GigaOM » solid-state drives

AWS beefs up cloud for super-fast data processing

Derrick Harris — Tue, 22 Jan 2013 12:57:04 +0000

Latching onto the trend toward in-memory storage for real-time computing, Amazon Web Services has added a new type of virtual server. The new option — the 10th such available on the EC2 offering — is called the High-Memory Cluster Instance and includes 88 EC2 Compute Units of compute capacity (running on two Intel Xeon E5-2670 processors, two 120 GB solid-state drives of instance storage and 244 GB of RAM.

It’s designed with speed in mind for uses such as in-memory analytics (including on SAP’s popular HANA platform) and certain scientific workloads that require data delivery to keep up with processing speed. The faster applications can read and write data — and doing so from an in-memory cache or solid-state drives is much faster than doing so from hard drives — the sooner that processors can compute it.

And because the new instance is part of AWS’s Cluster Compute family, multiple instances are connected via a 10 GbE network for speedy server-to-server data transfer. In benchmark tests from a site called CloudHarmony in 2010, Cluster Compute instances far outperformed anything else on the market (GigaOM Pro subscription req’d) at the time. They’ve also been used to spin up clusters that can compete with traditional supercomputers in terms of sheer performance — reaching No. 102 on the lastest Top500 list with a peak speed of 354.1 teraflops.

Although, it should be noted, AWS isn’t the only game in town for users wanting this type of beefy core in order to handle their real-time data processing needs. Liquid Web’s Storm cloud service, for example, offers some high-memory, SSD-powered servers of its own at nearly $1.50 per hour less than what AWS charges (albeit with fewer cores and absent the 10 GbE backbone and list of features that comes along with the AWS platform).

Whatever the cloud, though, ever-higher-performing instances mean new classes of workloads and more business for cloud providers that offer them. Especially as big data and analytics applications pick up steam and move from batch to real-time, clouds that can handle demanding users are in a good position.

Feature image courtesy of Shutterstock user ssguy.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Cloud and data third-quarter 2012

Tue, 16 Oct 2012 03:55:56 +0000

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Nimble Storage gets $40M as IPO approaches

Derrick Harris — Mon, 10 Sep 2012 10:00:39 +0000

Updated: Flash-based storage provider Nimble Storage has closed a $40.7 million mezzanine round months ahead of schedule, as investors are lining up to get a piece of the next big storage initial public offering. Sequoia Capital and Accel Partners led the round, which brings Nimble’s total funding to $98 million and puts its valuation in the range of other recent storage-industry success stories Data Domain and 3PAR, according to CEO Suresh Vasudevan.

Update: Nimble has been remarkably successful since it began shipping its hybrid flash-plus-hard-drive gear two years ago. The company, which focuses on small and mid-size enterprises, has amassed more than 1,100 deployments across more than 600 customers and hopes to be bringing in quarterly revenue between $25 million and $35 million relatively soon, Vasudevan said during a recent interview. It comes up against large vendors such as NetApp, Dell and EMC about 85 percent of the time, he added, and it typically wins those deals.

Flash storage is a white-hot market right now because of the significant performance and efficiency improvements it provides over hard drives — important considerations in a world where virtualization reigns supreme — and because the gap in price between the two is closing fast. In the past several months, EMC paid $430 million for all-flash startup XtremIO, while Violin Memory ($80 million) and Pure Storage ($40 million) have both brought in hefty investments. Nutanix and Tintri, both of which, like Nimble, fuse flash and hard drives and target mid-market businesses, recently raised $33 million and $25 million, respectively.

Putting both flash drives and hard disks in the same array means customers can save money on bulk storage while still getting the flash performance boost where it’s needed. As I explained when covering Nimble’s previous funding round in July 2011, customers seem to love the flexibility of its appliances. They can change the ratio of flash to hard to disk capacity to suit their needs, and some customers even use a single Nimble appliance for both primary storage and backup (with hot data in flash and backup data on the spinning disks).

