Changes between Version 2 and Version 3 of PlasticSlices/BaselineEvaluation/Baseline4Details
 Timestamp:
 06/07/11 10:59:11 (13 years ago)
Legend:
 Unmodified
 Added
 Removed
 Modified

PlasticSlices/BaselineEvaluation/Baseline4Details
v2 v3 2 2 3 3 Here are the details of [wiki:PlasticSlices/BaselineEvaluation#Baseline4 Baseline 4], divided by slice. 4 5 We changed how we were capturing logs for this baseline, using screen's 'hardcopy' function rather than its 'screenlog' function. This created more readable logs, but caused each screen process to consume unacceptably large amounts of memory in order to maintain large scrollback buffers, and even those large buffers weren't sufficient for some experiments. 4 6 5 7 = plastic101 = … … 25 27 == Results == 26 28 27 Note that we don't have the first few pings, to show flow setup times, due to a change in how we were logging results, which unfortunately resulted in only the last 100,000 lines of log output being captured. It also sometimes resulted in a missing line in the final output, which is why some of the results sections are different from others.28 29 29 ganel.gpolab.bbn.com: 30 30 … … 84 84 == Analysis == 85 85 86 ''Forthcoming.'' 86 All results seem consistent with what we'd expect. 87 87 88 88 = plastic102 = … … 166 166 == Analysis == 167 167 168 ''Forthcoming.'' 168 All results seem consistent with what we'd expect. 169 169 170 170 = plastic103 = … … 221 221  222 222 [ 3] local 10.42.103.51 port 56294 connected with 10.42.103.111 port 5103 223 [ ID] Interval Transfer Bandwidth224 223 [ 3] 0.076399.7 sec 21.7 GBytes 2.44 Mbits/sec 225 224 }}} … … 233 232  234 233 [ 3] local 10.42.103.112 port 41987 connected with 10.42.103.80 port 5103 235 [ ID] Interval Transfer Bandwidth236 234 [ 3] 0.076399.2 sec 15.7 GBytes 1.76 Mbits/sec 237 235 }}} … … 239 237 == Analysis == 240 238 241 ''Forthcoming.'' 239 All results seem consistent with what we'd expect. 242 240 243 241 = plastic104 = … … 303 301 == Analysis == 304 302 305 ''Forthcoming.'' 303 All results seem consistent with what we'd expect. 306 304 307 305 = plastic105 = … … 387 385 == Analysis == 388 386 389 ''Forthcoming.'' 387 All results seem consistent with what we'd expect. 390 388 391 389 = plastic106 = … … 450 448 == Analysis == 451 449 452 ''Forthcoming.'' 450 All results seem consistent with what we'd expect. 453 451 454 452 = plastic107 = … … 510 508 == Results == 511 509 512 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so I ran some grep commands on the logs to count the number of total checksums, and the number withthe expected value.510 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so we ran some grep commands on the logs to count the number of total checksums printed in each log, and the number where the checksum had the expected value. 513 511 514 512 planetlab5.clemson.edu: … … 554 552 == Analysis == 555 553 556 ''Forthcoming.'' 554 All results seem consistent with what we'd expect. 557 555 558 556 = plastic108 = … … 613 611 == Results == 614 612 615 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so I ran some grep commands on the logs to count the number of total checksums, and the number withthe expected value.613 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so we ran some grep commands on the logs to count the number of total checksums printed in each log, and the number where the checksum had the expected value. 616 614 617 615 wingsopenflow3.wail.wisc.edu: … … 647 645 == Analysis == 648 646 649 ''Forthcoming.'' 647 All results seem consistent with what we'd expect. 650 648 651 649 = plastic109 = … … 696 694 == Results == 697 695 696 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so we ran some grep commands on the logs to count the number of total checksums printed in each log, and the number where the checksum had the expected value. 697 698 698 navis.gpolab.bbn.com: 699 699 … … 748 748 == Analysis == 749 749 750 ''Forthcoming.'' 750 All results seem consistent with what we'd expect. 751 751 752 752 = plastic110 = … … 797 797 == Results == 798 798 799 Since we transfered the file to each client hundreds (if not thousands) of times, we didn't save all the copies, but we did generate an MD5 checksum after each download, and log that, so we ran some grep commands on the logs to count the number of total checksums printed in each log, and the number where the checksum had the expected value. 800 799 801 gardil.gpolab.bbn.com: 800 802 … … 849 851 == Analysis == 850 852 851 ''Forthcoming.'' 853 pl5.myplc.grnoc.iu.edu ended up with many thousands of zerolength files; it looks like the netcat process on the server died, possibly when the SSH connection to the plnode was lost. All other results seem consistent with what we'd expect.