Full Cisco Datacenter Stack Using NexentaStor ZFS

Adcap engineers design and deploy a lot of Cisco Unified Computing Systems (UCS) at our customers. This is usually in conjunction with Cisco Nexus core switching, as well as with one of the leading storage vendors.

We really like Cisco hardware, so it exciting that we have a Cisco storage solution running in our lab, ready for customers. This is a picture of a Cisco C240 server set up with 22 SAS drive and 1 SSD drive in the front, and dual 10G Ethernet as well as dual Fibre Channel interfaces in the back.

Right now the system is connected to a Nexus 5596 using the dual 10G Ethernet interfaces, and we are running VMware View using NFS. Over the next couple weeks we are going to put this through its paces, testing Fibre Channel connectivity, adding a second SSD so it can do both read and write caching, and lots of other things as well.

The base operating system is NexentaStor, and the filesystem is the well-proven ZFS system originally developed by Sun Microsystems. This gives us the following advantages:

1. High performance storage system with lots of features and High Availability.
2. Flexible hardware configuration on Cisco servers.
3. Multi-protocol storage access with NFS, CIFS, WebDav, iSCSI, Fibre Channel.

As a Nexenta Certified Partner, Adcap is working closely with the engineers at Nexenta to certify both NexentaStor and NexentaVSA for VMware View on Cisco hardware. The C240 is the first of a number of different configurations Adcap is developing and testing for our customers.

Cisco has been working with Nexenta and VMware to test and certify Cisco UCS on since early 2012:

• Cisco website lists Nexenta as certified for deployment on UCS Rack Mount servers
• Cisco website PDF article about using Nexenta on Cisco C210
• VMware website post about Cisco UCS, Nexenta VSA for View
• Cisco PDF website presentation about using UCS and Nexenta VSA for View
• Nexenta website page for Cisco and VMware solutions

At this point, the datacenter stack is:

• Cisco UCS Blade server
• Cisco Nexus 5548 and Cisco Nexus 5596 with Nexus 2248
• Cisco C240 running NexentaStor ZFS/dual 10G Ethernet/NFS

NexentaStor Features

• 128-bit File System — ZFS-based technology provides the most scalable and flexible 128-bit file system.
• Unlimited Storage Capacity — Designed for large-scale growth with unlimited snapshots and copy-on-write clones.
• Unlimited File Size — While most legacy solutions limit the size of the file system, there are no such limitations with ZFS.
• Unified Appliance — Support for NAS (NFS, CIFS WebDAV, FTP) and support for SAN (iSCSI & FC) means flexibility.
• Data Deduplication & Native Compression — Inline data deduplication and compression reduce the use of primary storage.
• Hybrid Storage Pools — Exploit I/O cache to accelerate read & write performance — SSD.
• Integrated Snapshot Search — Perform indexing & Boolean searches from the file system to search for files within snapshots.
• Heterogeneous Block & File Replication — Synchronous or asynchronous replication for easy disaster recovery.
• Block-level Mirroring — Setup remote backups and disaster recovery at off-site locations
• Simplified Disk Management — Manage disks and JBODs using either command line or NexentaStor Management Viewer (NMV).
• Total Product Safety — Proactive, automated alert mechanisms send alerts when configuration deviates from “Golden Image” (best configuration).
• VM Integration — VMware, XEN, Hyper-V
• End-to-End Data Integrity — No silent data corruption.

Additional Features

• Support of stretch cluster deployments — Real-time failover between sites spanning up to 30 miles apart.
• Reduce the amount of required storage in VDI deployments — SCSI UNMAP as a client-side feature frees up storage in the back end, in the context of thin provisioning (a 100-to-one reduction in space for VDI when using NexentaStor).
• Reserve space for future growth — Reserve pool space, ensuring to never run out of space accidentally, allowing for work continuation without disruption with ZFS.
• Synchronization to multiple destinations — Site-to-site replications across disparate destinations and improves optimization by supporting CIFS cross-forest (groups of clients) trust.
• Quick replication — Between different data centers asynchronously through the use of a new Layer 5 multi-connection, multi-destination, multi-pathing protocol.