Live Life To The V-Max

It was early 2009 when I first received word of EMC’s new Enterprise Storage, which at that time was being coined ‘The Tigron’. Rumours were abound that EMC were now going down the same route as the HDS USPV and taking the virtualisation through the array route. Some days later though, the launch of V-Max took place and what was initially thought of as marketing hyperbole did indeed present us with a completely new proposition altogether….

After the slight disappointment of the USPV launch in that personally it didn’t really seem to be a major change from the USP – granted it had 4 Gbps Fibre Channel connections to disk drives and hosts, new processors, support for half-size controller cards etc. I never felt that HDS really stepped up the mark when you consider the fact that the 1152 drive count was the same. So was V-Max also just another beefed up Symmetrix?

Upon observation architecturally V-Max is quite different from previous Symmetrix models even though the same software base is used with the familiar front end/back end functional design. The first significant change is the global cache which is now distributed among the directories’ memories as opposed to the centrally located and separate entity it used to be. Furthermore via the Virtual Matrix technology the directors are now physically interconnected via a dual-star network, enabling director-to-distributed global cache and director-to-director communications.

Another significant change is the underlying Power PC-based processing hardware replacement with Intel x86, coupled with Intel multi-core processors on each director. Thus the functionality of both front-end and back-end directors merge onto one processing complex, enabling local access to hardware for what were only global cache contents.

With up to eight engines which each provide two directors, the V-Max directors each comprise two Intel Xeon 5410 64-bit quad-core processors and their associated main memory and PCIe serial buses. Via the Virtual Matrix each director’s memory is then made available to all the other directors for a maximum of 1 TByte of global memory. And while custom ASICs have been utilized in previous Symmetrix models, by having the Virtual Matrix Interface (the ASIC / System Interface Board) to bridge memory access onto the RapidIO-based Virtual Matrix, the V-Max instead uses a fully standard interconnect between directors and global memory with all the custom hardware encapsulated together.

Furthermore while the predecessor Symmetrix models used two separate networks or buses for data and messages, the new V-Max uses QOS features which prioritize traffic as both messages and data travel over the RapidIO network. The V-Max also boldly claims to give three times the I/O bandwidth of the DMX-4 with double the number of ports.

So is this is a major step up from the Symmetrix? – It certainly seems so and one can only wait with excitement to see what new features EMC will add to this mechanical beauty as they prepare to launch the new V-Max version next year. In the meantime we wait for news on what move HDS will make and whether their imminent replacement of the USPV will be just more of the same or something with more than just a new name.

VM Backups Should Not Be A Virtual Nightmare

As I look forward to attending the upcoming VSphere 4 – What’s New course, I thought I’d share some thoughts on one of the main issues I hope Vsphere will improve upon, namely backups of VMs.

Often people like to stick to what they know, scared to venture into the unknown. Standard backup methods is one of them and it is now leading to the detriment of traditionalists questioning whether they have too many virtual machines on a single server. Scared because the amount of VMs on their single physical server will equate to longer backup times, the traditionalist workaround is to then limit the number of virtual machines placed on an ESX server, henceforth decreasing the overall objective of virtualization. To make matters worse you then find situations where companies have bought extra physical servers to compensate for the backup requirements of the virtual machines – ludicrous and bizarre as it sounds it is happening in a datacenter near you….

From my own limited dealings with colleagues, customers and fellow seminar-geeks which I’ve come across in my travels it’s still surprising to see how few can vouch for their VMware servers being backed up by VCB. Still content with backup software designed for physical servers, I even met one fellow who claimed he’d been to a site where the customer was running their backup software at the physical level inside the ESX server, something which haunted me with nightmare images similar to that of Freddy Kreuger being in charge of cabling Enterprise Storage Systems. The inevitability of having to do daily full backups is a given as any change in a VM results in a modification of the timestamp of its associated VMDK files. Thus there ends up being little difference between incremental or full backups.

Upon attending the ESX 3.5 course and attaining VCP status nearly two years ago, I was desperate to implement VCB and see how great the results would be. Installing a physical Windows server next to the ESX server and thus giving it access to the storage for the VMFS file systems, it was a straight forward process providing access to both block-based (Fibre Channel and iSCSI) and NFS-based data stores. The server would then act as a proxy server to back up the data stores without the I/O having to go through the ESX server. Fabulous I thought, until I realized I was one of the few who was actually calling for its implementation.

Step forward and we see that as technology progresses so do solutions and it was recently that I came across Continuous data protection (CDP) and near-CDP backup products which are being marketed as deduplication-like software. By installing them on the VM the ability to back up virtual machines as in the same vein as a physical server is now possible. But while this constitutes to an advantageous low CPU and I/O load I’ve yet to come across a software that will recover an entire machine, a problem if your VM is deleted.

Like every optimist I do see one promising possibility for future development - the storage systems themselves of which some are claiming to have VMware-aware near-CDP backup built in. Dell EqualLogic, FalconStor Software Inc. and NetApp are already trumpeting this ability. By having VMDKs stored directly on their storage, a tool designed for VMware allows you to tell the system when to run a back up of VMware. Similar to VCB, VMware performs a snapshot which then triggers the storage system to perform its snapshot of the VMware snapshot. By replicating that backup to another box you then end up with your backup, with minimal CPU load on the ESX server and I/O hits on the storage. NetApp has gone one step further with this and uses the VMware tools to do the snapshots and can even dedupe the VMware data including live data.

Surely it’s only a matter of time before the other vendors catch up and do likewise (I give it the usual 6 months.) So as I embark upon my course I look forward to seeing and learning what new strategies are available – I will keep you all posted.

Zetta Wants To Make The Cloud Better

The evolution of Cloud computing took a unique direction this week with new boys Zetta openly challenging EMC, NetApp and other NAS System providers with its Enterprise Cloud Storage service. After months of beta testing and evaluations, Zetta is offering to handle original copies of customers' important data hence showcasing the cloud as an alternate and more cost effective method of storing tier-2 data than NAS. Going against the current trend of Cloud computing which has focused on inactive data such as archives, backups or disaster recovery copies, Zetta is trying something new - something which always grabs my attention and deserves a blog. So how does it work?

To allow data to be sent to the cloud, Zetta has developed its own file system instead of a customary Application Programming Interface. Incorporated within their proprietary file system are continual data integrity checks and data distribution over hardware nodes in an N+3 redundant configuration. With such a premise it’s obvious why they can boldly aim at enterprise data storage shops of 10 TB or greater, posing themselves as the new primary file system for tier-2 applications.

Based on just three layers i.e. a protocol translation, a file system management and a data management layer, the protocol translation layer provides the necessary NFS, CIFS, http or FTP access into its cloud for customers’ on site applications. Volume virtualization and quality of service management are also performed at this layer. Additionally customers receive write receipt confirmations that their data has been stored successfully via an inline data verification which uses a hashing algorithm. Once that data is stored the inline data verification performs continuously to keep tabs on any problems with data integrity, availability or performance. This leads the file system management layer to be handled by Zetta internally while the data management layer is responsible for where the data is stored. A fairly straightforward procedure which alleviates the burdens many enterprises are facing running in house data centers.

Currently with two data centers in Silicon Valley and plans to add facilities in New Jersey, Virginia, the Chicago area, Texas and Southern California over the next two years, Zetta’s pricing of just $0.25 per gigabyte per month, for a minimum of 1TB sounds a cost effective solution, that has the potential of taking off in the current economic climate.

But as with every great new idea and concept it's a given to have the image of a Storage Manager scrupulously assessing the risk of asking the CIO to place his company in a situation which is currently going against the grain. I myself already have reservations on whether Zetta themselves can make a success of this or not simply based on the fact that they will have to pitch to a Data Center Manager or Storage Manager a solution which indirectly makes the recipient less effective in their roles!

That doesn’t deviate from the fact that if the foundations of this direction of cloud storage service can be proven, we are on the crest of witnessing an exciting future transition to the cloud. Coupled with the news that HP have shown interest in going the same route, Zetta may just be onto something…..

Was InVista the New Betamax?

The best method of Storage virtualization has been one of the most debated and argued issues within the industry. Nobody argues that while it is nothing more than an abstraction between the storage device and its application, the benefits that come with it such as consolidation, ease of management, online migrations etc. make it a fundamental aspect of the constantly non-heterogeneous emerging world of storage.

Of course virtualization is on everyone’s lips with the advent of VMotion and Vstorage offered by the Server-based storage virtualization solution of VMware. Veritas Volume Manager and SUN’s ZFS are others which come to mind which have made virtualization an inbred of the Storage management arena.

But it was not so long ago back in the pre- VMAX days that most of the debate revolved around whether virtualization should be via the SAN or via the Array.

HDS pushed the way for external storage to be virtualised behind their enterprise arrays extending array functionality to modular systems and setting up the premise for a tiered storage framework via a single management console. The HDS solution works and is adopted and implemented by HP and SUN customers as well wherein storage systems that would have otherwise been dumped in the garbage are kept alive and given a strategic purpose hence bringing substantial savings.

One snag that always remained with the HDS solution was that everything was now tied to the enterprise array which in itself had an end of life and end of support and needed to be replaced with a newer model i.e. what occurred when the USP was replaced with the USPV. Having to replace the enterprise system didn’t now just mean migrating off the one system but also the storage externally attached and configured via virtualization – no easy task.

It was sometime during 2007 that EMC then announced what they termed ‘InVista’. Despite sounding like the title of a new pension scheme it was intriguing to say the least as Cisco in turn launched their compatible SSM modules. So what was it all about – Virtualisation through the SAN.

It made great sense and the concept floored the virtualization through the array argument on the basis of scalability alone. It would also cover protocols as they changed to 8Gb, 10Gb, FCoE or iSCSI . As storage systems would need replacing or infrastructures changed the changing of ports via modules made far greater economical sense than the huge enterprise array which everything else sat behind.

While it doesn’t require a genius to realize that fabric-based virtualisation would enable the appliance to be integrated into a SAN thus making data migration simple, it does require someone with an immense amount of confidence to go against the grain. Therein was the beginning of the end.

Hence like Betamax before it, a product which arguably was a far better and sensible option to its alternative i.e. VHS, InVista seems to have suffered a slow death as storage vitualisation continues to be pursue it’s path through the array.

Did EMC really care? InVista did run the possibility of taking a market share away from SRDF, or was it simply a case of cutting losses and joining the popular bandwagon. Either way the customer seems to have lost out, but then again who am I to argue with Mr.T?

'Surrogates' - A Glimpse of the Future of Storage

Having just seen Bruce Willis’ new futuristic Sci-Fi blockbuster ‘Surrogates’, one always likes to witness how Hollywood presents the future of storage. Ever since watching ‘Enemy of the State’ where gadgets such as flash drives, GPS etc. were being showcased prior to them being accessible to the mass market consumer, it’s always been an intriguing experience to see what future technology may pop up while eating your popcorn.

Indeed ‘Data is exponential’ is one of those truisms that haunt a Storage Manager and leave them to ponder on what developments will occur to somehow manage the unstoppable growth of data being collected from PC users to corporate companies. Hence it was interesting to see that the future envisioned in ‘Surrogates’ has hard drives of data stored within the user themselves i.e. the human minds.

Interestingly enough for data to be transferred you still need a USB stick, (not much advancement there then). Furthermore the problem of archiving is still not solved as even after the host’s death the data can still be restored and accessed. So still no answer to the data dilemma but in the meantime here’s the trailer:

Has the SUN ORACLE Merger been SideKicked into Reality?

While personally, I believe the Sidekick disaster was just a stumbling block in the embracing of cloud computing for many organizations, today’s news that the newly formed alliance of SUN and Oracle was possibly to blame adds a whole new dimension to the issue.

According to some reports the Sidekick service crash involved an Oracle RAC database and Solaris and Linux servers. Currently unlike EMC who were quick to retract the finger pointers, Oracle and Sun declined to respond to the accusations.

To put a picture on the background of this scenario one needs to firstly look at the Oracle RAC database, a single database set up which runs across a cluster of servers for fault tolerance, performance and scalability reasons. If reports are to be believed the outage mainly stemmed from the Sun servers which led to the user data being inaccessible in the Oracle database and its backup. While the data was not deleted, it couldn't be found and hence accessed until the system was rebuilt. In other words the corruption caused by the SUN servers during an update process was passed onto the Oracle RAC which in turn made the data inaccessible.

So while the initial fear that the data outage experienced by T-Mobile's Sidekick phones was the disaster of unrecoverable data loss, current reports that Microsoft, (the owner of the infrastructure service behind Sidekick) is able to recover most of the data acts as a slight sense of relief to all the proponents of the cloud.

In turn though what Microsoft’s claim also does is a place a rather huge dent in what initially started off as a brave and exciting merger between SUN and Oracle.

Hitachi Reaches For The Clouds

Hitachi Data Systems recently showcased the new Hitachi Content Platform penned ‘the Cloud-friendly’ replacement to the hardware formerly known as HCAP. So what is different about the HCP compared to its predecessor apart from the removal of ‘Archive’ from its title and is this a really Hitachi’s way of embracing cloud computing?

As up and coming vendors enter the game pushing products strictly focused on cloud computing, the entrance of the major storage vendors is as guaranteed as Paris Hilton attending another A-list celebrity bash i.e. she might not be invited but you just try stopping her. What baffles me though is to why HDS chose now of all times to make this announcement. It’s not even been a week since Hitachi Data Systems was accused of being part of the Sidekick SAN failure that led to a humiliating data loss and in turn tarnished the very name of cloud computing. Indeed a platform like this to be launched when certain eye brows are being raised regarding Hitachi's reliability is bold to say the least. But then again I’m a big fan of the HDS products and if they’re confident enough to make this announcement at this time then it certainly requires closer inspection….

Upon closer inspection you quickly see why HDS want to show off this little beauty. Improving upon its predecessor the HCP supports logical partitions to segregate data and administration for multitenancy, access rights to prevent unauthorized access, as well as encryption. These are all in addition to the expected storage for unstructured data and support to the rest of the HDS Storage family.

Additionally to really prove the point that to every cloud there is a silver lining, Hitachi have also incorporated a Representational State Transfer Interface. Hence connection to the cloud, namespaces, chargeback, and supports compression and single instancing would be via the REST interface.

Block and file storage on one platform with additional cloud computing benefits, HDS have laid their cards on the cloud table, so who will now come up next to show their hand?