The Virtual View

A New Home for LeftHand Musings...

John Spiers' posts have moved to HP's Around the Storage Block blog.

Many thanks to our loyal readers. Come join us at the new location for our posts!

http://www.communities.hp.com/online/blogs/datastorage/default.aspx

HP's Recent LeftHand New Starter SAN Announcement

You saw the announcement. It’s a great Starter SAN at a great price. A few people in the blogging community have interpreted that this announcement somehow relates to LeftHand only shipping on HP hardware from here on out. I don’t see that information in the release, so I figured I would set the record straight.

LeftHand’s software is hardware agnostic. Case in point, our Virtual SAN Appliance that can turn any storage server hardware in to a distributed, scale-out SAN, and it is not going away. So this pretty much puts a bullet in that theory. 

A second point made in the blogging community is that we are moving away from a software only model. We have been moving away from a software-only approach for some time. We quickly learned from our customers that it is easier to buy storage as an integrated storage system. Our software is still supported on other platforms and going forward, we will ship on HP.  HP is the leader in servers for a reason, so why not ship on the best, most cost effective storage server available in the market. Currently, there is nothing preventing a customer from incorporating an HP-based LeftHand storage system with their LeftHand/Dell or LeftHand/IBM SAN, they all work seamlessly together. Or if a customer chooses to turn those Dell or IBM servers in their branch offices into a shared SAN and automatically replicate the data back to a LeftHand SAN at head quarters – no problem. Of course if I had a chance to install HP blade servers in my remote offices in place of those dusty old Dell or IBM servers, I most certainly would.

So go ahead and run LeftHand on any hardware, including blade servers. The options are limitless. You can have scalable SAN storage with the VSA or LeftHand storage systems; it’s really up to you.

-John

Coming to a city near you…Disaster Recovery for Virtualized Environment Workshops

It is no surprise that reliable data protection is critical to a healthy bottom line. Even day-to-day problems like server failures, smoke or water damage, and human error can lead to devastating data loss.

Luckily, recent advances have helped to reduce cost and simplify the management of a disaster recovery initiative even for the resource constrained.

However, to achieve true business continuity required for today’s rapidly growing databases, a storage network solution must be pro-active, automated and able to scale at the first signs of growth.

We view business continuity as a spectrum.  At one end is high availability (HA), which means no down time and no data loss due to a disaster or failure. On the other end is disaster recovery (DR); which almost always involves downtime, lost access to data or data loss.

Companies today recognize that the benefits of virtualization aren’t limited to large, centralized data centers. Virtualization enables even small remote offices to have high availability using a smaller number of servers to support the applications they need. Companies who are implementing server virtualization without a complementary SAN solution are only solving half the problem. You can’t get true system high availability without virtualized storage.

To hear more about this subject, we are hosting the Disaster Recovery for Virtual Environments Workshop series in over 30 cities in the next seven weeks. In these workshops will highlight the advancements that are helping mid-sized companies achieve true HA and DR.

Click the video to learn more about our Disaster Recovery for Virtual Environment Workshops. For more information, please contact 866-355-3068 or register online here.

Listed below are the dates and cities we plan to visit during our workshop series.
  
Chicago, IL    Feb 10th
Albany, NY    Feb 11th
Tampa, FL    Feb 12th
Houston, TX,    Feb 17th
King of Prussia, PA    Feb 18th
Birmingham, AL    Feb 19th
Seattle, WA    Feb 19th
Minneapolis, MN    Feb 24th
Cincinnati, OH    Feb 25th
Virginia Beach, VA    Feb 26th
Phoenix, AZ    Feb 26th
Dallas, TX    March 3rd
New York City, NY    March 3rd
Jersey City, NJ    March 4th
Orlando, FL    March 5th
Denver, CO     March 5th
Los Angeles, CA    March 10th
Chicago, IL    March 10th
Burlington, MA    March 11th
Atlanta, GA    March 12th
San Francisco, CA     March 12th
Appleton, WI    March 18th
Ottawa, Canada    March 18th
Baltimore, MD    March 19th
Sacramento     March 19th
Troy, MI    March 24th
Nashua, NH    March 25th
Charlotte, NC    April 1st
Memphis, TN    April 2nd
Albuquerque, NM    April 2nd

 

LeftHand Networks Tapped by US Courts for Reliable Data Access

Today we released news that more than 20 of the United States Courts have selected LeftHand’s SANs announced for reliable disaster recovery, high-speed data access and centralized backup for remote and branch offices.

This latest announcement includes the United States District Court, District of New Jersey and United States Bankruptcy Court, Eastern District of New York.

To learn more click here.

Disaster Recovery for Virtualized Environments

Providing high availability and effective disaster recovery across geographically separated data centers is very challenging for most customers and has traditionally had a high price tag associated with it. The old way of doing this requires expensive remote replication software and a new SAN for the remote site. Prior to iSCSI SANs, a customer would typically have to purchase expensive fibre channel SAN replication software and fibre channel to IP/internet bridge equipment. It also took professional services to install the DR software and hardware and do things like tune fiber channel buffer credits on the bridges so that the SAN wouldn’t shut down from link latency.

When using these legacy SAN DR solutions the worst of part of it comes when a site fails and the applications have to be manually started up on the remote site. This requires setting up all the fun stuff that exists on the primary site including storage replication transaction log analysis, remapping HBAs to LUNs and security setup; LUN masking and switch zoning. If the link went down instead of a site, transactions could have been written to the remote site without the acknowledgment being received by the primary site. This can result in what’s referred to as a “split brain”, which means that you may have to completely rebuild the primary site from the secondary site, or play around with logs for hours to determine which transactions went where.

The good news is that times have changed. First of all, with iSCSI, it’s all IP end-to-end and you only have one network to manage. And TCP/IP takes care of transmitting over any latency, so you don’t have to worry about any specialized gear to get your data to the other side.

The LeftHand SAN technology not only offers an iSCSI-based solution, but is the only SAN solution in the industry that can create virtual, redundant volumes that span multiple sites. What this means is that servers see the same volumes, and connect to the volumes through the same IP address (or a different IP address or subnet, your choice) at each site. This makes life very simple when failing over servers and virtual machines. For example, when combined with VMware HA, a site failure can be detected within 15 seconds and the virtual machines started up within a minute at the remote site—as opposed to the several hours that are typically required for an administrator to physically go to the site and bring the servers online and connect the VMs to a different SAN with distinct volume copies. When failing over to a secondary location with the LeftHand SAN, the virtual machines are connecting to the exact same SAN volumes that they were connected to at the primary site. In other words, your data is always online, and it’s just a matter of getting your servers and virtual machines re-connected to the always-available SAN volumes. This can be setup for redundancy across racks, floors, buildings and sites many miles away.

What’s really cool is to think about what lies ahead. Take VMware’s Fault Tolerance software, for example. VMware Fault Tolerance is leading-edge technology that provides continuous availability for applications in the event of server failures.  It does this by creating a live shadow instance of a virtual machine that is in virtual lockstep with the primary instance. By allowing instantaneous failover between the two instances in the event of hardware failure, VMware Fault Tolerance eliminates even the smallest of data loss or disruption. When you combine this with LeftHand’s Multi-site SAN capability, you end up with true HA and DR with no reboot and seamless cutover; you can power off a site with no interruption to end users.

There is also LeftHand Remote Copy software that has very similar capabilities, but works over slower, higher latency links, and is certified with VMware SRM. What’s really remarkable is that LeftHand’s Multi-site SAN and Remote Copy software are both included with all of LeftHand’s SAN products, and managed from the same GUI. We figure customers should have this capability whether they plan to use it now or not, because we believe some day they will want to setup an HA/DR environment, or remote backup site, and the software will be ready. And in most cases they won’t need to purchase a new LeftHand SAN for the remote site, just spread the existing SAN across both sites. Remote offices can also be replicated automatically back to a central site with the use of LeftHand’s Virtual SAN Appliance, with no additional SAN hardware purchases required.

Now that’s HA and DR the way it should be. Stay tuned, we have some great DR events coming to a city near you.

Happy Holidays and 2009 Storage Industry Predictions

Most of HP will be closing over the Holidays and that means we won't be posting to the blog until we return the week of January 5th.  I'll be on vacation and it may take a few days before I see comments.

Before we sign off for the year, I wanted to leave you with my thoughts on 2008 and some storage predictions for the New Year.

