Firstly, apologies for the recent lack of posts. I’ve been on holidays and then started a new job and it’s all been not very related to this blog. Secondly, while it was tempting to call this blog part 5 in the VNX7500 series - these configuration guidelines work well for most all of the VNX range of arrays, not just the 7500. Thirdly, forgive me if I’ve said some of this stuff before. And finally, yes, I know I promised I’d upload some sample designs and talk about them, and I promise I will. Soon. Or soonish. So, in no particular order, here’s a list of things that you should keep in mind when designing solutions around the VNX.
Note that Pool-based LUNs, EFD-based LUNs, FAST VP LUNs, and FAST Cached LUNs do not benefit from file system defragmentation in the way traditional LUNs do. This might require a bit of education on the part of the system administrators – because you know they loves them some defragmentation action.
When configuring FAST Cache on an array, it is important to locate the primary and secondary drives of the RAID 1 pair on different Back End ports. The order the drives are added into FAST Cache is the order in which they are bound. So pay attention when you do this. The disabling of FAST Caching of Private LUNs is recommended (these include the WIL, Clone private LUNs and Reserved LUN Pool LUNs). However, you shouldn’t disable FAST Cache for MetaLUN components.
If you’re using EFDs for “Tier 0″, you’ll get good performance with up to 12 EFDs per Back End port. But if you’re on the hunt for the highest throughput, it is recommended that this number be kept to about 5.
It is recommended that you use RAID 6 with NL-SAS drives of 1TB or greater. This has some interesting implications for FAST VP hetergenous Pool configurations and the use of 15 vs 25-disk DAEs. I’m hoping to put together a brief article on ways around that in the next week or so.
When architecting for optimal response time, limit throughput to about 70% of the following values:
It is considered prudent to plan for 2/3 of IOPS for normal use – this will give you some margin for burst and degraded mode operation.
When it comes to fancy RAID Group configurations – EMC recommend that a single DAE should be the default method for RAID Group provisioning. If you use vertical provisioning make sure that: for RAID 5, at least 2 drives per port are in the same DAE; for RAID 6, 3 drives in are the same DAE; and for RAID 1/0, both drives of a mirrored pair are on separate Back End ports. It should be noted that parity RAID Groups of 10 drives or more can benefit from binding across 2 Back End ports – this reduces rebuild times when you pop a disk.
Finally, it should be noted that you can’t use Vault drives in a FAST VP pool. I still prefer to not use them for anything. |
[复制链接]
