iiBench Contest

Published on 05 December 2008 by bradley in TokuView

I’d like to advertise my previous iiBench posting again (now that we are feeding into PlanetMySQL.)

0 comments | Continue Reading

At the recent OpenSQL Camp in Charlottesville, VA, Tokutek offered a challenge to the MySQL community – who can insert a billion rows into MySQL the fastest?  We will post the results on our website and the winner gets a $100 Starbucks card, along with valuable bragging rights.

Tokutek’s technical founders (Michael A. Bender, Martin Farach-Colton, [...]

8 comments | Continue Reading

Recall that I’ve claimed that it takes 28 years to fill a disk with random insertions, given a set of reasonable assumptions. Recall what they are:
We are focusing on the storage engine (a la MySQL) level, and we are looking at a database on a single disk — the one we are using for [...]

1 comment | Continue Reading

I’ve been waving my hands about lower bounds. Well, sometimes I haven’t been waving my hands, because the lower bounds are tight. But in other cases (lenient insertions, range queries), the lower bounds are very far from what we’re used to.
So now, for a bit of math:
Brodal and Fagerberg showed in 2003 that [...]

1 comment | Continue Reading

Sorry for the delay, now on to range queries and lenient updates. Let’s call them queries and updates, for short. So far, I’ve shown that B-trees (and any of a number of other data structures) are very far from the “tight bound.” I’ll say a bound is a tight if it’s a [...]

0 comments | Continue Reading

How Fast Can Updates Run?

Published on 11 February 2008 by Martin Farach-Colton in TokuView

Last time, I introduced the notion of strict and lenient updates. Now it’s time to see what the performance characteristics are of each.
Just to rehash, we are focusing on the storage engine (a la MySQL) level, and we are looking at a database on a single disk — the one we are using for [...]

0 comments | Continue Reading

Updates & Discipline

Published on 05 February 2008 by Martin Farach-Colton in TokuView

So far, I’ve analyzed point and range queries. Now it’s time to talk about insertions and deletions. We’ll call the combination updates. Updates come in two flavors, and today we’ll cover both.
Depending on the exact settings of your database, the updates give a varying amount of feedback. For example, when a [...]

0 comments | Continue Reading

Last time I talked about point queries. The conclusion was that big databases and point queries don’t mix. It’s ok to do them from time to time, but it’s not how you’re going to use your database, unless you have a lot of time. Today, I’d like to talk about range queries, [...]

0 comments | Continue Reading

The Trouble with Point Queries

Published on 18 January 2008 by admin in TokuView

Insertion and Queries
Databases are complicated beasts, but I’d like to focus on the storage engine, just the part that talks to the storage system, and doesn’t have to worry about SQL, etc.: just transactions, concurrency, compression, updates and queries. In the next couple of blog entry, I’d like to just focus on updates (insertions [...]

0 comments | Continue Reading