The value of HP 3PAR StoreServ’s mesh active controller architecture and its ALUA support come into focus as enterprises look to deliver a “higher” form of HA. Since the HP 3PAR StoreServ does not need ALUA to identify the best or “active” path to the backend LUNs on a single array as all of its LUNs are “Active” on all of controllers, HP 3PAR StoreServ repurposes ALUA to deliver a “higher” form of HA.
Two HP 3PAR StoreServ storage arrays that span two locations are presented to a VMware vSphere Metro Storage Cluster (MSC) as a single stretched cluster using its Peer Persistence Software. The HP 3PAR StoreServ arrays use Remote Copy to synchronously replicate data to keep all of the data on the LUNs presented to the VMs in the vSphere MSC in sync with one another.
Since HP 3PAR StoreServ controllers are Active-Active, the vSphere cluster at the primary production does not need to dedicate ALUA to doing path management at the primary site. Rather the vSphere MSC uses ALUA at the secondary site and marks its path to the HP 3PAR StoreServ array at this location as “Passive.”
Now the HP 3PAR Peer Persistence software plays its part. The HP 3PAR Peer Persistence software and vSphere work together to detect any path failures for any VM. Should vSphere detect a path failure at the primary site, vSphere will vMotion the VM to a physical server at the secondary site.
vSphere will at the same time generate an alert that it has moved a VM to a physical server at the secondary site. A storage administrator may leverage the HP 3PAR StoreServ Peer Persistence software to issue a switchover command to change the status of the “Passive” path at the failover site to “Active” and downgrade the “Active” path at the primary site to “Passive.”
This switchover may be done manually at a later time to preserve the integrity of the data of this VM and others and, once the switchover is done, HP 3PAR StoreServ arrays automatically reverse the direction of replication. Regardless if this switchover occurs, application processing for the moved VM continues uninterrupted.
The final piece of this HA puzzle is the Quorum Witness. Should a complete array or site outage occur at the primary site two sets of activities are triggered. On the vSphere MSC side, should only the array fail, it continues processing on the physical servers at the primary site. Only now it redirects all traffic through the “Passive” path (which is now made “Active“) at the secondary site. Should a full site outage occur, vSphere will automatically start its cluster at the secondary site.
On the array side, the Quorum Witness detects the failure and notifies the HP 3PAR Peer Persistence software to mark all paths at the recovery site as “Active” so regardless of what action VMware MSC takes (path redirect or complete failover of all VMs) application processing may continue uninterrupted. The Quorum Witness triggers this recovery without any manual intervention to ensure continuous application availability with no VM restarts.
Load Balancing Comes Along for the Ride
The ability to non-disruptively failover and failback VMs between sites is already powerful. Load balancing just adds to its appeal as it addresses two of the major drawbacks of both BCP and HA: the expense and waste associated with creating recovery sites.
Unlike in the past when enterprises built or leased recovery sites and then saw these resources either sit idle or go largely unused, they can now unlock their value in a number of ways. Minimally they can create private clouds with production VMs hosted at both the primary and secondary sites. In this way all resources are used and should perform better while still giving them the flexibility to automatically fail all of the VMs to the other site should some type of disaster occur.
The other intriguing possibility is that enterprises may even have the option to lease server and storage capacity from a cloud provider. Four out of five of the world’s largest service providers already use HP 3PAR StoreServ as their storage solution. By selecting one of these providers as their cloud partner, enterprises can create a secondary site without having to physically build a second site. Further, HP 3PAR StoreServ also offers multi-tenant capabilities so enterprises have access to these same load balancing features as if they had acquired and deployed an HP 3PAR StoreServ in their own data center.
The Icing on the Cake
Normally this is where enterprises start to get nervous. They understand the features. They see the potential. They are sold on the idea. Then they see the price tag and they realize it will never happen in their lifetime.
The pricing on the HP 3PAR StoreServ is the icing on the cake as it makes HA more affordable and accessible to enterprises than ever before. Starting as low as $40,000 for the HP 3PAR StoreServ 7400, enterprises can get access to features that are now largely reserved for storage arrays with high six if not seven figure price tags.
In HP 3PAR StoreServ, enterprises get support for ALUA. They get a mesh active controller with support for up to four (4) controllers for performance intensive environments. They have access to the HP 3PAR Peer Resistance and Remote Copy software so they synchronously data and then implement uninterrupted VM failovers and failbacks without needing to implement a third party appliance or replication software. They also get intangibles like the industry’s best integration with VMware vSphere and the flexibility to tap into HP’s extensive network of service providers to use to create a secondary site.
Bottom line: Some midrange storage arrays offer some of these features found on the HP 3PAR StoreServ. Only HP 3PAR StoreServ offers all of the features on a storage array that are needed to deliver this higher form of HA that enterprises now seek.
The HP 3PAR StoreServ: The Best Storage Solution for Achieving a Higher Form of VMware vSphere HA
BCP is good but as enterprises are finding out, delivering on it is still labor and time intensive, comes with recovery risks and does not eliminate unwanted costs and downtime. In its place, they see the value that uptime and load balancing offer but until now they have been hard pressed to deliver it at any level much less achieve “higher” forms of HA and load balancing that spans data centers or even extends into the cloud.
Using the HP 3PAR StoreServ and its Peer Persistence feature in conjunction with VMware vSphere, enterprises can now do what has to date been largely impossible. It puts these higher forms HA and load balancing within reach for their VMware vSphere-hosted apps that other storage solutions at the mid-tier level simply cannot match.
Part 1 of this 2-part blog series discussed the six features a highly available solution must deliver to achieve a higher form of HA.