Synchronous and asynchronous replication provides the highest level of protection against threats to the application, system, and data center. BlueArc’s multi-stream replication features allow administrators to create one or more identical copies of data while keeping the source and targets synchronized. Performance is assured as multiple concurrent streams are leveraged during data transfers. This is particularly useful in environments replicating numerous small files where there tends to be significant metadata “overhead.” The use of concurrent streams to transfer the data takes advantage of BlueArc’s inherent capability to “parallelize” metadata and data access. Leveraging policy based management and automated scheduling, asynchronous replication can be conducted between file systems within the same array, storage pools or even tiers within the storage ecosystem – even if they are physically separated. In the case of synchronous replication between systems, data is copied simultaneously between both servers and storage arrays, with multiple acknowledgements. This ensures complete protection from corruption or data loss. Additionally, during the replication process, NFS and CIFS permissions are preserved for the replicated copy of data.
IDR uses snapshots as a basis for replication, maintaining the last snapshot as the reference point for the next replication to occur. Using snapshots as a means for replication also ensures files that would otherwise be skipped, as they are in use, are replicated and protected. Using snapshots for replication also ensures that only changed files are replicated, drastically reducing the amount of replication traffic.
Titan and Mercury can support inter-server replication (local or remote) as well as intra-server replication, using BlueArc's unique Tiered Storage.
Accelerated Data Copy
Accelerated Data Copy (ADC) - allows the system administrator to define a policy-based data migration, or a mass data migration to occur between BlueArc servers. Using SiliconFS™ Tiered Storage, ADC can move data between the various tiers of storage behind the server, in a non-intrusive fashion to the clients that connect to the server.Incremental Data Replication
Incremental Data Replication (IDR) - allows system administrators to setup a scheduled, incremental backup of a volume or a directory on the volume. Multiple schedules can be defined on a per server basis with support for pre and post scripting, enabling automated functions to occur prior and post the IDR schedule.IDR uses snapshots as a basis for replication, maintaining the last snapshot as the reference point for the next replication to occur. Using snapshots as a means for replication also ensures files that would otherwise be skipped, as they are in use, are replicated and protected. Using snapshots for replication also ensures that only changed files are replicated, drastically reducing the amount of replication traffic.
Intra-server migration
The data migration can be intra-server using the Fibre Channel network to migrate data between the tiers, and as the NDMP functions in Titan and Mercury have their own, dedicated resources that are independent to the normal data access from clients, the data can be moved between tiers without affecting network clients, maintaining performance and removing any impact that this migration has on the Ethernet network.Inter-server migration
In a inter-server data migration, one of the Gigabit Ethernet interfaces can be used as a dedicated ADC or IDR interface, allowing data to be moved across servers and across the tiers of storage that each server supports. As the interface is dedicated to ADC or IDR, data migration is non-intrusive to the clients that connect to the server, again removing any impact to the network clients.Titan and Mercury can support inter-server replication (local or remote) as well as intra-server replication, using BlueArc's unique Tiered Storage.
