Category Archives: Storage

SAS, SATA, and iSCSI – A Tutorial

Posted on by
Reply

Yesterday there was a great piece over at TechRepublic on the confusing intersection of SAS, SATA and iSCSI arrays. For anyone who has ever had a difficult time understanding and differentiating these technologies, this is a very valuable resource. Excerpts are cross-posted below.

SATA and SAS are storage interface and bus types designed to aid in the movement of data from one place to another. Think of SAS and SATA as different kinds of computer interfaces, such as PCI Express, but there are actually multiple components that make up the overall SAS architecture.

  • Initiators. The initiator is the SAS controller to which SAS expanders or targets can be connected.
  • Expanders. Expanders sit between initiators and targets, but can also connect to other expanders, as you can see in Figure A. Expanders are sort of like network switches in that they can direct traffic and they provide the ability to scale the SAS architecture beyond single port limits.
  • Targets. A target is either a SAS drive or a SATA disk. SATA disks can be connected to SAS expanders and initiators, but do not perform quite as well as SAS disks.

Continue reading →

The Evolution of Storage – 2012 Isn’t Just the Year of the Dragon

Posted on by
Reply

2012 is quickly shaping up to be an exciting year in a variety of technology verticals. Just last week NVIDIA® announced a new production release of their CUDA computing toolkit, accelerating GPU computing. Meanwhile, everyone is excitedly awaiting the launch of the new Intel products shipping towards the end of Q1.

But of all the areas in tech innovation, storage may be the one to set itself apart this year. Yesterday Computerworld ran a very thorough and informative piece titled “2012: The year storage becomes a celebrity,” in which they laid out some of the things to look forward to in the development of enterprise storage this year.

The Overview

While data storage has always been a necessary building block for technology, it’s rarely garnered as much attention as it has in the past two years. The reason: Corporate and retail consumers are being forced to store greater amounts of data and they need to make that data more useful — and accessible.

Enterprise storage, and storage in general, is one of those things that trends dictate will get increasingly cheaper. That doesn’t always mean that it will become more accessible, as storage needs may outpace dropping costs. However, in general storage has become more and more affordable, making a big difference to smaller and even mid-sized organizations. It’s also something that is shared across all industries almost without exception. Storage is not just an “IT” issue, but rather plays a critical role in healthcare, entertainment, finance, engineering, etc.

And ten years ago, we did not have the wide variety of options we do today…

Continue reading →

Future trends in HPC, part 1

Posted on by
Reply

As we near the end of 2011, we take a moment to reflect on the past year. It’s been a busy year for IT across virtually all verticals, from mobile and search to enterprise servers and cloud computing. When we attended HPC360 a few weeks ago, we had the pleasure to attend a keynote presentation by Addison Snell, CEO of Intersect Research in which he discussed the most important trends in high performance computing (HPC).

HPC is an exciting and growing industry that ICC has been moving into the past couple years. The traditional HPC space revolved around high-end research facilities particularly in science and engineering. However, with each year technological innovations and tailored systems such as our Supermicro GPU Simcluster have brought the realm of HPC closer to reality for many small/medium-sized business and organizations.

In this 2-part series we will look at the top 10 future trends in HPC from Intersect360′s research, coupled with our own analysis and thoughts. No better way for us computer nerds to close the year right? Let’s get started.

Top 10 HPC Trends for 2012 and Beyond

Future Trends for High Performance Computing Image

Continue reading →

The Impact of Thailand and Hard-Drive Shortages

Posted on by
Reply

Massive Flooding in Thailand Everyone in our industry seems to be keeping at least one eye on the impact of the massive flooding in Thailand and the hard-drive shortages resulting from it. If you haven’t been, here is a quick summary:

  • Thailand is experiencing record flooding – the worst in 50 years.
  • Manufacturers are struggling to continue work in the face of suspended plants and suppliers.
  • Western Digital and Toshiba have shut down their hard-drive production facilities in Pathum Thani province, near Bangkok.
  • Nidec, a leading supplier of components (including roughly 70-80% of hard-drive motors used by major manufacturers) has been substantially and adversely affected.
  • Thailand is a top producer of hard-drives (second only to China) – these events are driving up absolute prices for hard-drives, anywhere from a 50-200% increase (varying depending on the brand and where you are in the chain of purchasing the equipment.)

Continue reading →

Switching to the cloud? Advantages and disadvantages

Posted on by
1

Cloud computing graphic (courtesy of Sam Johnston, accessed on Wikipedia)With tougher economic times, companies are reducing IT budgets but are still finding the need to replace legacy systems. Because of this, claims a Gartner report released earlier this year, many CIOs have turned to cloud computing as a way to save on IT costs.

