fix bug concurrent read of user_description_file

instance1.py

@@ -41,7 +41,7 @@ def run_expe(expe_num, user_category, window_size, clean_log):
     wl_folder = f'{WL_DIR}/expe{expe_num}'
     pf = f"{ROOT_DIR}/platform/average_metacentrum.xml"
     wl = f"{WL_DIR}/empty_workload.json"
-    uf = f"{ROOT_DIR}/sched_input/user_description_file.json"
+    uf = f"{EXPE_DIR}/cmd/user_description_file.json"
 
     # Demand response window, from 12 to (12 + window_size) on day2
     dm_window = [(24+12)*3600, (int) ((24+12+window_size)*3600)]

scripts/util.py

@@ -2,6 +2,8 @@
 import os
 import os.path
 import subprocess
+import numpy as np
+import pandas
 from matplotlib import figure, pyplot as plt
 from evalys.jobset import JobSet
 from evalys.metrics import compute_load
@@ -90,4 +92,37 @@ def plot_load_and_details(expe_file):
     plt.xlim(begin, end)
     fig.savefig(expe_file + '_viz.png')
     plt.show()
-    plt.close(fig)
\ No newline at end of file
+    plt.close(fig)
+
+def energy_consumed_in(window, OUT_DIR):
+    """Return the energy consumed during the time window (in kWh)."""
+    # The problem is that batsim time series don't always have the specific
+    # timestamp, we need to extrapolate
+    data = pandas.read_csv(OUT_DIR + "/_consumed_energy.csv")
+    energy = [0, 0]
+    for i in range(2):
+        first_greater = data[data['time'].ge(window[i])].index[0]
+        df_entry = data.iloc[first_greater]
+        energy[i] = df_entry['energy']
+        delta_energy = (df_entry['time'] - window[i]) * df_entry['epower']
+        energy[i] -= delta_energy
+
+    return (energy[1] - energy[0]) / 3600 / 1000
+
+
+def scheduling_metrics_in(window, OUT_DIR):
+    """Return the usual scheduling metrics for the subpart of jobs that have their submission time within the time window."""
+    [inf, sup] = window
+    data = pandas.read_csv(OUT_DIR + "/_jobs.csv")
+    data_in_window = data[(data.submission_time
+                           >= inf) & (data.submission_time <= sup)]
+
+    out = {}
+    out["makespan"] = data_in_window["finish_time"].max() - inf
+    out["#jobs"] = len(data_in_window.index)
+    out["mean_waiting_time"] = data_in_window["waiting_time"].mean()
+    out["max_waiting_time"] = data_in_window["waiting_time"].max()
+    out["mean_slowdown"] = data_in_window["stretch"].mean()
+    out["max_slowdown"] = data_in_window["stretch"].max()
+
+    return out
\ No newline at end of file