A company called Atlantis has come up with a new wheeze on how to deal with VDI-crippling I/O bottlenecks: detect and delete dud I/Os at the NTFS level. Atlantis' ILIO 2.0 product – ILIO stands for In Line Image Optimisation – is a software incarnation of its hardware appliance, and runs as a virtual appliance that works with …
A score years back or so...
... you could do much the same thing with things like mounting the same /usr r/o on many netbooted images and a bit of handy nfs caching trickery. <insert snarky comment on how fscking things up so bad as to cause third party vendors to reinvent the wheel is really micros~1's contribution to "innovation">
Anyhow. Progress, isn't she great? I'm sure this cookie-cutter will enable a lot of happy users and create jobs and foster growth and suchlike.
unprovoked Microsoft bashing attributed to early onset of senility
nfs caching is an oxymoron. No such thing with a large enough dataset that is write intensive. Couple that with small IOs 1K,2K,4K across a massive dataset - 2TB on average for 100 Desktop VMs - caching does nothing - zippo, nada, balls, zock!
Heavy writers stand alone.
There are some things VDI will not do great at. Workstations with large datasets, like CAD, movie editing, write heavy databases, etc. For the rest of the monkeys VDI is fine, checking some email, writing a word document, using whatever application is required in their industry are what this is shooting at.
You can run a storage area network based upon ZFS Dedup and get the same effect (or better), eliminating this particular product and deduping every virtual OS, application, and data block (instead of images only.)
You can run a hypervisor under Intel Solaris using ZFS Dedup and get the same effect but better - still leverage cheap memory and disks - and get superior data integrity with every block being checksum'ed (and corrected), where memory is available to accelerate the virtualilzed desktop performance.
You can run a hypervisor under Intel Solaris using ZFS Dedup and Compression, getting superior effects over any other option, where memory and CPU are available to accelerate the virtualized desktop performance.
Oracle has a real story to tell here, but they seem to be unable to get people to understand the value of sunsetting old infrastructure and replacing it with something that will pay for itself in a number of months.