sdcc_users-l AT lists.bnl.gov

Subject: Scientific Data & Computing Center

List archive

[Sdcc_users-l] ib congestion

From: "Caramarcu Costin" <caramarc AT bnl.gov>
To: <sdcc_users-l AT lists.bnl.gov>
Subject: [Sdcc_users-l] ib congestion
Date: Tue, 26 Jun 2018 14:35:35 -0400

Hi all,

As some of you may noticed the IB fabric is currently congested and despite our best efforts we are not sure why this is happening.

In order to make the fabric more uniform we will upgrade the IB cards firmware to the same version asap. I set the whole cluster to be drained and as soon as a node becomes drained we will perform firmware updates and resume the node.

We are currently also planning a 1-2 days outage starting Monday July 2^nd in an effort to identify/isolate the problem.

Regards,

Costin

[Sdcc_users-l] ib congestion, Caramarcu Costin, 06/26/2018