back to article All-flash storage or will you settle for hybrid? How to decide

Remember thrashing? Back in the early days of server virtual memory systems, the amount of RAM was so limited that the operating system spent most of its time paging for data on its disks, leaving little or no time for processing applications. It happened because there was a gross mismatch between the number of applications, …

  1. M. B.

    You could have...

    ...taken the last two paragraphs, made them into a single paragraph, and skipped the rest of the article entirely. It's what we do - capture statistics with vendor sizing tools, determine requirements as far as features go, and build out a couple BoMs for different vendors products. Then we discuss with the client regarding performance, features, and cost comparisons. At the end of the exercise they end up with a properly sized array that performs well and does what they need it to regardless if its all-flash, hybrid, or even all-disk (yes, I'm not going to recommend flash to a cost-sensitive SMB who needs 10TB but only 200 IOPS). We sleep well knowing they are going to be satisfied with the product, and we make money off the implementation and training services. Happy customers.

  2. Alex McDonald 1

    A simple rule of thumb helps illustrate

    If you want to work it out for yourself, then this simple equation

    Average access time = Hit time + Miss rate × Miss time

    will help. It's fairly obvious that reducing the average access time can be achieved by any or all of

    (a) reducing the miss rate by employing a bigger cache

    (b) reducing the miss time by employing a faster cache

    (c) reducing the hit time by making memory faster

    Some solutions will change the variability of the access time; for example, a small fast cache (closer in speed to memory) reduces the variability, whereas a bigger but slow cache doesn't reduce it at all.

    Working set sizes affect the the miss rate. Write-back or write-thru policies to cope with assymetric write/read times also play a part -- flash is faster to read than to write.

    And so on. I agree with the overall summary; get expert help.

  3. Gavin Mc

    There's an assumption here

    You've assumed that all hybrid arrays use flash as a cache?

    X-IO's Hybrid ISE constantly analyses the workload and uptiers to flash if there's a potential return on investment, not just because the data is accessed. The means that the performance of all-flash can be delivered at a much lower price point and also last longer, hence the inclusive 5 year warranty.

    (Disclaimer: I work for X-IO but want to set the record straight).

  4. El Storage Guy

    Good article... but I was really waiting for better punch line at the end. :-)

    As others mentioned, it seems pretty obvious to the reader to do their own homework and determine which one, the hybrid or all-flash will make sense in any given particular environment.

    What I thought was missing the fact that there's plenty of ALL-flash arrays betting on the future of ALL-SSD data centers, yet their market (All-Flash) still only constitutes a fraction of the overall capacity footprint needed (this includes disk, tape, flash, etc.).

    Also, worth mentioning, is the fact that usually, these speed-thirst applications are usually the business crown jewels, which means that arrays will be required to provide real enterprise level reliability levels (many times beyond the simple dual-controller) and, full integrated data mobility.

    In the end, it seems to me that as much as we want the world to be all-flash. We are simply not there yet.

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like