On Mon, 9 Apr 2018, Sylvain MILOT wrote:
On Fri, 6 Apr 2018, Reuti wrote:
Am 06.04.2018 um 18:43 schrieb Sylvain MILOT:
I found and fixed the network lag issue, as these two systems are KVM
guests on an Ubuntu 16.04 server.
Yet, the qlogin/qrsh problem persists ... ideas ?
Does such a setup work on any machine? You could need several forwardings
to the KVM from the main OS I think - depending on the network setup of the
KVM of course.
aside from those 2 KVM guests, qlogin/qrsh works on all nodes, even those
running as Xen guests.
qsub works as expected and I can connect with ssh as a privileged user, as
otherwise ssh is blocked.
I have observed this behavior in the past, with SGE 8.1.9 and also with
gridengine 6.2u5-1, without any virtualization involved - but the problem was
I'm confronted with this issue again but it's currently quite consistent for
these 2 systems.
I still observe some lag related to NFS, even after disabling KSM (which
showed improvements when seen through iperf), so perhaps this is (also)
causing a timeout of sorts.
I will investigate this NFS related lag and get back with my findings.
NFS lag is gone and qlogin/qrsh work as expected.
I guess this confirms that qlogin/qrsh are somehow sensitive to this kind of
issue, while qsub is not.
SGE-discuss mailing list