work in process, but the goal is to avoid fully meshed nodes.
-
-
-
-
-
-
Replying to @FrancescoC
Hmmm, we should run another massive bench on Akka Cluster, last time we stopped at 2400 nodes.
1 reply 0 retweets 0 likes -
Replying to @viktorklang
spoke to the implementer. Goal is tens of thousands, but in one step at the time.
1 reply 0 retweets 1 like -
Replying to @FrancescoC
There's a tradeoff to be made in terms of convergence and failure detection. Is the membership dynamo based?
1 reply 0 retweets 0 likes -
Replying to @viktorklang
I do not have the details, but no, not based on the Dynamo principle. They took a decentralised approach.
1 reply 0 retweets 0 likes -
Replying to @viktorklang
no, this is about connectivity and messaging, not state.
4:28 AM - 9 Sep 2016
1 reply
0 retweets
0 likes
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.