… way in the Linux asynchronous IO library to get time metrics for particular IO block. so my testing command line looks… run You may see I gather metrics every 10 sec to see how stable the performance is, and it really helps to… it seems suitable to work with MySQL. I will publish sysbench oltp benchmarks running MySQL on RAID10 over 4 STEC MACH16 cards…
Comment: Percona white paper: Forecasting MySQL Scalability
April 17, 2012 By 6 Comments
Hi Baron, Your first paper – Forecasting MySQL Scalability with the Universal Scalability Law was really very interesting. … to see you gave one session on – Extracting Scalability and Performance Metrics from TCP Traffic in Surge Conference 2011. Is there any…
Post: Testing Samsung SSD SATA 256GB 830 - not all SSD created equal
April 25, 2012 By 10 Comments
… the most popular. I do not particularly like its write performance – I wrote about it before, that’s why I am… run You may see I gather metrics every 10 sec to see how stable the performance is, and it really helps to… you are interested more in SSD and MySQL questions – I will be giving a webinary “MySQL and SSD” on May-9. It…
Post: The two even more fundamental performance metrics
May 5, 2011 By 6 Comments
…. I derived all of these metrics from two “even more fundamental” performance metrics, which I’ll call the “basic” metrics. That’s what this… it. Ladies and gentlemen (drum roll please), the two basic performance metrics: Arrival time Completion time If we know the instant in… 50 microseconds, maybe a bit longer. This is common in MySQL servers I work with when they’re running a simple…
Post: The four fundamental performance metrics
April 27, 2011 By 15 Comments
… are many ways to slice and aggregate metrics of activity on a system such as MySQL. In the best case, we want… powerful. These are the key metrics we need to model scalability with the Universal Scalability Law, perform queueing analysis, and do capacity… more. We derived our four long-term average metrics from the four fundamental metrics, and we derived those in turn from the…
Post: Followup on performance metrics: slides, video
July 11, 2011 By 6 Comments
… extract an amazing amount of information about a system’s performance, scalability, queueing, and more by just measuring request arrivals and… this into a more complete description of how to analyze MySQL’s performance and scalability through nothing more than TCP/IP packet…
Post: Percona white paper: Forecasting MySQL Scalability
November 16, 2010 By 6 Comments
… can apply it to MySQL servers. One thing alluded to in the paper is extracting the necessary metrics from network traffic. I… file. It turns out that two simple metrics can provide amazingly rich insight into system performance and scalability, in combination with Little… must expose these simple metrics. (I have filed a feature request for Percona Server to add these metrics for MySQL users.) I’ll…
Post: Why you should ignore MySQL's key cache hit ratio
February 28, 2010 By 27 Comments
… each buffer hit or miss takes. If you approach application performance optimization from the standpoint of response time measurements, which you… good instrumentation in MySQL to guide your decisions. It is also not the be-all and end-all of MySQL performance, and people… a performance analysis metric because they are a) ratios of b) counters. You need to look at absolute magnitude, not ratios. For performance…
Comment: The four fundamental performance metrics
April 27, 2011 By 15 Comments
… said, I believe Baron is trying to construct something out mysql performance counters because not much is already available (e.g., not… term “performance metrics” over the oft-used “performance statistics” to remind myself that we first must have reliable and meaningful base metrics or measurements…
Post: Why don't our new Nagios plugins use caching?
February 19, 2012 By 1 Comment
… reasons: Performance. Cacti runs some of its polling processes serially, so if each graph has to reach out to the MySQL server…; I didn’t cache the data retrieved from MySQL, I cached the resulting metrics. This avoids having to do InnoDB parsing repeatedly… inverse of the two reasons that graphing should be cached! Performance doesn’t matter. First, most Nagios checks are run once…
