Sign in / up

back to article Infinidat adds predictive analytics to Infinibox OS. But what's it mean?

Infinidat says that its upcoming OS release will provide advanced performance analytics with across-the-board instrumentation, and enhanced quality of service (QoS) facilities. Infinidat, founded by Moshe Yanai of Symmetrix and XIV fame, provides probably the most reliable and available monolithic primary data storage array in …

COMMENTS

Post your comment
House rules Send corrections
Add to 'My topics' unstar *
  1. Nate Amsden

    faster than flash

    only because they have GOBS of memory I am sure. I had a VAR come to me a few years ago (after EMC dropped some cupcakes on our CIO). Said they could sell me an array with a TERABYTE of cache (at this point for some reason they shifted from selling EMC to selling HDS). I sort of laughed, I said yeah I know you can, but we can't afford it so why bring it up.

    Looks like their high end box has up to 4.5TB of memory and up to 36TB of flash cache (not sure if that is a read or read/write cache)

    For HP 3PAR (what I know best of course) their high end system has up to 3.5TB of memory and up to 48TB of flash cache(read cache on that system). "Only" six nines of availability there (though they also commit to 6 nines on any 4-controller 3PAR system).

    I do realize the extra 9 is not a trivial amount of extra availability. Not sure what level of availability HP may commit to if you throw in peer persistence between two arrays(automatic/transparent failover without any external boxes or complexity).

    0 0 Reply
    1. Anonymous Coward
      Reply Icon
      Anonymous Coward

      Re: faster than flash

      Come on , Nate, come clean. You're on the payroll or get some kind of royalties.

      0 0 Reply
  2. Rob Isrob

    FC delays

    I get a giggle when I see this, quite often lately:

    "Fibre Channel/iSCSI-type network transit delays and provide very much faster access to data by servers."

    Riddle me this Batman, what is the delay in 16 gbit FC (more common now and going forward), what will the delay in 32 bit FC be? Google is your friend. Point here is somebody is passing around a really bad batch of koolaid in that folks are so concerned with the big-bad FC delays. Yes... you can cheat for this quiz and look at each others' answers, open book, zero point quiz.

    0 0 Reply
  3. Anonymous Coward
    Anonymous Coward

    Infinidat looks like a souped up XIV, which makes sense as Moshe is behind both of them. I wonder if Infinidat is going into the IBM XIV install base to sell them Infinidat.

    0 0 Reply
  4. Anonymous Coward
    Anonymous Coward

    @Rob

    In this context it is about the entire round trip time including software stack and protocol activities not about 101 level wirespeed issues. The counterpoint is always measuring the difference between a read from memory versus one that has to be found outside of memory to be loaded first, and what that path entails. Keep up.

    0 0 Reply
    1. Rob Isrob
      Reply Icon

      Re: @Rob

      We know about these things. Let's define delays at each point and how much each contributes. Want to play along with real numbers or just do hand-waves like we read in this article? My point is "FC delays" is a canard and no one puts actual numbers to it. It's rather silly ... really. FC-NVMe demoed and coming and apparently 30-40% reduction in transport delays: http://www.theregister.co.uk/2015/12/08/old_school_fibre_channel_gets_new_school_nvme_treatment/. It's good old FC that originates the "FC delay" chatter. But it isn't as if they are ignoring NVMe.

      0 0 Reply
  5. PAT MCCLUNG

    If anybody says "Quality of Service" to you, grab them, four wraps of malleable aluminum wire around the ankles, three wraps around the wrists, kneel down, one 9MM bullet in the head. Get a back hoe, dig a big hole, throw them in with a bag of lime.

    Go home, sleep like a baby.

    0 0 Reply
    1. Rob Isrob
      Reply Icon

      QoS for ingest over-runs?

      They have superior ingest rates. The problem is (from my view) is disobedient upstream customers or TAs that think "that's your problem." You got large backup servers and DB warehouse servers that will and can over-run ports, etc. I would *think* the only reason they want to intro QoS is for very large customers with disobedient internal clients and very large customers asking for this feature. Most folks will look at the QoS radial and be like: "okay, whatever... don't need this."

      0 0 Reply

POST COMMENT House rules

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

Forgotten password ?

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon