Skip to main content

Access to ECCO

The Economics Compute Cluster (ECCO) has migrated to the BioHPC environment, and accounts are not handled on this website anymore. See the BioHPC User Guide.

Latest Tweets

Error: Could not authenticate you.

UPDATE on: NSF01 upcoming storage migration/downtime

Print Friendly, PDF & Email

An update on the upcoming storage migration/downtime: it will occur at the earliest 3 weeks from now.

  • there is still a lack of destination storage capacity (i.e., there is not enough storage capacity in the new SAN to satisfy all of NSF01's storage requirements). There are two possible methods, but neither of them is currently available. The current downtime window is thus moved to between 3 and 6 weeks from now. (I will keep you updated). Until then, no changes will be made to the current environement.
  • I did testing on the future access method to the CES RDC Data Warehouse (via NFS instead of direct attached storage), and found abysmal throughput. CSvD concurs, and have identified the problem. The proposed solution requires them to identify a potential hardware problem, but will also lead to NFS throughput over up to 4 Gigabit ethernet paths rather than a single GigE path. The appropriate cables will be pulled between now and the downtime (and the downtime won't occur unless they are in place). Note that this does not affect the throughput to /temporary, /mixedtmp, or /rdcprojects, only to areas like /mixed or /economic
  • On the new SAN, /mixedtmp/lehd will be a single filesystem (still only 5TB) rather than 3 distinct filesystems. No changes are currently being planned for the two /temporary filesystems, unless the engineers come up with (and test) a more efficient/faster solution.