[Gluster-users] Confusing lstat() performance
mail at nh2.me
Sun Sep 17 23:34:15 UTC 2017
I found the reason now, at least for this set of lstat()s I was looking at.
bup first does all getdents(), obtaining all file names in the
directory, and then stat()s them.
Apparently this destroys some of gluster's caching, making stat()s ~100x
What caching could this be, and how could I convince gluster to serve
these stat()s as fast as if a getdents() had been done just before them?
More information about the Gluster-users