|
So we inherited another department's equpment and I am a happy recipient of an unexpected EqualLogic PS6100 and some 6224 switches; maybe not the latest and greatest; but wont hurt to have operational. I'm reading through the documentation, and am looking for what I think is pretty stupid clarification: Just trying to confirm (looking only at one card for now, say controller 0) Ports 1 and 3 should be on a separate subnet from ports 2 and 4. Setting up for MPIO and iSCSI exactly as configured here; but nowhere does the Dell docs have anything about subnet configuration for MPIO
|
# ¿ Nov 5, 2015 14:11 |
|
|
# ¿ Apr 29, 2024 07:02 |
|
NippleFloss posted:For EQL all members of the same group should have their ports connected to the same subnet. Thanks! Was just coming back to say I found that information in some other discussion after enough googling. Much appreciated!
|
# ¿ Nov 5, 2015 17:22 |
|
I have an EqualLogic I want to benchmark for an SQL environment. Any tips for tests to run with iometer? It's tough to pull from environment history as this is a new pilot under development, so i can only guess (mostly reporting, writes aren't terribly intensive, at least that's the plan). Just trying to get a feel for what the array can handle - I'm not a storage guy by any means, so whatever tests I can concoct with iometer that'd make sense would be very helpful!
|
# ¿ Dec 9, 2015 04:47 |
|
Anyone worked with FusionIO cards? I have a 1.2tb one that's not behaving as anticipated. It's for a lab and out of warranty but very very low use. edit: nevermind; it looks like I needed to reinstall the chipset drivers for the host server. Walked fucked around with this message at 18:38 on Feb 8, 2017 |
# ¿ Feb 8, 2017 17:20 |
|
Mr Shiny Pants posted:Is it a regular PCIe card? Home much do you want for it? It is! And it's going to find a home in my desktop if I cant get what I want out of it for a storage server. H110Hawk posted:We are playing these games right now as well. Can you describe how it's performing, kernel version, benchmark, and copy/paste your partitioning + FS creation commands? I will see if I can find mine. We're playing with "LIQID" NVMe cards. And yes it's pronounced liquid it is a dumb name and I pronounce it lick-id. I'm actually running inside Windows Server 2016; as I'm hoping to use it as a StarWind VSAN cache disk. Although I'm ready to dump and move to a ZFS build if this keeps up. I've tried it all; Local benchmarks are good. ~1.5gbps ready / ~1.2gbps write. IOPS within range (and insane on small block sizes ) As soon as I throw it on a network of ANY kind or even just a Hyper-V VHD stored on there, performance drops to ~200mbps read / ~400mbps write; IOPs are still find on lower block sizes though. I've tried setting 512 and 4096 sector sizes, NTFS / ReFS, MBR and GPT. That said; I just updated all my chipset drivers are I'm seeing much closer to spec performance inside my test system. I'm going to re-build this server today and see where I end up. EDIT: nevermind performance is terrible again Walked fucked around with this message at 18:44 on Feb 8, 2017 |
# ¿ Feb 8, 2017 18:41 |
|
Any time I expose the storage to anything other than the native host bare metal, and performance tanks by 80% or so. Hyper-V VHD on there? Performance in the VM is garbage time. And this was my local test to rule out network somehow being related. Present the drive or a folder on the drive via SMB and the performance tanks. Present the drive or a VHD on the drive via iSCSI and performance tanks. It's quite strange. But I think I'm getting somewhere. I've updated the drive firmware and reinstalled my chooser firmware again. A brief iometer run shows MUCH better numbers (close to theoretical max) but I want to run that a tad longer to be sure and calling it a day.
|
# ¿ Feb 9, 2017 01:09 |
|
H110Hawk posted:I would focus on this one, as it likely has the fewest variables. I am 100% unfamiliar with Windows but: Is there a way to map through the FusionIO drive to your Hyper-V instance with its VHD somewhere else? Or is that exactly what you're doing? Basically put the root disk for your windows instance elsewhere and expose through localhost a smb share or similar. I've run both routes. However, after the firmware update and chipset driver reinstall - all is still benchmarking as it should be, and for sustained periods now. Saturating 10gbe in style edit: nm; performance tanked again over network. Just going to use this for my vmware workstation as I'm tired of fighting with it for what amounts to a cache disk I dont really need for pure lab stuff Walked fucked around with this message at 04:25 on Feb 9, 2017 |
# ¿ Feb 9, 2017 03:13 |
|
Who should I be looking at for cost effective storage these days? Just took a new position that needs a relatively cost-conscious virtualization storage system. What's the current hotness in that space?
|
# ¿ Mar 24, 2017 18:54 |
|
|
# ¿ Apr 29, 2024 07:02 |
|
Moey posted:Can you be more specific about your requirements? Size and workload? Sure; we're aiming for something 20-30tb for a very generic "virtualization" workload; no particular high io workloads; but significant VM usage. Clustered environment. I've used the Equallogic PS6000 series in the past and it's handled this workload well; but I want to see if there's another option to consider this time through, as cost is a bigger consideration here.
|
# ¿ Mar 24, 2017 20:24 |