When FAST is not properly fast.

I am not really convinced (regardless of whether the technology comes from EMC or Compellent) that automatic tiering is good. Seems to me that this would cause data fragmentation and impact overall performance. Do you have some solid information on how many people have bought DP and how many people are using it? What type of Applications or IO characteristics benefit from Compellent’s DP?

G-Man,
A lot of analysts studies show the problem of inactive data on the storage (sometimes 70% or more). Automated Tiered Storage is one of the most discussed storage topics this year because customers ask for it. I followed directly some installations: customers , after a first natural skepticism, are very satisfied about the results.

DP helps every application ranging from file servers to DBs and mail server, etc. Moreover It simplifies the storage layout avoiding automagically the hot spots!

Think about a DB: transaction logs are frequently changed with sync writes, some data files are frequently changed and others contain old data.
In a traditional layout you need to configure more LUNs with raid-1 for logs and raid 1 or 5 for datafiles. With an automated tiered storage (block level of course) you will have a single LUNs where blocks frequently change (logs and new rows) will be written in tier1 and old data will be moved to less valued tiers!
all in all: you need less T1 disks to achieve performance needs, T2 disk to fulfill space requirements, less power consumption, less management (less TCO overall!)… not bad.

ES

Your bias has clearly clouded your objectivity. Probably would have been better to ask the questions first before you scored the game.

* FAST v1 will be available for DMX later this year as well.

* FAST for CLARiiON CX4 will be available at the end of 2009, or early 2010.

* FAST v1 is indeed designed specifically for full LUNs, which make up well over 90% of the LUNs in use today by Symmetrix customers. The #1 customer request for Flash Drives in today’s world is that we automate the decision process of what goes onto Flash and what goes onto SATA.

* FAST v2 will provide sub-LUN tiering to V-Max Virtual Provisioning. At that point, we expect most customers will move from FAST v1 to v2.

* There are already migration paths to get from full LUNs to VP LUNs, with more on the way.

* FAST policies can be assigned to Snapshots, Clones and remote replicas.

* And indeed, FAST will be smart enough to keep the remote replica’s disk allocation aligned with the source so that fail-over can occur without loss of performance.

* On V-Max and CX, RAID type can be changed by FAST as well as disk class.

* SAS drives offer no significant value over FC drives – they cost the same, they use the same power, they’re the same sizes, and the deliver the same net performance as FC drives. It is thus rather silly to be using the disk interface as a competitive differentiator.

* And in fact, SAS being so new, it is probably more risky to use a SAS back-end than a FC one. FC is extremely reliable today thanks to years of refinement, while SAS in large drive count configs is immature and the issues have yet to be found, much less resolved.

Barry,

- Ok, so DMX customers will have FAST V1 (and V2 too?) and informations reported by other bloggers are incorrect: “the first unique features of the Symmetrix V-Max line”! or, perhaps, my english is worse than i think!
sorry, if i have misunderstood.

- Ok, So is V1 (LUNs level migration) suitable for 90% of your users? because they are not using TP! This answer really fails in convincing me but, at least, is an answer.
I think it can be painful to move SSDs LUNs to SATA, back and forth, if your customers have spent their bucks for SSDs they need them to cure their performance issues, the only way to automagically gain performance and space is granularity!
And, Ok, you will get granularity in a year, more or less. Granularity will permit your customers to not re-layout (or slice) big LUNs in small ones to use FAST (but if your LUNs are sliced you can move them manually to less valued disks and not buy FAST).

- Ok, migration paths: what do you mean with “migration paths”? , I suppose a GUI interface with a “point-and-click” button “convert-lun-from-fat-to-thin-without-pains-and-no-servise-interruption”… or something more complex?

- Ok, so FAST is flawless/limitless about snapshots, clones, replicas and customers will create profiles with integrated relocation of blocks managed by this features… does it mean that FAST will allow to create profiles, for each LUN, or group of, and its related snapshots?

- Ok, SAS has the same value of FC. All storage industry is going that way and you will too!. Other vendors offer this option right now.

ciao,
Enrico

Barry,
We could continue for days, or more probably, months, in this discussion so this will be my last comment to not annoy your/mine readers.

just to add last things:

Ok, EMC is more than twenty years old and Compellent was born only 5 years ago! On the other hand Compellent is growing very fast… Compellent is very small if compared to EMC, but lot of new Compellent’s customers are ex-traditional storage vendor customers (and now they are happier than ever!).

Your Array can deliver 2PB and 64000 LUNs! really? Compellent can deliver 1PB and infinite LUNs (so they are not so distant ) but i don’t think that theoretical maximums will be reached soon on installed systems… of course, i could be wrong! please let me know if you can show me an installed V-MAXs with 2PB of raw storage, 64.000 LUNs with “tens of thousands of physical and hundreds of thousands of virtual servers” connected to it… i’m very curious to know who have a similar installation!!!!

And about SAS…. i could reverse thoughts about every technology, you will push it if you are an early adopter!

ciao,
ES

Yes, indeed, there are V-Max customers who have already installed 2PB arrays, including Microsoft AdSense, who participated in the V-Max launch. And those numbers I quote aren’t “theoretical maximums” – we actually test and verify those configurations in QA before we announce the product.

I doubt Compellent has tested an “infinite” number of LUNs .

And vendors tend to push new technologies BECAUSE they offer new value: such is the case for FCoE, Flash Drives, server virtualization, etc.

I have not yet seen anyone offer any unique value for SAS drives, other than that they are a “new technology.” Until they are cheaper, faster, smaller and their supporting infrastructure is proven to be more reliable, more scalable and more efficient than todays’ Fibre Channel drive, there is really nothing to be proud of as an early adopter.

Finally, the emergence and growth of Compellent is commendable, and I in no way mean to belittle the company. In pointing out the size of the Symmetrix installed base, I was merely trying to explain why we would focus first on FAST for “thick” LUNs before delivering the sub-LUN implementation.

Perhaps one day Compellent will be faced with the challenges of balancing new innovations with the needs of a significant installed base. The good news (for Symmetrix customers) is that EMC isn’t standing still – it is bringing new capabilities and features into the product line without disrupting customer’s legacy environments or sacrificing the 24-by-Forever availability that so many of the installed base require.

Barry,
No doubts, You are doing your Job very well!
you convinced me, tomorrow I will buy a V-MAX.

[...] post, nella versione inglese, ha generato una bella discussione con The Storage Anarchy, un blogger di [...]

[...] SubLUN automated tiered storage is a key technology asked by customers and already implemented by Compellent with Data Progression and soon from others. [...]

[...] FAST V1 is a very limited product, I wrote about it in the recent past. [...]