My Oracle Support Banner

AFD causing incorrect LoadAvg in Idle system (Doc ID 2420550.1)

Last updated on MARCH 23, 2020

Applies to:

Oracle Database - Enterprise Edition - Version to [Release 12.1 to 18]
Oracle Database Exadata Cloud Machine - Version N/A and later
Oracle Cloud Infrastructure - Database Service - Version N/A and later
Oracle Database Cloud Exadata Service - Version N/A and later
Oracle Database Exadata Express Cloud Service - Version N/A and later
Information in this document applies to any platform.


We stopped the cluster stack entirely via "crsctl stop crs" and then unloaded all oracleXXX drivers via rmmod. The load then reaches nearly zero. After inserting the module oracleafd via modprobe, the load increases to at least 1.0 without showing any CPU usage (neither user nor system).

afd_log goes into uninterruptable wait state causing incorrect load average


 [oracle@host1 ~]$ ps -efl | grep -E '^. D'
1 D root 2705 2 0 80 0 - 0 AfdgWa Apr06 ? 00:01:10 [afd_log]
1 D root 3070 2 0 80 0 - 0 KsWait Apr06 ? 00:01:10 [oks_plog]

 Stopped all crs resources disable crs auto start ,  After this restart the system .

 load average is 0.09 , 0.11 , 0.05 ----------->before starting oracleafd

After that loaded afd

#modprobe oracleafd
 load average is 1.01 ,0.87,0.49 ------------->after starting oracleafd





To view full details, sign in with your My Oracle Support account.

Don't have a My Oracle Support account? Click to get started!

In this Document

My Oracle Support provides customers with access to over a million knowledge articles and a vibrant support community of peers and Oracle experts.