Quantcast
Channel: HECC User Support (Tips & Tricks)
Browsing latest articles
Browse All 10 View Live

Avoiding Job Failure from Overfilling /PBS/spool

When your PBS job is running, its error and output files are kept in the /PBS/spool directory of the first node of your job. However, the space under /PBS/spool is limited, and when it fills up, any...

View Article



Using Access Control Lists for File Sharing

A common way to share files and/or directories with group members or others is to use the chmod command to change the permissions. Yet chmod has limitations, so using Access Control Lsts (ACLs) may...

View Article

Using 'Giveto' to Copy Files and/or Directories to Another User

NAS's in-house developed giveto script is built on the use of Access Control Lists (ACL). It allows one user (the giver) to copy files and/or directories to a /nobackup directory of another user (the...

View Article

File Transfers Tips

Below are some quick and easy techniques that may improve your performance rates when transferring files remotely to or from NAS. Transfer files from the /nobackup file system, which is often faster...

View Article

Increasing File Transfer Rates

Summary: If you are moving large files, use the bbftp or shiftc commands instead of cp or scp. An online NAS service can help diagnose your remote network connection issues, and our network experts can...

View Article


Preparing to Run on Pleiades' Sandy Bridge Nodes

To help you prepare for running jobs on Pleiades' Sandy Bridge compute nodes, this short review includes the general node configuration, tips on compiling your code, and PBS script examples. Overview...

View Article

Running Jobs Before Dedicated Time

The PBS batch scheduler for Pleiades and Endeavour supports a feature called shrink-to-fit (STF). This feature allows you to specify a range of acceptable wall times for a job, so that PBS can run the...

View Article

Preparing to Run on Endeavour

Overview of Endeavour The Endeavour supercomputer comprises two nodes, Endeavour1 and Endeavour2, and has been installed to replace Columbia as the new shared memory system at NAS. Endeavour1 includes...

View Article


Preparing to Run on Pleiades' Ivy Bridge Nodes

The Pleiades supercomputer is being upgraded with 46 racks of Ivy Bridge nodes, which will replace 64 racks of Harpertown nodes. This article is being updated to reflect these changes to the computing...

View Article


Preparing to Run on Pleiades' Haswell Nodes

To help you prepare for running jobs on Pleiades' Haswell compute nodes, this short review includes the general node configuration, tips on compiling your code, and PBS script examples. Overview of...

View Article
Browsing latest articles
Browse All 10 View Live




Latest Images