Created infrastructure for calculating scaling factors.

1 files changed, 108 insertions, 25 deletions

diff --git a/parse/sched.py b/parse/sched.py
index 1213f0d..1f07751 100644
--- a/parse/sched.py
+++ b/parse/sched.py
@@ -2,8 +2,8 @@ import config.config as conf
 import os
 import re
 import struct
-import sys
 import subprocess
+import sys
 
 from collections import defaultdict,namedtuple
 from common import recordtype
@@ -33,8 +33,9 @@ class TimeTracker:
         self.job   = record.job
 
 # Data stored for each task
-TaskParams = namedtuple('TaskParams',  ['wcet', 'period', 'cpu'])
-TaskData   = recordtype('TaskData',    ['params', 'jobs', 'blocks', 'misses'])
+TaskParams = namedtuple('TaskParams',  ['wcet', 'period', 'cpu', 'level'])
+TaskData   = recordtype('TaskData',    ['params', 'jobs', 'loads',
+                                        'blocks', 'misses', 'execs'])
 
 # Map of event ids to corresponding class, binary format, and processing methods
 RecordInfo = namedtuple('RecordInfo', ['clazz', 'fmt', 'method'])
@@ -124,6 +125,7 @@ def read_data(task_dict, fnames):
 
 def process_completion(task_dict, record):
     task_dict[record.pid].misses.store_time(record)
+    task_dict[record.pid].loads += [record.load]
 
 def process_release(task_dict, record):
     data = task_dict[record.pid]
@@ -131,7 +133,9 @@ def process_release(task_dict, record):
     data.misses.start_time(record)
 
 def process_param(task_dict, record):
-    params = TaskParams(record.wcet, record.period, record.partition)
+    level = chr(97 + record.level)
+    params = TaskParams(record.wcet, record.period,
+                        record.partition, level)
     task_dict[record.pid].params = params
 
 def process_block(task_dict, record):
@@ -140,14 +144,27 @@ def process_block(task_dict, record):
 def process_resume(task_dict, record):
     task_dict[record.pid].blocks.store_time(record)
 
+def process_switch_to(task_dict, record):
+    task_dict[record.pid].execs.start_time(record)
+
+def process_switch_away(task_dict, record):
+    task_dict[record.pid].execs.store_time(record)
+
 register_record('ResumeRecord', 9, process_resume, 'Q8x', ['when'])
 register_record('BlockRecord', 8, process_block, 'Q8x', ['when'])
-register_record('CompletionRecord', 7, process_completion, 'Q8x', ['when'])
+register_record('CompletionRecord', 7, process_completion, 'QQ', ['when', 'load'])
 register_record('ReleaseRecord', 3, process_release, 'QQ', ['release', 'when'])
-register_record('ParamRecord', 2, process_param, 'IIIcc2x',
-                          ['wcet','period','phase','partition', 'task_class'])
+register_record('SwitchToRecord', 5, process_switch_to, 'Q8x', ['when'])
+register_record('SwitchAwayRecord', 6, process_switch_away, 'Q8x', ['when'])
+register_record('ParamRecord', 2, process_param, 'IIIcccx',
+                ['wcet','period','phase','partition', 'task_class', 'level'])
+
+saved_stats = []
+def get_task_data(data_dir, work_dir = None):
+    '''Parse sched trace files'''
+    if data_dir in saved_stats:
+        return data_dir
 
-def extract_sched_data(result, data_dir, work_dir):
     bin_files   = conf.FILES['sched_data'].format(".*")
     output_file = "%s/out-st" % work_dir
 
@@ -157,24 +174,46 @@ def extract_sched_data(result, data_dir, work_dir):
 
     # Save an in-english version of the data for debugging
     # This is optional and will only be done if 'st_show' is in PATH
-    if conf.BINS['st_show']:
+    if work_dir and conf.BINS['st_show']:
         cmd_arr = [conf.BINS['st_show']]
         cmd_arr.extend(bins)
         with open(output_file, "w") as f:
             print("calling %s" % cmd_arr)
             subprocess.call(cmd_arr, cwd=data_dir, stdout=f)
 
-    task_dict = defaultdict(lambda :
-                            TaskData(0, 0, TimeTracker(), TimeTracker()))
+    task_dict = defaultdict(lambda :TaskData(0, 0, 0, [], TimeTracker(),
+                                             TimeTracker(), TimeTracker()))
 
