Strata Gems: Who needs disks anyway?

RethinkDB uses SSDs to their full advantage

We’re publishing a new Strata Gem each day all the way through to December 24. Yesterday’s Gem: Kinect democratizes augmented reality.

Strata 2011 Today’s databases are designed for the spinning platter of the hard disk. They take into account that the slowest part of reading data is seeking: physically getting the read head to the part of the disk it needs to be in. But the emergence of cost effective solid state drives (SSD) is changing all those assumptions.

Over the course of 2010, systems designers have been realizing the benefits of using SSDs in data centers, with major IT vendors and companies adopting them. Drivers for SSD adoption include lower power consumption and greater physical robustness. The robustness is a key factor when creating container-based modular data centers.

That still leaves the problem of software optimized for spinning disks. Enter RethinkDB, a project to create a storage engine for the MySQL database that is optimized for SSDs.

As well as taking advantage of the extra speed SSDs can offer, RethinkDB also majors on consistency, achieved by using append-only writes. Additionally, they are writing their storage engine with modern web application access patterns in mind: many concurrent reads and few writes.

The smartest aspect of what RethinkDB are doing, however, is creating their product as a MySQL storage engine, minimizing barriers to adoption. Currently in rapid development, you can obtain binary only downloads of RethinkDB from their web site. Definitely a project to watch as it matures over the course of the next year.

tags: , , , ,

Get the O’Reilly Data Newsletter

Stay informed. Receive weekly insight from industry insiders.

  • Baron Schwartz

    I like RethinkDB’s ideas, because I have seen them tried before almost point for point and they only failed due to lack of marketing. But, I think your post is wildly optimistic. RethinkDB *says* they are optimized for SSD — only time will tell, and I can promise it’s a lot harder to achieve than to design for. And it’s going to take a lot longer than the course of the next year to mature. I think five years is a more realistic estimate.

  • Wai Yip Tung

    It is worthwhile effort. On the other hand, Michael Stonebraker seems lukewarm on SSD though. His assertion 3 about Data Warehouses is the vast majority of data warehouses are not candidates for main memory or flash memory.

  • SteveL

    HDDs still have the lowest cost per TB, which maps to the lowest cost per petabyte. If you commit to SSD everywhere, you are saying you are prepared to throw away data rather than preserve or analyse it.

    Stonebraker? Isn’t he the one who denounced MapReduce until his product supported it? I can imagine him saying that about SSDs..

  • Roger Weeks

    The jury is still out on whether SSDs have greater physical robustness than spinning disks.