removed unnecessary stuff

This commit is contained in:
josch 2010-11-12 16:10:37 +01:00
parent d6fe38272e
commit 75081040d1
54 changed files with 0 additions and 6613 deletions

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View file

@ -1,7 +0,0 @@
# Records # Splitter(s) Grouper(s) Merger(s) Branch A Branch B Records Match
3811 0.6 0.74 2.81 146 143 68
26521 24.8 34.95 144.75 1800 1816 1683
56992 53.06 57.68 443.36 1985 2004 2438
99925 100.03 136.09 960.34 3644 3684 4038
298063 475.83 1415.34 11485 16412 16666 15131
916633 1706.32 50141 50338

View file

@ -1,6 +0,0 @@
# Records Splitter(s) Grouper(s) Merger(s) Branch A Branch B Records Match
26521 6.1 6.17 6.23 243 243 486
56992 13.2 13.2 13.23 158 61 219
99925
298063
916633

View file

@ -1,5 +0,0 @@
# Records # Splitter Grouper Merger
3811
26521
56992
298063

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

4298
parser.out

File diff suppressed because it is too large Load diff

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View file

@ -1,885 +0,0 @@
/var/netflow/ft-data-fall09/sne-ft-data/2009/sneze/2009-11-29/
26521 records
1683 records matched the http request
deepcopy
Splitter initiated
Parsing and validation finished: 0.31
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 27.19
Finished grouping branch A
Finished grouping branch B
Finished filtering groups for branch A
Finished filtering groups for branch B
Group filter time elapsed: 45.0
Finished merging branches: ['B', 'A']
Merger time elapsed: 162.3
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 168.99
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done
real 2m49.129s
user 2m44.070s
sys 0m5.824s
Splitter initiated
Parsing and validation finished: 0.33
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 30.16
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch B
Finished filtering groups for branch A
Group filter time elapsed: 34.2
Finished merging branches: ['B', 'A']
Merger time elapsed: 138.3
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 143.71
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done
real 2m24.193s
user 2m19.957s
sys 0m4.608s
deep_copy
Splitter initiated
Parsing and validation finished: 0.36
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 24.02
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch B
Finished filtering groups for branch A
Group filter time elapsed: 32.74
Finished merging branches: ['B', 'A']
Merger time elapsed: 155.7
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 162.56
Closing remaining open files: ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done
real 2m43.294s
user 2m38.782s
sys 0m4.628s
Splitter initiated
Parsing and validation finished: 0.26
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 24.8
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch A
Finished filtering groups for branch B
Group filter time elapsed: 34.95
Finished merging branches: ['B', 'A']
Merger time elapsed: 144.75
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 149.73
Closing remaining open files: ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done
real 2m36.640s
user 2m27.385s
sys 0m3.508s
Splitter initiated
Parsing and validation finished: 0.3
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 24.2
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch A
Finished filtering groups for branch B
Group filter time elapsed: 31.15
Finished merging branches: ['B', 'A']
Merger time elapsed: 145.9
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 151.19
real 2m31.325s
user 2m26.629s
sys 0m5.412s
modified reset/deepcopy
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 64), (26521, 11.015153884887695, 11.560714000001838))
(('new_group', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 21), (1466, 6.5672850608825684, 5.3123339999998507))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 25), (1468, 775.12532043457031, 766.78390699999591))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 15), (3228, 155.0828640460968, 160.51002500000152))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/splitter.py', 37), (3229, 87.616034030914307, 89.193573000000356))
(('append', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 118), (3490, 35.743690967559814, 30.529941999999664))
(('notify', '/usr/lib/python2.6/threading.py', 270), (6570, 10.859287977218628, 10.72066600000062))
(('_is_owned', '/usr/lib/python2.6/threading.py', 219), (6695, 9.4564809799194336, 9.1245670000004111))
(('final_result', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 57), (26521, 5.4859673976898193, 5.0482840000003648))
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 45), (26521, 85.135001659393311, 88.205508000023968))
(('_deepcopy_dict', '/usr/lib/python2.6/copy.py', 251), (26712, 73.298033714294434, 75.524687000011454))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 129), (27270, 27.118208885192871, 27.781735000003209))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 72), (97059, 33.632721662521362, 30.013754000007793))
(('read_row', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 99), (99360, 518.74268817901611, 468.40537100055235))
(('iterrows', '/usr/local/lib/python2.6/dist-packages/tables/table.py', 1441), (99377, 118.15105223655701, 106.11463399998161))
(('read_rows_list', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 105), (99797, 522.83437442779541, 472.12965100054475))
