Implementing failover processes between storage stamps

One or more computer storage device having computer-executable instructions embodied thereon, that when executed by a computing system having a processor and memory, cause the computing system to perform a method for implementing an abrupt failover of a client's storage account from a primary storage stamp to a destination storage stamp, the method comprising:

• experiencing a disaster at a first geo-location, wherein the primary storage stamp for the storage account exists within the first geo-location;
• automatically triggering a failover from the primary storage stamp to the destination storage stamp in accordance with a predefined policy, wherein the destination storage stamp for the storage account exist in a second geo-location that is geographically remote from the first geo-location, and wherein the failover comprises:
• (a) disconnecting the primary storage stamp from taking client requests;
• (b) ensuring that an ongoing replication between the primary storage stamp and the destination storage stamp is severed such that the communication of transactions therebetween is interrupted;
• and
• (c) replaying the transactions held in a geo message log (GML) on the destination storage stamp that were delivered prior to experiencing the disaster:
• and
• bootstrapping the storage account from the destination storage stamp to a third storage stamp, wherein bootstrapping comprises:
• generating a log of incoming changes to the destination storage stamp while replicating a copy of the storage account to the third storage stamp;
• and
• updating the third storage stamp using the log of incoming messages.

A computer system within a distributed networking environment for conducting a clean failover for a storage account, the system comprising:

• a primary storage stamp that includes one or more source partitions that represent a key range of initial data associated with a storage account, wherein the one or more source partitions are configured for accepting live traffic and for sending transactions to one or more destination partitions for carrying out replication thereto;
• a secondary storage stamp that includes the one or more destination partitions that represent a key range of replicated data associated with the storage account, wherein the one or more destination partitions are configured to replay the transactions such that the replicated data substantially minors content of the initial data;
• and
• a location service for managing the storage account based on a domain name service (DNS) storage namespace mapping to the storage account, wherein the storage account specifies the primary storage stamp and the second storage stamp for the storage account, and wherein the location service is further configured for managing partitions independently of each other for invoking changes to the configuration of the one or more source partitions and for invoking changes to the configuration of the one or more destination partitions upon receiving an indication to failover from the primary storage stamp to the secondary storage stamp, wherein invoking changes to implement the failover comprises:
• (a) instructing the one or more source partitions to refrain from accepting live traffic;
• (b) instructing the one or more source partitions to independently perform a flush-send operation that attempts to flush the transactions remaining at the partitions to the secondary storage stamp;
• (c) instructing the one or more destination partitions to independently perform a flush-replay operation that replays pending transactions at the secondary storage stamp;
• (d) upon an individual destination partition, of the one or more destination partitions, substantially completing the flush-send operation, allowing the individual destination partition to commence accepting live traffic prior to others of the one or more destination partitions;
• and
• (e) upon each of the one or more destination partitions substantially completing the flush-send operation, designating the secondary storage stamp as a new primary storage stamp for the set of data failed over.