----- Original Message ----- > From: "Pranith Kumar Karampuri" <pkarampu@xxxxxxxxxx> > To: "Raghavendra Gowdappa" <rgowdapp@xxxxxxxxxx> > Cc: "Gluster Devel" <gluster-devel@xxxxxxxxxxx>, "gluster-users" <gluster-users@xxxxxxxxxxx> > Sent: Thursday, May 4, 2017 4:03:18 PM > Subject: Re: [Gluster-users] [DHT] The myth of two hops for linkto file resolution > > On Sun, Apr 30, 2017 at 9:33 AM, Raghavendra Gowdappa <rgowdapp@xxxxxxxxxx> > wrote: > > > All, > > > > Its a common perception that the resolution of a file having linkto file > > on the hashed-subvol requires two hops: > > > > 1. client to hashed-subvol. > > 2. client to the subvol where file actually resides. > > > > While it is true that a fresh lookup behaves this way, the other fact that > > get's ignored is that fresh lookups on files are almost always prevented by > > readdirplus. Since readdirplus picks the dentry from the subvolume where > > actual file (data-file) resides, the two hop cost is most likely never > > witnessed by the application. > > > > A word of caution is that I've not done any testing to prove this > > observation :). > > > > May be you should do it and send an update. That way we can use the > knowledge to do something. I understand the importance of performance numbers. But, I am tied up with other things :). We can measure them when we really need this information. If you (or anyone else) have anything lined up which needs this data, please let me know and I can devote sometime to provide it. Till then, Other things take high priority. regards, Raghavendra _______________________________________________ Gluster-devel mailing list Gluster-devel@xxxxxxxxxxx http://lists.gluster.org/mailman/listinfo/gluster-devel