(('read_rows_list', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 133), (99797, 550.52120852470398, 497.50723100058826))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 23), (147484, 24.74915337562561, 21.317261000004237))
(('deepcopy', '/usr/lib/python2.6/copy.py', 144), (187567, 161.90160441398621, 165.33823200019515))
(('read', '/usr/local/lib/python2.6/dist-packages/tables/vlarray.py', 700), (195364, 274.85678458213806, 246.25141199899576))
(('<genexpr>', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 102), (294714, 294.22120332717896, 264.55258099813909))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 178), (856942, 596.70967555046082, 576.32406800022113))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 101), (861729, 430.92800951004028, 418.1861820004529))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 126), (989422, 290.51547265052795, 272.90903400041935))
(('idx2long', '/usr/local/lib/python2.6/dist-packages/tables/utils.py', 66), (784846, 75.146798133850098, 69.772329999996373))
(('is_idx', '/usr/local/lib/python2.6/dist-packages/tables/utils.py', 44), (784846, 26.284930467605591, 21.873351000002572))
/var/netflow/ft-data-fall09/kur-ft-data/2009-11-17/
56992 records
2438 records matched the http request
With profiler off:
real 8m8.700s
user 7m47.945s
sys 0m12.909s
Splitter initiated
Parsing and validation finished: 1.29
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 58.21
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch A
Finished filtering groups for branch B
Group filter time elapsed: 59.8
Finished merging branches: ['B', 'A']
Merger time elapsed: 471.27
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 480.68
56992
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py http-download.flw
0.72
Splitter initiated
Started filtering
Group filter time started: 0.29
3955
Filters ready
Splitter finished
Splitter time elapsed: 53.06
Number of records in branch A 1985
Number of records in branch B 2004
Finished grouping branch A
Finished group-filtering for branch A
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 57.68
Finished merging branches: ['B', 'A']
Merger time elapsed: 443.36
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 452.1
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done
real 7m46.456s
user 7m21.036s
sys 0m11.921s
(('new_group', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 21), (1824, 9.5541517734527588, 9.8766150000006974))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 25), (1828, 1249.1410629749298, 1300.497268999989))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/splitter.py', 37), (3955, 59.615991353988647, 62.479928999999061))
(('split', '/home/melnikovkolya/classes/semester-3-project/flowy/splitter.py', 17), (3955, 30.423548460006714, 32.126016000000902))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 15), (3956, 456.31715869903564, 475.12168400000229))
(('get', '/usr/lib/python2.6/Queue.py', 150), (3957, 35.274902582168579, 37.742364999999495))
(('append', '/usr/local/lib/python2.6/dist-packages/tables/vlarray.py', 452), (5486, 76.012235879898071, 76.39678599999479))
(('append', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 118), (5785, 81.44921350479126, 81.341101000000435))
(('notify', '/usr/lib/python2.6/threading.py', 270), (8002, 17.408251523971558, 17.825101000000359))
(('_is_owned', '/usr/lib/python2.6/threading.py', 219), (8101, 14.244855642318726, 15.092936000000464))
(('final_result', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 57), (56992, 15.892577886581421, 15.040958000006583))
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 45), (56992, 255.76119065284729, 262.48040000008808))
(('_deepcopy_dict', '/usr/lib/python2.6/copy.py', 251), (57183, 218.50618243217468, 224.26205200008098))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 89), (58365, 30.709211587905884, 31.189945000012358))
(('iterate_fixed_fields', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 93), (58365, 19.963983297348022, 19.749231000007512))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 129), (58365, 86.714945554733276, 88.23755700004449))
(('_deepcopy_list', '/usr/lib/python2.6/copy.py', 224), (114144, 72.901082038879395, 73.184596000045076))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 90), (117636, 47.137009859085083, 43.210651000023745))
(('_deepcopy_atomic', '/usr/lib/python2.6/copy.py', 197), (171331, 14.566928386688232, 13.152824000005694))
(('_keep_alive', '/usr/lib/python2.6/copy.py', 261), (343098, 47.557926893234253, 39.274455000023863))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 72), (343759, 89.168351411819458, 86.809352999718158))
(('read_row', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 99), (347405, 1355.7759656906128, 1345.6080879980259))
(('iterrows', '/usr/local/lib/python2.6/dist-packages/tables/table.py', 1441), (347422, 306.37827634811401, 304.82301899932509))
(('read_rows_list', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 105), (348171, 1369.7901601791382, 1360.4090329980108))
(('deepcopy', '/usr/lib/python2.6/copy.py', 144), (400864, 485.14781737327576, 489.78665900019996))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 82), (408197, 79.613070487976074, 80.693067999662162))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 23), (527995, 64.410658597946167, 62.123842999773387))
(('read', '/usr/local/lib/python2.6/dist-packages/tables/vlarray.py', 700), (689950, 714.14480590820312, 706.58424299669286))
