Allocation of replica-sets in a storage cluster

摘要

A data storage system may be configured to allocate replica-sets in a balanced manner and mark some of these balanced replica-sets as being spares. As one or more drives or machines fail, the data storage system may move all copies of an affected replica-set to a marked spare replica-set and mark the affected replica-set as being inactive or invalid. As the failed drives are replaced, the data storage system may reconfigure those inactive replica-sets and use them as new spares. The data storage system may implement a coordinator module that handles the balancing and allocation of spares within a sub-cluster. The coordinator may also reallocate entire replica-sets across sub-clusters to maintain balance at the cluster level.

主权项

1. A method comprising:
detecting a failed data volume in a sub-cluster among multiple sub-clusters within a cluster of data storage machines,
the sub-cluster including an affected replica-set with e failed data volume and including a spare replica-set,the affected replica-set being a first group of mirrored data volumes,the spare replica-set being a second group of mirrored data volumes; marking non-failed data volumes of the affected replica-set as inactive in response to the detecting of the failed data volume in the affected replica-set, the marking of the non-failed data volumes being performed by a processor of a machine; determining a spare percentage for the sub-cluster, the spare percentage indicating a proportion of spare replica-sets among multiple replica-sets in the sub-cluster of data storage machines; copying data from the affected replica-set to the proportion of spare replica-set in response to the detecting of the failed data volume; detecting a replacement of the failed data volume with a substitute data volume in the affected replica-set; and marking the non-failed data volumes and the substitute volume as a further spare replica-set in response to the detecting of the replacement of the failed data volume.