Ceph » rbd

librbd cpu usage is quite huge currently, around 4-5x higher than krbd.

(Tested with fio+krbd vs fio+librbd, random read 4K)

Perf report is attached to this tracker

Mailing list discussion about this:
http://article.gmane.org/gmane.comp.file-systems.ceph.devel/22089/match=client+cpu+usage+kbrd+vs+librbd+perf+report

Sage:
----

I'm a bit suprised by the some of the items near the top
(bufferlist.clear() callers). I'm sure several of those can be
streamlined to avoid temporary bufferlists. I don't see any super
egregious users of the allocator, though.

The memcpy callers might be a good place to start...

sage

Mark
----
Wasn't josh looking into some of this a year ago? Did anything ever
come of that work?

Haomai Wang
-----------
Hmm, I think it's a good perf topic to discuss about buffer
alloc/dealloc. For example, maybe frequency alloced object can use
memory pool(each pool stores the same objects), but the most challenge
to this is also STL structures.