Henry Newman's Storage Blog Archives for February 2012

The Future of SSD: Reality Catches Up to Hype

It might be a bit late, but I am just back from vacation. While away, I was sent an interesting article on the future of SSD technology and the actual study.

This is not really news to me. A few years ago, I argued that lithography limits and disk drive density were going to keep SSD from replacing spinning disks. Now, the industry is coming around to the realization that NAND will not last forever. We have not seen much in density growth for SSDs since I wrote that article almost 18 months ago, and I did not expect much of any. The other issues discussed in the article regarding garbage collection and errors were not a surprise to me either.

So what is going to happen to the SSD market? For one thing, as I have said over and over again, the market is going to and is in consolidation. The other thing that will likely happen is NAND will be replaced. Is it going to be phase change memory (PCM), Memristor or something else? Right now PCM has the lead, but we are still limited in two major ways in my opinion.

First, the I/O stack has a lot of latency overhead going from the application to the OS, file system device driver and so on. Second, the PCIe bus is limiting the long-term performance potential for storage. We are not at just 1 GB/sec per lane.

Put that in perspective -- here are the number of IOPS with PCIe 3.0 by lane count.

Request Size
(in Bytes)
1 Lane 4 Lanes 8 Lanes

512

2,097,152

8,388,608

16,777,216

4096

262,144

1,048,576

2,097,152

8192

131,072

524,288

1,048,576

16384

65,536

262,144

524,288

32748

32,788

131,152

262,304

With PCIe 4 around four years away (PCIe 3.0 really has not hit the market yet), I am not sure that longer term we are going to be dealing with a new level of memory like registers, L1 cache, L2 cache, L3 cache, DDR and some non-volatile storage.

Labels: SSD, PCIe, NAND, IOPS, PCIe SSDs, NAND Flash, density

posted by: Henry Newman

Why Use Enterprise Tape?

It is now February 2 -- Groundhog Day -- and LTO-6 has not been officially announced. The most recent press release on the lto.org website is from August 24. What is the proposed media type, what is the density, and how will that compare with enterprise tape from the two enterprise vendors, Oracle and IBM? At least today, the LTO hard error rate is two orders of magnitude less than enterprise tape at 10E17 bits vs. 10E19 for enterprise tape. For those sites that have large amounts of LTO tape, I believe it is time to consider looking at the enterprise alternatives. Both have greater density than LTO, both are faster read and write than LTO, and both are considered more durable than LTO. Of course, everyone will say the price for LTO is lower. I encourage everyone to look at not just the tape and tape drive prices, but also the cost of the library and the bandwidth comparison, looking at:

  1. Tape library costs, as with LTO you will need a large library for the same amount of storage. Do not forget to include all of the licensing costs.
  2. Tape drives based on bandwidth. Yes, LTO drives are less expensive than enterprise drives, but you will need more of them to achieve the same bandwidth. Do not forget to consider the load and unload times, as generally enterprise drives are faster.
  3. You of course will need many more LTO tapes given the differences in density.

Everyone will need to run the numbers for themselves to see the cost differences, but I think you will see some surprising results with very large storage configurations. Of course, the larger the configuration, the more data moved and therefore the higher probability that you hit the hard error rate with LTO. Time for a second look at enterprise tape.

Labels: tape storage, tape drives, tape, LTO-5, LTO

posted by: Henry Newman