Abstract: Techniques for continuous lock-minimal checkpointing and recovery with a distributed log-based datastore are described. A continuous, fault-tolerant checkpoint process is run on a node in a cluster in a compute-optimized or memory-optimized manner, thereby checkpointing the in-memory replica state of the node to a durable checkpoint datastore. A node can partially restore its replica state by obtaining checkpoint data, which includes an identifier of a low-water mark in a journal shard. The node can attach to the journal shard using the low-mater mark as the point of attachment, enabling the node to finalize the restoration of the replica state to be current.