April 28, 2010 4:27 PM
Posted by: Beth Pariseau
Earlier this week, we ran a story about email hosting provider Intermedia attributing a recent outage to a failure in its EMC SAN. After the story ran, we received feedback from Bob Adams, a storage systems engineer at a leading Boston teaching hospital, on the case:
“I can’t see how Intermedia can truly blame this on EMC,” Adams wrote in an email.
First of all, the EMC SAN referred to here is clearly an EMC CLARiiON based on the information provided. The fact that one of the storage processor’s had a failure, probably a bugcheck panic (like a windows BSOD…CX’s run Windows OS on the SP’s) due to a bug in the firmware aka FLARE code is a case that their SAN Admin hadn’t been patching/updating the FLARE code on a regular basis as he/she should be doing.
Then with the failure and having to run on one storage processors is something the CLARiiON is designed to be able to do for fault tolerance as well as load balancing, again the SAN admin was at fault for this CLARiiON was clearly over utilized. The utilization on the storage processors has to be within a CPU percentage range so that if an SP had a failure the second SP could handle its own load plus the load of the other. Meaning if the utilization of say SPA was 75% and the utilization of SPB was 75%, there is no way if SPA failed SPB will be able to handle the load. Which sounds what happened here. I see this as more of Intermedia’s own fault over EMC.
What do you think? Comments operators are standing by…
April 27, 2010 9:10 PM
Posted by: Beth Pariseau
Unitrends Inc. has put its own spin on data reduction for small and midsized businesses (SMBs) that use its backup appliances.
Previously, Unitrends has offered file-level compression and post-process subfile data deduplication with its products, but said the CPU overhead of doing subfile level deduplication on its customers’ relatively small data sets resulted in the need for beefier processors and appliance hardware. This in turn might be more expensive for some small customers than just buying more disk, according to Unitrends COO Mark Campbell.
Unitrends today announced what it calls Adaptive Deduplication, and Campbell says the goal is to offer users the best storage utilization possible without compromising performance. Adaptive Deduplication adds a light content-aware algorithm that evaluates the type of data (structured or unstructured) as well as its size as it comes into the system, and determines how the best data reduction ratio can be achieved. All files are compressed as they come into the system, but only larger data objects will be pulled apart for sub-file dedupe later.
“Typically structured data is better served by the compression ratio — files almost always dedupe pretty quickly,” he said. Now, if a user is making small incremental changes to a database, the system won’t have to pull apart every small block to look for additional data reduction beyond compression — it can just compress the data and move on.
While the high performance overhead of doing data deduplication has been a major issue with the technology since its inception, users at midsized and larger companies have been willing to pay the price for processors in order to contain unmanageable backup capacity growth.
But Campbell brings up an interesting challenge to dedupe-as-panacea: Unitrends customers are often in small shops that require as little as seven days data retention, and “they don’t get great ratios with traditional block-level deduplication. When disk drives are so cheap, it’s not necessarily a no-brainer to purchase next generation hardware to push subfile dedupe.”
The compression and file-level dedupe will be included with the software that comes on all Unitrends appliances, and current customers will be able to download it beginning next month. For customers still looking for subfile dedupe, Unitrends will also come out with a new appliance heavier on processors than capacity later this year, which will make subfile deduplication more likely under Adaptive Deduplication. “It sounds funky and weird and why not just put [a new appliance] out there, but it’s a price-performance issue,” Campbell said.
April 26, 2010 9:14 PM
Posted by: Beth Pariseau
Fibre Channel SANs
, Fibre Channel switches
Virtual Instruments, a spinoff of network monitoring company Finisar, rolled out a new hardware configuration for its Traffic Access Port (TAP) devices, which watch bi-directional Fibre Channel traffic on SAN switch links to diagnose problems.
TAPs are an option with Virtual Instruments’ VirtualWisdom and NetWisdom FC SAN monitoring products, which also involve software components and can be deployed with or without adding TAPs to the SAN. Previously, according to Virtual Instruments VP of marketing Len Rosenthal, users wishing to use TAPs would have to attach two fiber optic splitters to each connection they wanted to monitor. That was time consuming and disruptive if it involved critical connections. It could also result in more ”light loss” from the fiber optic connections depending on how many TAPs were in place.
Today, Virtual Instruments introduced a new patch panel hardware form factor for TAPs, which allows multiple fiber optic connections to be connected to one 10-Gigabit panel that can be dropped into a user’s existing core switches. This makes connecting to the TAP once it’s in place simpler and uses patch cables, which Rosenthal said users should also be familiar with.