Cloud computing, for all of its recent publicity, is not new. In the decades before PCs, companies purchased computing resources on mini-mainframes that were accessed through end-user terminals. Cloud computing’s recent re-emergence is a result of companies again considering the cost savings of having someone outside the company handle IT infrastructure and maintenance.

But the companies that have arguably the most to gain from cloud computing, small and medium sized businesses (SMBs), are still unconvinced. According to a recent Newtek survey, 48% of small businesses owners do not see a switch to the cloud as a cost-reducing move. Continue reading →

Cluster computing for small and medium businesses

Posted on by
1

Image of an ICC Modular Server (IMS)We’ve updated our high-density servers webpage with a solution tailored to small and medium businesses (SMB): the ICC Modular Server (IMS). Built on similar principles to blade servers, we are selling our IMS to organizations that can benefit from an upgrade of their current (limited) server resources to an entry-level cluster solution. Let’s take a look at the advantages and disadvantages of this product to get an idea of whether it’s right for you.

The ICC Modular Server (IMS) contains compute servers, a separate storage area network (SAN), and management modules all housed and centrally controlled within one 6U enclosure. As the name implies, all components are “modular” (so, easy to expand or replace) and hot-swappable, and cabling is absolutely minimal (just like blade servers).

There are several advantages of this type of solution over, say, having multiple 1U rack servers networked together in one’s office:

  • The IMS’s modular design makes it much easier to maintain
  • The complete IMS system has about the same low noise level as a 1U server (though it house six compute nodes)
  • The drives are separate from the compute nodes, which allows all six of the compute nodes to access the up-to 18TB of storage in the SAN Continue reading →

Our solution for an NCSA high-performance storage prototype

Posted on by
2

Read LSI's case study about ICC's storage solution for NCSAA storage solution that we developed for NCSA that will eventually become part of an HPC cluster was featured in an LSI case study this week. There are two cool things about the case study: the fact that the cluster will eventually be used to test some of Einstein’s theories about the universe, and the way the storage system gets around the I/O bottleneck problem. I’ll provide a brief overview here (see the case study for greater detail).

The prototype storage system will become a tool for the Dark Energy Survey, which seeks to answer one of the most fundamental questions in astrophysics today: why is the expansion of the universe speeding up? This is what we have observed with our telescopes, but Einstein’s Theory of General Relativity, which is our best description of the rules of physics to date, predicts a slowing down of the expansion of our universe.  Scientists in the Americas and in Europe will seek to answer why our observations don’t match our theories so that we can better understand the heavens.

The prototype storage system that we developed for the National Center for Supercomputing Applications (NCSA) is designed around the latest LSI MegaRAID CacheCade technology, which allows solid-state drives (SSDs) to be used as RAID controller cache. This helps overcome the I/O bottleneck plaguing storage technology today so that DES can transfer the approximately 400GB of data that will be generated each day by the new telescope in Chile to storage systems in the United States. The plan is to eventually add more than one controller per node so that the controllers can also pool their SSD-based cache. Initial tests showed significant performance gains. Read more here.

OpenSFS formed to lead development of Lustre file system

Posted on by
Reply

Photo accessed on Wikipedia (http://en.wikipedia.org/wiki/File:Open_HDD_and_SSD.JPG)OpenSFS (Open Scalable File Systems, Inc.), a non-profit corporation, has recently been formed to continue development of the Lustre file system alongside Oracle, which owns and maintains the Lustre code even though it is an open-source technology.

Lustre has been and continues to be used by many high-performance clusters for managing storage systems. When Oracle acquired Sun Microsystems, the former owner of Lustre, earlier this year, they became the keepers of the Lustre source code. Oracle has been developing Lustre for its own hardware, but there is a large sector of Lustre users who have an interest in continuing to add their own functionality to the file system. Enter OpenSFS. While they are explicitly not seeking to branch off from Oracle’s Lustre project (they are doing the exact opposite, actually, in hoping to implement their modifications as future updates to Oracle Lustre) these groups are seeking to develop the file system for non-Oracle deployments.

Membership in the OpenSFS partnership, according to an HPC Wire article, is based upon contribution. For $5,000 a year, one can become a participant on a working group in OpenSFS; for $50,000 a year, one can manage a working group; for $500,000 a year, one can become a member of the board of executives. Currently about 20 organizations have become members in one form or another on OpenSFS. The founding members were Cray, Direct Data Networks, Oak Ridge National Laboratory, and Lawrence Livermore National Laboratory (Lustre updates developed by OpenSFS will be tested first on supercomputers at the latter two locations).

This is an exciting development because it signals a strong effort to continue development of Lustre for applications beyond those needed by Oracle. Hopefully this will become an active community that will keep this heavily-deployed open-source project alive for many years to come.

