perfsonar-user - Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp
Subject: perfSONAR User Q&A and Other Discussion
List archive
- From: Mark Feit <>
- To: Kirill Smirnov <>, "" <>
- Subject: Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp
- Date: Wed, 11 Jan 2023 21:35:59 +0000
- Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=internet2.edu; dmarc=pass action=none header.from=internet2.edu; dkim=pass header.d=internet2.edu; 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-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=aeb1tE7mCryQG4USRkuFdq7NlAkHPhP/cgknK21Yrc8=; b=m0rqsHlTXQjF3rKszVsc33eQj+v/Fb/iWJ+MK/YAnTr3WmP6hT3zKLXKwd9E/fKmN47v0BuJuH5XRINbml2WeBnjF3WD+5kfLp61NButCUQIHXEZdv0jj+Qji0whwpZQ5gURmxZSEpCnCQvRjsWL4/7FXM970pcYYibW2x47HAwQ8ltNvwZhUQogL6c7t3AhcSBkDlaDJbK7NmoEIcvz2Asgu+AE2c9dk/XCf/kuczT0txjiJIBifiV2oMga8P7W45IEe6AAXjrvZQZ39ba7hZO3K13gp93h4NWgQnU2Zx7ygR9n/Udl4291DNEjJOPTrXkb6wi83i0egbcO53r6VQ==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=Tf8chO/U6xoqQP56ZjbCDo0/plMQ1Wtp9Ydzrhf4W2TtVLOqJRfbgMEnwbqOWrxSm/3oVCQgL4OiQNGwZVDRT93zBIph0GhFjLdli+NpI7Y1b48+PG2HAwZ4w4sfwSJKiU4NffvFtuXGOluCInsfhvWW7OTfmMl2jMfIXlogA4xGo7wnDUmpUdck61aE9HlKmkztj8pzBOx1l9qdTwmYYgflM4gL74nrXrftYC9Iwlq82YLNLuIOWnuOvIiVNo1IIY/ByAwzDd+hEwBiR+0HBYtL4l56UIaoawgSUlFocwKOwVau0tl5IM6SJ8GmV6njxZ15xfGRFC3AXAJmj5mOng==
[Re-added perfsonar-user since this is of general interest.]
Kirill Smirnov writes:
I need parallel upload and download throughput test in same time like a:
pscheduler task --tool iperf2 throughput --source foo --dest bar pscheduler task --tool iperf2 throughput --source foo --dest bar –reverse
We don’t support that for a couple of reasons:
One is that running resource-intensive measurements in parallel can have quality-of-measurement implications. E.g., For two outbound throughput tests on the same interface at the same time, the interface will become a bottleneck and the measurements will reflect that. We’ve considered doing resource management to detect that condition and either warn about it or figure out if the system has enough resources to pull it off. It’s a huge modeling problem whose benefits don’t outweigh the costs.
The other is that the throughput result format lacks provisions for holding multiple results. That is something that can be changed, but it has to be done in a way that doesn’t break software that expects the existing format.
We have an open issue on this (https://github.com/perfsonar/pscheduler/issues/951), so it won’t fall through the cracks.
--Mark
|
- [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Kirill Smirnov, 01/11/2023
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Szymon Trocha, 01/11/2023
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Mark Feit, 01/11/2023
- Message not available
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Mark Feit, 01/11/2023
- Message not available
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Mark Feit, 01/11/2023
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Szymon Trocha, 01/11/2023
- <Possible follow-up(s)>
- Re: [perfsonar-user] parallel test via cli pschd or psconfig publish temp, Doug Southworth, 01/11/2023
Archive powered by MHonArc 2.6.24.