     # Gather per-task values
     read_data(task_dict, bins)
 
-    stat_data = {"avg-tard"   : [], "max-tard"  : [],
-                 "avg-block"  : [], "max-block" : [],
-                 "miss-ratio" : []}
+    saved_stats[data_dir] = task_dict
+    return task_dict
+
+class LeveledArray(object):
+    """Groups statistics by the level of the task to which they apply"""
+    def __init__(self):
+        self.name = name
+            self.vals = defaultdict(lambda: defaultdict(lambda:[]))
+
+    def add(self, name, level, value):
+        if type(value) != type([]):
+            value = [value]
+        self.vals[name][task.config.level] += value
 
-    # Group per-task values
+    def write_measurements(self, result):
+        for stat_name, stat_data in self.vals.iteritems():
+            for level, values in stat_data.iteritems():
+                if not values:
+                    continue
+
+                name = "%s%s" % ("%s-" % level if level else "", stat_name)
+                result[name] = Measurement(name).from_array(arr)
+
+def extract_sched_data(result, data_dir, work_dir):
+    task_dict = get_task_data(data_dir, work_dir)
+
+    stat_data = LeveledArray()
     for tdata in task_dict.itervalues():
         if not tdata.params:
             # Currently unknown where these invalid tasks come from...
@@ -184,15 +223,59 @@ def extract_sched_data(result, data_dir, work_dir):
         # Scale average down to account for jobs with 0 tardiness
         avg_tard = tdata.misses.avg * miss_ratio
 
-        stat_data["miss-ratio"].append(miss_ratio)
-        stat_data["avg-tard"  ].append(avg_tard / tdata.params.wcet)
-        stat_data["max-tard"  ].append(tdata.misses.max / tdata.params.wcet)
-        stat_data["avg-block" ].append(tdata.blocks.avg / NSEC_PER_MSEC)
-        stat_data["max-block" ].append(tdata.blocks.max / NSEC_PER_MSEC)
-
-    # Summarize value groups
-    for name, data in stat_data.iteritems():
-        if not data:
+        level = tdata.params.level
+        stat_data.add("miss-ratio", level, miss_ratio)
+        stat_data.add("avg-tard",   level, avg_tard / tdata.params.wcet)
+        stat_data.add("max-tard",   level, tdata.misses.max / tdata.params.wcet)
+        stat_data.add("avg-block",  level, tdata.blocks.avg / NSEC_PER_MSEC)
+        stat_data.add("max-block",  level, tdata.blocks.max / NSEC_PER_MSEC)
+
+    stat_data.write_measurements(result)
+
+ScaleData = namedtuple('ScaleData', ['reg_tasks', 'base_tasks'])
+def extract_mc_data(result, data_dir, base_dir):
+    task_dict = get_task_data(data_dir)
+    base_dict = get_task_data(base_dir)
+
+    stat_data = LeveledArray()
+
+    # Only level B loads are measured
+    for tdata in filter(task_dict.iteritems(), lambda x: x.level == 'b'):
+        stat_data.add('load', tdata.config.level, tdata.loads)
+
+    tasks_by_config = defaultdict(lambda: ScaleData([], []))
+
+    # Add tasks in order of pid to tasks_by_config
+    # Tasks must be ordered by pid or we can't make 1 to 1 comparisons
+    # when multiple tasks have the same config in each task set
+    for tasks, field in ((task_dict, 'reg_tasks'), (base_dict, 'base_tasks')):
+        for pid in sorted(tasks.keys()):
+            tdata = tasks[pid]
+        tlist  = getattr(tasks_by_config[tdata.params], field)
+        tlist += [tdata.execs]
+
+    # Write scaling factors
+    for config, scale_data in tasks_by_config:
+        if len(scale_data.reg_tasks) != len(scale_data.base_tasks):
+            # Can't make comparison if different numbers of tasks!
             continue
-        result[name] = Measurement(str(name)).from_array(data)
 
+        all_pairs = zip(scale_data.reg_tasks, scale_data.base_tasks)
+        for reg_execs, base_execs in all_pairs:
+            if not reg_execs.max  or not reg_execs.avg or\
+               not base_execs.max or not base_execs.avg:
+                # This was an issue at some point, not sure if it still is
+                continue
+
+            max_scale = float(base_execs.max) / reg_execs.max
+            avg_scale = float(base_execs.avg) / reg_execs.avg
+
+            if (avg_scale < 1 or max_scale < 1) and config.level == "b":
+                sys.stderr.write("Task in {} with config {} has <1.0 scale!"
+                                 .format(data_dir, config)
+                continue
+
+            stat_data.add('max-scale', config.level, max_scale)
+            stat_data.add('avg-scale', config.level, avg_scale)
+
+    stat_data.write_measurements(result)