Future Storage Systems: A pause in workflow

October 17, 2008

Since I started this article series, I’ve had the awesome opportunity to have my ideas (well, some of the early articles at least) reviewed by person(s) who deal with the actual infrastructure of storage systems day in, day out.  The benefit of such peer review is that you get to learn at the symbolic “feet” of the masters and discover flaws, omissions, and understated features that need to be understood and incorporated.  This post is dedicated to some of those discussions and, where applicable, my understanding of how the FSS either incorporates or misses the boat.

Read the rest of this entry »


Future Storage Systems: Part 3a – Node Expansion Overview

October 9, 2008

In the previous two articles on the Future Storage System (FSS), I took a general look at a basic storage system architecture (Part 1) and then went a bit deeper into some of the more interesting bits of that system from a platform standpoint (Part 2).  In this article, I want to dive a bit deeper into how I envision nodes to be building blocks for additional capabilities and processing directives.  I will be referencing the image below as part of this article.

Hypertransport Node Expansion (detailed)

Hypertransport Node Expansion (detailed)

Read the rest of this entry »


Future Storage Systems: Part 2 – Detailed Node View

October 8, 2008

So, in my article yesterday, I gave a global view of a very simple storage system for the future. Since I LOVE this type of conjecture and theoretics (is that a word?), I decided to take this a step further and flesh out some of the other intricacies of the design.  Check out the image below and then click through to read the rest.

Fleshing out the Hypertransport Storage System

Fleshing out the Hypertransport Storage System

Read the rest of this entry »


Snoop Filters and the Tyan S5397

September 26, 2008

Just to add to the ever-growing information data base on the excellent Tyan S5397.

If you seem to be having problems with reported memory bandwidth in your favourite worthless synthetic benchmark or reality-based simulation workload, try disabling the Snoop Filter in the bios.

Remember, the Intel Xeon processors use a different set of prefetch schedulers than standard “consumer” level parts, so, this can also affect workload.

Reblog this post [with Zemanta]

Search Term Tuesday – June 3rd Edition

June 3, 2008

Note: I’m trying to tighten up the layout of content on the landing page, so, I’ll be using excerpts more and more.

Continuing from last week, this edition of Search Term Tuesday will tackle the most important searches (or at least highest ranked statistically) that landed you at this blog.

Search Term #1: cx3-10 create raid group

Read the rest of this entry »


I *heart* SMB

April 24, 2008

I Love SMB
There’s somewhat of a misconception that EMC dislikes the SMB market. While it’s true that we’ve largely ignored it, our partners in the channel (Dell, CDW, to name a few) have successfully brought our Clariion lines to the mid-level companies out there and have solved their storage needs through aggressive cost-cutting, etc. All that was well and good, but, still, there was a general sense that we were ignoring the small guys out there who had explosive growth potential for storage and revenue and who wouldn’t be able to buy in to commercial grade arrays. Enter the Clariion AX4-5 line.

In my current role, I work almost exclusively with customers who are either new to EMC or who have admired from afar our capabilities for the commercial market. They’ve perhaps been exposed to EMC through co-branding and software bundling in external hard drive technologies, smaller ASN partners that are localized by geography, or, through a channel source like CDW. Truthfully, the greatest “capture” of these customers has been through the channel and partners who have spent the time on developing relationships with their customers versus the standard “Hey, buy my product…” One of the greatest challenges then, is for EMC to step in to the ring and actually become more “friendly” or approachable with our product and personnel.

I have been critical of the Iomega acquisition in the past based on what I felt were misappropriated metrics (namely, “buying” our way into the SMB channel using stale products versus innovative new products). The Iomega name, which was once an entity noted for innovation, has diluted to nothing notable in the channel. Companies like Enhance Technology, Buffalo, etc. which continue to innovate in the SMB space have experienced great growth because they’ve continued to innovate and make their technology approachable to the masses. That being said, here’s what I see EMC doing in the SMB space.

Intel or Iomega?
It’s no secret that EMC has a special place in their heart for Intel. Our arrays (with the exception of the Symmetrix) are built around their processors, we are firmly esconced in the Win-Tel alliance with Microsoft and, well, you know the rest. We started our SMB push with rebranding Intel 4200-E units and coupled them with EMC’s Lifeline (or is it Fortress?) software. While the 4200-E is a great box, I personally viewed the “Baxter Creek” 4000-E with a little more favour since it allowed for NFS, CIFS within the same box. The 4200-E has media functions, disk protection, etc. but it is truly the software that makes the box anything special. As I’m no expert regarding the software, I’ll defer to that product team for guidance. In any case, with the Iomega acquisition, Intel will need to be relegated to a smaller portion of the EMC market to allow for Iomega to gain some traction with SMB.

