Jim Ferenczi a4ed7b1ca1 Decouple shard allocation awareness from search and get requests (#45735) ... With this commit, Elasticsearch will no longer prefer using shards in the same location (with the same awareness attribute values) to process `_search` and `_get` requests. Instead, adaptive replica selection (the default since 7.0) should route requests more efficiently using the service time of prior inter-node communications. Clusters with big latencies between nodes should switch to cross cluster replication to isolate nodes within the same zone. Note that this change only targets 8.0 since it is considered as breaking. However a follow up pr should add an option to activate this behavior in 7.x in order to allow users to opt-in early. Closes #43453		2019-09-04 21:48:03 +02:00
..
allocation_awareness.asciidoc	Decouple shard allocation awareness from search and get requests (#45735)	2019-09-04 21:48:03 +02:00
allocation_filtering.asciidoc	[DOCS] Reworked the shard allocation filtering info. (#36456)	2018-12-11 07:44:57 -08:00
disk_allocator.asciidoc	Always auto-release the flood-stage block (#45274)	2019-08-08 11:47:14 +01:00
misc.asciidoc	Periodically try to reassign unassigned persistent tasks (#36069)	2018-12-13 09:15:27 +00:00
shards_allocation.asciidoc	[DOCS] Reworked the shard allocation filtering info. (#36456)	2018-12-11 07:44:57 -08:00