Nimble is eyeing late 2013 or or 2014 for its IPO, Vasudevan said, although it raised its final funding six to nine months before it planned to because outside firms kept approaching it with aggressive and attractive term sheets. In the end, Nimble took money from all of its existing investors as well as newcomer GGV Capital. Vasudevan said the new investment will help fuel international expansion as well as a planned surge in headcount over the next 18 months.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Etsy unveils its infrastructure (and its Supermicro love)

Derrick Harris — Fri, 31 Aug 2012 23:27:34 +0000

Online marketplace Etsy has been on a mission of openness lately — last week, it gave an in-depth explanation of a few recent outages — and on Friday it shared the details of the hardware architecture that powers its popular business. Etsy isn’t Facebook in terms of scale or specialization, but it’s always interesting to see what’s under the covers of growing web companies.

And under the covers at Etsy is a lot of Supermicro gear. According to blog post author Laurie Denness, a single class of Supermicro 2U, 4-node chassis powers powers a high number of workloads including memcached and web serving. Like many large web companies, including eBay, Etsy tries to stick with a limited hardware stack that’s versatile enough to handle multiple workloads.

With that in mind, Denness wrote, “A general configuration for these would be 2x 8 core Intel E5620 CPUs (@ 2.40ghz), 12GB-96GB of RAM, and either a 600GB 7200pm hard disk or an Intel 160GB SSD.”

He also notes the lack of RAID in this sytem, which could have a negative effect on redundancy. However, because Etsy uses Chef, and another tool called Cobbler, to quickly rebuild failed nodes, Etsy doesn’t think wasting power on RAID is necessary: “In our view, why power two drives when our datacenter staff can replace the drive and rebuild the machine and have it back in production in under 20 minutes?”

Etsy beefs up this same general-purpose chassis for its search engine, replacing the 8-core processors with 16-core Sandy Bridge processors and adding a boatload of solid-state storage:

[This setup] gives us machines that can handle over 4 times the workload of the generic nodes above, whilst using the same density configuration and not that much more power. … The nodes have 96GB of RAM and a single 800GB SSD for the indexes. This follows the same pattern of not bothering with RAID; The SSD is perfectly fast enough on it’s own, and we have BitTorrent index distribution which means getting the indexes to the machine is super fast.

Etsy’s Hadoop nodes

Supermicro is the name of the game for Hadoop and backup at Etsy as well. Although the post doesn’t disclose how big Etsy’s Hadoop cluster is, Denness notes that the company crams 96 cores, 384GB RAM and 24TB per 2U of rack space. For backup, it’s a 4U Supermicro box packing 36 2TB hard drives that deliver “a blistering 1.2 gigabytes/second sequential write throughput and a total of 60TB of usable disk space across two RAID6 volumes.”

HP also gets a little love at Etsy, powering both its MySQL database and a handful of special jobs, such as its Hadoop NameNodes “that don’t need much horsepower, but we deem important enough to have RAID,” Denness wrote.

Etsy’s hardware choices aren’t earth-shattering news by any means, but this type of openness is critical as a great number of businesses make their home on the web. Speaking openly about this stuff (hint, hint, Twitter) helps give other companies ideas about how to improve their systems, while also providing the opportunity to learn from suggestions from others (a la profiting from code contribution in open source software). It also helps advance the idea of a crowdsourced model for performance benchmarking, where everyone can see setups and performance data from in-the-wild systems that haven’t been tuned to the nth degree by vendors.

In a webscale world where software reins supreme, a floating hardware tide floats all boats.

Feature image courtesy of Shutterstock user MilousSK.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Tintri gets $25M to tune flash storage for VMs

Derrick Harris — Tue, 24 Jul 2012 14:53:20 +0000

A Mountain View, Calif., storage startup called Tintri has raised $25 million for its virtualization-focused flash storage appliances. The appliances, called VMstore, mix hard-disk and solid-state drives and promise better storage performance than traditional systems for virtualized applications.

We wrote about Tintri last summer as the storage system behind gaming startup Digital Chocolate. Essentially, each appliance contains up to 13.5TB of usable capacity and boosts performance of virtualized environments because the storage software is designed from the ground up for virtualization. The idea is that it’s easier for storage administrators because they can track performance at the virtual-machine level — just like with their virtualization-management software — rather than by trying to negotiate the traverse between VMs on one side and LUNs, files and other traditional storage-system divisions on the other side.

Flash storage is becoming increasingly appealing appealing for virtualized applications such as databases that need higher throughput than hard disks can comfortably handle. Rather than providing brute performance with an all-flash array, though, Tintri claims its specialized software lets it make maximum use of a relatively small flash tier (only 2.4TB of raw capacity on its high-end appliance compared with 24TB of hard disk capacity) while still keeping prices low.

