I can't believe I did that :). Feel very weird. But looking at the code I feel that there will be reads that will fail in the interim. Am I way off here? Apologies if I am wrong and I will continue looking. I am very curious is knowing how this works.
First off Bill I don't think I brainwashed you to an extent where you start signing off as me :). Don't do that on my check books. That's an interesting question and like I had said I am not too sure about this is handled in the current OSS version. Jonathan is your best bet for this response. Writes will be handled fine like we discussed.
AvinashOn Thu, Feb 4, 2010 at 9:46 PM, Bill Hastings <firstname.lastname@example.org> wrote:
---------- Forwarded message ----------
From: Bill Hastings <email@example.com>
Date: Thu, Feb 4, 2010 at 9:41 PM
Subject: Re: Adding new nodes
I just had a conversation with one of the FB guys (Avinash) at FB and landed up signing off as him :). He wasn't quite sure about how this works in the OSS branch. Hence the question to the broader audience. The question is more about the change in topology and reads going to a machine before data migration.
BillOn Thu, Feb 4, 2010 at 9:36 PM, Bill Hastings <firstname.lastname@example.org> wrote:
Sorry I guess I was not clear enough. While the existing data is being moved do requests for reads go to the new nodes? If so what if that data has not yet migrated? There is no problem for writes. But how is the routing for the reads handled in this situation?
AvinashOn Thu, Feb 4, 2010 at 9:07 PM, Jonathan Ellis <email@example.com> wrote:
Data is moved to the new correct nodes.
On Thu, Feb 4, 2010 at 10:52 PM, Bill Hastings <firstname.lastname@example.org> wrote:
> Hi All
> Could someone explain to me how the following is done - when new nodes are
> added how do we read existing data since the topology changes? How does
> Cassandra ensure that reads and writes are successful?