HPE Storage Users Group

VMware can do host based replication without an SRM license, we do it all the time. That said vmware Host Based replication is crude and basically has serious issues and limitations.

As for NAS heads, we tried HP's X9320 and they bought it back from us after several months of failed attempts to get it working to our satisfaction.

The problem I have seen with NAS heads especially if you are a heavy MS Windows shop is they all have issues and limitations as they are some flavor of UNIX/Linux trying to AD integrate and emulate Windows. We ran a NetApp filer for a few years and it was acceptable, but you had to be aware of some of it's limitations as well and work around them. They were always late adopting latest SMB features.

yeah the host based replication is a touch on the crude side. Plus I'm not sure I would be all that thrilled to complicate my environment by using multiple replication/recovery methodologies.

The problem I have with windows is that while I know they say they have improved DFS, I have been burned by DFS very badly in the past (specifically, massive data loss which required a lot of time and energy to restore), and I am not willing to stick my neck out for that particular piece of technology again.

I do tend to agree with you that NAS heads being unix/Linux attempting to emulate windows are less than ideal, they are at least in my mind less risky in terms of things like data loss.

I had a conversation with HP not all that long ago regarding their ibrix product (yeah... I still call it ibrix, not storeall or whatever they have re-branded it as). At the end of the day the rep basically told me that while he understands my problems with DFS, what I'm trying to do just isn't in the green zone for this product. On the upside, they seem to have learned from the experience of having to buy it back from folks like you that ibrix/storeall/x series just isn't a good general purpose file server head.

I have thought about doing a netapp v-series head for file, but again, I don't want to overcomplicate my environment. I have used netapp in the past, and I have been very pleased with their file storage, but it's more complex since I'd be using a netapp head with HP back-end, and more expensive as well.

Here's hoping HP will manage to execute this file persona thing well. If they do, I think they'll sell like hotcakes. There aren't a lot of really great options in the space at the moment. (again, at least IMHO. Maybe you all feel differently).

Too bad we're all not local. I feel like if the regulars on here were to have lunch, there would be a hell of a conversation.

Seems a bit misleading on the "online upgrade"

Integrated file servers seems to be more a "me too" attitude (ie competitors have had it for years) and not really innovative. Would have been nice to see them add the feature in a limited fashion to existing 7000-series arrays ala how actual 3Par would add new features to the V and F class arrays in years past...I guess that's HP getting their hands on it, really disappointing.

I would bite on the controller upgrades but they still are limiting the RCIP ports to a single 1GB interface per controller at which point I'll pass.

The new System Reporter replacement looks to be interesting possibly, time will test as it's "announced but not released".

I don't have an issue with them requiring a controller lift to enable the file persona. My assumption (and perhaps it's a poor one), is that the reason it took so long for HP to add file persona is that they wanted to do it right, and in order to do it right, it took more resources than they had available on the hardware. The other thing is that prior to the HP acquisition, the original 3par crew was very adamant about not wanting to run additional features like file persona, AO, etc on the node. they wanted to minimize the load on the node CPU/Memory as much as humanly possible. So it took awhile for the culture to change enough where the engineers would be ok with adding that feature.

At the end of the day, features like file persona, dedupe, etc are never especially innovative in and of themselves. What I love about 3par is that hp has added these features without even requiring an offline upgrade, which imo is impressive. That being said, compare how HP has done file with EMC and Netapp (the other big players in the converged storage arena), and I see a number of advantages. (warning, I'm about to get into marketspeak. My opinions are my own. I do not work for HP or EMC or Netapp, but some of HP's marketing has really rung true for me)

In EMC VNX, despite the fact that it's "converged" it's really only converged in the management. You still need the file heads (celerra) to support file. In EMC VNXe, the file head runs as a VM, and required dedicated disks. Yep that's right folks, you can't store file and block on the same set of disks. There's a bunch of other stuff about VNXe that makes me nuts, that being one. EMC does the same thing with flash cache. You have to dedicate disks to flash cache, and they cannot also be used as a tier for primary data.

In Netapp, the whole thing runs file natively, and they added a block emulator. This means netapp is great for file, but block gets the short end of the stick.

In 3PAR, the file persona runs on top of block (the way it should be. Why on god's green earth would you put a block emulator which writes to file which get's translated back to block to go out to the disks netapp? WHY?). We can share the disks between block and file with no issues. All the goodies we know and love like inline dedupe, zero detect, thin provisioning, AO, DO, replication apply to file the same way they to file that they do to block, and we don't need any additional hardware or VM to run file (I'm looking at you EMC).

On it's surface, it may not seem especially innovative, but HP seems to have implemented this feature the right way, and the details seem to me anyway to be pretty innovative. And while it's disappointing, I can understand the need to do a controller lift to get it. As far as online, I will admit that my head might explode of HP can controller lift a 7200/7400 online. I mean seriously, that would be impressive in a huge way. Even more so when EMC can't firmware upgrade xtremeIO online!

also, as far as the RCIP goes, personally, I have no issue with the 1Gbps RCIP ports (it's plenty).

But I believe you can add the 10GbE nic and use it for RCIP. It costs a little extra coin, but it'll get you there if you really need 1250MBps as opposed to the 125MBps on the 1Gb RCIP

Here is what we finally did. WE had huge corporate file servers (10's of millions of files spread across 3 huge servers of over 20TB) that we tried ibrix/x9320 and did not work. We finally just stood up Windows files servers on vmware and replicate the datastores at the desired RPO. Has turned out to be the best solution we have done. NetApp was nice, but limitations, some incompatibilities back then and so on.

It looks like the information I received that the controller upgrade could be done online was incorrect. I have spoken to another HP guy who was more expert in this area and he has confirmed the process is offline.

In terms of file not being available on the existing 7000 models I believe this is because they had to add additional hardware, specifically cache to the newer models to ensure that performance was not compromised.

I have written an additional post with the additional information I have received during the course of the week here: http://wp.me/p4wKu7-9o

I'm hoping to receive some more screenshots from the new console in the next few days so look out for them. I also got the chance to meet some lead guys from the 3par team and was promised lots more significant announcements coming next year, so watch this space.

_________________
Twitter @d8taDude

We maxed out one of our 10400, and got an all flash 7440c to grow into.
According to the storage dept pricing is at 15k disk if we meet an estimated 1:4 dedupe ratio. (with 2TB SSD)
It is going to be very interesting when we start putting load on this one,
if we are getting good dedupe ratio and good dedupe performance,
I see absolutely no reason to purchase spinning disk for production again.

Not sure if I'll be able to do any performance testing before x-mas though..

The file services thing interests me, I work with netapp a lot and file is great, until y need to back it up, it's a pain.

The only real way to do it is ndmp, which then means you dedicate fc ports to plug the tape drive into, if not you are doing it over the network. But this also means you can only restore it back to a similar system.

The file server is a vm running on the controller, Linux based I believe, how resilient will it be, will it be mirrored per controller or hosted on disk like the .srdata volume for system reporter.

It's good to get a boost in specs, but is it worth going for them when we're pretty sure there's new hardware coming around the corner next year?

All good stuff though

Depends on your change rate. I'm maxing the current RCIP ports and it has problems keeping up. HP has said it's on the "roadmap" in the past but as the years pass, the only faster than 1GB option is RCFC...which IMO would be fine if we could direct-connect two arrays together without needing the FC switch in the middle.