Tanel Poder Blog

Here’s the High Performance Block IO on Linux hacking session video.

TL;DR Modern disks are so fast that system performance bottleneck shifts to RAM access and CPU.

Here’s a little SQL query that lists all Oracle wait events where Oracle kernel developers have added additional “human readable” descriptions.

FYI: I will be speaking about similar topics at P99Conf in Oct 2023 (online, free event) There are plenty of JVM profilers out there, but before attaching with a profiler, you can get a high-level overview by just sampling the Linux /proc/PID/comm and /pr…

Here’s a list of reasons why SELECT * is bad for SQL performance, assuming that your application doesn’t actually need all the columns.

In this post I will show you how to break down Linux system load by the load contributor or reason.

As I promised in the end of the last hacking session (about Oracle SQL Monitoring, I will run another one on 2.

Update: I have uploaded the videos to YouTube and embedded the playlist below.

When talking about Oracle background processes, there’s a term/qualifier “fatal” background process.

There was a discussion at Oracle-L about shared pool chunk eviction and I thought I’d show how to see a shared pool memory chunk’s position in the LRU list yourself.

As you may know, I like to use low tech scripts when possible, ideally such ones that don’t even require you to be root.

I hereby announce that I will retire in 2030 and replace myself with a computer!

My ASH wait chains scripts started returning the ORA-12850 error on Oracle 19c RAC installations: SQL> @ash/dash_wait_chains program2||event2 1=1 sysdate-1 sysdate -- Display ASH Wait Chain Signatures script v0.5 BETA by Tanel Poder ( https://tanelpoder.…

As running Oracle databases as (partially) managed services in the cloud has become quite popular, I thought to start a little series about troubleshooting Oracle (performance) stuff when not having OS access.

I have uploaded the 3-hour hacking session video into my YouTube channel in 2 parts.

As promised, I will run one more hacking session in the end of January.

If you use my TPT scripts for Oracle troubleshooting, I have some good news for you.

I have uploaded the 3 hour hacking session video about Oracle instance state objects and how to read Oracle systemstate dumps to my YouTube channel: Note that as I just uploaded the video, you may want to wait for a few hours until YouTube publishes HD ve…

Here’s a blog entry about some “new” Oracle execution plan displaying scripts that I’ve had since 2011 or so - I just tidied them up recently and added some improvements too.

This post is written mostly for fun, not for practical everyday usability (enjoy!).

I have created a new page & uploaded videos of my Linux Process Snapper hacking session: Resources Homepage: https://tp.dev/psnapper GitHub: https://github.com/tanelpoder/psnapper Videos Video 1: Exploring /proc Filesystem & System Calls Hacking Session V…

As I’m having fun preparing for my Linux troubleshooting training, I’ll also do another informal hacking session to give you an idea of what’s coming up!

I talked about a new diagnostic event wait_event[] back at OakTableWorld 2014.

As I’m delivering my Linux Troubleshooting training soon, I am going to blog about some typical issues and techniques we’ll troubleshoot in the class too.

As I announced last year, I’m running a new online Practical Linux Performance and Application Troubleshooting training class, starting on 29.

When I delivered my Advanced Oracle SQL Tuning training last week, I jumped into a free-form demo to show that the PARALLEL hints don’t really force anything other than adjusting the cost of parallelizable operations for CBO evaluation as usual.

Update: I wrote a follow-up article about adding Loop Counters and Row Counts to SQL Plan FlameGraphs.

The Oracle SQL Developer team has released version 18.3 of this tool.

I was recently involved in troubleshooting an interesting performance issue with some non-intuitive background process & wait event behavior.

It’s almost the beginning of September, time to get back to school, everyone!

Update: Starting from 2022, I am delivering all my classes in a new format, via my new Learning Platform.

I was recently involved in a discussion around why would a regular Oracle foreground session wait for the log file sequential read wait event.

I have uploaded my TPT-oracle scripts to GitHub and have formally open sourced them under Apache 2.0 license as well.

I have uploaded the the video of my Secret Hacking Session: Oracle X$TRACE, Wait Event Internals and Background Process Communication to my Oracle performance & troubleshooting Youtube channel.

Update: I unexpectedly ended up falling ill and decided to reschedule this hacking session to January 24, 10am PST.

A lot of people have asked me to do another run of my Oracle Troubleshooting training or at least get access to previous recordings – so I decided to geek out over the holiday period, update the material with latest stuff and run one more AOT class in 201…

We are running a “Gluent New World training month” in this July and have scheduled 3 webinars on following Wednesdays for this!

This Gluent New World webinar is based on my RAM is the new disk and how to measure its performance article series: RAM is the new disk – Introduction RAM is the new disk – tools for measuring CPU efficiency and RAM access RAM is the new disk – Columnar vs

Here are the two BIWA Summit 2016 presentations I delivered today.

If you haven’t read the previous parts of this series yet, here are the links: [ Part 1 | Part 2 ].

I have created a new youtube channel – and have uploaded some videos there already!

Here’s an updated presentation I first delivered at Hotsos Symposium 2015.

Here’s my latest OOW presentation – SQL Monitoring in Oracle Database 12c: [direct link] You can download all my scripts from /files/

It took a while (1.5 years since my last class – I’ve been busy!)

[ part 1 | part 2 | part 3 ] In the previous article I explained that the main requirement for high-speed in-memory data scanning is column-oriented storage format for in-memory data.

[ part 1 | part 2 | part 3 ] RAM is the new disk, at least in the In-Memory computing world.

Here’s the video of E4 keynote we delivered together with Kerry Osborne a few weeks ago.

I have some news, two items actually.

Vishal Desai systematically troubleshooted an interesting case where the initial symptoms of the problem showed a spike of enq: SQ – contention waits, but he dug deeper – and found the root cause to be quite different.

I’ve updated some of my ASH scripts to use these 4 arguments in a standard way: What ASH columns to display (and aggregate by) Which ASH rows to use for the report (filter) Time range start Time range end So this means whenever I run ashtop (or dashtop) f…