This is an old revision of the document!
This page will be maintained and provide information to get users started using the compute cluster. It is a merger of the old “brief description” page and the “queue description” page.
The High Performance Compute Cluster (HPCC) is comprised of several login nodes (all are on our domain wesleyan.edu behind VPN for off campus access)
cottontail
(Supermicro 4U), Openlava scheduler and snapshot enginecottontail2
(HP Proliant G380 2U), backup scheduler, standby for /sanscratchswallowtail
(Dell PowerEdge 2950 2U), backup scheduler, databasespetaltail
(Dell PowerEdge 2950 2U), test box (may crash), Warewulf provisioninggreentail
(HP Proliant G380 2U), /sanscratch primary NFS serverwhitetail
(Angstrom Blade 1U), Hadoop Cloudera test serversharptail
(Supermicro 4U), /home primary NFS serversharptail2
(Supermicro 2U), disaster recovery for /home, off siterstore0
and rstore2
(Supermicro 4U), NFS mounts and Samba sharesSeveral types of compute nodes are available via the OpenLava scheduler, http://www.openlava.org:
Compute node categories which usually align with queues:
All queues are available for job submissions via all login nodes. All nodes on Infiniband switches for parallel computational jobs (excludes tinymem, mw128 and amber128 queues). Our total job slot count is roughly 1,712 with our physical core count 1,192. Our total teraflops compute capacity is about 38 cpu side, 25 gpu side (double precision floating point). Our total memory footprint is about 144 GB gpu side, 7,408 GB cpu side.
Home directory file system are provided (via NFS or IPoIB) by the node sharptail
(our file server) from a direct attached disk array. In total, 10 TB of /home disk space is accessible to the users. Node greentail
makes available 33 TB of scratch space at /sanscratch via NFS. In addition all nodes provide local scratch space at /localscratch (excludes queue tinymem). The Openlava scheduler automatically makes directories in both these scratch areas for each job (named after JOBPID). Backup services for /home are provided via disk-to-disk point-in-time snapshots from node sharptail
to node cottontail
disk arrays. (daily, weekly, monthly snapshots are mounted read only on cottontail
for self-serve content retrievals). Some chemists have their home directories on node ringtail
which provides 33 TB via /home33. Some psyc folks also have their own storage of 110 TB via /mindstore. In addition no-quota, no-backup user directories can be requested in /homeextra1 (7 T) or /homeextar2 (5 T).
Two Rstore storage servers each provide about 104 TB of usable backup space which is not mounted on the compute nodes. Each Rstore server's content is replicated to a dedicated passive standby server of same size, located in same data center but in different racks. As of Spring 2019 we have added two new Rstore servers of 220 T each, fully backed up with replication.
Commercial software has their own queue limited by available licenses. There are no scheduler license resources, just queue jobs up in appropriate queue. Jobs are processed on the nodes of hp12, mwgpu mw256, and mw256fd queues. That can change if we need to.
Queue | Nr Of Nodes | Total GB Mem Per Node | Total Cores In Queue | Switch | Hosts | Notes |
---|---|---|---|---|---|---|
stata | na | na | na | QDR infiniband | any host | 6 licenses |
Note: Matlab and Mathematica now have “unlimited licenses”.
Queue | Nr Of Nodes | Total GB Mem Per Node | Job SLots In Queue | Switch | Hosts | Notes |
---|---|---|---|---|---|---|
hp12 | 32 | 12 | 256 | QDR infiniband | n1-n32 | CPU |
mwgpu | 5 | 256 | 120 | QDR infiniband | n33-n37 | GPU & CPU |
mw256fd | 8 | 256 | 192 | QDR infiniband | n38-n45 | CPU |
tinymem | 14 | 32 | 448 | gigabit ethernet | n39-n59 | CPU |
mw128 | 18 | 128 | 648 | gigabit ethernet | n60-n77 | CPU |
amber128 | 1 | 128 | 24 | gigabit ethernet | n78 | GPCU & CPU |
Some guidelines for appropriate queue usage with detailed page links:
There are no wall time limits in our HPCC environment except for queue test
. You are responsible for checkpointing though. Consult these pages, all nodes in all queues are BLCR enabled. Logins nodes and storage nodes are on UPS but all compute nodes are on utility power. Crashes do happen, be prepared to restart your long running jobs.
Home directory policy and Rstore storage options HomeDir and Storage Options
Checkpointing is supported in all queues, how it works DMTCP page
For a list of software installed consult Software List page
Details on all scratch spaces consult Scratch Spaces page
For HPCC acknowledgements consult Acknowledgement page
Sample scripts for job submissions (serial, array, parallel, forked and gpu) can be found at /home/hmeij/jobs/
From off-campus you need to VPN in first at http://webvpn.wesleyan.edu