Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.
That sucks, what are you going to use to move all the data to while you delete it and reinstall to update for 3.0 code? 2.4 > 3.0 requires a full reinstall of the system. Going forward they are telling us its non disruptive though.
Yes its pure flash, they use hitachi 800gb sas ssds. I...
Newest storage array... EMC XtremIO. This is the first array in cincinnati. It consistent of 2x 20TB bricks.
We've not really done any IOP saturation but based on some vmotion and msc other task it easily produces 500,000 io.
Supermicro stuff is hit and miss though really. They've had some shitty designs where they had to release an entire new motherboard to fix basic things.. like nic ordering LOL.
Depends what your doing, if you have a lot of sequential IO the 10G will help, if you do a lot of iops multiple 1g ports with multipath will be just fine.
If you need quotes on nimble stuff pm me, I can help you get a good deal!
Let me give you some advice. Disk only based systems are VERY reliable and have guaranteed performance. You know how many spindles are available and what sort of iops that data set will have at all times. With a cache accelerated system like nimble tintri ect... your data is only as fast as...
Way less, blades are extremely power efficient, I wish we would have moved to it sooner. I'd say nearly 50% less power used on our blade systems than rack mount servers.
10G Ethernet with FCOE. No LACP is for the birds. We do a lot of active active software defined networking and vmware...
The blades are dedicated servers for customers. I work with a hosting provider.
Back of them:
They are kinda hard to cable, the power cables are generally to long and because they are 12 gauge cabling we don't have to many options. Each PSU in the blade center is 2700 watts.
The upper disk are part of a Dell MD3620F which is used to export block devices for NAS. It has 56 3TB SAS disk.
The bottom EMC array is a VNX 5300 with 20 2TB 7.2k and 50 300GB 15k.
Don't buy new cisco gear, let someone else take the hit. You can pick up 48p 3750/3560g for $1400 and have absolutely no limitations.
The dell switches are manufactured by SMC and have terrible feature sets.. kinda like buying a hub when a switch is just slightly more.. sure both do the same...
Dell 62XX BLOW. Do NOT buy that trash.
If your ever plan to do ANY layer3 at all get some real switches, Cisco 3560G, Force10 S55, Juniper Ex3200/4200... Just because you have some dell server's don't mean their re-branded SMC gear is good to.
We have TONS of gear and I can give you...
You beat me there! We have a compellent system coming in later this year with over 200 disk.. pretty excited to get some new storage in. The way EMC handles iscsi is a little different than what I'm use to... still warming up to the design.
Got bored today and went down to the DC and started building out some new cabs. (I been sick thrus and friday so I worked this weekend)
Cisco 3560G and F10 S50
Business end of the R710 cluster
Onapp BLOWS.
Xenserver all the way, vmware license scheme can suck it. Prefer having the option to run paravirt and full virt anyway, no reason to virt if you can get 2x performance with para and the same features.
Compellent and EMC know how to build storage, netapp is fancy but...
No I'm talking bout the black boxes all stacked, they have BNC ports on them, more than likely DS1.
Yep the gallery is extremely old, we have 6 rows of gear, 8 racks wide. I'll grab some pics of the new EMC storage we have coming.
The network is mixed. Most of the public switches are...
You do want to separate your recursive/authoritative servers.
It is possible for the recursion to feedback a bad entry from another server, you don't want it answering if it don't know.