Isilon, EMC's scale-out filer product, now stores 33 per cent more data after adding support for 4TB disk drives. It used to top out at just over 15PB in a single pool, with an NL-Series system using 3TB SATA disks. Now it can store up to 20PB in a single volume with 4TB SATA spinners, and, EMC says, use 30 per cent less power …
EMC Isilon benefits from 4TBs!!! Really?
As if EMC Isilon is the only manufacturer that benefits from supporting 4TB drives. REALLY? Lots of vendors have had these for months. Like every manufacturer that uses them, they too provide "33%" more capacity for the same spindle count, use 30% less power and require less hardware to provide equivalent capacity to 3TB based solutions.
How about just an article about the availability of 4TB drives in the industry .... and the obvious merits therein? Lose the vendor slant ... pick up some credibility.
Re: EMC Isilon benefits from 4TBs!!! Really?
True, I don't understand the purpose of this article. Every storage vendor has, or will soon have, 4 TB drives. All of the storage companies buy their drives from the same few drives vendors... who will sell the same 4 TB drives to all of their array OEMs. Seems like an Isilon advertisement.
Here's Why. Isilon doesn't have the rebuild limitations associated with 4TBs HDDs and RAID
Usual full disclosure - I work for the Isilon Storage Division of EMC. The Reg didn't explicitly cover this, but this is why 4TB drives and Isilon is very news-worthy.
The way Isilon's OneFS file system distributes chunks of files, first across all nodes, and then deep across drive in a cluster means that on a drive failure, a complete drive rebuild is not required. Only the bits of files that were on the failed device are restored. As example, assuming the cluster/drives are 70% full, only 70% of the content of the failed drive is reconstructed. And the process is accomplished with huge amounts of parallelism with all the nodes participating in the file reconstruction to free space distributed throughout the cluster. The more nodes in the cluster the faster the file rebuilds. Elegantly scalable data protection.
The Isilon architecture doesn't have the drive rebuild bottlenecks of many RAID based systems which need to reconstruct the complete 4TB drive by reading parity from a rather small number of drives in a RAID set and writing the data to a single hot spare. The hot spare becomes the rebuild bottleneck at ~140MB/sec and considering that in a common 8+2 RAID-6 group a drive rebuild requires 8x4TB reads - 32TB read to rebuild 4TB.
Isilon can adopt big fat 4TB spinners and with its parallel file rebuilds and elegantly scalable data protection, it greatly reduces the risk of multiple drive failures and/or non-recoverable bit errors causing data loss. Something that most RAID based architectures can't scale with drive size.