wiki:PlasticSlices/BaselineEvaluation/Baseline3Details

Version 7 (modified by Josh Smift, 13 years ago) (diff)

Cleaned up and analyzed Round 1.

  1. plastic-101
    1. Commands run on each client
    2. Round 1
      1. Results
      2. Analysis
    3. Round 2
    4. Round 3
    5. Round 4
    6. Round 5
    7. Round 6
  2. plastic-102
    1. Commands run on each client
    2. Results
    3. Round 1
      1. Analysis
    4. Round 2
    5. Round 3
    6. Round 4
    7. Round 5
    8. Round 6
  3. plastic-103
    1. One-time prep commands run on each client and server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  4. plastic-104
    1. One-time prep commands run on each client and server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  5. plastic-105
    1. One-time prep commands run on each client and server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  6. plastic-106
    1. One-time prep commands run on each client and server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  7. plastic-107
    1. One-time prep commands run on each server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  8. plastic-108
    1. One-time prep commands run on each server
    2. Commands run on each server
    3. Commands run on each client
    4. Round 1
      1. Results
      2. Analysis
    5. Round 2
    6. Round 3
    7. Round 4
    8. Round 5
    9. Round 6
  9. plastic-109
    1. One-time prep commands run on each server
    2. One-time prep commands run on each client
    3. Commands run on each server
    4. Commands run on each client
    5. Round 1
      1. Results
      2. Analysis
    6. Round 2
    7. Round 3
    8. Round 4
    9. Round 5
    10. Round 6
  10. plastic-110
    1. One-time prep commands run on each server
    2. One-time prep commands run on each client
    3. Commands run on each server
    4. Commands run on each client
    5. Round 1
      1. Results
      2. Analysis
    6. Round 2
    7. Round 3
    8. Round 4
    9. Round 5
    10. Round 6

Here are the details of Baseline 3, divided by slice.

In this baseline, we ran six rounds of experiments, one per day; except that too many things were down on the second day, so we ran two on the last day. In rounds 1 through 5, we ran all ten experiments simultaneously; in round 6, we ran them sequentially.

The Stanford FlowVisor was suffering from significant instabilities during this baseline. We were originally planning to use of-planet3.stanford.edu and of-planet4.stanford.edu in three experiments, but those plnodes were VMs, and were frequently unreachable. We switched to using of-planet1 and ofplanet2, which are on dedicated hardware, for round 1, but the FlowVisor problems also left them unreachable too much of the time, so we dropped the Stanford plnodes from this baseline entirely for rounds 2 - 6. The tables of client/server pairs are for rounds 2 - 6.

plastic-101

GigaPing, using count=100000, and this table of client/server pairs:

client server server address
ganel.gpolab.bbn.com planetlab5.clemson.edu server=10.42.101.105
planetlab4.clemson.edu plnode2.cip.gatech.edu server=10.42.101.101
plnode1.cip.gatech.edu pl5.myplc.grnoc.iu.edu server=10.42.101.73
pl4.myplc.grnoc.iu.edu orbitplc2.orbit-lab.org server=10.42.101.112
orbitplc1.orbit-lab.org pl02.cs.washington.edu server=10.42.101.81
pl01.cs.washington.edu wings-openflow-3.wail.wisc.edu server=10.42.101.96
wings-openflow-2.wail.wisc.edu gardil.gpolab.bbn.com server=10.42.101.52

Commands run on each client

server=<ipaddr>
sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server

Round 1

Results

ganel.gpolab.bbn.com:

--- 10.42.101.105 ping statistics ---
100000 packets transmitted, 99979 received, 0% packet loss, time 768419ms
rtt min/avg/max/mdev = 59.355/59.580/604.942/7.380 ms, pipe 71

planetlab4.clemson.edu:

+$ server=10.42.101.101

+$ sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server
write failed: Broken pipe

plnode1.cip.gatech.edu:

+$ server=10.42.101.73

+$ sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server
write failed: Broken pipe

pl4.myplc.grnoc.iu.edu:

--- 10.42.101.112 ping statistics ---
100000 packets transmitted, 0 received, 100% packet loss, time 1009280ms

orbitplc1.orbit-lab.org:

--- 10.42.101.91 ping statistics ---
100000 packets transmitted, 0 received, 100% packet loss, time 1099200ms

of-planet1.stanford.edu:

