I am dusting off the cobwebs of my blog. After almost 3 months of inactivity, (and trying to avoid the Social Guidelines Media of my present company), I have bolstered enough energy to start writing again. I am tired, and I am finishing off the previous engagements prior to joining HDS. But I am glad those are coming to an end, with the last job in Beijing next week.
So officially, I will be in HDS as of November 4, 2013 . And to get into my employer’s good books, I think I should start with something that HDS has proved many critics wrong. The notion that HDS is poor with NAS solutions has been dispelled with a recent benchmark report from SPECSfs, especially when it comes to NFS file performance. HDS has never been much of a big shouter about their HNAS, even back in the days of OEM with BlueArc. The gap period after the BlueArc acquisition was also, in my opinion, quiet unless it was the gestation period for this Kick-Ass announcement a couple of weeks ago. Here is one of the news circling in the web, from the ever trusty El-Reg.
HDS has never been big shouting like the guys, like EMC and NetApp, who have plenty of marketing dollars to spend. EMC Isilon and NetApp C-Mode have always touted their mighty SPECSfs numbers, usually with a high number of controllers or nodes behind the benchmarks. More often than not, many readers would probably focus more on the NFSops/sec figures rather than the number of heads required to generate the figures.
Unaware of this HDS announcement, I was already asking myself that question about NFSops/sec per SINGLE controller head. So, on September 26 2013, I did a table comparing some key participants of the SPECSfs2008_nfs.v3 and here is the table:
In the last columns of the 2 halves (which I have highlighted in Red), the NFSops/sec/single controller head numbers are shown. I hope that readers would view the performance numbers more objectively after reading this. Therefore, I let you make your own decisions but ultimately, they are what they are. One should not be over-mesmerized by the super million NFSops/sec until one looks under the hood. Secondly, one should also look at things more holistically such as $/NFSops/sec, $/ORT (overall response time), and $/GB/NFSops/managed and other relevant indicators of the systems sold.
But I do not want to take the thunder away from HDS’ HNAS platforms in this recent benchmark. In summary,
To reach a respectable number of 607,647 NFSops/sec with a sub-second response time is quite incredible. The ORT of 0.59 msecs should not be taken lightly because to eke just about a 0.1 msec is not easy. Therefore, reaching 0.5 millisecond is pretty awesome.
This is my first blog after 3 months. I am glad to be back and hopefully with the monkey off my back (I am referring to my outstanding engagements), I can concentrating on writing good stuff again. I know, I know … I still owe some people some entries. It’s great to be back 🙂
Welcome back. Good luck with the new role!
Thanks Allan! All the best to you too!
You really should try to use “HorribleNAS” before you start jumping for joy. The software is riddled with bugs, hard to upgrade, hardly supports SMB2, had IMMENSE problems after BlueArc had to start using HDS storage. The OS is immature, mirroring is a “HAM” nightmare, and has over 1000 cli commands. I’m sure the blatant omission of cost per GB or TB is trying to hide what is otherwise widely known. Performance numbers using SSD backends are hardly financially viable or very usual. Guess trying to copy EMC marketing is easier than making a good product…
Hi Bob
Thank you for your candid overview about the HNAS product. I love it when someone like you share your honest experience about a technology, and I keen to know why.
Your reply do put me in a spot, because firstly I just started working for HDS in Malaysia 3 months ago. It is a non-technology role and therefore, hardly require me to enquire deep with HDS about their technology deficiency. On the other hand, I am who I am. I write honestly in my blog.
I don’t know who you work for, but if you are sincere about this, show me a few examples of how weak HNAS is and the issues you face. Let me challenge myself to put something out there after your input. Who knows? It might get me FIRED because I am not supporting my employer, but then again, I am curiously wicked to find out what could happened.
So, I appreciate what you will say next. 😉
Thank you
/Chin-Fah
To comment on Bob’s (or Berry’s) statements.
Mirroring doesn’t use HAM for HNAS. That’s something you use for the VSP. (And I hear its getting updated). You use Object replication (Jet mirror) for HNAS if your using the new kit and it works really well. The old replication (going back to the old Titans) was kind of limited (Little more than RSYNC in my opinion) but the new stuff is really nice.