Distributed storage nodes having backup power supplies and write-back caching capabilities can be pooled for servicing write requests. For example, a management node of a distributed storage system can determine a subset of storage nodes, from among a group of storage nodes of the distributed storage system, coupled to backup power supplies based on status information received from the group of storage nodes. The status information can indicate whether a respective storage node of the group of storage nodes is coupled to a corresponding backup power supply. The management node can then generate a node pool that includes the subset of storage nodes with write-back caching enabled. The node pool can be configured to perform write-back caching in relation to a write request.