It’s been an incredible journey for LeftHand and the storage industry in general.  Just to highlight a few of our achievements, LeftHand hit a milestone of 3,000 customers this year and just last week, LeftHand was named the CDW partner of the year, which is a real testament to LeftHand being the iSCSI storage leader in the channel. But the biggest announcement had to be that our company was acquired by the best computer company in the world with one of the fastest growing storage businesses.  HP’s storage business grew 13.5% in 2008, and with the acquisition of LeftHand I predict HP will soon be the fastest growing storage company. 

I still remember back in 2000 when LeftHand was raising money on the promise of block storage over Ethernet and a revolutionary storage virtualization technology with scale-out clustering. A Venture Capitalist brought in Bernard Daines, widely regarded as the "Father of the Gigabit Ethernet," to do due diligence on LeftHand’s vision for storage over Gigabit Ethernet.  I don’t remember his exact words, but he basically said that it’s not viable because of TCP overhead and latency.  I have news for you Bernard, in the past three years we witnessed iSCSI becoming the storage industry’s fastest growing technology, which brought about IBM’s OEM agreement with NetApp, Dell’s acquisition of EqualLogic and HP’s acquisition of LeftHand Networks. In short, iSCSI's going strong, even in the face of old pundit warnings that iSCSI had limited performance compared with Fibre Channel and therefore would be inappropriate for mission-critical apps.

Ok, enough about us, it’s now time for my storage industry predictions. These predictions are mine only and may not be shared by HP.

• 2008 will be the year 10 Gigabit iSCSI becomes a reality. We will also see the Fibre Channel industry throw in the towel on traditional Fibre Channel and endorse Fibre Channel over Ethernet (FCoE). Of course we all know how I feel about that (see my “Fibre Channel is Dead” blog.

• Companies will require a dynamic IT infrastructure that adapts on-the-fly to deliver compute  cycles and storage capacity with quality of service guarantees for performance and availability. In 2008 we witnessed server and storage virtualization going mainstream. Of course customers are still confused because of the abuse of the “V-word.”  To make matters worse “virtualization” is rapidly being replaced by “cloud,” which makes it all the more nebulous.  In a nut shell customers want an easy to manage IT environment that scales without disruption to their business, delivers high availability and data protection against failure and finally, is secure.

• The age of storage virtualization and management layer being tied to a proprietary dual-processor controller boxes will go the way of the dinosaurs. A key architecture requirement to deliver on this promise is the ability to add or remove hardware resources on-the-fly underneath the virtualization layer to deliver these service guarantees. One of the most fundamental requirements to deliver on this promise is for the virtualization layer to run without being tethered to specific hardware. VMware and other virtualization engines deliver this with the ability to move running applications across server hardware on the fly. LeftHand’s SAN/iQ software delivers on this promise by providing a storage infrastructure where physical storage can be of any type, geographically dispersed and managed as a single entity.

I'd like to thank our readers/subscribers to the Virtual View storage blog that was launched in August of this year.  Its progress has been steady, but over the last few months, with the help of our PR firm and participation by other LeftHanders, it’s really starting to take off. We look forward to our blogs hitting prime time in 2009 and invite you, our readers, to participate in the discussion.

Happy Holidays!

LeftHand Customer Awarded Storage Virtualization Project of the Year

We at LeftHand are happy to share that our customer, Oxford University was a runner up for the UK' Storage Virtualization Project of the Year Award.  Part of the SNS Achievements in Technology Awards, the Storage Virtualization Project of the Year Award recognizes UK-based successful storage virtualization projects of any size.

The oldest University in the English-speaking world, Oxford is a leader in learning, teaching and researching. It plays host to more than 20,000 undergraduate and postgraduate students, 8,500 University staff and 3,000 College staff. Oxford University was recognized for its resilient, multi-site, virtualized storage infrastructure using LeftHand Networks iSCSI SANs.

At two sites, LeftHand SANs were installed and clustered to form a single SAN that could facilitate two-way replication. This deployment is ideal for organizations with multiple locations like Oxford University, which has IT services widely distributed across many locations. Its central computing service has around 150 employees; but there are many hundreds more spread throughout the 38 university colleges and myriad departments.

