<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>For awhile now I've believed that the current built-in Lustre tests have a number of problems and limitations that are limiting their usefulness in finding Lustre bugs or providing a good proxy for Lustre quality. We started this initially with a discussion on TWG, further refined some ideas for our LAD presentation, and have now finally articulated them in a semi-coherent manner <a href="http://goo.gl/mCtwU">here</a>:</div><div><a href="http://goo.gl/mCtwU">http://goo.gl/mCtwU</a></div><div><br></div><div>Chris Gearing at Intel is also heavily interested in this, and has started turning some of these thoughts into an actual spec, but before I integrate those I'd like to get a little feedback from the community on the high-level concepts. I'd also like to hear back from others that are interested in the topic (and hopefully willing to work on it) so we can put together a special-interest list for discussion.</div><div><br></div><div>I've given everyone comment rights and Chris and Roman edit rights for this doc - if anyone else wants to be an editor, let me know.</div><div><br></div></body></html>