--- 10.42.101.81 ping statistics ---
100000 packets transmitted, 88364 received, 11% packet loss, time 787022ms
rtt min/avg/max/mdev = 152.667/206.759/24389.256/963.374 ms, pipe 3866

pl01.cs.washington.edu:

--- 10.42.101.96 ping statistics ---
100000 packets transmitted, 66226 received, 33% packet loss, time 854819ms
rtt min/avg/max/mdev = 59.682/70.918/1729.623/93.323 ms, pipe 166

wings-openflow-2.wail.wisc.edu:

--- 10.42.101.52 ping statistics --- 
100000 packets transmitted, 95409 received, 4% packet loss, time 892338ms 
rtt min/avg/max/mdev = 29.549/29.626/330.938/3.001 ms, pipe 36 

Analysis

Many things were down here: Clemson couldn't ping GT, GT couldn't ping Indiana, Indiana couldn't ping Rutgers, Rutgers couldn't ping Stanford. Stanford could ping Washington, but with noticeable packet loss. Similarly, washington could ping Wisconsin, with substantial packet loss. And Wisconsin to BBN also showed noticeable packet loss. Only BBN - Clemson worked as expected.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-102

GigaPing, using count=100000, and this table of client/server pairs:

client server server address
sardis.gpolab.bbn.com planetlab4.clemson.edu server=10.42.102.104
planetlab5.clemson.edu plnode1.cip.gatech.edu server=10.42.102.100
plnode2.cip.gatech.edu pl4.myplc.grnoc.iu.edu server=10.42.102.72
pl5.myplc.grnoc.iu.edu orbitplc1.orbit-lab.org server=10.42.102.111
orbitplc2.orbit-lab.org pl01.cs.washington.edu server=10.42.102.80
pl02.cs.washington.edu wings-openflow-2.wail.wisc.edu server=10.42.102.95
wings-openflow-3.wail.wisc.edu bain.gpolab.bbn.com server=10.42.102.54

Commands run on each client

server=<ipaddr>
sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server

Results

Round 1

sardis.gpolab.bbn.com:

--- 10.42.102.104 ping statistics ---
100000 packets transmitted, 99817 received, 0% packet loss, time 800241ms
rtt min/avg/max/mdev = 164.715/165.578/1646.129/27.737 ms, pipe 179

planetlab5.clemson.edu:

+$ server=10.42.102.100

+$ sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server
write failed: Broken pipe

plnode2.cip.gatech.edu:

+$ server=10.42.102.72

+$ sudo ping -i .001 -s $((1500-8-20)) -c 100000 $server
write failed: Broken pipe

pl5.myplc.grnoc.iu.edu:

--- 10.42.102.111 ping statistics ---
100000 packets transmitted, 0 received, 100% packet loss, time 1005458ms

orbitplc2.orbit-lab.org:

--- 10.42.102.91 ping statistics ---
100000 packets transmitted, 0 received, 100% packet loss, time 1098507ms

of-planet1.stanford.edu:

--- 10.42.102.80 ping statistics ---
100000 packets transmitted, 95045 received, 4% packet loss, time 759672ms
rtt min/avg/max/mdev = 20.055/38.484/18150.472/522.726 ms, pipe 2243

pl02.cs.washington.edu:

--- 10.42.102.95 ping statistics ---
100000 packets transmitted, 68156 received, 31% packet loss, time 861675ms
rtt min/avg/max/mdev = 59.674/76.396/2832.148/112.947 ms, pipe 262

wings-openflow-3.wail.wisc.edu:

--- 10.42.102.54 ping statistics ---
100000 packets transmitted, 92299 received, 7% packet loss, time 829997ms
rtt min/avg/max/mdev = 29.549/29.679/438.234/4.634 ms, pipe 38

Analysis

As with plastic-101, many things didn't work well here. BBN - Clemson was ok, but everything else either failed outright or had noticeable packet loss.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-103

GigaPerf TCP, using port=5103, size=350, and this table of client/server pairs:

client server server address
pl02.cs.washington.edu navis.gpolab.bbn.com server=10.42.103.55
ganel.gpolab.bbn.com orbitplc1.orbit-lab.org server=10.42.103.111
orbitplc2.orbit-lab.org pl01.cs.washington.edu server=10.42.103.80

