[lustre-discuss] a question of balance

John White jwhite at lbl.gov
Fri Dec 11 09:29:20 PST 2015

Alright, so the rule is always balance luns.  Capacity and performance should be uniform across all luns or you’ll run into unpredictable or inefficient IO patterns.

What is the current state of that rule in relation to Lustre?  I have an existing file system, lives on a DDN 12k.  3TB drives, 8+2p, very common config.  We’re looking to grow that FS and bossman keeps asking if we really need to stick with those 3TB spindles or if we could go with the nice pricing we’re seeing for 4TB and beyond.  This obviously makes me cringe, but I see two options (both involve wiping the existing FS, regardless):

-Just do it - Set up the 2 arrays 8+2p, have 24TB luns and 32TB luns and let lustre weighted allocation kick in when it feels it should.

-2 storage pools in the same namespace.  Set up the namespace with 2 primary directories, a pool for each.  Deal with the insanely annoying job of allocating user data to each, deal with the horror of imbalanced workloads manually placed on each.

I’d love someone to say the first option is just peachy these days but I suspect it’s still the muddy, murky freakshow people always warn against (especially when you start hitting that 75% fs capacity mark).

Comments?  Screeds?  Insults?  I’d love to hear some insight here.

More information about the lustre-discuss mailing list