(('<genexpr>', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 102), (1037339, 765.8496515750885, 758.55947299578656))
(('_processRangeRead', '/usr/local/lib/python2.6/dist-packages/tables/leaf.py', 449), (1037372, 470.43238306045532, 463.84111299771757))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 101), (1380363, 747.47748589515686, 753.67501099601259))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 178), (1380426, 1028.9652721881866, 1053.8537989941979))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 126), (1740570, 498.78313732147217, 495.35881499854258))
(('EQ', '/home/melnikovkolya/classes/semester-3-project/flowy/operators.py', 63), (2370745, 182.36606240272522, 156.70575899921459))
(('idx2long', '/usr/local/lib/python2.6/dist-packages/tables/utils.py', 66), (2764694, 214.65504741668701, 203.63286399914659))
(('is_idx', '/usr/local/lib/python2.6/dist-packages/tables/utils.py', 44), (2764694, 75.347645044326782, 63.899976999761293))
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 64), (56992, 31.726502895355225, 31.213908000036554))
(('deep_copy', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 41), (56994, 15.406083345413208, 16.889049000018872))
7 days of data
python ft2hdf.py /var/netflow/ft-data-fall09/sne-ft-data/2009/sneze/2009-12-0* netflow-trace.h5
246350 records in total
12394 records match the query
profiling:
Splitter initiated
Parsing and validation finished: 2.22
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 1130.1
Finished grouping branch B
Finished filtering groups for branch B
Finished grouping branch A
Finished filtering groups for branch A
Group filter time elapsed: 2123.665408
Finished merging branches: ['B', 'A']
Merger time elapsed: -185.553776
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: -114.543776
no profiling:
Splitter initiated
Parsing and validation finished: 0.26
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 320.43
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch B
Finished filtering groups for branch A
Group filter time elapsed: 922.42
Finished merging branches: ['B', 'A']
Merger time elapsed: 1039.122704
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 1074.252704
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done
start()real 90m16.511s
user 86m23.020s
sys 3m7.356s
Splitter initiated
Parsing and validation finished: 0.31
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 346.66
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch B
Finished filtering groups for branch A
Group filter time elapsed: 916.19
Finished merging branches: ['B', 'A']
Merger time elapsed: 1037.532704
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 1073.552704
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 64), (246349, 940.52704691886902, 994.15005099796895))
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 64), (246349, 111.18868279457092, 105.20649999988791))
(('deep_copy', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 41), (246351, 61.105264902114868, 52.447237999959725))
(('read_rows_list', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 105), (3155228, 13582.554839611053, 13318.368595361764))
(('read_rows_list', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 133), (3155228, 14223.106386899948, 13948.747855334786))
(('read', '/usr/local/lib/python2.6/dist-packages/tables/vlarray.py', 700), (6280932, 6694.1691343784332, 6541.9808274548959))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 178), (30651429, 17337.516788959503, 17566.637794171394))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 101), (30677828, 12477.594463348389, 12583.8665639143))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 126), (35383022, 8230.0888061523438, 8037.6824171527333))
(('EQ', '/home/melnikovkolya/classes/semester-3-project/flowy/operators.py', 63), (40143460, 2728.9575715065002, 2304.1001345953482))
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time flow-cat /var/netflow/ft-data-fall09/kur-ft-data/2009-11-16/ | flow-print | wc -l
99925
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py http-download.flw0.77
Splitter initiated
Started filtering
Group filter time started: 0.33
7222
Filters ready
Splitter finished
Splitter time elapsed: 100.03
Number of records in branch B 3684
Number of records in branch A 3644
Finished grouping branch A
Finished group-filtering for branch A
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 136.09
Finished merging branches: ['B', 'A']
Merger time elapsed: 960.34
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 974.11
Closing remaining open files: ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done
real 16m39.728s
user 15m49.067s
sys 0m26.002s
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python ft2hdf.py /var/netflow/ft-data-fall09/sne-ft-data/2009/sneze/2009-11-* netflow-trace.h5
298063
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py http-download.flw
0.84
Splitter initiated
Started filtering
29448
Filters ready
Splitter finished
Splitter time elapsed: 475.83
Number of records in branch B 16666
Number of records in branch A 16412
Finished grouping branch B
Finished group-filtering for branch B
Finished grouping branch A
Finished group-filtering for branch A
Group filter threads joined: 1415.34
Finished merging branches: ['B', 'A']
Merger time elapsed: -1347.101888 = 11485
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: -1301.531888 = 11531
