Today if an index is set to `auto_expand_replicas: N-all` then we will
try and create a shard copy on every node that matches the applicable
allocation filters. This conflits with shard allocation awareness and
the same-host allocation decider if there is an uneven distribution of
nodes across zones or hosts, since these deciders prevent shard copies
from being allocated unevenly and may therefore leave some unassigned
shards.
The point of these two deciders is to improve resilience given a limited
number of shard copies but there is no need for this behaviour when the
number of shard copies is not limited, so this commit supresses them in
that case.
Closes#54151Closes#2869
Today we document the settings used to control rebalancing and
disk-based shard allocation but there isn't really any discussion around
what these processes do so it's hard to know what, if any, adjustments
to make.
This commit adds some words to help folk understand this area better.
`cluster.routing.allocation.cluster_concurrent_rebalance` setting,
clarifying in which shard allocation situations the rebalance limit
takes effect.
Closes#20529
Today we throttle recoveries only for incoming recoveries. Nodes that have a lot
of primaries can get overloaded due to too many recoveries. To still keep that at bay
we limit the number of threads that are sending files to the target to overcome this problem.
The right solution here is to also throttle the outgoing recoveries that are today unbounded on
the master and don't start the recovery until we have enough resources on both source and target nodes.
The concurrency aspects of the recovery source also added a lot of complexity and additional threadpools
that are hard to configure. This commit removes the concurrent streamns notion completely and sends files
in the thread that drives the recovery simplifying the recovery code considerably.
Outgoing recoveries are not throttled on the master via a allocation decider.