Iomega brings a much needed “middle ground” that the Intel boxes cannot cover. You’re looking at budgetary allocations between $1,000.00 to the top end of around $15,000.00 based on features and pricing. Now, I don’t know exactly what they’ll be changing or re-aligning (and one has to hope they’re going to stop this ridiculous whitebox rebranding stuff they’re doing now….) but chances are we’ll see DAS and NAS offerings that will allow for SMBs to start consolidating their storage. At risk is virtualization support and integration, but honestly, most of the offerings in that market have a buy-in around $6,000.00+ (based on the product, no less), so, it could be considered part of a larger spend for that company. In any case, I’d expect EMC branded software (Lifeline?) to appear in the boxes with some level of larger integration with our Core offerings. *shrug*

Iomega or EMC Core?

In the notes above, I’ve laid out how Iomega and Intel will be at odds with each other within the same market space (very briefly). In this section, I’d like to examine potential intersection points with Iomega and EMC Core products (Clariion, Celerra).

The Clariion AX4-5 units have been positioned as near-line SMB/Commercial storage arrays. By near-line, I’m simply referring to their ability to straddle both SMB and Commercial, not necessarily their data storage/retrieval capabilities (though, to be honest, the AX4-5 is a GREAT box to have). With our partners, you can get ready-made AX4-5 units starting around $9,000.00 (minimum config, to be honest) and scale into full featured SAS/SATA powered SAN storage for (obviously) more than that. A lot of the configs that I’ve worked on have hit the sweet spot for AX4-5 entry (with typical app integration with VMWare and SQL, for example) hitting around $35,000.00 all in. That’s not a bad place to start, especially since you get enterprise grade SAS and SATA drives that we’ve tested the living stuffing out of. 😉 Same applies for the EMC Celerra NS-2x line. I’ve worked with configs that will slap high IOP fibre drives and long term storage SATA drives within the same array for around 15% more than the AX4-5s. Again, this is optimized by the environments that I’m scoping out and, in most cases, this represents the best fit for performance and capacity. How is Iomega going to fair in that world? I’m not sure.

Nothing that Iomega has put forth so far really strikes anyone with any sort of wow-factor or “I must have it NOW.” For example, the high end 450R is simple a 4 drive server that has two GigE ports on the backend. For small shops, this may be worth it, but, again, the Intel “Baxter Creek” 4000-E does the same thing for about $4,000.00 less, fully configured. Now, you can’t really compare it against an AX4-5, to be sure, but, even a single SP AX4-5 is going to start you out around $4,000.00 above the 450R with better management. Put this into a financing or leasing model and….well, you’ll make out like a bandit. Truth be told, I’m assured that new products with new innovation will be coming down the road so, I’ll reserve my final judgment for that period of time, however, the clock is ticking.

Time to innovate…

EMC has the resources and ability to create new and exciting product at a price any SMB can afford. What they cannot afford to do is miss this opportunity. They’re counting on Iomega’s reputation and channel presence more than anything to drive their business home to the millions of SMB customers out there. The problem is, reputation and presence only go so far. There has to be better products brought to the table or else, competition will undercut and drive us out. We can’t rest on our laurels as a storage entity (truth be told, EMC isn’t well known in the SMB space at all…) because SMB doesn’t care. What matters the most is that they feel protected in their growth, from a storage AND business perspective. A misplaced investment on yesterday’s technology can destroy the confidence and ability to grow of ANY business, but is particularly pertinent in SMB.

SMB drives innovation; it breathes it out with every swell of its ranks. It is the cornerstone of tomorrow’s Commercial accounts and if we screw it up with SMB now, we’re going to have a hard time taking that ill taste from their mouths at the commercial level.

cheers,

Dave

Seed Newsvine
Add to Technorati Favorites


More on Seagate vs. STEC

April 15, 2008

EDIT:  4/15/08 @ 827pm EST

After careful consideration, it has become apparent to me that putting myself in jeopardy of commenting on active litigation that (potentially) involves my employer isn’t a smart thing to do. That being said, I’ve decided to leave this content here, but with the following disclaimer:

The opinions expressed here are my personal opinions. Content published here is not read or approved in advance by EMC and does not necessarily reflect the views and opinions of EMC. The information I’ve presented below is through personal research through publically available news sources (news.google.com and other media outlets) and does not represent anything but a high level overview of the potential consequences of this lawsuit. 

