IBM DS3500 vs EMC VNXe vs Iomage vs Dell MD3200i ~ MD3260i

[habibalby]

Hello Guys,

I'm on the process of selecting a SAN Storage for our Test and Development / DR Environment. And I'm comparing the features, functionality and cost wise among those SAN Storage.

If anyone work with any of these Storage or have one already in his/her environment. Please give me a hint about it.

• IBM DS3500
• EMC VNXe
• Dell MD 3200i & MD3260i
• Iomege

I highly appreciated.

Thanks,

S.Hussain

[idle-jam]

IBM 3500 has built in replication and it suitable for DR. i'm not sure for the rest as i have never used them before ..

[habibalby]

Thank you for your reply, still looking for some info for real experience as I have plenty of brochures and .PDF

[little_horse]

I think you use the wrong approach. Firstly, you need to define your requirements to a storage system, and then you can compare them with products' specs. Maybe even some freeware product, like Openfiler, is a right solution for you.

[habibalby]

Hi,

The environment is small which has got maximum 30 VMs with small I/O iops. That's why I'm putting the SAN's mentioned above are best fit for this environment. I'm posting this, just to get people feedback if anyone has worked with any of them.

Thanks,

[briroy]

Which decision did you go with?

I would be interested to see a comparison particualrly between the DS3500 and VNXe as I am about to make this same decision.

[mcowger]

I would say that the DS3500 & VNXe are in a different class from the Iomega (single controller) and the Dell units (MD series).

If we have any needs in the future thinking about things like replication, etc or resiliency, I'd go with one of those two.

Now, I work for EMC, so obviously I'm somewhat biased, so take what I say with a grain of salt (or a huge bag!), but I'd next consider VMware integration quality.  I think if you look at that, you'll find the VNXe is well ahead of the DS3500 on that front.

I've personally run over 60 VMs simulatenously on a VNXe in a heavy usage scenario.

[HPstorageGuy]

Disclaimer - I work for HP.  I think all of the products you're looking at are fine products.  Did you consider the HP P2000 G3 MSA?  Not to widen your net of products but the P2000 has a lot of things to consider for VMware - including support for VAAI and a free vCenter plug-in to manage the P2000. The P2000 is one of the few if not only entry level arrays to support VAAI (Matt just told me that VNX does support it but not sure that's entry level).  The P2000 also includes licenses for 64 snapshot and volume copies included with the base product. There are multiple versions of the P2000: iSCSI (1 and 10 GbE), FC, and SAS and even a combo controller with iSCSI and FC.

If you consider the P2000 and eliminated it, please forgive my intrusion; if you want to know more, I'd be happy to connect you up with the product manager - just send me a message. Hope you find what you're looking for.    

[mcowger]

Gotta agree with Calvin here - P2000 is definitly in the same camp as VNXe and DS3500 and totally worth considering.

[habibalby]

Hi All,

Decision made to go with the IBM DS3500 due to price .. I will implemented and post my feedback about this

[briroy]

I've just implemented a DS3500 (Dual Controller - with iSCSI), I have actually direct connected my hosts with SAS (I only have two nodes).  I went for the 2GB cache upgrade but decided against the "Performance Boost addon" in the meantime.  I have to say, performance wise I am delighted after upgrading from the DS3400 (4GB FC) although I have also added more cache, spindles and arrays for my VMs it is not really a fair comparison.

I did consider EMC storage (I used to sell IBM, HP and EMC storage), however at the end of the day my environment is fairly simple and I didn't want to over complicate my storage with features I didn't need and would probably never use.

One issue I have come across and would be interested if you or anyone else has experienced it - when I add/change/rename and array or LUN I get a failover event flagged on the DS3500 and all my paths move to one of the controllers - I then have to manually change the paths back.  I initially thought the problem was caused by by old ESX nodes connected by iSCSI for the migration but it turns out not to be the case.....

[habibalby]

Hello,

Yesterday I have received this Box IBM DS3500 and I have attached it to 2 ESX hosts 4.1. The configuration of this SAN is single Controller with two management ports and 4 iSCSI ports. Each ESX has two vmnic for iSCSI connections.

Any idea how to setup Multipathing in this DS3500? I did notice in the documanetation that, I cannot use the same subnet for the four iSCSI ports, I have to use different subnet.

I focused on one of the ESX host and configure that host with one vSwitch that attached to only one vmnic. In the vSwitch, I have created four iSCSI portgroups. In the beginning, I can ping all the iSCSI ports in the DS3500, but after awhile I can ping only two iSCSI ports. Something worried is going on.

Any help?

Thanks,

[habibalby]

Hello,

Here's an update of the issue that I was facing yesterday. I configured each SCSI port in the IBM DS3500 with different subnet, Port-3 10.10.10.1, Port-4 10.10.20.1, Port-5 10.10.30.1, Port-6 10.10.40.1 /24.

I have two Dell 2724 switches, 10.x subnet goes into Port-1 in pSwitch1 and subnet 20.x goes into pSwitch1 Port-2, Subnet 30.x goes into pSwitch2 into Port-1 and Subnet  40.x goes into pSwitch2 Port-2.

In the ESX side, I have one vSwitch attached to two vmnic's vmnic2 and vmnic3. In this vSwitch I have created four VMkernel Portgroups,

• iSCSI-01 10.10.10.30
• iSCSI-02 10.10.20.30
• iSCSI-03 10.10.30.30
• iSCSI-04 10.10.40.30

If all the nics are active at the same time and try to vmkping to the Storage Processor, I will be getting (DUP!) Duplicate pings from one of the subnet, then the ping will stop working but it will work for the other Storage Processor.

What I did to overcome this issue is to have the vmnic2 is active for iSCSI-01 and iSCSI-02 and vmnic3 unused for iSCSI-01 and iSCSI-02. The same for the other Portgroups, vmnic3 is Active only for iSCSI-03 and iSCSI-04 and vmnic2 is unused these two Portgroups. After that the ping is steady without (DUP!).

iSCSI Binding is done on the iSCSI adapter to have all the VMkernel Portgroups. esxcli swiscsi nic add -n -d vmk# vmhba33.

After that, all the four pathes are appeared, and changed the Storage Path to Round Robin to have them all Active(I/O) at the same time.

Testing were done, by switching off pSwitch1 and connection were alive to the SAN Storage, and the number of paths changed from four to Two. Turned off pSwitch2 and the connection were alive too to the SAN Storage and the number of paths changed from four to two.

As per IBM, they say it's not the recommended way ot having this config and it's unsupported I don't know the reason why it's not supported / recommended. The only support method they say as per the IBM engineer who installed this SAN Storage is to have only two paths if only one Controller is installed and cannot put four connections!!! But he surprised of what he has seen from my configuration:). As per him, he said I can use the 8 Paths ONLY if the second controller is installed, which is logcially I can't find any answer for it why is that!!!!

Hope someone esle will make use of this.

Thanks,