Closing remaining open files: ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done
real 192m11.507s = 11531
user 185m39.648s
sys 7m25.104s
The following example shows how heavy is the influence of performing the match operations (and the consequences in case of a match being found) by having a different load for 2 different branches.
We can see that processing of Branch A, which has been matching records against a port number 443, has a running time of around 17 seconds, while the branch, which checked whether a record entry has a TCP protocol has taken around 90 seconds. The reason for a larger running time is that many more entries that match the prot=TCP requirement have been fround, and it takes an additional processing to index and to append the record to a group.
Though each of the executions of the reset function takes on average 9-10 times more time than the match function, the number of the executions of the match function is at least 30 times greater than that of the reset function.
After spot-profiling (running multi-thread profiler on certain sections of the code only), I could verify that the time spent in executing the match calls of the grouper module was causing most significant slow-down in all of the code, up to the merger module. Depending on the complexity of each of the match() calls, the execution time varied for the same number of function calls. The three match() calls from different classes form a nested chain, where one match() function, relies on another match(). The heaviest (in terms of time per execution) of all three match functions is the top-most match(), that comes from the Group class of the grouper module. Besides relying on a double-nested match call from two other classes, it also performs a
and calculates the first and the last records of newly-formed group, which is necessary for relative comparisons.
with an average time spent per cycle (including the profiler overhead) being:
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 193), (280246, 151.20158743858337, 154.237679000132))
A very simple GrouperModule class match, with a single
def match(self, record, group):
for rule in self.rules:
if not rule.match(record, group):
return False
return True
This was followed by the filtering operation
Splitter initiated
GF validation started at: 0.89
GF Validation required: 0.09
Parsing and validation finished: 0.32
Started filtering
Grouping started at:Fitlering time started at: Grouping started at: 1.0
1.0
1.0
Finished filtering
Filtering required: 16.87
Filters ready
Splitter time elapsed: 17.11
Finished grouping branch A
Grouping time required branch A 17.34
Current time is: 18.34
Finished filtering groups for branch A
Finished grouping branch B
Grouping time required branch B 90.08
Current time is: 91.08
Finished filtering groups for branch B
Group filter time elapsed: 90.41
Finished merging branches: ['B', 'A']
Merger time elapsed: 111.58
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 111.75
Closing remaining open files: ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done
real 1m52.516s
user 1m50.411s
sys 0m2.136s
The performance of the group-filters differs significantly, depending on how many matching records have been found in the filtering stage.
I.e., a filter for the port 443 results in relatively few records, while the filter for a port number >30000 results in many record matching it. The matching records need to be processed and stored for further group-filters, where the group filters try to form groups from the matched records. An example of running a query, which identifies flows with a destination port 443 and a source port > 30000, is shown next. It can be seen, that group-filtering of branch B, which is responsible for filtering out the srcport > 30000 request has a much larger running time than that of branch A, which looks only for those few records with a destination port of 443.
Splitter initiated
Parsing and validation finished: 0.28
Started filtering
Fitlering time started at: 0.98
Finished filtering
Filtering required: 33.49
Filters ready
Splitter time elapsed: 33.61
Finished grouping branch A
Grouping time finished for branch A 40.49
Finished filtering groups for branch A
Finished grouping branch B
Grouping time finished for branch B 228.46
Finished filtering groups for branch B
Group filter time elapsed: 227.86
Finished merging branches: ['B', 'A']
Merger time elapsed: 252.77
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 253.31
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done
real 4m11.671s
user 4m9.296s
sys 0m4.880s
==================================HTTPS PROFILE===========================================
A query that selects source and destination ports is defined as follows. We used that query to compare simple running times of different tools:
splitter S {}
filter www_tcp {
dstport = 443
}
filter www_port {
srcport = 443
}
grouper g_www_tcp {
module g1 {
}
aggregate srcip, dstip, sum(bytes) as bytes, count(rec_id) as n,
bitOR(tcp_flags) as flags, union(srcport) as srcports
}
grouper g_www_port {
module g1 {
}
aggregate srcip, dstip, sum(bytes) as bytes, count(rec_id) as n,
bitOR(tcp_flags) as flags, union(dstport) as dstports
}
groupfilter ggf {
bitAND(flags, 0x13) = 0x13
}
merger M {
module m1 {
branches B, A
A m B delta 1440min
}
export m1
}
ungrouper U {}
"./netflow-trace.h5" -> S
S branch A -> www_tcp -> g_www_tcp -> ggf -> M
S branch B -> www_port -> g_www_port -> ggf -> M