Tintri has raised $60 million thus far. Menlo Ventures led this round and was joined by existing investors NEA and Lightspeed Venture Partners.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

EMC goes all-flash, buys XtremIO for $430M

Derrick Harris — Thu, 10 May 2012 15:00:43 +0000

As expected, EMC has bought Israeli flash-storage startup XtremIO for $430 million, according to Israeli news site Globes. The acquisition was expected after rumors began swirling in late April that EMC was courting the company, which sells a storage array composed entirely of flash memory.

When fully incorporated, XtremIO’s technology will be just the latest in a growing lineup of flash options EMC offers customers. When I spoke recently with VMware CTO Steve Herrod, who, it was reported, was part of the contingent in Israel speaking with XtremIO leading up the acquisition, he told me he envisions flash as a major hardware component of tomorrow’s software-defined data centers. Clearly, VMware and EMC, VMware’s majority shareholder, are on the same page.

It will be interesting in the next few months to see if EMC’s acquisition sparks an acquisition frenzy among the large storage vendors trying to keep up with the industry leader. As I noted last month, there are a lot of flash startups and specialists in the marketplace now — all promising higher performance and efficiency than spinning disks at ever-lower prices — and all signs point to at least a few of them getting snatched up.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Flash storage never sleeps

Derrick Harris — Tue, 01 May 2012 17:52:02 +0000

The flash-storage market got another jolt of momentum last week with speculation that EMC is considering an acquisition of Israeli flash startup XtremIO, but that might have been just a sign of things to come. Although a flash M&A spree is likely to ensue if EMC closes that deal, the two biggest names in the flash storage space — Violin Memory and Fusion-io– are keeping the hits coming in the meantime.

For Violin the news is (what else?) more money. The company is expanding the $50 million Series D round it closed in late March to $80 million and is making room for new strategic investor GE Asset Management. The previous $50 million was at an $800 million valuation, although Violin CEO Don Basile told me then he expects the company is worth billions should it go public later this year.

A couple commenters noted in my post on the EMC-XtremIO rumors that Violin is all about performance, and that such a focus won’t necessarily win the day for flash-storage companies hoping to become standard fare within enterprise data centers. Whether that’s a fair assessment of Violin is open for debate, the commenters’ general point about quality of service, virtualization integration and other enterprise-grade features as the true differentiators is well taken. If all car buyers cared about was speed, luxury automobiles would resemble racecars more than dens. Still, barring a colossal collapse, Violin’s piles of cash, huge valuation and laundry list of strategic investors suggest it has the goods to find itself among the industry leaders for a long time.

For Fusion-io, which went public itself last year, and has been flying high since, its momentum comes in the form of early support behind its recently released ioMemory software development kit. Fusion-io and Violin are architecturally quite different — the former being a server-side PCIe component and the latter being a network-attached storage array — but Chris Mellor at The Register offers an insightful take on how certain deployment scenarios are blurring the line between the two companies.

Specifically, he writes, deployments of new Fusion-io SDK partner Couchbase and new Violin partner SAP (with its HANA in-memory database) end up looking remarkably similar in theory. Either way, hot application data resides in-memory (DRAM), while everything else resides on flash. Couchbase on Fusion-io is more like a motorcycle with the passenger holding onto the drivers waist, while SAP on Violin is more like a motorcycle with the passenger riding in a sidecar, but they’re both accomplishing the same goal.

If Violin and Fusion-io do start competing more directly, we’ll be in for a wild ride. What seems certain, however, is that it’s just a matter of when, not if, flash storage catches on in a major way. With more money and more software-vendor support always flowing into the market, there will soon be precious few reasons not to give the technologies a serious look.

