, total_capacity)
ax.plot(stack_xs, total_capacity, label="Total allocated capacity")
handles, labels = ax.get_legend_handles_labels()
lgd = ax.legend(handles, labels, bbox_to_anchor=(1.04, 1), loc="upper left")
output_name = output / f"{label}-{attr}-{region}_stacked.png"
fig.savefig(output_name.as_posix(), format='png', bbox_extra_artists=(lgd,), bbox_inches='tight')
plt.close(fig)
elif 'QueueLength' != attr:
get_logger().warning("Missing data to draw stackplot for %s %s in %s", label, attr, region)
except:
get_logger().exception("Unexpected error")
