When I was a kid I used to watch Gilligan’s Island® a lot. For those of you who never had the pleasure, it was a show about a “3 hour tour” by boat that stranded passengers on a small desert isle, including the first mate, Gilligan.LakshadweepIsland

Turns out, this would be good training for managing an EDA project.  Why?  Well, managing an EDA project typically starts out straightforward; You allocate computers and storage to the project based on estimates, leverage your experience from other projects and use it to predict how many cores you will need to run simulation regressions (how many directory trees you’ll want for the ASIC, and how much space each will require). And then, months later, the storm hits. You realize the need to add a new test area and to allocate space for it. “No worries,” you think, “I’ve been paying for that space and I know it’s available.”

And that’s when you realize…you are stranded on an island and can’t get what you need. If only you had Gilligan to save the day.

As it turns out, many enterprises have deployed “scale-up” storage technologies that tend to create what we call “islands of storage”. These islands are created when IT administrators are forced to create multiple partitions of data, and each partition (or volume) is managed separately. While this doesn’t sound bad on the surface, the reality is that for many organizations, the number of volumes managed can quickly grow to hundreds or even thousands. Why should you care? Because it means the “pool” of storage space you’ve been paying for is actually distributed across many separate storage SILOs, creating waste.

Once deployed, scale-up enterprise storage solutions tend to hit an architectural capacity limit, which forces new, independent volumes to be created. These volumes are managed separately, making each behave like its own island. As time progresses and more capacity is needed, IT creates more and more of these islands. Since data must typically be moved manually between each island, new projects start to get fragmented. Some portions of the design flow might be hosted on one island, others on a different island, and full chip simulation hosted on yet another.

The trouble comes when you look closer at the allocations. Let’s say your project has been allocated 30 TBs of storage. According to the billing you receive from IT, you’re paying for the full 30TBs even though you’re actually using only 24TBs. While it’s painful to have to pay for the six you’re not using, it’s your insurance policy.

Now a bug is found and your team needs to do some additional testing ASAP. They need 4 TBs to create a new verification directory tree, so you ask IT for it. That’s when you find that there is no space available. Yep. You’re paying to have an additional 6TB to tap into at your disposal, yet you won’t be able to get IT to immediately provision the additional 4TB within the same directory where you need the space—even though you’re feverously trying to tape-out. The problem is fragmentation across multiple volumes with no one volume having 4TBs available.

unbalanced storage utilizationFigure 1 Unbalanced storage utilization due to independently managed storage silos

To fix this problem, you must wait for IT to optimize the available storage by moving project data manually while you try to tape-out. That’s painful for IT, and means that your project will grind to a halt while they move that data. Since that can involve 10s to 100s of TBs of data, it can be a long wait (so much for “ASAP”).

Fortunately, there is an alternative storage architecture—“scale-out”—which is used by EMC Isilon and can help avoid all these problems. With Isilon, capacity can be added without creating islands. The existing volume simply grows in capacity with zero downtime.  More importantly, adding capacity would not have been necessary with Isilon. With no islands of storage, the 6 TBs of data you were paying for on Isilon would have been available immediately—even in the midst of a tape-out.

Like the seasons of the year, your quarterly bill for storage is a sure thing. You’re going to get charged for the storage you use as well as your rainy day stash of extra storage.  With traditional storage architectures, however, that rainy day can quickly turn into an unexpected storm leaving you, like Gilligan, stranded on a desert isle.  Fortunately there’s a new ship in town – Isilon – that’s designed to ride out unexpected storms and eliminates desert islands.  So next time you get that quarterly storage bill, you might want to ask what you’re paying for – or at least check the weather…

Lawrence Vivolo

Lawrence Vivolo

Sr. Business Development Manager at EMC²
Lawrence Vivolo

Latest posts by Lawrence Vivolo (see all)

Tags: EDA, File Storage, Isilon, scale-out storage, Storage Utilization

Let’s block ads! (Why?)

Related Posts

Facebook Comments

Return to Top ▲Return to Top ▲