However, even with the new patch panel there will still be some disruption when retrofitting already-running SANs with TAPs. Rosenthal said Virtual Instruments advises users to TAP new SAN connections as a part of installation. “Life is so much easier if the TAP is in there to begin with,” he said.
April 22, 2010 3:07 PM
Posted by: Dave Raffo
NAS vendor Isilon made it two straight profitable quarters when it beat expectations for last quarter to report 46% year-over-year revenue growth.
Isilon’s revenue of $39.3 million was even up 5% over the previous quarter, and it’s rare for storage companies to increase revenue from the fourth quarter of one year to the first quarter of the next. Isilon had $1.1 million of net income, up from $100,000 in the previous quarter. That compares to a $10.4 million loss in the first quarter of 2009. Isilon executives even raised their forecast for 2010 revenue from growth in the low-to-mid 20% range to an increase in the mid-30% range.
Isilon CEO Sujal Patel said the revenue growth came partly from pent-up demand of customers who has budget constraints in 2009, as well as better international sales and an increased channel focus. He also said Isilon is moving into more mainstream enterprise NAS accounts to go with its previous success in verticals such as media and entertainment.
Patel says Isilon is also benefiting from an industry focus on scale out NAS because its main NAS competitors don’t have clustered products yet.
“We have very little competition in the scale out space,” Patel said today on the Isilon earnings conference call. “There are lots of announcements out there from large companies, but most of the products we compete with are still two-controller products.”
After adding support for solid state drives (SSDs) and other hardware enhancements over the past year, Patel said Isilon’s product focus will be on software this year.
He says Isilon plans an operating system upgrade this year with and new software applications in 2010 and early 2011. He didn’t offer details, but Isilon could benefit from greater optimization with virtual servers and mainstream storage applications such as Oracle databases as well as native data deduplication.
April 21, 2010 8:24 PM
Posted by: Beth Pariseau
Network and application management software maker SolarWinds today said it is re-releasing the storage resource management (SRM) products it bought in January with its $42 million acquisition of Tek-Tools under a SolarWinds branding and pricing scheme.
The products are now known as SolarWinds Storage Profiler, Backup Profiler and Server and Virtualization Profiler. Backup Profiler and Server and Virtualization Profiler will be licensed according to the number of physical or virtual servers being monitored (previously pricing varied depending on whether servers were virtual or physical). The new licensing scheme for Storage Profiler will be based on the number of disks being monitored and will be priced in tiers, starting at $2,995 for the first tier (up to 50 disks).
SolarWinds is planning to convert all customers to the new licensing scheme even if they are not changing their deployments, according to vice president of product marketing and management Sanjay Castelino. But one customer says the details about how that process will happen haven’t been made clear yet.
“I don’t understand if they’re just going to straight swap our license in some fashion,” said the customer, an administrator for a financial services company speaking on condition of anonymity. “For example, we have eight [disk arrays] with over 1,000 disks combined, but no one has asked us that so how can they issue a new license? One thing they could be doing better is reaching out and explaining this better because the email [sent to customers] does not explain the process, it just lists the new pricing scheme.”
April 21, 2010 12:11 PM
Posted by: Dave Raffo
, disk-based backup
Sepaton today launched its next generation enterprise virtual tape library (VTL) series, built on Hitachi Data Systems storage.
The Sepaton S2100-E2 Series 1900 and 2900 VTLs that will be available in June use the Hitachi Adaptable Modular Storage (ASM) 2100 system as the underlying storage through a global reseller deal with HDS. This is a different type of relationship Sepaton has with Hewlett-Packard, which sells Sepaton software on its own hardware to make up the HP Virtual Library Systems (VLS) product. In this case, Sepaton is selling HDS hardware integrated with the Sepaton S2100-ES2 VTL appliance, and its DeltaStor data deduplication and DeltaRemote replication software. However, Sepaton VP of worldwide marketing Jay Kramer says the HDS sales force will also sell the new 1900 and 2900 systems.
Sepaton will continue to support its S2100-ES2 1000 series – built on storage from Dot Hill – and the new systems can be used to expand existing customers’ VTLs, but only the 1900 and 2900 systems will be available for new enterprise customers. The 1900 uses 1 TB SATA drives for 12 TB usable capacity per shelf and the 2900 uses 2 TB drives for 24 TB per shelf. The appliances scale to eight nodes and the 2900 can support 1.6 PB.
