Simon Brassington, strategist at HP StorageWorks UK & Ireland, took issue with our reporting of HP's new P9500 array. This is based on Hitachi's VSP, technology, and using solid state drives and 2.5-inch but not 3.5-inch disk drives. He said: "Your impression of the HDS system is a 'solid and effective refresh of HDS' top-end …
It is LITERALLY bullet proof?!
That is a test video I would like to see. Also, what calibre?
It was a .308. Google will find the (very irritating) video. It was on an XP12000. it's really a demonstration of redundancy. Just don't aim your shot to takes out the redundancy so avoid both copies of a mirrored pair, controllers etc.
The stuff that dreams are made of
Bulletproof XP array coming up!
I think the commenters on the original article were pretty well in agreement with the HP line on this (and one assumes those were not HP employees and, it appears, have practival experience of these issues).
That is that high capacity 3.5" FATA type drives have no real place in an array of this sort and that it is possible to achieve storage tiering using much more cost effective techniques than using up an expensive enterprise chassis with inherently low access density disks. There are "out of frame" expansion techniques that still provide the front-end functionality of the storage array. The 3.5" forem facor is dying as an enterprise format and if you look inside many of them you'll find the platter sizes are reduced in diameter in order to support higher spin speeds and reduced seek time. This is not a new thing - many of us will remember hard drives of 14" diameter. The need to reduce latency by higher spin speeds and shorter seek paths inevitably drives towards the smaller form factor.
The original article also allowed what looked like a pretty free voice to a competitor with a number of unspecific, but dismissive comments. I'm not suprised HP thought the original article wasn't balanced, and from what I can see, it misunderstood what enterprise arrays are generally used for.
@RJ. Is that video not still on YouTube? HP shot an XP array with a rifle through the boards and it kept running. The shot was obviously carefully placed and I assume an armour piercing round was used, otherwise the impact with the first board would have deformed the bullet and it would have shattered later boards rather than simply leaving a small round hole.
Standard .308 IIRC
www.hp.com/go/disasterproof for the short version and the 'follow-on'
Just as irritating - but bigger.
Anon - coz - I'm in it.
Is it just me?
Somehow the idea of tiering and large capacity SATA drives on an enterprise array is like the idea of having economy seats on the (now sadly out of service) Concorde.
Tiering between High performance drives and Flash - yes, and then suddenly the array WILL NOT scale to fill all available drive slots, so the HP view makes the most sense.
LFF Drives and HDS
My HDS colleague tells me that HDS aren't going down the LFF route either - they were originally but decided against it at the last minute - deciding to stick with SFF based on performance and drive roadmaps.
Original article was poor
It's worrying that the first article was so misinformed. The P9500 will clearly replace the XP24k but in a staged fashion. In terms of performance it sits above the XP24k. So what if it can hold less capacity internally, because as other people have pointed out, you would surely put 'capacity' tiers behind the P9500 as external storage!
Of course your own mileage may vary, but if you've ever had to actually pay for HDS storage (and probably the other vendors, but I've only experience with HDS), you'll know that the USP-V(M) and the VSP are all capacity based. Thankfully now the thin provisioning (Hitachi Dynamic Provisioning) comes with the VSP whereas it was an option for the USP-V(M) but the block-based tiering is still licensable. We have AMS2500s behind USP-VMs (with no disk) and it's a very expensive way to provision bulk storage i.e. 3.5" disks.
The block level tiering removes many of the requriemetns for fast disk access, so the 2.5" form factor makes more sense, since the difference between a 2.5" and a 3.5" 600 GB disk is the rotational speed and thus latency. Trust me, provisioning SATA through a USP-VM is a very expensive business. Use a mid-range array for that.
- Review Apple takes blade to 13-inch MacBook Pro with Retina display
- Munich considers dumping Linux for ... GULP ... Windows!
- Game Theory The agony and ecstasy of SteamOS: WHERE ARE MY GAMES?
- Intel's Raspberry Pi rival Galileo can now run Windows
- Microsoft and HTC are M8s again: New One mobe sports WinPhone