LeftHand Networks: Closing the Deal

LeftHand Networks runs into the competition in the lobby of a mutual prospect. This light-hearted video shares some of the key features built into every LeftHand SAN. These features include:

• Storage Clustering
• Network RAID
• Thin Provisioning
• Snapshots
• Remote Copy

LeftHand Named CDW Partner of the Year

We were pleased to be one of five companies to receive CDW’s Partner of the Year award at the recent CDW Summit. One of the great things about this recognition is that it reinforces our dedication to the channel. Our success is dependant on our partners’ success and our long and successful partnership with CDW exemplifies that.

The Partner of the Year awards were presented at the 2008 CDW Partner Summit in Las Vegas on November 18th. The awards are based on input from CDW customers, account managers, product management teams, advanced technology specialists and executives as well as on the growth of sales through CDW. The partners’ financial performance is also a factor.

So to the customers, product managers and executives involved in our success with CDW, as well as those who helped select LeftHand Networks for this award, we thank you! Our new colleagues at HP also shared their enthusiasm for this achievement, click here to visit HP's Storage Around the Block post.

SSD – The Next Big Thing?

It seems like the industry is getting hyped up over Solid State Disk (SSD) drives again. Analysts have been predicting the death of electromechanical disk drives and the coming of Solid State drives for close to 3 decades now. The first ferrite memory SSD devices emerged during the era of vacuum tube computers, but were discontinued with the introduction of cheaper drum storage units. In the 1970s and 1980s, SSDs were implemented in semiconductor memory for early supercomputers of IBM, Amdahl and Cray, but the high prices make them seldom used in mainstream storage products, which is the case to this day. As of mid-2008, Flash SSD prices are still considerably more costly per gigabyte than comparable conventional hard drives. SSD is typically $2 to $3.50 per GB for flash drives compared to less than USD 0.15 per gigabyte for hard drives. With the advent of MLC (multi-bit per cell), SSD cost is being reduced by 50% in $/GB annually and analysts are expecting prices to be competitive with that of Hard Disk Drive (HDD) by 2012.

In the mean time the disk drive guys have blown past many predictions of when they would reach the Superparamagnetic Limit (the theoretical maximum number of bits that can be recorded per square in.) They have already hit 1 trillion bits per square inch (or 1 terrabit/in²), which means we will see 5TB 3.5” drives before long. Physics will catch up to them sooner or later. My prediction is that they will hit the wall within the next 10 years and SSDs will begin to take over. Seagate is already working on hybrid drives (solid state memory with a traditional disk drive), so we will have a period in the industry with hybrid drives, which promises increased performance form a front-end read/write cache combined with economical high density disk.

Today’s major impediments to the widespread usage of SSD are Flash write endurance limitation, data loss in terms of non-recoverable bit errors and random write performance. Flash-memory cells wear out after 1,000 to 10,000 write cycles for MLC, and 100,000 write cycles for SLC (single bit per cell). Some high endurance cells may have an endurance of 1–5 million write cycles, but many log files, file allocation tables, and other commonly used parts of the file system can easily exceed this over the lifetime of a computer. Special file systems or firmware designs can mitigate this problem by spreading writes over the entire device (so-called wear leveling), rather than rewriting files in place. In 2008 wear leveling was just beginning to be incorporated into devices.

In the case of HDDs, the drive industry took twenty years to perfect disk controllers to overcome electromechanical and magnetic media imperfections for reliable storage.  Similarly, the SSD controllers have to evolve and mature to solve the endurance and reliability problems created by MLC Flash and the process technology as it scales from the current 65nm to smaller process nodes over the next few years.  The existing SSDs that EMC and other storage vendors have announced use expensive SLC (single bit per cell) Flash chips and their controllers offer an incomplete solution to the performance, endurance and data loss problems. The global NAND Flash fabrication capacity is shifting completely to MLC owing to its higher density and lower cost, therefore SLC drives will be short lived.

All of this suggests SSDs are at least a generation away from full usability, especially in the enterprise. However, IDC is forecasting that deployment of SSDs in enterprise computing will pick up by 2010 and that enterprise computing applications will grow from 12% of SSD revenue in 2007 to more than 50% by 2011. I believe SSDs will be predominately used for things like boot applications, or for applications requiring high random read performance, but won’t be used for primary storage applications intended for high duty cycle workloads, or applications requiring high write performance & reliability until the cost comes down further and the error correction technology for MLC flash matures.