If iRODS[1] is used to manage petabytes of data on high perfromance filesystem like Lustre[2]. You may want to set some specific parameters (like striping) before uploading the data set. This can usually be done by command-line tools, however, when you expect a high throughput of I/O calling os.system from python rule engine for every… Continue reading How to automate stripping setup on Lustre using iRODS for data ingest management.
Category: lustre
How client-side meltdown patches affect lustre 2.10 performance ?
Analysis of client side meltdown kernel patches on luster 2.10 performance. Done under load and without load on a PB scale file system.
Analysing performance of shared file system on production cluster.
Shared filesystem performance analysis on the production cluster without maintenance window – lustre client 2.5 vs 2.10