From 615c7a204b9386e05c5bab658bfe96766ad1e680 Mon Sep 17 00:00:00 2001 From: Brian Cline Date: Tue, 1 Sep 2015 10:51:20 -0500 Subject: [PATCH] Adds useful dispersion info from changelog Change-Id: I1a45088fc32620b02ff9a754b02ec1eb75a59d6e --- doc/source/overview_ring.rst | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/doc/source/overview_ring.rst b/doc/source/overview_ring.rst index d1f43affa5..ac82562ff1 100644 --- a/doc/source/overview_ring.rst +++ b/doc/source/overview_ring.rst @@ -168,6 +168,21 @@ on them than the disks in nodes A and B. If 80% full is the warning threshold for the cluster, node C's disks will reach 80% full while A and B's disks are only 72.7% full. +********** +Dispersion +********** + +With each rebalance, the ring builder calculates a dispersion metric. This is +the percentage of partitions in the ring that have too many replicas within a +particular failure domain. + +For example, if you have three servers in a cluster but two replicas for a +partition get placed onto the same server, that partition will count towards the +dispersion metric. + +A lower dispersion value is better, and the value can be used to find the proper +value for "overload". + ********************* Partition Shift Value *********************