How a SAS switch can improve storage management

Posted on by
Reply

LSI SAS 6Gb/s switch and accessoriesLast week, LSI announced their release of “the industry’s first 6Gb/s SAS switch”. The switch offers unique opportunities for cluster managers to improve the architecture of their storage systems.

The value of the SAS switch is its function of transforming a cluster from a NAS (network-attached storage) structure into a DAS (direct-attached storage) structure. With DAS, storage data does not have to be transferred from the SAS protocol to the network protocol (Ethernet or InfiniBand) and back to SAS. The bottleneck of the middle step is eliminated – the LSI switch allows all I/O of data to happen through just the SAS protocol. This is especially useful for clusters which have or plan to upgrade to 6Gb/s RAID controllers – their throughput will be increased when connected to a 6Gb/s switch rather than to a network.

Another advantage of switching to a DAS configuration for a cluster is it migrates the RAID controllers from the storage nodes to the compute nodes. In a NAS cluster, each storage node typically has its own RAID controller which communicates with the compute nodes through a network. In a DAS cluster with a SAS switch, the storage nodes are JBODs (“Just A Bunch Of Drives” – essentially hard drive warehouses without other computing components within their chassis) that are all accessed by RAID controllers located directly inside the compute nodes.

This configuration separates the RAID controllers from the storage drives and centralizes each of them for simpler management and improved performance. Now, as many RAID controllers as the cluster administrator decides can access any quantity of drives on separate JBOD-based storage. The process that allows this kind of interaction is known as SAS zoning and is illustrated in the diagram below:

Diagram showing the DAS configuration of a cluster with a SAS switch

Diagram showing the DAS configuration of a cluster with a SAS switch, RAID controllers located on the compute nodes, and SAS zoning of the JBOD storage nodes.

For more detailed information about the various uses of the LSI 6Gb/s SAS switch, read their white paper about this product. As storage technology continues to evolve, new solutions such as a DAS cluster configuration with a 6Gb/s SAS switch are helping overcome the various I/O bottlenecks that hamper computing performance.

The I/O Bottleneck and Solid-State Drives (SSD)

Posted on by
3

HPCintheCloud.com, a new and highly-recommended website, has a recent article describing the I/O Bottleneck and how solid-state storage can overcome it.

In a nutshell, the I/O Bottleneck is a performance problem in computer hardware as a result of storage technology falling behind the times. Server performance is largely determined by three factors – processor speed, networking speed and storage drive speed. As the above article describes, processor technology (such as the new Intel Xeon 5600 and AMD Opteron 6100 multi-core processors that we have been following on this blog) and networking innovations (such as InfiniBand) have outpaced storage technology, which has been hamstrung by its reliance on spinning hard disk drives (HDD).

Solid-state drives (SSD) with no moving parts are poised to replace HDDs and allow storage to catch up with processors and networking standards. There are several advantages that SSD storage has over HDD. With the growth of cloud computing and Web 2.0, the way data is accessed from drives has become more sporadic and random. According to the HPC in the Cloud article,

Enterprise servers, running applications in the datacenter range from Web2.0 to HPC to business analytics, can generate hundreds of thousands of random I/O operations per second (IOPS).  In these environments, the HDDs available today can only perform thousands of IOPS combined.  HDDs are great for capacity and large blocks of sequential data but are not very good at delivering small pieces of random data at a high IOPS rate.  The physical characteristics and power envelope of the HDD make it an expensive option for increasing application throughput.  Consequently, the CPUs are under-utilized as they wait for data.

The scenario above illustrates well why HDDs are thought of as a bottleneck – with inadequate storage performance, the powerful CPUs of today are forced to sit and wait for the slower HDDs. Many data hosting companies solve this problem by just purchasing more servers with HDD storage, whereas they could just as well boost performance by running less servers (which would save space, energy, and maintenance fees) with SSDs.

There are several factors to consider when purchasing SSD storage for servers. First, there are volatile (DRAM) and non-volatile (flash) SSDs. The volatile SSDs will lose their data if the power supply stops while the non-volatile flash drives – modified versions of which are used in portable USB drives,  iPods, and mobile phones – do not.

Within the flash SSD category, there is single-level cell (SLC) memory and multi-level cell (MLC) memory. Most consumer products like cameras and phones use MLC, but this should not be used for enterprise environments unless you want to replace your storage drives every few weeks. If you are looking for flash SSD drives for servers, definitely get SLC flash memory.

A new standard for storage is gaining popularity called Tier-0. This class of flash and PCI-E SSD storage solutions will offer data centers the full advantage of their increasing processor performance, reduce maintenance costs because there will be less moving parts in the server, and make the random I/O functions demanded by contemporary applications and cloud computing more efficient. Once the cost of SSD storage goes down, the decision to switch from HDDs will be a no-brainer. As for now, the intrepid hosting companies that do decide to adopt SSD will be reaping the benefits before everybody else.