Florida International University (FIU) is seeking a business partner to develop and commercialize a device that creates an independent failure-domain locally at a host server. This Locally-attached independent failure domain (LA-IFD) has independent power, compute, storage, and network connectivity and can operate entirely independently of the host server when necessary.
Distributed computing architectures widely use Cloud service datacenters to meet the performance of servers as many computing applications are adopting a “cloud service” computing model. Typical examples of such architectures include physical or logical separation of the computation domain and the storage domain or the usage of distributed replicated storage, where a host server replicates its data to remote servers. With these new architectures, many high-performance servers in the datacenter either locally cache, or store a copy of the data in a distributed storage system or, in the case of a centralized storage system, locally cache the remotely-stored persistent data. Such caching is performed in order to improve data access performance. When an application using the cloud service needs to update the data being used from a local cache or store, challenges can arise due to data transfer latencies between the layers of a distributed architecture.
FIU inventors have developed techniques and systems for enabling local independent failure domains in a host server or data center to address the challenges using a communications protocol between the LA-IFD and its host server. These techniques include receiving a request to write a data segment to persistent storage; synchronously storing the data segment in a buffered data segment at the LA-IFD and initiating an asynchronous update of the data segment at a remote storage system; sending a write acknowledgement indicating completion to the requestor; and, after receiving a completion notification from the remote storage system, removing the buffered data segment from the LA-IFD. In some cases, techniques allow a host server and LA-IFD pair to monitor one another for failures and implement a modified protocol in the event of unavailability.
- Scalable datacenter environments
- High-performance Servers
- Improves blocking performance on host servers.
- Maintains scalability and data integrity levels.
- Less time spent in blocking can improve:
- performance for users of the application,
- resource management/utilization on the host server.