May 24, 2012

Post: How Percona does a MySQL Performance Audit

you know the term “thin-slicing.” That describes an experienced consultant’s approach to the problem very well. Theyou‘ve seen there really isn’t any such thing. Post your questions in the comments, and I’ll try to answer

Post: How Percona strives to remain neutral and independent

Peter‘s post on bias) based on our knowledge of the product, regardless of whether thethe product. The more we know, the more valuable we can be to you and to our clients who might purchase theto speak. The answer is that vendors might not be ready with their product. We aren’t here to

Post: Heikki Tuuri Innodb answers - Part I

to guess where our search would end in the B-tree. To verify that we arrived at the right position, we need to know theto whatever use in whatever segment. After that, a segment always reserves whole 64 page extents. Thus, the answer to the

Post: Heikki Tuuri answers to Innodb questions, Part II

answers to the second portions of the questions you asked Heikki. If you have not seen thethe web about flash memories, and noticed that random writes to them are actually slower than to a mechanical disk. I do not know how

Post: How Percona diagnoses MySQL server stalls

the conditions occur. Analyze the diagnostic data. The answer will usually be obvious. Step 1 is usually pretty simple, but it’s the most important to

Post: Percona Server with XtraDB Case Study, Behind the Scenes

the right data. Maybe you have too little, or too much, or you have the signal mixed in with the noise. Knowing when and how toto do was wait until the problem happened, look at the diagnostics, and a couple minutes later I had my answer. What were the problems? The

Comment: COUNT(*) vs COUNT(col)

the performance of counting all the rows in a table. This discussion is a good example of Peter‘s other comments today … simple answersto have a more complete understanding of the technology, so you can make the best decisions on how to apply it to

Comment: MySQL Server Memory Usage

to know is howto track down where the bottleneck is… I’ve read Peter Z two guides but cannot really convert the gained knowledge tothe answer to ‘b’ is 2mb then the total amount of memory would be something like 1800 + 2*600 = 3G right? To much to

Comment: Linux schedulers in tpcc like benchmark

… much more), a possible answer would be that …Peter, my comment about O_DIRECT w/o BBU was based on theyou :) You are also very on point when you bring up latency in theto consumers (although MySQL offers INSERT DELAYED). Back to the subject, I don’t know anything about tpcc (and even less about how