One-time prep commands run on each client and server

sudo yum -y install iperf

Commands run on each server

server=<ipaddr>
nice -n 19 iperf -B $server -p 5103 -s -i 1

Commands run on each client

server=<ipaddr>
nice -n 19 iperf -c $server -p 5103 -n 350M

Round 1

Results

of-planet1.stanford.edu:

+$ server=10.42.103.55  

+$ nice -n 19 iperf -c $server -p 5103 -n 250M 
connect failed: Connection timed out 

ganel.gpolab.bbn.com:

+$ server=10.42.103.111  

+$ nice -n 19 iperf -c $server -p 5103 -n 250M 
connect failed: Connection timed out
write1 failed: Broken pipe
write2 failed: Broken pipe
------------------------------------------------------------
Client connecting to 10.42.103.111, TCP port 5103
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 0.0.0.0 port 44169 connected with 10.42.103.111 port 5103
[  3]  0.0- 0.0 sec  0.00 Bytes  0.00 bits/sec

orbitplc2.orbit-lab.org:

+$ server=10.42.103.80  

+$ nice -n 19 iperf -c $server -p 5103 -n 250M 
connect failed: Connection timed out
write1 failed: Broken pipe
write2 failed: Broken pipe
------------------------------------------------------------
Client connecting to 10.42.103.80, TCP port 5103
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 0.0.0.0 port 40359 connected with 10.42.103.80 port 5103
[  3]  0.0- 0.0 sec  0.00 Bytes  0.00 bits/sec

pl02.cs.washington.edu:

+$ server=10.42.103.91  
 
+$ nice -n 19 iperf -c $server -p 5103 -n 250M 
connect failed: Connection timed out 

Analysis

Everything failed here... Stanford couldn't even connect to BBN. BBN got a couple of failures trying to connect to Rutgers, then got through, but then couldn't transfer any data. Ditto Rutgers to Washington; and then Washington couldn't even connect to Stanford.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-104

GigaPerf UDP, using port=5104, size=500, rate=100, and this table of client/server pairs:

client server server address
planetlab4.clemson.edu gardil.gpolab.bbn.com server=10.42.104.52
planetlab5.clemson.edu orbitplc2.orbit-lab.org server=10.42.104.112

One-time prep commands run on each client and server

sudo yum -y install iperf

Commands run on each server

server=<ipaddr>
nice -n 19 iperf -u -B $server -p 5104 -s -i 1

Commands run on each client

server=<ipaddr>
nice -n 19 iperf -u -c $server -p 5104 -n 500M -b 100M

Round 1

Results

planetlab4.clemson.edu:

------------------------------------------------------------
Client connecting to 10.42.104.52, UDP port 5104
Sending 1470 byte datagrams
UDP buffer size:  109 KByte (default)
------------------------------------------------------------
[  3] local 10.42.104.104 port 56957 connected with 10.42.104.52 port 5104
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-41.8 sec   500 MBytes   100 Mbits/sec
[  3] Sent 356659 datagrams
[  3] Server Report:
[  3]  0.0-40.3 sec   480 MBytes  99.7 Mbits/sec   0.048 ms 14467/356658 (4.1%)
[  3]  0.0-40.3 sec  177 datagrams received out-of-order

planetlab5.clemson.edu:

------------------------------------------------------------
Client connecting to 10.42.104.112, UDP port 5104
Sending 1470 byte datagrams
UDP buffer size:  109 KByte (default)
------------------------------------------------------------
[  3] local 10.42.104.105 port 39103 connected with 10.42.104.112 port 5104
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-41.8 sec   500 MBytes   100 Mbits/sec
[  3] Sent 356659 datagrams
[  3] WARNING: did not receive ack of last datagram after 10 tries.

Analysis

Clemson to BBN got nearly 100 Mbits/sec, and with a fairly good success rate for UDP. Clemson to GT didn't work at all -- there's no "Server Report" section because the client never made contact with the server.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-105

GigaPerf TCP, using port=5105, size=250, and this table of client/server pairs:

client server server address
wings-openflow-2.wail.wisc.edu planetlab5.clemson.edu server=10.42.105.105
planetlab4.clemson.edu sardis.gpolab.bbn.com server=10.42.105.53
bain.gpolab.bbn.com plnode2.cip.gatech.edu server=10.42.105.101
plnode1.cip.gatech.edu wings-openflow-3.wail.wisc.edu server=10.42.105.96

