Skip to Content.
Sympa Menu

perfsonar-user - Re: [perfsonar-user] Strange performance results - AT&T VPLS circuit

Subject: perfSONAR User Q&A and Other Discussion

List archive

Re: [perfsonar-user] Strange performance results - AT&T VPLS circuit


Chronological Thread 
  • From: Jason Zurawski <>
  • To: Jared Schlemmer <>
  • Cc:
  • Subject: Re: [perfsonar-user] Strange performance results - AT&T VPLS circuit
  • Date: Mon, 31 Jul 2017 13:53:21 -0400
  • Ironport-phdr: 9a23:wLuH1xy0P/idEu7XCy+O+j09IxM/srCxBDY+r6Qd2+4XIJqq85mqBkHD//Il1AaPBtSLraocw8Pt8InYEVQa5piAtH1QOLdtbDQizfssogo7HcSeAlf6JvO5JwYzHcBFSUM3tyrjaRsdF8nxfUDdrWOv5jAOBBr/KRB1JuPoEYLOksi7ze6/9pnQbglSmDaxfa55IQmrownWqsQYm5ZpJLwryhvOrHtIeuBWyn1tKFmOgRvy5dq+8YB6/ShItP0v68BPUaPhf6QlVrNYFygpM3o05MLwqxbOSxaE62YGXWUXlhpIBBXF7A3/U5zsvCb2qvZx1S+HNsDtU7s6RSqt4LtqSB/wiScIKTg58H3MisdtiK5XuQ+tqwBjz4LRZoyeKfhwcb7Hfd4CRmRPUMZfVzZPDYyzcYUBEuQBMuREoIfyvFYOsRizChOwCO/z0DJFhHn71rA63eQ7FgHG2RQtEdYUv3TPq9X1MroZXuOozKnS1zrCYehW2TT86IPVdR0goOyMXahqfsvf0kkvFALFg06Opoz+JT+V0PoCs3SC4udmSOmhiHYnphlsrjSxxcogkIfEipgax1zZ7yl0wYU4KcWlREJnYtOoCpVduzyAO4drQM4uXXtktDsmxrACv5OwYTIEx449xxHFbvyKa4iI7QznVOaWOTp4imxqdbylixa26kegzvfwVsaz0FZUtiZFk9/MuW4R1xHL98SLVPhw8l2v1DqV2A3f9/tILEE3mKbDLp4u2L8wlp4dsUTZGS/2nV37ja6LdkU+4Oep5f/nYrbnppKHKYB0kRvyMqIwlcyjGeg4KBQBX3CH+eSg073u5VX5T6tQjv04ianZt5baKt4BpqKgHg9VyZgs6wykAjei0dQYhmUHLElbdB6djojpPU3OL+7iDfe5nVusjClny+rYMbL8H5WeZkTExZXoZ7txo3VXyA4+yNVS/doACLwaK/L3V0rZtdrUDxY/Okq5z/uxW+9wzocPZWXaGqKDPrjVt1aSo/80LvOkZYkJtSz7JuR/ofPikDtxu1YHcKXh5pAXbH29G/l8axGbbGHngtMMFE8LuAY/RerjzlCOTGgASWy1Wvce7yo8DsqUEJ3KWZuugfTVzjqhF4JNZWFuB0vKF3r0IdbXE8wQYT6fd5cy2gcPUqKsHsp4jUmj

Greetings Jared;

Clarification questions:

- Are both hosts connected at 1G NIC-to-switch bottlenecks, or are they connected at 10G yet have a 1G step-down in the path to traverse the circuit?

- Is the latency between Sunnvale and Monterey about 5ms give or take?

- 'whats in the path' besides the AT&T gear? Can you describe the things you know are on the edges?

To your questions,

a) 1G over ~5ms doesn't need much window - a bit more than 512K will do.

b) TCP is designed to back off. If your testing was competing with local needs, it would result in lower performance. Regarding what user's are seeing 'it depends'. Are they all trying to run bwctl, or are enterprise things 'slow'. Get more data on what they are unhappy about first if possible. My guess is that a commodity circuit of that type has oversubscription somewhere in the path - and that will lead to variable performance.

Thanks;

-jason

Jared Schlemmer wrote:
We just turned up a new network endpoint that connects to an existing aggregation
site via a 1gb AT&T VPLS connection and I’m seeing some interesting
performance results. The sites are Monterey Bay and Sunnyvale, CA. Tests from
Sunnyvale to Monterey Bay are good, but the reverse direction, Monterey Bay
toward Sunnyvale, I see this:

Connecting to host port 5332
[ 16] local port 58534 connected to port 5332
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 16] 0.00-1.00 sec 110 MBytes 0.92 Gbits/sec 0 1.16 MBytes
[ 16] 1.00-2.00 sec 113 MBytes 0.95 Gbits/sec 64 553 KBytes
[ 16] 2.00-3.00 sec 111 MBytes 0.93 Gbits/sec 32 498 KBytes
[ 16] 3.00-4.00 sec 112 MBytes 0.94 Gbits/sec 32 434 KBytes
[ 16] 4.00-5.00 sec 112 MBytes 0.94 Gbits/sec 32 362 KBytes
[ 16] 5.00-6.00 sec 112 MBytes 0.94 Gbits/sec 0 669 KBytes
[ 16] 6.00-7.00 sec 112 MBytes 0.94 Gbits/sec 32 622 KBytes
[ 16] 7.00-8.00 sec 111 MBytes 0.93 Gbits/sec 32 574 KBytes
[ 16] 8.00-9.00 sec 112 MBytes 0.94 Gbits/sec 32 519 KBytes
[ 16] 9.00-10.00 sec 112 MBytes 0.94 Gbits/sec 32 458 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 16] 0.00-10.00 sec 1.09 GBytes 0.94 Gbits/sec 288 sender
[ 16] 0.00-10.00 sec 1.09 GBytes 0.93 Gbits/sec receiver

My questions are, a) how is it that we see retries and such a small window
size and yet still get near line-rate throughput, and b) what is the real
world impact of a test like this? Users at the Monterey site are reporting
wildly varying performance out to the internet.

There are likely a lot of factors going on here, but I wanted to focus just on
the testing between these two sites through the AT&T cloud. Any insights,
theories or suggestions would be much appreciated. Thanks,


Jared Schlemmer
Network Engineer, GlobalNOC at Indiana University








Archive powered by MHonArc 2.6.19.

Top of Page