Search results matching tags 'parallel processing', 'PASS', and 'Performance'

Query Tuning Mastery at PASS Summit 2012: The Video

Adam Machanic — Tue, 13 Nov 2012 14:49:00 GMT

An especially clever community member was kind enough to reverse-engineer the video stream for me, and came up with a direct link to the PASS TV video stream for my Query Tuning Mastery: The Art and Science of Manhandling Parallelism talk, delivered at the PASS Summit last Thursday. I'm not sure how long this link will work, but I'd like to share it for my readers who were unable to see it in person or live on the stream.

Start here.

Skip past the keynote, to the 149 minute mark.

Enjoy!

Query Tuning Mastery at PASS Summit 2012: The Demos

Adam Machanic — Mon, 12 Nov 2012 04:00:00 GMT

For the second year in a row, I was asked to deliver a 500-level "Query Tuning Mastery" talk in room 6E of the Washington State Convention Center, for the PASS Summit. (Here's some information about last year's talk, on workspace memory.) And for the second year in a row, I had to deliver said talk at 10:15 in the morning, in a room used as overflow for the keynote, following a keynote speaker that didn't stop speaking on time. Frustrating!

Last Thursday, after very, very quickly setting up and getting sound and video checks, the rest of the talk went surprisingly smoothly. My deck--a brand new version created specifically for PASS--helped me get across the message I wanted to communicate, my demos ran without any failure, and my jokes didn't drive too many people out of the room before the end of the talk. I even received a round of applause when I managed to take a 26 minute query plan and, using a few query rewrites, deliver the same exact data in 9 seconds. That, I have to say, was pretty cool.

Here's the abstract for the session:

Query Tuning Mastery: The Art and Science of Manhandling Parallelism
As a database developer, your job boils down to one word: performance. In today's multi-core-driven world, query performance is very much determined by how well you're taking advantage of the processing power at your disposal. Are your big queries using every clock tick, or are they lagging behind? And if your queries are already parallel, can they be rewritten for even greater speed?

In this session, you'll learn to take full advantage of SQL Server query parallelism. After a terminology review and technology refresher, the session will go deep, covering T-SQL patterns that allow certain queries to scale almost linearly across your multi-core CPUs. You'll see when and why the optimizer makes a parallel plan choice and how to impact the decision. Along the way, you’ll manipulate costs and row goals, challenge generally accepted tuning practices, and take complete control of your parallel queries.

Since the talk was being broadcast live on "PASS TV," I had Paul White join me at the front of the room to moderate questions delivered via Twitter. This worked out reasonably well and I hope to do something similar in the future. Huge thanks to Paul for helping out -- and for giving me a really ugly scowl when one of my jokes fell totally flat.

Demos for the talk are attached. Let me know if you have any questions.

Thanks again to everyone who watched, either in person or at home. I had a blast. Hope you enjoyed it even half as much as I did!

PASS Summit 2010 Post-Conference Seminar on Parallel Processing

Adam Machanic — Wed, 04 Aug 2010 16:37:00 GMT

I am honored to have been selected for a second year in a row to present a full-day seminar at the PASS Summit. This year's seminar will be a "post-con", and will be delivered on Friday, November 12.

The title of the seminar is "A Day of Doing Many Things at Once: Multitasking, Parallelism, and Process Distribution," and the focus is on maximizing performance by taking full advantage of your server's CPU infrastructure.

As IT professionals we're all used to the ever-increasing nature of server resources, but things have changed over the past few years. Next-generation server hardware is shipping with more CPU power, but in the form of more CPUs rather than faster CPUs. This means that we can no longer expect that new hardware will automatically make all of our existing processes faster and better; we need to understand how to tune our software to properly leverage these resources.

A one-paragraph abstract and registration information is available here.

What follows is a basic outline of what will be covered over the course of the day. Feel free to leave me a comment below if you have any questions about the seminar and what will or will not be included. My goal is to deliver a seminar that will give you a number of useful tools and techniques that you can take back to the office and immediately apply, and I think that the list below encompasses the majority of what you'll see as you work with parallel processing in currently shipping versions of SQL Server.

Part 1: Background
A Brief History Lesson
CPU Evolution Over Time
Heat and Dissipation
A Brief Theory Lesson
Moore's Law
Amdahl's Law
Gustafson's Law
How This All Fits Together
Windows Process/Thread Internals
SQL Server Scheduler Internals

Part 2: Query Processor Parallelism
How Queries are Processed in Parallel
Parallel Iterators
Non-Parallel Iterators
Row Distribution Strategies
How to Read and Mine Data From Parallel Query Plans
Controlling Parallelism at the Query Level
Ideal Parallel Query Patterns
Parallelism Inhibitors and Workarounds
Part 3: Administration
Server Settings that Influence Parallelism
Affinity Masks
Worker Threads
MAXDOP
Cost Threshold
Resource Governor
How to Configure Server Settings
OLTP vs. OLAP vs. Mixed Workload Considerations
Monitoring Parallel Processes
Parallel Task Architecture and the Tasks DMV
Parallel Waits and the Waiting Tasks DMV
CXPACKET
LATCH_EX
Finding Out How Much Work is Being Done
Finding Parallel and Serial Plans in the Cache
Diagnosing Intra-Query Parallel Deadlocks

Part 4: Alternative Solutions for Parallel Data Processing
Service Broker
SSIS
SQLCLR

Looking forward to seeing many of you in Seattle!

PASS Performance Virtual Chapter: Parallelize Your Queries!

Adam Machanic — Mon, 02 Aug 2010 15:51:00 GMT

Last month a new PASS Virtual Chapter was introduced, one with a theme that is near and dear to much of what I like to work on: performance. Tomorrow, Tuesday August 3rd at noon Eastern time, the chapter will have its second meeting, and I will be doing the presentation. The topic is Parallelism and Performance. Here's the abstract:

In today's multi-core-driven world, query performance is very much determined by how well you're taking advantage of the processing power at your disposal. Are your big queries using every available clock tick, or are they lagging behind? And if your queries are already going parallel, can they be rewritten for even greater speed? In this session you will learn the background necessary to take full advantage of parallelism. We'll cover what parallelism is, why it's important, and the basics of how to read parallel query plans. Examples will be shown to illustrate some of the huge performance gains that can be had when we learn to properly control SQL Server's parallel processing capabilities. This session is a small preview of some of the material that will be covered in Adam Machanic's full-day PASS Summit post-con, "A Day of Doing Many Things at Once."

This is a free webcast. Click here for more information and to register.

Looking forward to seeing you there (well, virtually speaking).