Oracle trace events hunting : Events annotations/Events Sniffing

Based on my previous blog posts :

• Oracle trace events hunting : dbgdChkEventIntV
• Oracle trace events hunting : Undocumented events/Filling the gaps
• Oracle trace events hunting : KST tracing/ X$TRACE

I created two files that can help us to quickly extract Events checked in specific oracle core function :

• oracle_function_to_event_mapping18c.txt
• oracle_function_to_event_mapping18c.sed

Using those files we can for example :

Oracle trace events hunting : KST tracing/ X$TRACE

This  is my third blog post about Oracle trace events hunting.For the previous one please check part1 and part2.

When we take a look at the TRACE event which is the Main event to control the UTS tracing  we notice that it have a memory option which mean activate the tracing in-memory (If possible)

Oracle trace events hunting : Undocumented events/Filling the gaps

In my last blog post Oracle trace events hunting : dbgdChkEventIntV i talked about how we can extract events that are checked in specific oracle core function by analyzing the arguments passed to dbgdChkEventIntV function. I used for that a mapping file called dbgdChkEventIntV_event_list.txt   (Basically mapping EventId to actual Event Name)

When we analyze the mapping file we observe something :

The different events seems to have a sequential Event ID  (stored in an array ?)  ! So what is stored in slot 1160002,116004 ,116007 etc ? Let’s check !

Oracle trace events hunting : dbgdChkEventIntV

Few days ago i published a blog post talking about write consistency & DML restart  . During my investigation i was interested in the function “dmltrace” and i noticed that this function was instrumented with the dbk*/dbg*  debug functions introduced in 11g.

The question is how to enable this tracing facility ?  Which events are checked by that function ?

We know how to extract the trace events number from the old ksdpec function (kernel service debug internal errors parser post event and check trigger condition using http://orafun.info/ of course 😀  ) thank to Dennis Yurichev see here and here. 

We also know how to extract it from dbkdChkEventRdbmsErr (DB kernel debug check event of RDBMS error) thanks to Yong Huang see here.

But here the function is instrumented differently !

Slow database startup and unified auditing

Few days ago i was notified of a very slow database startup time after someone installed a new application. Here is the result obtained in a clone environment  :

5 Min ! That’s great … let’s see what’s going on :

Write consistency and DML restart

Few weeks ago Tanel Poder published a great video talking about Oracle’s write consistency , DML restarts and demonstrating also how we can detect them.He also published a script that allow finding UPDATE/DELETE statements that hit the write consistency issue & have to restart under the hood. But as he stated it uses V$SQL_PLAN_MONITOR, so requires Diag+Tuning pack licenses.

The purpose of this blog post is to show another way to detect statements hitting the write consistency issue.