Commit 325947e7 authored by Klaus Aehlig's avatar Klaus Aehlig

Clarify hbal man page

In the sense of hbal, and, in fact, all htools, drained nodes
are considered as offline. Also, the cluster score is not just
the sum of its component, but, e.g., the count of instances on
offline nodes is weighted stronger.
Signed-off-by: default avatarKlaus Aehlig <aehlig@google.com>
Reviewed-by: default avatarMichele Tartara <mtartara@google.com>
parent 79780863
......@@ -91,7 +91,8 @@ At each step, we prevent an instance move if it would cause:
- a node to go into N+1 failure state
- an instance to move onto an offline node (offline nodes are either
read from the cluster or declared with *-O*)
read from the cluster or declared with *-O*; drained nodes are
considered offline)
- an exclusion-tag based conflict (exclusion tags are read from the
cluster and/or defined via the *\--exclusion-tags* option)
- a max vcpu/pcpu ratio to be exceeded (configured via *\--max-cpu*)
......@@ -102,15 +103,16 @@ CLUSTER SCORING
~~~~~~~~~~~~~~~
As said before, the algorithm tries to minimise the cluster score at
each step. Currently this score is computed as a sum of the following
components:
each step. Currently this score is computed as a weighted sum of the
following components:
- standard deviation of the percent of free memory
- standard deviation of the percent of reserved memory
- standard deviation of the percent of free disk
- count of nodes failing N+1 check
- count of instances living (either as primary or secondary) on
offline nodes
offline nodes; in the sense of hbal (and the other htools) drained
nodes are considered offline
- count of instances living (as primary) on offline nodes; this
differs from the above metric by helping failover of such instances
in 2-node clusters
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment