An observant person has probably noticed that SQL queries requiring disk reads not only have longer duration but also higher CPU times. It is not hard then to deduce that disk access (for both HDD and SSD), which involves the OS performing an IO call, the SQL Server process finding a place in the buffer cache for the data pages, and possibly ...

You might encounter a situation, under a very heavy workload, where processing for certain transactions starts out very efficiently, but over time becomes much less efficient.    A good place to start troubleshooting is, of course, PerfMon.  But PerfMon can fail to reveal the culprit, since the CPU can remain stable and moderate ...

If you’ve ever taken the time to read http://www.tpc.org/results/FDR/TPCC/hp_orca1tb_win64_fdr.pdf, you might find a bit in there that’s confusing.   ''Microsoft SQL Server 2005 Enterprise Edition 64-bit Service Pack 1 was configured to utilize ''soft NUMA'', a feature that allows network connections to be affined to specific groups of CPUs ...

If you're well-versed in using PerfMon, I'd like to hear about the counters that you use regularly and what constitutes a good or bad value.  However, it's a rare individual who knows their way around PerfMon and its multitude of performance objects and counters.  Which ones should you track?  And even if you know the ...

Back in the 1997 time frame, I gave a presentation projecting out when 64-bit operating systems and applications should become pervasive in the high volume platforms. My best estimate was this would be some time in 2003 or 2004. This meant that hardware platforms should be ready in 2001 or 2002 to allow for reasonable software availability, ...

Just a quick note to send a big Thank You to Christoph Stotz of Frankfurt, Germany for his hospitality on Sunday.  Thank you, Christoph!  Slava Oks has a rather well-known blog entry about how hyperthreading can negatively impact the performance of a SQL Server 2000 instance: ...

Over the years, I've heard people mention that they wanted a way to determine the physical processor configuration on a machine, for example, how many cores are on the server, is hyperthreading enabled, etc. The good news is that uber-genius of the SQL Server engine, Slava Oks, has published a blog entry on this a while ...

Greg Linwood, a fellow SQL Server MVP, has started a series of articles in which he attempts to prove that having a clustered index on each table is not a good practice. However, he has failed to include the effects of fragmentation into account, so I decided to run some tests for myself. One of those test had rather upsetting ...