Regarding Coherence Network Performance test?

Question

Hi,
We have performed the datagram tests for two servers that we have using the coherence datagram test scripts.
We have shared the results that we got after a run of 60 – 65 seconds each for the unidirectional and bidirectional tests.
Please refer to
https://docs.google.com/spreadsheet/ccc?key=0Atn1ma-myp6ndEc0THBKRTFDSnBaN0NqV1o1Ym1jRnc#gid=0
for the results.But we want to understand from these results if this performance is under the agreeable range, for which we don’t have any absolute references with us.
Can someone suggest if this network performance is good enough or if there are any problems based on these statistics?
Quick help much appreciated. Thanks in advance.
Edited by: saiyansharwan on Jan 11, 2012 5:40 AM

Answer 1

Appreciate your response much. For your reference I am putitng the details on the excel sheet right on the reply.
For unidirectional test
=============
Test Parameters -
1     Buffersize     89 (Changed as exception occurred due to OS buffer size limitations)
2     Packet size     1468 (default size adopted)
3     Command on Server A     sh datagram-test.sh serverb
4     Command on Server B     sh datagram-test.sh -rxBufferSize 89 ( to limit the receive buffer size assumed by coherence to match with the actual value in the OS.)
Results:
Server A as publisher and Server B as listener          
Publisher Details     Byte transfer rate for Server A     111 MB/sec
     Packet transfer rate for Server A     79550 packets/sec
Listener Details
Sl.No     Parameter     Server B values
1     elapsed     61547ms
2     packet size     1468 packets
3     throughput     111 MB/sec
          79614 packets/sec
4     received     4900000 of 4902366
5     missing     2366 packets
6     success rate     0.9995174
7     out of order     0
8     avg offset     0
9     gaps     802
10     avg gap size     2
11     avg gap time     0ms
12     avg ack time     -1.0E-6ms; acks 0
For Bidirectional test
============
Test Parameters -
Sl.No     Parameters     Values     Remarks
1     Buffersize     89     Changed as exception occurred due to OS buffer size limitations
2     Packet size     1468     default size adopted
3     Command on Server A     sh datagram-test.sh -polite serverb -rxBufferSize 89     started on polite mode to wait till it receives data
4     Command on Server B     sh datagram-test.sh servera -rxBufferSize 89     
Results:
Publisher Details
     Byte transfer rate for Server A     114 MB/sec
     Packet transfer rate for Server A     81367 packets/sec
     Byte transfer rate for Server B     84 MB/sec
     Packet transfer rate for Server B     59768 packets/sec
Listener Details
Sl.No     Parameter          Server A               Server B
1     elapsed          65037ms               64932ms
2     packet size          1468 packets          1468 packets
3     throughput          107 MB/sec               65 MB/sec
               76618 packets/sec          46202 packets/sec
4     received          4982987 of 5050738          3000000 of 3001389
5     missing          67751 packets          1389 packets
6     success rate          0.9865859               0.9995372
7     out of order          0               0
8     avg offset          0               0
9     gaps          20097               119
10     avg gap size          3               11
11     avg gap time     0ms               0ms
12     avg ack time          1.149157ms; acks 309602     1.169717ms; acks 1017381
As you may observe, unlike the test you performed, bidirectional tests are showing much better success rate in this case.
But what I was looking for was some standards to compare against to decide if these statistics indicate good network performance.
Any suggestions?
Best Regards.