Storage Networking is a tricky animal. My brush with networked storage platforms started from the time we needed few hundred megabytes of shared storage for building a cluster to enable database and email consolidation in the late 90’s.

The goal of block-based network storage is to protect and consolidate mission critical workloads. Networked storage using traditional FC-SAN’s is getting more complicated in the quest for speed and functionality. Yet, there is a need to simplify networked storage to reduce risk, decrease mean-time-to-repair and reduce costs.

Drawing from my personal experience, more complicated SAN sub-systems and network elements are harder to understand, harder to troubleshoot and expensive to deploy. Because of that I, personally, have moved away from SAN implementations with FC-Front end networks after attempting to use use FC-to-iSCSI routers and put up with the complexity in the network layout and provisioning challenges.

The approach I took was to select medium-to-high performance native iSCSI storage arrays with FC-Disk based backend networks. I deployed the front-end network (for connecting to servers) with Redundant Gigabit Ethernet (layer 3 capable) switches to mimic a FC network for Multi-Pathing and fault tolerance. This allowed me to maintain the essential performance posture (with FC disk backends) while maintaining the front-end simplicity for iSCSI networking.

There is still a question of performance in activities like synchronous replication, where FC-SAN technologies are superior — but these needs are becoming less acute with applications like MS-Exchange supporting varied data replication topologies (Cluster Continuous Replication-CCR, Local Continuous Replication-LCR, Standby Cluster Replication-SCR). Databases (Oracle, MS-SQL, MySQL, Postgres) are all supporting high availability using grid/federation, mirroring and master/slave models.

Advances in storage awareness in modern operating systems (Windows, Linux and Solaris) also allow support for native multi-pathing for iSCSI. Support for Features like VSS and VDS on Windows, GFS on Linux and ZFS on Solaris allow for less stringent application-aware iSCSI friendly asynchronous replication between storage systems.

Another major challenge is the emergence of Virtual Machines and their impact on performance and availability of Networked Storage. FC-Storage systems have an inherent disadvantage in VM-based environments due the multiple layers of device drivers and in-memory indirection of I/O calls. The practical impact on processor usage in hypervisor-based VM setups using FC-SAN are evident due to the lack of availability and optimization of transparent ToE type solutions for FC. The ability of a Virtual Machine to use raw ethernet adapters with ToE capable drivers results in little or no loss of storage I/O performance. There is practically zero impact on processor performance due to the use of networked storage.

In conclusion, with the emergence of relatively inexpensive 10 gigE switch and HBA Solutions, continued sophistication of operating systems and applications, the time is right to start adopting iSCSI for your mission critical storage networking needs.