One-time prep commands run on each client and server

sudo yum -y install iperf

Commands run on each server

server=<ipaddr>
nice -n 19 iperf -B $server -p 5105 -s -i 1

Commands run on each client

server=<ipaddr>
nice -n 19 iperf -c $server -p 5105 -n 250M

Round 1

Results

wings-openflow-2.wail.wisc.edu:

------------------------------------------------------------
Client connecting to 10.42.105.105, TCP port 5105
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 10.42.105.95 port 36006 connected with 10.42.105.105 port 5105
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-220.5 sec   250 MBytes  9.51 Mbits/sec

planetlab4.clemson.edu:

------------------------------------------------------------
Client connecting to 10.42.105.53, TCP port 5105
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 10.42.105.104 port 35513 connected with 10.42.105.53 port 5105
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-278.9 sec   250 MBytes  7.52 Mbits/sec

bain.gpolab.bbn.com:

------------------------------------------------------------
Client connecting to 10.42.105.101, TCP port 5105
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 10.42.105.54 port 56129 connected with 10.42.105.101 port 5105
[  3]  0.0-702.1 sec    250 MBytes  2.99 Mbits/sec

plnode1.cip.gatech.edu:

------------------------------------------------------------
Client connecting to 10.42.105.96, TCP port 5105
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 10.42.105.100 port 40317 connected with 10.42.105.96 port 5105
[  3]  0.0-355.5 sec    250 MBytes  5.90 Mbits/sec

Analysis

All results seem consistent with what we'd expect. (Which is itself somewhat unexpected at this point.)

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-106

GigaPerf UDP, using port=5106, size=500, rate=100, and this table of client/server pairs:

client server server address
planetlab5.clemson.edu wings-openflow-2.wail.wisc.edu server=10.42.106.95
wings-openflow-3.wail.wisc.edu plnode1.cip.gatech.edu server=10.42.106.100

One-time prep commands run on each client and server

sudo yum -y install iperf

Commands run on each server

server=<ipaddr>
nice -n 19 iperf -u -B $server -p 5106 -s -i 1

Commands run on each client

server=<ipaddr>
nice -n 19 iperf -u -c $server -p 5106 -n 500M -b 100M

Round 1

Results

planetlab5.clemson.edu:

------------------------------------------------------------
Client connecting to 10.42.106.95, UDP port 5106
Sending 1470 byte datagrams
UDP buffer size:  109 KByte (default)
------------------------------------------------------------
[  3] local 10.42.106.105 port 46561 connected with 10.42.106.95 port 5106
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-41.8 sec   500 MBytes   100 Mbits/sec
[  3] Sent 356659 datagrams
[  3] WARNING: did not receive ack of last datagram after 10 tries.

wings-openflow-3.wail.wisc.edu:

------------------------------------------------------------
Client connecting to 10.42.106.100, UDP port 5106
Sending 1470 byte datagrams
UDP buffer size:  109 KByte (default)
------------------------------------------------------------
[  3] local 10.42.106.96 port 43047 connected with 10.42.106.100 port 5106
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-41.7 sec   500 MBytes   100 Mbits/sec
[  3] Sent 356659 datagrams
[  3] Server Report:
[  3]  0.0-40.8 sec   464 MBytes  95.5 Mbits/sec   0.131 ms 25488/356658 (7.1%)
[  3]  0.0-40.8 sec  210 datagrams received out-of-order

plnode2.cip.gatech.edu:

{{{{


Client connecting to 10.42.106.104, UDP port 5106 Sending 1470 byte datagrams UDP buffer size: 122 KByte (default)


[ 3] local 10.42.106.101 port 33743 connected with 10.42.106.104 port 5106 [ 3] 0.0-1482.0 sec 17.2 GBytes 99.8 Mbits/sec [ 3] Sent 12572788 datagrams [ 3] Server Report: [ 3] 0.0-1481.8 sec 16.1 GBytes 93.2 Mbits/sec 0.138 ms 833663/12572787 (6.6%) [ 3] 0.0-1481.8 sec 223 datagrams received out-of-order }}}

Analysis

Clemson to Wisconsin has no Server Report section, but looking at the server-side log (not quoted here), it looks like the expected amount of data was actually transfered. Wisconsin to GT looks good. GT to Clemson is also good, except that it ran for nearly half an hour due to a bug in the version of iperf that comes with Fedora 8, which causes it not to exit when run as a UDP client.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-107

