Download FAQ Mailing Lists perfSONAR Documentation

Announcing release of psUI 1.6.0

Posted November 30, 2015 - permalink

Version 1.6.0 of psUI has been released and has been deployed on the demo instance:

The main theme of the release was internal user management in the psUI. This allows management of users, theirs’ preferences, access levels to parts of the application and much more in the future. Users coming from internal database are equal in all aspects to users coming from federated authorization source such as eduGAIN.

Each user can set the default community for the service points, which behaves like an additional filter in the selection dialog. This makes endpoint dialog much lighter and more relevant to the user displaying only endpoints with matching community. Server admins can set server’s default community. On the demo instance the default community is “GEANT”.

This release also fixes bugs related to eduGAIN integration so now all users who have their federated account and are members of eduGAIN can access the demo instance.

Full release are here

Please report any bugs in psUI JIRA here

NTP security update

Posted October 27, 2015 - permalink

Be aware of a recent NTP security update. Details can be found here:

It does not appear as serious as some of the previous NTP issues, but does highlight some vectors that could potentially be used to affect your clock. If you are running auto-updates, you likely already have the fixed version of the NTP packages. If not, you may run “yum update ntp ntpdate” to get the latest versions. The patched version of ntp is 4.2.6p5-5. No updates are required to any of the perfSONAR packages.

perfSONAR Toolkit congestion control bugfix update

Posted October 14, 2015 - permalink

A patch for the perfSONAR Toolkit has been released that fixes a long-standing bug in how the TCP congestion control algorithm is set. The bug is that the TCP congestion control algorithm is always set to “reno”, regardless of the state of NDT or NPAD. The intended behavior is that if NDT or NPAD are enabled, the algorithm is set to “reno”, otherwise it is set to “htcp”. In general, performance will be significantly worse with reno, but is required for NDT and NPAD since they assume specific reno behavior in their heuristics.

This has been corrected, so those of you not running NDT or NPAD may notice a significant increase in your throughput results once you install the patch. Please note that this bug was NOT introduced in the latest 3.5 release and dates back at least to the 3.4 release. For those of you still running either NDT/NPAD it may be a good time to review your use of these tools and whether enabling them is worth the associated performance hit. We strongly suggest not running NDT/NPAD on the perfSONAR host that you use for regular testing, and recommend using a separate, dedicated host for NDT instead.

For those running auto-updates, you should have the patch shortly. To manually update run the following:

yum update perl-perfSONAR_PS-Toolkit*

You will know if you have the patch if the toolkit version on your web interface is set to

perfSONAR 3.5 Deployment Trend

Posted October 2, 2015 - permalink

Adoption of perfSONAR 3.5 has been quick, aided by the automatic update procedure now available within the toolkit software.  The following chart shows this trend starting the day before the release was pushed to the software mirrors:

  Oct 2 Oct 1 Sept 30 Sept 29 Sept 28 Sept 27
perfSONAR Deployment Trends
3.3.x 126 120 124 134 142 142
3.4.x 296 351 373 780 1150 1143
3.5.x 1052 987 957 720 47 47

This trend can also be viewed graphically: