Please correct me if I am wrong on my question.  But here I go.

I have a user that writes files (logs) to an isilon cluster.  When a file is less than a certain size (the actual size escapes me right now), the file is written to a single node and then copied to other nodes for data integrity.

But, in cases where a file will grow, as in this log file, it will grow to a couple of Gigs in a 24hr period.  At what point does the file then get written as a "stripe" across the nodes?

Second part of this question.

This user claims that at a certain point, when they are trying to grep the file, the content is blank, zip, nadda content.  If they copy the file to their local workstation it has data in it.

Sorry for the poorly formed question(s).

Dave