As I was holding my 11 day old daughter last night (about 3am or so), I kept going back to this whole lawsuit issue between Seagate and STEC. There were a few things that were bugging me about the nature of this suit and, I thought I’d pose them here.

a.) Why STEC? In my mind, STEC represents the first successful ENTERPRISE foray for SSD drives in the storage market. BiTMICRO and mTron have done an excellent job of being the performance leaders for consumer drives, but, never quite reached that pinnacle of performance and reliability that is needed in the enterprise storage space. As such, STEC represents the single greatest danger to Seagate and their ability to continue to push FC disk as the performance leader in enterprise (SAS is another great challenger to that concept, but we’ll leave that for another discussion). Additionally, as pricing parity is reached between SSDs and magnetic disk, there becomes an even greater divide between price and performance.

The other aspect of “why STEC” has to do with the who else is in the market. Why didn’t Seagate sue Samsung, Intel, BiTMICRO, mTron, Crucial, et al. in addition? Each of these companies have SSD devices (either of their own design or OEM’d from others) that they’re pushing into the market…

b.) Why sue vs. purchase? Interesting concept, at least to me. Knowing that they were somewhat behind the times on this new technology, why didn’t Seagate investigate the potential benefits of purchasing STEC? It makes sense, really. Companies routinely purchase IP in order to gain advantage within the market. With Western Digital buying Komag (and locking up platter manufacturing), why not go down the route of buying your greatest threat? All in all, Seagate easily could have read the writing on the wall and seen where SSDs were going (especially after the EMC Symmetrix announcement!!!!). If Seagate truly wants to protect their shareholders, etc. it would make sense to get into a market segment that promises to be upwards of 8 billion dollars within the next year.

These are my initial thoughts for this morning. Let me know if you have any other ideas.

EDIT: 4/15/08 @ 12:21pm EST

c.) Is Seagate turning into the next Rambus? Sitting in a meeting this morning, I was again trying to review some of the peculiarities of this case (which have been somewhat validated by the statement issued by STEC below). Seagate’s main contention is that STEC violated the following four baseline patents within 3 discrete categories: error correction, memory-backup systems, and storage interfaces with computers. If we follow this particular logic, then, we must assume the following:

  • Seagate developed, controls, and receives royalty payments for: SAS, SATA, Fibre, SCSI interfaces within a given open system AND the signaling technology. (i.e. both physical and electrical connectivity)
  • Error-correcting algorithms are EXCLUSIVE to Seagate and as such, SMART, sector remapping, etc. are exclusive domains of Seagate’s IP.
  • BBUs (battery back up) devices specific to cache within a storage system are proprietary to Seagate and thus subject to oversite and/or royalties, etc.

What’s not really clear here (and mind you, I don’t have access to the patent #’s in questions and their technological backend), is the role of each of the governance boards in this (Fibre Channel Industry Association, SCSI Trade Association). What I find very fishy is that Seagate, being a part of each of these groups, would be allowed to patent something that is an open format (that I am aware) and a trade standard (i.e. Fibre connectivity). If you recall, Rambus did the EXACT same thing by sitting on the DRAM design boards and then backend patenting the technology that was developed. Not saying that Seagate is ultimately a mini-Rambus, but the sheer ferocity in which Seagate seems to be going after STEC is quite suprising.

oh, and in case you missed it, STEC released their counter-statement this morning:

STEC is one of the first companies to build SSDs, having designed, manufactured and shipped SSDs as early as 1994, long before any of the suggested patents were issued to Seagate. Given the effect SSDs are having on the HDD market, STEC believes that Seagate’s lawsuit is completely without merit and primarily motivated by competitive concerns rather than a desire to protect its intellectual property. STEC believes that Seagate’s action is a desperate move to disrupt how aggressively customers are embracing STEC’s Zeus-IOPS technology and changing the balance of power in enterprise storage. Seagate is sending a clear signal that it recognizes STEC as the leader in the SSD business and is attempting to slow down part of the growth that STEC is gaining through its SSD offering, particularly in the enterprise segment. STEC will aggressively pursue its defense to this infringement action.

In addition, STEC will also closely examine the patents asserted by Seagate as STEC believes it held such technology including prior patents, dating more than a decade prior to any of Seagate’s patents. Although STEC is in the process of analyzing the claims in this lawsuit, STEC believes that Seagate’s asserted patents pertain to technologies where STEC has years of prior experience and/or patents. STEC has significant patents related to SSD which have been developed through the decades of experience STEC has with developing, manufacturing and shipping SSDs. Beyond that long history, STEC also believes that many of Seagate’s claims are not relevant to SSD. For example, STEC was one of the originators of stacking technology with patents dating back to the mid-1990s, while Seagate’s patent on this matter was issued in 2005.

Through this process, STEC will determine if Seagate is misappropriating any of STEC’s core technologies; STEC will take appropriate action to protect its interests, including seeking the invalidation of Seagate’s patents.

(emphasis mine)

cheers,

Dave
Add to Technorati Favorites