The biggest knock against the X4500 I’ve heard is that it is too expensive. From a storage perspective it is actually absurdly cheap compared to the 5-10x charged by the name-brand storage vendors – and for lower data integrity than the X4500/ZFS system offers.
Considered as a server it is a different story. After all, the most popular servers are in the $1k-$5k range, so why not just glue the disks on with some cheap PCI-X adapters and be done with it?
Several reasons, as this brief post at c0t0d0s0.org notes. He points out some of the trade-offs that low-cost servers make in order to meet their price points, like bottlenecked architectures that offer connectivity at the expense of performance.
Sun’s server group should get some benchmarks out pronto of the X4500’s iSCSI and NFS performance, along with some TPC numbers. That is risky, since the storage group might hijack it out from under the server group. Yet the storage folks have their hands full with staff turnover – always a problem, but much worse right now – and the struggling STK integration effort. People need to see what this machine is capable off, sooner rather than later.
Let’s hope it’s lugged to try and buy customers soon, and I’m sure I’m not the only one eager to read their reports!
Booked a meeting with our Sun Account / Tech Rep, mentioned I was interested in the cheap storage options of the Sun X4500. I am thinking real cheap NFS Vmware (ESX 3) Dev storage.
Anyways, he brings along the Sun Storage Guy to the meeting and they try to sell me some NAS gear. Basically hardly spoke about the x4500.
They called the X4500 a “Data Server” – I have no idea what that is!
Evidently, neither does Sun!
Sun has a long history of lousy storage marketing. I competed against them when I was at DEC, worked there for several years and have since watched the circus continue unabated. I hope Schwartz and Yen can turn this around after years of McNealy’s indifference. We’ll see.
In my Computerworld blog I commented a bit about why you won’t hear about this from Sun. Seems like I was more right than I knew.
One solution would be for Schwartz to ask Andy Bechtolscheim, a Sun co-founder, to set up a small, dedicated “Data Appliance” marketing team reporting to him. Andy’s no marketing guy, but he has a visceral instinct for what makes sense and the X4500 makes loads of sense. He’s also got the clout to protect a nascent product line from the infighting that sucks the life out of most Sun marketing. A small “Data Appliance” guerilla marketing team, 3-5 people, is all that is needed. Get it rolling with the smartest customers and the battle is half won.
I found this interesting entry at:
>
“The new metric
I find I’m measuring what used to be considered huge amounts of data not in Megabytes, or Gigabytes, or even Terabytes, but in “thumpersâ€, with a thumper equaling 24 terabytes of raw storage.
48TB is 2 thumpers
For those that aren’t familiar a thumper is and why I would associate it with 24 TB of data you can get more information at x4500 aka thumpers home page
posted by jamesd_wi at Thursday, July 13, 2006 0 comments”
Anybody think this will catch on?
I have just made my first pass through the preliminary announcements for the “Thumper”.
I am excited!
This looks very much like Gene Amdahl’s conceptual Storage box design I saw in 1998 and never saw again. The comments at “http://www.c0t0d0s0.org/archives/1792-Do-it-yourself-X4500.html#extended”
set my alert bell ringing. In particular the comment:
“Now you have a different problem. Find a PCI-X board with 3 logical separate PCI-X busses. Every configuration sharing busses will see the bottleneck described . So you have to find a board with two AMD8132 Bridges, something i doubt you find on el-cheapo mainboards.”
There were some implementation problems with Gene Amdahl’s design but the concept was breath-taking. So is the “Thumper”.