GigaWeb, using count=30, port=4107, file=substrate.doc, md5sum=d4fcf71833327fbfef98be09deef8bfb, and this table of client/server pairs:

client server server address
planetlab5.clemson.edu pl4.myplc.grnoc.iu.edu server=10.42.107.72
pl5.myplc.grnoc.iu.edu plnode2.cip.gatech.edu server=10.42.107.101
plnode1.cip.gatech.edu pl02.cs.washington.edu server=10.42.107.81
pl01.cs.washington.edu planetlab4.clemson.edu server=10.42.107.104

One-time prep commands run on each server

sudo yum -y install pyOpenSSL patch
rm -rf ~/gigaweb
mkdir -p ~/gigaweb/docroot

cd ~/gigaweb
wget http://code.activestate.com/recipes/442473-simple-http-server-supporting-ssl-secure-communica/download/1/ -O httpsd.py
wget http://groups.geni.net/geni/attachment/wiki/PlasticSlices/Experiments/httpsd.py.patch?format=raw -O httpsd.py.patch
patch httpsd.py httpsd.py.patch
rm httpsd.py.patch

cd ~/gigaweb/docroot
wget http://groups.geni.net/geni/attachment/wiki/DeliverablePage/Spiral1%20substrate%20catalog.doc?format=raw -O substrate.doc

cd ~/gigaweb
openssl genrsa -passout pass:localhost -des3 -rand /dev/urandom -out localhost.localdomain.key 1024
openssl req -subj /CN=localhost.localdomain -passin pass:localhost -new -key localhost.localdomain.key -out localhost.localdomain.csr
openssl x509 -passin pass:localhost -req -days 3650 -in localhost.localdomain.csr -signkey localhost.localdomain.key -out localhost.localdomain.crt
openssl rsa -passin pass:localhost -in localhost.localdomain.key -out decrypted.localhost.localdomain.key
mv -f decrypted.localhost.localdomain.key localhost.localdomain.key
cat localhost.localdomain.key localhost.localdomain.crt > localhost.localdomain.pem
rm localhost.localdomain.key localhost.localdomain.crt localhost.localdomain.csr

Commands run on each server

server=<ipaddr>
cd ~/gigaweb/docroot
python ../httpsd.py $server 4107

Commands run on each client

server=<ipaddr>
rm -rf ~/gigaweb
mkdir ~/gigaweb
cd ~/gigaweb
for i in {1..30} ; do wget --no-check-certificate https://$server:4107/substrate.doc -O substrate.doc.$i ; done
du -sb .
md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."

Round 1

Results

planetlab5.clemson.edu:

+$ du -sb .
254626816	.

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match." 
All checksums match. 

pl5.myplc.grnoc.iu.edu:

+$ du -sb .
254626816       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

plnode1.cip.gatech.edu:

+$ du -sb .
254626816       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

pl01.cs.washington.edu:

+$ du -sb .
254626816       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

Analysis

All results seem consistent with what we'd expect.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-108

GigaWeb, using count=40, port=4108, file=substrate.doc, md5sum=d4fcf71833327fbfef98be09deef8bfb, and this table of client/server pairs:

client server server address
wings-openflow-3.wail.wisc.edu orbitplc1.orbit-lab.org server=10.42.108.111
orbitplc2.orbit-lab.org pl5.myplc.grnoc.iu.edu server=10.42.108.73
pl4.myplc.grnoc.iu.edu wings-openflow-2.wail.wisc.edu server=10.42.108.95

One-time prep commands run on each server

sudo yum -y install pyOpenSSL patch
rm -rf ~/gigaweb
mkdir -p ~/gigaweb/docroot

cd ~/gigaweb
wget http://code.activestate.com/recipes/442473-simple-http-server-supporting-ssl-secure-communica/download/1/ -O httpsd.py
wget http://groups.geni.net/geni/attachment/wiki/PlasticSlices/Experiments/httpsd.py.patch?format=raw -O httpsd.py.patch
patch httpsd.py httpsd.py.patch
rm httpsd.py.patch

cd ~/gigaweb/docroot
wget http://groups.geni.net/geni/attachment/wiki/DeliverablePage/Spiral1%20substrate%20catalog.doc?format=raw -O substrate.doc

cd ~/gigaweb
openssl genrsa -passout pass:localhost -des3 -rand /dev/urandom -out localhost.localdomain.key 1024
openssl req -subj /CN=localhost.localdomain -passin pass:localhost -new -key localhost.localdomain.key -out localhost.localdomain.csr
openssl x509 -passin pass:localhost -req -days 3650 -in localhost.localdomain.csr -signkey localhost.localdomain.key -out localhost.localdomain.crt
openssl rsa -passin pass:localhost -in localhost.localdomain.key -out decrypted.localhost.localdomain.key
mv -f decrypted.localhost.localdomain.key localhost.localdomain.key
cat localhost.localdomain.key localhost.localdomain.crt > localhost.localdomain.pem
rm localhost.localdomain.key localhost.localdomain.crt localhost.localdomain.csr

Commands run on each server

server=<ipaddr>
cd ~/gigaweb/docroot
python ../httpsd.py $server 4108

Commands run on each client

server=<ipaddr>
rm -rf ~/gigaweb
mkdir ~/gigaweb
cd ~/gigaweb
for i in {1..40} ; do wget --no-check-certificate https://$server:4108/substrate.doc -O substrate.doc.$i ; done
du -sb .
md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."

Round 1

Results

wings-openflow-3.wail.wisc.edu:

+$ server=10.42.108.90 

+$ for i in {1..30} ; do wget --no-check-certificate https://$server:4108/substrate.doc -O substrate.doc.$i ; done
--2011-05-26 17:25:36--  https://10.42.108.90:4108/substrate.doc
Connecting to 10.42.108.90:4108... connected.
^C

of-planet2.stanford.edu:

+$ server=10.42.108.111 

+$ for i in {1..30} ; do wget --no-check-certificate https://$server:4108/substrate.doc -O substrate.doc.$i ; done
--2011-05-26 17:25:28--  https://10.42.108.111:4108/substrate.doc
Connecting to 10.42.108.111:4108... failed: Connection timed out.

orbitplc2.orbit-lab.org:

+$ server=10.42.108.73 

+$ for i in {1..30} ; do wget --no-check-certificate https://$server:4108/substrate.doc -O substrate.doc.$i ; done
--2011-05-26 13:22:22--  https://10.42.108.73:4108/substrate.doc
Connecting to 10.42.108.73:4108... failed: Connection timed out.

pl4.myplc.grnoc.iu.edu:

+$ du -sb .
254626816       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

Analysis

Everything failed except Indiana to Wisconsin, but that one worked well.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-109

GigaNetcat, using count=25, port=6109, file=substrate.doc, and this table of client/server pairs:

client server server address
navis.gpolab.bbn.com pl5.myplc.grnoc.iu.edu server=10.42.109.73
pl4.myplc.grnoc.iu.edu pl02.cs.washington.edu server=10.42.109.81
pl01.cs.washington.edu planetlab5.clemson.edu server=10.42.109.105
planetlab4.clemson.edu wings-openflow-3.wail.wisc.edu server=10.42.109.96
wings-openflow-2.wail.wisc.edu ganel.gpolab.bbn.com server=10.42.109.51

One-time prep commands run on each server

sudo yum -y install nc
mkdir -p ~/giganetcat
cd ~/giganetcat
wget http://groups.geni.net/geni/attachment/wiki/DeliverablePage/Spiral1%20substrate%20catalog.doc?format=raw -O substrate.doc

One-time prep commands run on each client

sudo yum -y install nc

Commands run on each server

server=<ipaddr>
cd ~/giganetcat
for i in {1..25} ; do nc -l $server 6109 < substrate.doc ; echo "completed transfer #$i" ; md5sum substrate.doc ; done

Commands run on each client

server=<ipaddr>
rm -rf ~/giganetcat
mkdir ~/giganetcat
cd ~/giganetcat
for i in {1..25} ; do nc $server 6109 > substrate.doc ; echo "completed transfer #$i" ; md5sum substrate.doc ; mv substrate.doc substrate.doc.$i ; done
du -sb .
md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."

Round 1

Results

navis.gpolab.bbn.com:

+$ du -sb .
169752576       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

pl4.myplc.grnoc.iu.edu:

+$ du -sb .
169752576       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

pl01.cs.washington.edu:

+$ du -sb .
4096    .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.1
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.10
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.11
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.12
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.13
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.14
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.15
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.16
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.17
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.18
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.19
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.2
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.20
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.3
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.4
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.5
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.6
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.7
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.8
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.9

planetlab4.clemson.edu:

+$ du -sb .
5544    .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
cd78ddbe122d455a37e47204d21a93d2  substrate.doc

of-planet2.stanford.edu:

+$ du -sb .
8491520	.

