With this modification is guaranteed that at least 1 MDS pod is going to be placed in each of the available zones in the k8s cluster. This would be improved in the future using: <Pod Topology Spread Constraints> (still in alpha state since kubernetes V.1.16) This modification obtain the number of zones in the k8s cluster and appends an <antiaffinity> term using the topologyKey <topology.kubernetes.io/zone> in the same number of MDS pods. In the case that will be more MDS pods than zones, the <antiaffinity> term won't be added in these extra pods. Important Note: The antiaffiniy term only will work with nodes labeled using the NEW label: <topology.kubernetes.io/zone> present in k8s V.1.17 clusters. For previous versions of k8s clusters the label used is: <failure-domain.beta.kubernetes.io/zone> And therefore, in this kind of clusters this modification won't work. Resolves #4641 [test ceph] Signed-off-by: Juan Miguel Olmo Martínez <jolmomar@redhat.com>
82 lines
3.1 KiB
YAML
82 lines
3.1 KiB
YAML
#################################################################################################################
|
|
# Create a filesystem with settings for erasure-coding instead of replication. A minimum of three nodes with OSDs
|
|
# are required in this example since the default failureDomain is host.
|
|
# kubectl create -f filesystem-ec.yaml
|
|
#################################################################################################################
|
|
|
|
apiVersion: ceph.rook.io/v1
|
|
kind: CephFilesystem
|
|
metadata:
|
|
name: myfs-ec
|
|
namespace: rook-ceph
|
|
spec:
|
|
# The metadata pool spec
|
|
metadataPool:
|
|
replicated:
|
|
# You need at least three OSDs on different nodes for this config to work
|
|
size: 3
|
|
# The list of data pool specs
|
|
dataPools:
|
|
# You need at least three `bluestore` OSDs on different nodes for this config to work
|
|
- erasureCoded:
|
|
dataChunks: 2
|
|
codingChunks: 1
|
|
# Whether to preserve metadata and data pools on filesystem deletion
|
|
preservePoolsOnDelete: true
|
|
# The metadata service (mds) configuration
|
|
metadataServer:
|
|
# The number of active MDS instances
|
|
activeCount: 1
|
|
# Whether each active MDS instance will have an active standby with a warm metadata cache for faster failover.
|
|
# If false, standbys will be available, but will not have a warm cache.
|
|
activeStandby: true
|
|
# The affinity rules to apply to the mds deployment
|
|
placement:
|
|
# nodeAffinity:
|
|
# requiredDuringSchedulingIgnoredDuringExecution:
|
|
# nodeSelectorTerms:
|
|
# - matchExpressions:
|
|
# - key: role
|
|
# operator: In
|
|
# values:
|
|
# - mds-node
|
|
# tolerations:
|
|
# - key: mds-node
|
|
# operator: Exists
|
|
# podAffinity:
|
|
podAntiAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
- labelSelector:
|
|
matchExpressions:
|
|
- key: app
|
|
operator: In
|
|
values:
|
|
- rook-ceph-mds
|
|
# topologyKey: kubernetes.io/hostname will place MDS across different hosts
|
|
topologyKey: kubernetes.io/hostname
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- weight: 100
|
|
podAffinityTerm:
|
|
labelSelector:
|
|
matchExpressions:
|
|
- key: app
|
|
operator: In
|
|
values:
|
|
- rook-ceph-mds
|
|
# topologyKey: */zone can be used to spread MDS across different AZ
|
|
# Use <topologyKey: failure-domain.beta.kubernetes.io/zone> in k8s cluster if your cluster is v1.16 or lower
|
|
# Use <topologyKey: topology.kubernetes.io/zone> in k8s cluster is v1.17 or upper
|
|
topologyKey: topology.kubernetes.io/zone
|
|
# A key/value list of annotations
|
|
annotations:
|
|
# key: value
|
|
resources:
|
|
# The requests and limits set here, allow the filesystem MDS Pod(s) to use half of one CPU core and 1 gigabyte of memory
|
|
# limits:
|
|
# cpu: "500m"
|
|
# memory: "1024Mi"
|
|
# requests:
|
|
# cpu: "500m"
|
|
# memory: "1024Mi"
|
|
# priorityClassName: my-priority-class
|