M->U->"./ungroped.h5"
The same number of
/var/netflow/ft-data-fall09/sne-ft-data/2009/sneze/2009-11-29/
26521 records in total
486 records match
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py https-flows.flw
0.73
Splitter initiated
Started filtering
486
Filters ready
Splitter finished
Number of records in branch A 243 Number of records in branch B 243
Finished grouping branch A
Finished group-filtering for branch A
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined
Finished merging branches: ['B', 'A']
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 6.61
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done ./netflow-trace.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsB-merged.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA-merged.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/MergedM.h5... done ./ungroped.h5... done ./flowy-run/GroupsA.h5... done
real 0m14.245s
user 0m7.168s
sys 0m0.280s
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py https-flows.flw
0.81
Splitter initiated
Started filtering
486
Filters ready
Splitter finished
Number of records in branch B 243Number of records in branch A 243
Finished grouping branch A
Finished group-filtering for branch A
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined
Finished merging branches: ['B', 'A']
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 6.31
Closing remaining open files: ./netflow-trace.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/GroupsB-merged.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done ./ungroped.h5... done ./netflow-trace.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/GroupsA-merged.h5... done ./flowy-run/GroupsB.h5... done
real 0m9.051s
user 0m7.072s
sys 0m0.160s
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py https-flows.flw
0.83
Splitter initiated
Started filtering
Group filter time started: 0.23
486
Filters ready
Number of records in branch A 243
Splitter finished
Splitter time elapsed: 6.1
Finished grouping branch A
Finished group-filtering for branch A
Number of records in branch B 243
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 6.17
Finished merging branches: ['B', 'A']
Merger time elapsed: 6.23
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 7.36
Closing remaining open files: ./flowy-run/GroupsB.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsB-merged.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/GroupsA-merged.h5... done ./ungroped.h5... done ./flowy-run/MergedM.h5... done
real 0m15.893s
user 0m7.440s
sys 0m0.868s
Most frequent:
(('final_result', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 99), (26521, 1.8366894721984863, 1.7001189999999156))
(('reset', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 83), (26521, 3.138737678527832, 3.0042079999998066))
(('deep_copy', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 58), (26523, 1.7581963539123535, 1.6681159999999338))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 92), (26526, 3.3419792652130127, 3.0921969999998495))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 130), (26526, 9.8621282577514648, 9.6565820000015421))
(('iterate_fixed_fields', '/home/melnikovkolya/classes/semester-3-project/flowy/pytables.py', 96), (26526, 1.9721605777740479, 1.7561189999999769))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/record.py', 82), (27015, 4.6438140869140625, 4.6482780000005732))
(('mask', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 90), (53042, 1.6173598766326904, 1.5800989999999153))
(('EQ', '/home/melnikovkolya/classes/semester-3-project/flowy/operators.py', 63), (53044, 1.4263303279876709, 1.1120729999999632))
(('match', '/home/melnikovkolya/classes/semester-3-project/flowy/filter.py', 134), (53046, 5.1699655055999756, 4.6562810000002663))
Heaviest:
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/groupfilter_validator.py', 16), (1, 0.18725490570068359, 0.18801199999999962))
(('get_interval_records', '/home/melnikovkolya/classes/semester-3-project/flowy/timeindex.py', 57), (1, 0.2019498348236084, 0.20001300000000199))
(('pass_allen_indices_down', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 79), (1, 0.20258498191833496, 0.20001300000000199))
(('go', '/home/melnikovkolya/classes/semester-3-project/flowy/merger.py', 108), (1, 0.2162168025970459, 0.21201300000000245))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper_validator.py', 11), (1, 0.22698211669921875, 0.22401300000000002))
(('__iter__', '/home/melnikovkolya/classes/semester-3-project/flowy/grouper.py', 36), (4, 1.1266498565673828, 1.1920739999999945))
(('_form_master_re', '/usr/lib/pymodules/python2.6/ply/lex.py', 482), (1, 0.30334997177124023, 0.22801499999999986))
(('validate_rules', '/usr/lib/pymodules/python2.6/ply/lex.py', 723), (1, 0.33556008338928223, 0.31602000000000008))
(('validate_all', '/usr/lib/pymodules/python2.6/ply/lex.py', 567), (1, 0.33656787872314453, 0.31602000000000008))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/filter_validator.py', 10), (1, 0.37907099723815918, 0.3560230000000002))
(('go', '/home/melnikovkolya/classes/semester-3-project/flowy/groupfilter.py', 14), (2, 1.1871206760406494, 1.248076999999995))
(('create_impl', '/home/melnikovkolya/classes/semester-3-project/flowy/ungrouper_validator.py', 76), (1, 0.60985612869262695, 0.60803800000000052))
(('lex', '/usr/lib/pymodules/python2.6/ply/lex.py', 865), (1, 0.65552186965942383, 0.56003499999999995))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/parser.py', 9), (1, 0.6572871208190918, 0.56403499999999995))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/ungrouper_validator.py', 10), (1, 0.67348289489746094, 0.67204200000000114))
(('__init__', '/home/melnikovkolya/classes/semester-3-project/flowy/parser.py', 182), (1, 0.71254801750183105, 0.6200389999999999))
(('go', '/home/melnikovkolya/classes/semester-3-project/flowy/ungrouper.py', 29), (1, 1.85223388671875, 1.8081130000000023))
/var/netflow/ft-data-fall09/kur-ft-data/2009-11-17/
56992 records
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python ft2hdf.py /var/netflow/ft-data-fall09/kur-ft-data/2009-11-17/ netflow-trace.h5
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py https-flows.flw
0.7
Splitter initiated
Started filtering
Group filter time started: 0.27
219
Filters ready
Splitter finished
Splitter time elapsed: 13.2
Number of records in branch A 158
Finished grouping branch A
Finished group-filtering for branch A
Number of records in branch B 61
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 13.18
Finished merging branches: ['B', 'A']
Merger time elapsed: 13.23
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 13.83
Closing remaining open files: ./netflow-trace.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsB-merged.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/GroupsA-merged.h5... done ./ungroped.h5... done ./flowy-run/MergedM.h5... done
real 0m15.696s
user 0m13.653s
sys 0m1.004s
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python printhdf.py ungroped.h5 | wc -l
Closing remaining open files: ungroped.h5... done
219
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python ft2hdf.py /var/netflow/ft-data-fall09/kur-ft-data/2009-11-16/ netflow-trace.h5
99924
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# time python flowy.py https-flows.flw
0.71
Splitter initiated
Started filtering
Group filter time started: 0.27
1434
Filters ready
Splitter finished
Splitter time elapsed: 23.19
Number of records in branch A 748
Finished grouping branch A
Finished group-filtering for branch A
Number of records in branch B 686
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 23.23
Finished merging branches: ['B', 'A']
Merger time elapsed: 23.31
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 26.48
Closing remaining open files: ./netflow-trace.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsA.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsB-merged.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/GroupsA-merged.h5... done ./ungroped.h5... done ./flowy-run/MergedM.h5... done
real 0m28.767s
user 0m24.486s
sys 0m2.840s
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python printhdf.py ungroped.h5 | wc -l
Closing remaining open files: ungroped.h5... done
1434
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python ft2hdf.py /var/netflow/ft-data-fall09/sne-ft-data/2009/sneze/2009-11-* netflow-trace.h5
298063
root@melnikovkolya-laptop:/home/melnikovkolya/classes/semester-3-project/flowy# python printhdf.py ungroped.h5 | wc -l
Closing remaining open files: ungroped.h5... done
4087
0.76
Splitter initiated
Started filtering
4087
Filters ready
Splitter finished
Group filter time started: 53.73
Splitter time elapsed: 53.73
Number of records in branch A 2041
Finished grouping branch A
Finished group-filtering for branch A
Number of records in branch B 2046
Finished grouping branch B
Finished group-filtering for branch B
Group filter threads joined: 54.37
Finished merging branches: ['B', 'A']
Merger time elapsed: 54.47
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 63.47
Closing remaining open files: ./flowy-run/GroupsB-merged.h5... done ./netflow-trace.h5... done ./ungroped.h5... done ./flowy-run/MergedM.h5... done ./flowy-run/MergedM.h5... done ./netflow-trace.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsA.h5... done ./flowy-run/GroupsA-merged.h5... done ./flowy-run/GroupsB.h5... done ./flowy-run/GroupsB.h5... done
real 1m8.146s
user 1m3.576s
sys 0m0.776s
\begin{mytinylisting}
\begin{verbatim}
splitter S {}
filter www_req {
dstport = 443 OR dstport = 80 OR dstport = 8080
unix_secs > 1259413200
unix_secs < 1259445600
}
filter www_res {
srcport = 443 OR srcport = 80 OR srcport = 8080
unix_secs < 1259445600
unix_secs > 1259413200
}
grouper g_www_req {
module g1 {
}
aggregate bitOR(tcp_flags) as flags
}
grouper g_www_res {
module g1 {
}
aggregate bitOR(tcp_flags) as flags
}
groupfilter ggf {
bitAND(flags, 0x13) = 0x13
}
merger M {
module m1 {
branches B, A
A d B OR B d A
}
export m1
}
ungrouper U {}
"./h5ports.h5" -> S
S branch A -> www_req -> g_www_req -> ggf -> M
S branch B -> www_res -> g_www_res -> ggf -> M
M->U->"./portsungroped.h5"
\end{verbatim}
\end{mytinylisting}
%
Execution of that query
\begin{verbatim}
flowy# time python flowy.py ports.flw
0.83
Splitter initiated
Started filtering
Group filter time started: 0.3
1463
Filters ready
Splitter finished
Splitter time elapsed: 7.12
Number of records in branch B 1463
Finished grouping branch B
Finished group-filtering for branch B
Number of records in branch A 1463
Finished grouping branch A
Finished group-filtering for branch A
Group filter threads joined: 7.26
Finished merging branches: ['B', 'A']
Merger time elapsed: 7.26
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 13.92
real 0m14.788s
user 0m13.969s
sys 0m0.900s
\end{verbatim}

