If you need to traverse over the local data on all the nodes then broadcast a compute task to all of them and use ScanQuery with setLocal flag set to true.
Also, you can load balance the load by going for a similar approach with an affinity call per partition: https://www.gridgain.com/docs/latest/developers-guide/collocated-computations#collocating-by-partition The benefit of the affinity-based methods of the compute api is that a partition will be locked and won't be evicted until the computation is finished. The partition can be evicted if a cluster topology has changed, the partition was rebalanced to another node and now needs to be removed from the node the compute is running on. - Denis On Sun, Nov 17, 2019 at 7:43 PM camer314 <[email protected]> wrote: > Reading a little more in the Java docs about AffinityKey, I am thinking > that, > much like vector UDF batch sizing, one way I could easily achieve my result > is to batch my rows into affinity keys. That is, for every 100,000 rows the > affinity key changes for example. > > So cache keys [0...99999] have affinity key 0, keys [100000...199999] have > affinity key 1 etc? > > If that is the case, may I suggest you update the .NET documentation for > Data Grid regarding Affinity Colocation as it does not mention the use of > AffinityKey or go into anywhere near as much detail as the Java docs. > > > > > > > -- > Sent from: http://apache-ignite-users.70518.x6.nabble.com/ >