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
d41d8cd98f00b204e9800998ecf8427e  substrate.doc

wings-openflow-2.wail.wisc.edu:

+$ for i in {1..20} ; do nc $server 6109 > substrate.doc ; echo "completed transfer #$i" ; md5sum substrate.doc ; mv substrate.doc substrate.doc.$i ; done
completed transfer #1
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #2
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #3
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #4
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #5
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #6
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #7
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #8
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #9
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #10
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #11
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #12
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #13
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #14
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #15
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #16
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #17
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #18
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #19
d4fcf71833327fbfef98be09deef8bfb  substrate.doc
completed transfer #20
d4fcf71833327fbfef98be09deef8bfb  substrate.doc

Analysis

Washington to Clemson failed because Clemson didn't actually have the file to serve, so it quickly sent twenty zero-length files. Clemson to Stanford just failed. Stanford to Wisconsin died partway through the first transfer. Wisconsin to BBN worked fine, but we didn't capture the du and md5sum output, so we've listed the transfer log here.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.

plastic-110

GigaNetcat, using count=25, port=6110, file=substrate.doc, and this table of client/server pairs:

client server server address
gardil.gpolab.bbn.com pl01.cs.washington.edu server=10.42.110.80
pl02.cs.washington.edu orbitplc2.orbit-lab.org server=10.42.110.112
orbitplc1.orbit-lab.org pl4.myplc.grnoc.iu.edu server=10.42.110.72
pl5.myplc.grnoc.iu.edu plnode1.cip.gatech.edu server=10.42.110.100
plnode2.cip.gatech.edu sardis.gpolab.bbn.com server=10.42.110.53

One-time prep commands run on each server

sudo yum -y install nc
mkdir -p ~/giganetcat
cd ~/giganetcat
wget http://groups.geni.net/geni/attachment/wiki/DeliverablePage/Spiral1%20substrate%20catalog.doc?format=raw -O substrate.doc

One-time prep commands run on each client

sudo yum -y install nc

Commands run on each server

server=<ipaddr>
cd ~/giganetcat
for i in {1..25} ; do nc -l $server 6110 < substrate.doc ; echo "completed transfer #$i" ; md5sum substrate.doc ; done

Commands run on each client

server=<ipaddr>
rm -rf ~/giganetcat
mkdir ~/giganetcat
cd ~/giganetcat
for i in {1..25} ; do nc $server 6110 > substrate.doc ; echo "completed transfer #$i" ; md5sum substrate.doc ; mv substrate.doc substrate.doc.$i ; done
du -sb .
md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."

Round 1

Results

gardil.gpolab.bbn.com:

+$ du -sb .
169752576       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

pl02.cs.washington.edu:

+$ du -sb .
8495016 .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
2c43a5dd0efdeb2ce92381d245ec0081  substrate.doc

of-planet2.stanford.edu:

+$ du -sb .
4096    .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
d41d8cd98f00b204e9800998ecf8427e  substrate.doc
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.1
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.10
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.11
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.2
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.3
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.4
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.5
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.6
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.7
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.8
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.9

orbitplc1.orbit-lab.org:

+$ du -sb .
4096    .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
d41d8cd98f00b204e9800998ecf8427e  substrate.doc
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.1
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.10
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.11
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.2
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.3
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.4
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.5
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.6
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.7
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.8
d41d8cd98f00b204e9800998ecf8427e  substrate.doc.9

pl5.myplc.grnoc.iu.edu:

+$ du -sb .
169752576       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

plnode2.cip.gatech.edu:

+$ du -sb .
169752576       .

+$ md5sum * | grep -v d4fcf71833327fbfef98be09deef8bfb || echo "All checksums match."
All checksums match.

Analysis

BBN to Washington worked fine, but Washington to Stanford died during the second transfer. Stanford to Rutgers didn't work at all.

Round 2

To be added once the baseline finishes.

Round 3

To be added once the baseline finishes.

Round 4

To be added once the baseline finishes.

Round 5

To be added once the baseline finishes.

Round 6

To be added once the baseline finishes.