Binary file not shown.

Binary file not shown.

File diff suppressed because it is too large Load diff

View file

@ -1,25 +0,0 @@
0.82
[Input('./netflow-trace.h5', 50, set([]), set([]), set([])), BranchNode('S', 50, set([]), set([]))]
[BranchNode('S', 51, set([]), set([])), Branch('A', 51, None, set([]), set([])), BranchNode('www_req', 51, set([]), set([])), BranchNode('g_www_req', 51, set([]), set([])), BranchNode('ggf', 51, set([]), set([])), BranchNode('M', 51, set([]), set([]))]
[BranchNode('S', 52, set([]), set([])), Branch('B', 52, None, set([]), set([])), BranchNode('www_res', 52, set([]), set([])), BranchNode('g_www_res', 52, set([]), set([])), BranchNode('ggf', 52, set([]), set([])), BranchNode('M', 52, set([]), set([]))]
[BranchNode('M', 53, set([]), set([])), BranchNode('U', 53, set([]), set([])), Output('./ungroped.h5', 53, set([]), set([]), set([]))]
Splitter initiated
Parsing and validation finished: 0.31
Started filtering
Finished filtering
Filters ready
Splitter time elapsed: 346.66
Finished grouping branch B
Finished grouping branch A
Finished filtering groups for branch B
Finished filtering groups for branch A
Group filter time elapsed: 916.19
Finished merging branches: ['B', 'A']
Merger time elapsed: 1037.532704
Ungrouper U finished exectution
FINISHED!
Overall time elapsed: 1073.552704

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.