Image courtesy of Shutterstock user fotomak.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Infrastructure Q1: Cloud and big data woo enterprises

Thu, 19 Apr 2012 06:55:04 +0000

With enterprises now open to hybrid clouds, Amazon Web Services finally relaxed its rigid public-cloud-only stance and launched services to support hybrid-cloud deployments in the first quarter of 2012. On the big data front, the Hadoop players realized very few companies have teams of systems engineers to learn MapReduce. This has meant adding support for SQL and integrating Hadoop with existing data-management tools and systems. In other words, Hadoop has grown up and is now being taken seriously by companies like Oracle and Microsoft. This quarterly report examines these trends as well the exciting M&A and IPO news in this arena. It also includes a near-term outlook for the next 12–18 months.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Why Violin Memory is worth billions in an IPO

Derrick Harris — Fri, 30 Mar 2012 20:56:05 +0000

Violin Memory is a force to be reckoned within the storage world. The company, which sells high-end storage arrays loaded to the gills with flash memory, just closed a $50 million funding round. This is its fourth similarly sized round in two years putting the valuation of the company — slated to go public later this year– at about $800 million. If it follows through on those IPO plans, CEO Don Basile told me, the company will be valued in the billions.

It’s not just the industry shift toward solid-state drives replacing slower, less-efficient hard disk drives that’s driving Violin’s value through the roof, though, it’s also the company’s very strategic set of investors.

The latest investor to get on board is software giant SAP, whose mission-critical ERP and database products are deeply entrenched within large enterprises and could benefit greatly from the price-performance increases Violin’s systems offer over traditional HDD- and-DRAM-based systems. There’s also SAP’s new HANA in-memory analytic database, which is the focal point of SAP’s big data push. “To the extent that people view HANA as a big data technology,” Basile said, “it fits into our core thrust that we started last year [around big data].”

That “thrust” Basile mentioned is to build the “biggest, fastest, densest” big data systems in the world for technologies such as HANA, Hadoop and NoSQL databases. Violin has worked with various vendors to eliminate the I/O bottleneck in Hadoop that limits throughput into the processor to a few hundred megabytes per second. Using a Violin system, he said, “instead of needing 100 Hadoop servers, you might need 10.”

Violin also counts Juniper Networks among its strategic investors, although flash-memory manufacturer Toshiba might well be the most important. While other enterprise flash-storage vendors must react to consumer demands that regularly change what flash fabricators produce (generally, smaller, less-reliable NAND memory products), Violin gets to plan ahead. Basile said Violin manufactures four generations out because it knows what Toshiba has coming down the pike. Being the company’s only U.S. investment and one of its only strategic tech investments in years, “if you do business with us, you’re also doing business with Toshiba,” Basile said.

Of course, Violin’s chances of a successful IPO aren’t hurt by the story of a Fusion-io, a somewhat competitive company that sells solid-state components that plug directly into servers and serve as high-performance caching layers. Fusion-io has been experiencing major revenue increases and, as of late February, was trading at 160 times earnings.

As Basile explained, everyone involved in the flash space is riding the wave of ever-lower flash memory prices and the entry of mega companies such as EMC, Oracle (e orcl) and HP into the space. “The argument [for flash adoption] becomes not if, only when,” Basile said. “And then, how much?”

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

Morphlabs, Dell pitch all-SSD private cloud

Barb Darrow — Mon, 26 Mar 2012 15:35:43 +0000

Morphlabs and Dell are making an all-SSD-based cloud architecture available for companies needing the fastest storage performance for their private clouds.

Solid-state drives increase storage I/O performance while cutting power consumption compared to spinning disk and other traditional storage. That means faster launching of applications and faster access to data, but SSD technology has been seen as too expensive for broad use. That is starting to change, however, and even some cloud providers offer at least some SSD options. SSD storage underlies Amazon Web Services’ DynamoDB database, and CloudSigma added SSDs to its public cloud offering last fall.

Although it’s on-premise or hosted, Morphlabs said its new mCloud service will be priced on par with Amazon Web Services, but will bring with it the security of a private cloud to service providers and other companies that require it. Many companies still aren’t ready for the public cloud because of data security and other concerns about shared infrastructure. That’s the crowd Morphlabs is targeting with the new mCloud, which sits upon a Dell converged infrastructure unit featuring the company’s cloud-inspired PowerEdge C servers.

The appeal of a private cloud — or at least a hybrid cloud that lets companies keep some applications and data under their purview — is one reason Amazon partnered with Eucalyptus, which will makes it easier for companies to link Eucalyptus-based private clouds with public AWS cloud services. Amazon has announced several other services, including a storage gateway and workflow services, all geared to ease interaction between its public cloud and customer data centers.

As with any hot new technology, SSDs started out as a premium option. But as costs come down, expect to see them replace spinning disks more and more both in the cloud and on-premises.

Photo courtesy of Flickr user theaucitron.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.