Use thread information in latency analysis

xlap/analyse/latency.py

@@ -19,35 +19,38 @@ def _get_cyclestamp(df, event, idx):
     cycleevent = [x for x in list(df) if str(x) == cname][0]
     return list(df[cycleevent])[idx]
 
-def _happens_before(df, a, b):
+def _get_thread_for_event(config, e):
+    for name, data in config['stamps'].items():
+        if name == str(e)[:-2]:
+            return data['Thread']
+    return None
+
+def _happens_before(df, a, b, config):
     """
     check if a happens-before b in the trace
     """
     l = len(df[a])
-    # first, check if the timestamps are often equal. In this case, we have a
-    # very short region and we should therefore check cyclestamps as well.
-    #
-    # EPSILON represents a grace period, in microseconds, for detecting similar
-    # timestamps.
-    #
-    # TODO: we should only check the cycle stamps if a and b occur in the same
-    # thread.
-    EPSILON=1
-    numeq = len([i for i in range(l) if _get_timestamp(df, a, i) + EPSILON >= _get_timestamp(df, b, i) and _get_timestamp(df, a, i) <= _get_timestamp(df, b, i) + EPSILON])
-    if (numeq >= 0.95 * l):
-        # The region is so short that we have to take cyclestamps into consideration
+    # check whether a and b occur in the same thread. If so, a and b cannot be
+    # concurrent.
+    ta = _get_thread_for_event(config, a)
+    tb = _get_thread_for_event(config, b)
+    if (ta == tb and ta != None and tb != None):
         for i in range(l):
             tsa = _get_timestamp(df, a, i)
             tsb = _get_timestamp(df, b, i)
             if tsa > tsb:
                 return False
-            if tsa == tsb and _get_cyclestamp(df, a, i) > _get_cyclestamp(df, b, i):
-                return False
-    else:
-        # The region i long enough to use timestamps only
-        for i in range(l):
-            if _get_timestamp(df, a, i) >= _get_timestamp(df, b, i):
+            csa = _get_cyclestamp(df, a, i)
+            csb = _get_cyclestamp(df, b, i)
+            if tsa == tsb and csa > csb and csb != 0:
                 return False
+        return True
+
+    # since a and b occur in different threads, we cannot compare cyclestamps.
+    # If in doubt, a and b are concurrent.
+    for i in range(l):
+        if _get_timestamp(df, a, i) >= _get_timestamp(df, b, i):
+            return False
     return True
 
 def _fast_happens_before(df, a, b, hb):
@@ -94,9 +97,7 @@ def _plot_critical_regions(df,hdb):
         print("%-10f %10s -> %10s"%(region['Correlation'], region['Start'], region['End']), file=sys.stderr)
 
 
-def analyse(df):
-    #print(str(_happens_before(df, 'PrrtSendStart_T', 'PrrtSendEnd_T')), file=sys.stderr)
-    #print(str(len([i for i in range(len(df['PrrtSendStart_T'])) if _get_timestamp(df, 'PrrtSendStart_T', i) == _get_timestamp(df, 'PrrtSendEnd_T', i) and _get_cyclestamp(df, 'PrrtSendStart_T', i) < _get_cyclestamp(df, 'PrrtSendEnd_T', i)])), file=sys.stderr)
+def analyse(df, config):
     hb = []
     for event1 in df:
         if not str(event1).endswith("_T"):
@@ -107,10 +108,9 @@ def analyse(df):
                 continue
             if str(event1) == str(event2):
                 continue
-            if _happens_before(df, event1, event2):
+            if _happens_before(df, event1, event2, config):
                 hb += [{'Start':str(event1), 'End':str(event2)}]
 
-    #print (",".join(map(str,hb)), file=sys.stderr)
     hdb = []
     e2e = list(df['EndToEnd_D'])
     for event1 in df:

xlap/command_line.py

@@ -43,7 +43,7 @@ def main():
                 print(output)
         elif command == "latency":
             df_data = evaluate(data_files["sender"], data_files["receiver"], config=config, kind=0)
-            latency.analyse(df_data)
+            latency.analyse(df_data, config)
         else:
             df_data = evaluate(data_files["sender"], data_files["receiver"], config=config, kind=0)