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…..

http://www.zetta.net/

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?

Is The Future Really Flash?

With the performance boost as well as power savings that SSDs have to offer, the comprehensive move from mechanical drives to Solid State Disks is an inevitability, While the PC user faced an almost immediate phasing out of 3.5 inch floppy disk drives (let’s forget the brief Zip drive era) for GB USB sticks, surely the drive for tiered storage based upon different grades of SSDs should be just as rapid? But this hasn’t been the case with one left wondering as to why?

The first obvious answer is the price. Not many companies are prepared to fork out the extra 30 times price hike for SSDs to the already expensive magnetic disk drives they purchase.

The other and more controversial answer are the storage vendors themselves. Not yet amongst the big daddy of corporate companies, the production of SSDs are still limited to vendors not necessarily linked or partnered with any of the major storage vendors. Hence they can only market their products to consumers via the Storage vendors that already have their mechanical disk platforms in place in just about every datacenter in the world. Hence the emergence and availability of the readily compatible Flash drives ahead of the more complex DRAM SSDs.

Despite the obvious advantages of DRAM SSDs over their Flash counterpart , the marketing has been pushing for the ‘future of flash’ and their compatibility with the already existing storage systems. While it doesn’t take rocket science to realize that the storage vendors wanted to ensure that their current hardware didn’t prematurely pass their shelf date with the rapid development of SSDs, the marketing ploy stating that flash drives would provide superior performance can now be seen to be nothing more than hyperbole aimed at generating Google-keen I.T. Directors to part with their budgets.

The fad was clear: push flash drives as the new ‘super’ tier one, thus allowing customers to embrace the inevitability of SSD while still maintaining the sales and maintenance of current storage systems which could have flash drives installed in their back end. A good deal for the storage vendor but not so great for the customer or the developers and small companies who were producing SSDs of far superior quality and performance to the currently compatible flash drives.

So what exactly is the problem with Flash drives in comparison to DRAM SSDs?

Firstly their life time due to their limitation of erase/write cycles. Unlike DRAM, Flash is limited in the number of times it can be erased and rewritten which poses the problem of a write failure in the middle of a database transaction. All the redundant hardware and setup of your infrastructure becomes compromised with the risk writes which have already been committed being at risk due to a potential write failure. Coupled with the fact that Flash drives currently have no Self-Monitoring, Analysis and Reporting Technology, something which is found in magnetic disks and automatically monitors a disk drive’s health and reports potential problems. Hence proactive actions can be taken with magnetic disks to prevent impending disk failures but not so with Flash.

Furthermore the marketed performance improvements of Flash over their magnetic disk counterparts also need to be looked at with a shrewd eye. While DRAMs would sit in the front end cache, Flash disks reside on the back end of a storage system. That means behind a RAID controller, which is behind controller cache, which is behind storage port controllers, which are behind a SAN, which is behind a server! Hence purchasing Flash disks on the backend may not only be uneconomical but also illogical when placed in a situation where most I/Os are dealt with by front end hits to the cache. In addition when some applications stage the majority of I/O requests to server memory then the marketed advantages of Flash become very dubious certainly not 30 times greater than their magnetic cousins.

Undoubtedly the underlying point remains that It’s not a question of if, but when the mechanical drive will be made extinct by SSDs.

Developments such as Pliant’s claim that their 3.5-inch enterprise solid-state drive is able to run at speeds of almost 500 megabytes per second and can write the data at a speed of 320 megabytes per second, SUN Microsystem’s new 2TB SSD F5100 array and 2001’s announcement that their 2.5-inch SATA SSD will have built-in ECC (Error Correction Code) functionality all make it clear that while the future might not necessarily remain flash it certainly will be solid.