[ https://issues.apache.org/jira/browse/IGNITE-5357?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vyacheslav Daradur updated IGNITE-5357: --------------------------------------- Comment: was deleted (was: Hi, [~ascherbakov], I've updated [the PR|https://github.com/apache/ignite/pull/3578/files] to avoid memory's overhead. Please have a look, if you have time. Now it covers {{get}} and {{getAll}} operations. I moved logic to {{GridCacheUtils}} since classes have no suitable common superclasses in the hierarchy. New [ci.tests|https://ci.ignite.apache.org/viewLog.html?buildId=1115559&tab=buildResultsDiv&buildTypeId=IgniteTests24Java8_RunAll] look good. About such optimization for {{READ_COMMITED}} mode, I'd like to implement it in a separate ticket, since it may need significant changes.) > Replicated cache reads load balancing. > -------------------------------------- > > Key: IGNITE-5357 > URL: https://issues.apache.org/jira/browse/IGNITE-5357 > Project: Ignite > Issue Type: Bug > Components: cache > Affects Versions: 1.6 > Reporter: Alexei Scherbakov > Assignee: Vyacheslav Daradur > Priority: Major > Labels: newbie > Fix For: 2.5 > > > Currently all read requests from client node to replicated cache will go > through primary node for key. > Need to select random affinity node in topology and send request here (only > if readFromBackups=true) > If where are server nodes collocated on same host with client, must select > target node from them. -- This message was sent by Atlassian JIRA (v7.6.3#76005)