perfsonar-user - Re: [perfsonar-user] limits.conf for nightly throughput tests
Subject: perfSONAR User Q&A and Other Discussion
List archive
- From: Mark Feit <>
- To: Paul MEBALE-ASSAKO <>, "" <>
- Subject: Re: [perfsonar-user] limits.conf for nightly throughput tests
- Date: Fri, 21 Mar 2025 19:03:54 +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=arcselector10001; 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=jlFffsXeEFAjyJ6B1p6zB3xgwPlxcGS5/A1RLs46nP8=; b=MGHyUbgRXuiuIfjLXGITjIZDJXETkIxPNnuDnCv/DlNxuf71BO3xvpk0+HEwhFJbUWguZC9CcsvAiiQNWtVtkiKA5+BzySzXN8SZ8wChHiTk0JevgCRDcJvYOHdOukkDXW1UUB20KSXBlTMyCKhDKTb1S9tLsZaaOU35AJTY1QHwfK4Ck2GPRoAhndAKbmrRME3CDO2DewIYrrmJEzn7kuqm/dWZslKqQMYFdMgW+v18kEuVkH5OzWPX+cBLPldl1/AOJ7JhF2lD5PNJL1naSc50ynQQl0PX/K2Mr4fP3x5iByZH7SvHHIK2M1JhLjL2CcrfK+MoVTJ8NQck1e9TwA==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=w4jjQx/z87ufTJtEPuYkFBD2Ar5iOguPn7I6vQBu0TjFUGeCEpC7Klhr5DOpAk7S4Tz6xSC9udad775bY594fJzzeZQdAP4+0M7q0unhdrEXU35oOJg+yztoRi6E+/1E8ggiCBeggo64HrxPENkSwU8rSum3w+GPbL971bbmgx9z/1xtQp1QBkMsfk74VIGHgZvpuWNO1lyfM90BN8WT9/v6Jqwd8SyZwLaPCmmkY8yJHMJAR8BbZTODYh0hmadq90FTF1SpBhxsxXUe+KWt/Gjr7yVMxGJCOdnE8Kef1Cmbs+trRqvggvjlsEK/X15k+YX6hXbmMYE507rn7JP+KQ==
Paul MEBALE-ASSAKO writes:
Has anybody succedded configuring limits.conf to kind of constraint throughput tests to be run nightly only or at specific period of time?
There’s a limit available for that called run-schedule that will allow or deny runs based on the time being proposed for them to be put on the schedule. The docs are here:
I’ve attached a tarball with a sample configuration and test to run against it which you can unpack and use the limit-diags command to see how the limit processor will react to it. For example, this tests a throughput test to be run at 00:00:00, which is rejected because it’s outside the hours allowed by the configuration:
$ pscheduler limit-diags --config ./limits-time \ --start '2025-03-21T00:00:00' --duration 'PT5S' ./test-throughput For task starting at 2025-03-21T00:00:00 lasting PT5S: … Application: What's allowed Group 1: Limit 'test-is-throughput' passed Group 1: Limit 'throughput-allowed-hours' failed: Mismatch on hour Group 1: Want all, 1/2 passed, 1/2 failed: FAIL Application FAILS Proposal does not meet limits
This does the same thing, but at 05:00:00, which is acceptable:
$ pscheduler limit-diags --config ./limits-time \ --start '2025-03-21T05:00:00' --duration 'PT5S' ./test-throughput For task starting at 2025-03-21T05:00:00 lasting PT5S: … Application: What's allowed Group 1: Limit 'test-is-throughput' passed Group 1: Limit 'throughput-allowed-hours' passed Group 1: Want all, 2/2 passed, 0/2 failed: PASS Application PASSES Passed one application. Stopping. Proposal meets limits …
There’s a more-comprehensive example in the documentation.
Hope that helps.
--Mark
|
Attachment:
time-limits.tar
Description: time-limits.tar
- [perfsonar-user] limits.conf for nightly throughput tests, Paul MEBALE-ASSAKO, 03/20/2025
- Re: [perfsonar-user] limits.conf for nightly throughput tests, Mark Feit, 03/21/2025
- Re: [perfsonar-user] limits.conf for nightly throughput tests, Paul MEBALE-ASSAKO, 03/24/2025
- Re: [perfsonar-user] limits.conf for nightly throughput tests, Mark Feit, 03/21/2025
Archive powered by MHonArc 2.6.24.