Pricing starts at $175,000 for 12 TB of storage and a 24 TB system costs $417,600. Those prices include Sepaton’s DeltaStor data deduplication software, which is now bundled on all appliances. Previously, DeltaStor was licensed separately. DeltaRemote replication is still a separate add-on, Kramer said.
Sepaton will continue to use Dot Hill for its midrange S2100-MS2 VTLs.
The industry transition from 4 Gbps to 8 Gbps Fibre Channel was the impetus for Sepaton’s new hardware platform. The new systems are Sepaton’s first to support 8-gig. Sepaton says the systems provide for five-nines of data availability with no single point of failure, and support hot swappable major components, dual-battery backup for cache, and RAID-6 dual parity support. They also include Sepaton’s DeltaView central management suite for monitoring and reporting.
The change in storage suppliers isn’t unusually for Sepaton – the vendor used storage from Apple and LSI before picking Dot Hill for its previous generation. But HDS gives Sepaton more than a hardware platform. Sepaton executives are counting on a sales boost as well from the HDS sales force, especially since HDS doesn’t have its own deduplication product. It resold Diligent ProtectTier VTL software with deduplication and Data Domain’s deduplication appliances, but that was before IBM bought Diligent and EMC acquired Data Domain.
“A major player of HDS’ standing is now a partner to us,” Kramer said. “We think this will make us a significant presence the marketplace.”
April 20, 2010 6:21 PM
Posted by: Beth Pariseau
A new company has emerged from stealth in the cloud data storage industry this week at Cloud Expo. TwinStrata Inc. is previewing what it calls its “cloud enablement strategy” today, though it’s not disclosing product details yet.
One thing TwinStrata’s product is not, according to CEO Nicos Vekiarides, is a cloud storage service. Instead, the company bills itself as a Storage Cloud Enablement specialist.
In its slide deck for press, TwinStrata listed the key requirements for Storage Cloud Enablement as the following:
•Non-disruptive integration w/existing business + data protection apps
•Supports all industry file systemsandblock-level access
•Intelligent caching architecture, delivers local performance
•Supports virtual and physical IT environments
•Easy to deploy, manage in self-service manner via UI, CLI and API
•Compute AnywhereTMapplication accessibility: on/off-premise, cloud
•Local and cloud data copies, zero-footprint snapshots
•Encryption for security
•Bandwidth savings via caching, compression, deduplication
•Support multiple cloud providers,with data mobility across providers
•Support providers that offer SLAs for regulatory & compliance
These aren’t confirmed product features, but the picture that’s emerging for me is a cloud gateway similar to Nasuni or StorSimple. Analysts have described these hybrid cloud gateways as the next frontier for file virtualization, so it wouldn’t surprise me to see more competitors enter this space this year.
Whatever the product turns out to be, TwinStrata says it will target medium-sized businesses (which it defines as companies with between $25 million and $99 million in annual revenue) and midsized enterprises ($100 million – $999 million).
April 20, 2010 5:40 PM
Posted by: Beth Pariseau
Here’s another new twist on converged networking: the InfiniBand Trade Association (IBTA) has released a new specification for building Remote Direct Memory Access (RDMA) into 10-Gigabit Data Center Ethernet (DCE) networks.
InfiniBand providers claim their value proposition is the same as Fibre Channel over Ethernet (FCoE) — the ability to combine multiple types of network traffic over one wide pipe. But according to Brian Sparks, senior director of marketing communications at Mellanox and co-chair of the IBTA’s Marketing Working Group, RDMA over Converged Ethernet (RoCE, pronounced “Rocky”) can theoretically be run over DCE alongside Fibre Channel traffic. “With priority flow control in DCE, you can do both, but it’s up to the NIC provider,” Sparks said.
Sparks said Mellanox is planning to release products that support RoCE, and that other members of the IBTA manufacturers including Broadcom, Intel and Chelsio, may be working on 10-gigE NICs that support RoCE as well. The IBTA envisions RoCE finding use cases in financial services companies or businesses with a similar reliance on databases and low tolerance for latency.
IBTA is also hoping this spec will fare better than its last attempt to drive RDMA into the Ethernet world, a spec for RDMA over 1 Gigabit Ethernet iSCSI links called iSER, known in its Intel incarnation as iWARP. “It’s had a hard time getting market adoption, since the adapters are a little high on the power side,” Sparks said. “They require a slightly more expensive NIC and maybe only get a microsecond or two latency benefit.”
RoCE will be different, Sparks said, because latency is much improved over 10-Gig networks, and DCE will do away with the need to offload TCP/IP traffic, one of the hindrances to better performance with iWARP.