We're trying to catch up on a very full filesystem (we were down to ~60M inodes free), and I'm looking at the options for speeding up purge/cleanup.
Has anyone tried running on something like a KNL node with a really high thread count? I'm wondering where I'm likely to hit bottlenecks (I suspect the DB - If we had a full scan, it'd be ~2TB (Max inodes for /scratch is ~1.9 billion), so need something *fast* to handle that number of IOPS What are site's preferences for several boxes (one DB, one or more robinhood boxes) vs one combined DB/cleanup for architecture? Many thanks Andrew (muttering at OpenFOAM users) ------------------------------------------------------------------------------ Check out the vibrant tech community on one of the world's most engaging tech sites, Slashdot.org! http://sdm.link/slashdot _______________________________________________ robinhood-support mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/robinhood-support
