perfsonar-user - [perfsonar-user] FW: Dual stack throughput test failures
Subject: perfSONAR User Q&A and Other Discussion
List archive
- From: "Uhl, George D. (GSFC-423.0)[Arctic Slope Technical Services, Inc.]" <>
- To: "" <>
- Subject: [perfsonar-user] FW: Dual stack throughput test failures
- Date: Fri, 6 Dec 2019 19:44:01 +0000
- Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=nasa.gov; dmarc=pass action=none header.from=nasa.gov; dkim=pass header.d=nasa.gov; arc=none
- Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=7A3pWIduIsQBvEsAdT2L1Jxf87PqWERJmL/5hVbl7+U=; b=auk0YLlDhFnOiOPM4jiSfNH76/2QXfUQ/i5nzDeoTLsS/XfyJSBK4r4mHuo+V314EnMqAvug7oYcLwbskahx7dYd7pqIVQ5QJFlv6q9cjBatjbaQ6QQlgDx9y8JfjhR+u6/rjPqXRrixg/2y2ljVdqFiqDx/iIs1w6dm8nd5mdzMIQx/YvCDpg2Uck6skUM5L2/VT6Gn7+/OBbPlywUfI8c33z+RHllclpMjhEkPLrFvim/ottpqATJGO5KoH2v85CVkTR9ckgOq63PSSbPaCeL04cZh5CGoG5gVo05ooU+y+7bga655jM4DwOW8tYPi+vTIUAoeXTevZuwAMg3GYw==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=R9N6Cs5msatIiFlGs5tKIm9shcUVkyMw8nH/GmqGYGvpTXjhXGcrSqyp1K1a7AOx4HrBYgwzk4ZyEZBnB7kdwnO+H7WHm8v8S4jJDXXCFNSzhWkhUNfAW3NhwH0fkLzsqB+EMcQYjT+ldZssP1zjouviNCPmm8SMhQ91ZVUJhBkFp6+mCvTA1iIAcscZdFuMUbG3ZgovQnI5kSW06DiwprzPMbYiSlo524W5vQUeqe0Yp5u5TflkQusbxoIIbscSKXprLd2qc2AZOkHn/gkQa5LICuW783U81i0EOXhZdXNDrVuph8Oyd2D2ZJHiZ8UDqGBEzv8Bpc0/KMeIOpk1eA==
- Dkim-filter: OpenDKIM Filter v2.11.0 ndjsvnpf101.ndc.nasa.gov 14387401012E
Forward to pS user list.
From: "George.D.Uhl" <>
Hi,
I run a mesh with a dual stack local host that is failing to run ipv4 throughput tests to any non-agent dual stack remote host when the remote host shares a single hostname for IPv4 and IPv6. I’ve attached some test cases showing conditions when tests work vs. when they fail.
Specifying ip-version as IPv4 in the pscheduler command line doesn’t seem to make a difference. The local test node has an advanced configuration which includes multiple test interfaces, policy routing and a non-test interface that is used by the main routing table as the default path. The issue appears that the non-agent remote host prefers using it’s IPv6 address when it translates the “--destination hostname” given to it by the local pscheduler during test setup/tool negotiation. Thus the ip-version parameter is used to specify the protocol for testing only and isn’t used as part of the test setup. Would it be possible to support a new feature that specidies the preferred protocol during test setup?
Thanks, George |
The local test node has an advanced configuration which includes multiple
test interfaces, policy routing and anon-test interface that is used to by
the host's main routing table as the default path.
CASE 1 - specify an ipv4 test only using hostnames
# pscheduler task --lead-bind enpl-pt2-10g.eos.nasa.gov throughput --source
enpl-pt2-10g.eos.nasa.gov --dest uhmanoa-tp.ps.uhnet.net --ip-version=4
Submitting task...
Failed to post task: Error getting tools from uhmanoa-tp.ps.uhnet.net: Could
not resolve host: enpl-pt2-10g.eos.nasa.gov; Unknown error
The 'pscheduler troubleshoot' command may be of use in problem
diagnosis. 'pscheduler troubleshoot --help' for more information.
CASE 2 - specify an IPv4 test using hostnames except for the destination
which is an IPv4 address literal
# pscheduler task --lead-bind enpl-pt2-10g.eos.nasa.gov throughput --source
enpl-pt2-10g.eos.nasa.gov --dest 132.160.6.178 --ip-version=4
Submitting task...
Task URL:
https://enpl-pt2-10g.eos.nasa.gov/pscheduler/tasks/d9727824-d2ec-4543-afc0-a72a5eabcd22
Running with tool 'iperf3'
Fetching first run...
Next scheduled run:
https://enpl-pt2-10g.eos.nasa.gov/pscheduler/tasks/d9727824-d2ec-4543-afc0-a72a5eabcd22/runs/3917927e-7c5d-4e72-b27c-974ee90bf19d
Starts 2019-12-06T07:59:50-05 (~36 seconds)
Ends 2019-12-06T08:00:09-05 (~18 seconds)
Waiting for result...
* Stream ID 5
Interval Throughput Retransmits Current Window
0.0 - 1.0 187.57 Mbps 0 1.13 MBytes
1.0 - 2.0 922.80 Mbps 0 65.71 MBytes
2.0 - 3.0 1.53 Gbps 0 65.71 MBytes
3.0 - 4.0 1.52 Gbps 0 65.71 MBytes
4.0 - 5.0 1.54 Gbps 0 65.71 MBytes
5.0 - 6.0 1.51 Gbps 0 65.71 MBytes
6.0 - 7.0 1.54 Gbps 0 65.71 MBytes
7.0 - 8.0 1.52 Gbps 0 65.71 MBytes
8.0 - 9.0 1.53 Gbps 0 65.71 MBytes
9.0 - 10.0 1.53 Gbps 0 65.71 MBytes
Summary
Interval Throughput Retransmits
0.0 - 10.0 1.33 Gbps 0
No further runs scheduled.
CASE 3 - specify an ipv4 test using an IPv4 address literal as the lead-bind
and with hostnames for the remaining parameters
# pscheduler task --lead-bind 169.154.197.28 throughput --source
enpl-pt2-10g.eos.nasa.gov --dest uhmanoa-tp.ps.uhnet.net --ip-version=4
Submitting task...
Failed to post task: Error getting tools from uhmanoa-tp.ps.uhnet.net: bind
failed with errno 22: Invalid argument
The 'pscheduler troubleshoot' command may be of use in problem
diagnosis. 'pscheduler troubleshoot --help' for more information.
- [perfsonar-user] FW: Dual stack throughput test failures, Uhl, George D. (GSFC-423.0)[Arctic Slope Technical Services, Inc.], 12/06/2019
- AW: [perfsonar-user] Dual stack throughput test failures, Garnizov, Ivan, 12/09/2019
Archive powered by MHonArc 2.6.19.