Linux perf and uprobes for tracing and profiling Oracle workloads. 
Author: [email protected]
January 2016

See details at:
http://externaltable.blogspot.com/2016/02/linux-perf-probes-for-oracle-tracing.html

----
Selected examples:

Probes on the wait event interface:

# export ORACLE_HOME=/u01/app/oracle/product/11.2.0.4/rdbms

# perf probe -x $ORACLE_HOME/bin/oracle kskthewt timestamp=%di event=%si
# perf probe -x $ORACLE_HOME/bin/oracle kskthbwt timestamp=%si event=%dx
# perf probe -x $ORACLE_HOME/bin/oracle kews_update_wait_time wait_time=%si event=%r13

# perf record -e probe_oracle:kews_update_wait_time -e probe_oracle:kskthbwt -e probe_oracle:kskthewt -p <pid>
<ctrl-c> to stop gathering data
# perf script

Probe on SQL hard parsing:

# perf probe -x $ORACLE_HOME/bin/oracle opiprs length=%dx sql='+0(%si)':"string"
# perf record -e probe_oracle:opiprs -p <pid> 
# perf script

----
Note a workaround is needed for Oracle 12c when using Perf on recent kernels. The workaround is simple and consists in tracing the next instruction (for example kskthewt+2 instead of kskthewt), see [Oracle12_and_Perf](https://mahmoudhatem.wordpress.com/2017/03/22/workaround-for-linux-perf-probes-issue-for-oracle-tracing/)