1 files changed, 40 insertions, 3 deletions

diff --git a/parse_exps.py b/parse_exps.py
index cc4372a..7a99d8a 100755
--- a/parse_exps.py
+++ b/parse_exps.py
@@ -1,12 +1,14 @@
 #!/usr/bin/env python
 from __future__ import print_function
 
+import copy
 import common as com
 import multiprocessing
 import os
 import parse.ft as ft
 import parse.sched as st
 import pickle
+import re
 import shutil as sh
 import sys
 import traceback
@@ -38,6 +40,9 @@ def parse_args():
                       default=max(multiprocessing.cpu_count() - 1, 1),
                       type='int', dest='processors',
                       help='number of threads for processing')
+    parser.add_option('-s', '--scale-against', dest='scale_against',
+                      metavar='PARAM=VALUE', default="type=unmanaged",
+                      help='calculate task scaling factors against these configs')
 
     return parser.parse_args()
 
@@ -45,9 +50,9 @@ def parse_args():
 ExpData = namedtuple('ExpData', ['path', 'params', 'work_dir'])
 
 
-def parse_exp(exp_force):
+def parse_exp(exp_force_base):
     # Tupled for multiprocessing
-    exp, force = exp_force
+    exp, force, base_table = exp_force_base
 
     result_file = exp.work_dir + "/exp_point.pkl"
     should_load = not force and os.path.exists(result_file)
@@ -76,6 +81,12 @@ def parse_exp(exp_force):
             # Write scheduling statistics into result
             st.extract_sched_data(result, exp.path, exp.work_dir)
 
+            # Write scaling factors into result
+            if base_table and exp.params in base_table:
+                base_exp = base_table[exp.params]
+                if base_exp != exp:
+                    st.extract_mc_data(result, exp.path, base_exp.path)
+
             with open(result_file, 'wb') as f:
                 pickle.dump(result, f)
         except:
@@ -127,6 +138,27 @@ def load_exps(exp_dirs, cm_builder, force):
     return exps
 
 
+def make_base_table(cmd_scale, col_map, exps):
+    if not cmd_scale:
+        return None
+
+    # Configuration key for task systems used to calculate task
+    # execution scaling factors
+    [(param, value)] = dict(re.findall("(.*)=(.*)", cmd_scale))
+
+    if param not in col_map:
+        raise IOError("Base column '%s' not present in any parameters!" % param)
+
+    base_table = TupleTable(copy.deepcopy(col_map))
+
+    # Fill table with exps who we will scale against
+    for exp in exps:
+        if exp.params[param] == value:
+            base_table[exp.params] = exp
+
+    return base_table
+
+
 def get_dirs(args):
     if args:
         return args
@@ -145,12 +177,17 @@ def fill_table(table, exps, opts):
     procs  = min(len(exps), opts.processors)
     logged = multiprocessing.Manager().list()
 
+    sys.stderr.write("Parsing data...\n")
+
+    base_table = make_base_table(opts.scale_against,
+                                 table.get_col_map(), exps)
+
     pool = multiprocessing.Pool(processes=procs,
     # Share a list of previously logged messages amongst processes
     # This is for the com.log_once method to use
                 initializer=com.set_logged_list, initargs=(logged,))
 
-    pool_args = zip(exps, [opts.force]*len(exps))
+    pool_args = zip(exps, [opts.force]*len(exps), [base_table]*len(exps))
     enum = pool.imap_unordered(parse_exp, pool_args, 1)
 
     try: