How to Get Debugging Symbols Working in Linux Perf Tool Inside Docker Containers

How do you get debugging symbols working in linux perf tool inside Docker containers?

Running the container with -v /:/host flag and running perf report in the container with --symfs /host flag fixes it:

 96.59%  a.out  a.out              [.] function
  2.93%  a.out  [kernel.kallsyms]  [k] 0xffffffff8105144a
  0.13%  a.out  [nvidia]           [k] 0x00000000002eda57
  0.11%  a.out  libc-2.19.so       [.] vfprintf
  0.11%  a.out  libc-2.19.so       [.] 0x0000000000049980
  0.09%  a.out  a.out              [.] main
  0.02%  a.out  libc-2.19.so       [.] _IO_file_write
  0.02%  a.out  libc-2.19.so       [.] write

Part of the reason why it doesn't work as is? The output from perf script sort of sheds some light on this:

...
           a.out    24 3374818.880960: cycles:  ffffffff81141140 __perf_event__output_id_sample ([kernel.kallsyms])
           a.out    24 3374818.881012: cycles:  ffffffff817319fd _raw_spin_lock_irqsave ([kernel.kallsyms])
           a.out    24 3374818.882217: cycles:  ffffffff8109aba3 ttwu_do_activate.constprop.75 ([kernel.kallsyms])
           a.out    24 3374818.884071: cycles:            40053d [unknown] (/var/lib/docker/aufs/diff/9bd2d4389cf7ad185405245b1f5c7d24d461bd565757880bfb4f970d3f4f7915/a.out)
           a.out    24 3374818.885329: cycles:            400544 [unknown] (/var/lib/docker/aufs/diff/9bd2d4389cf7ad185405245b1f5c7d24d461bd565757880bfb4f970d3f4f7915/a.out)
...

Note the /var/lib/docker/aufs path. That's from the host so it won't exist in the container and you need to help perf report to locate it. This likely happens because the mmap events are tracked by perf outside of any cgroup and perf does not attempt to remap the paths.

Another option is to run perf host-side, like sudo perf record -a docker run -ti <container name>. But the collection has to be system-wide here (the -a flag) as containers are spawned by docker daemon process which is not in the process hierarchy of the docker client tool we run here.

Using debug symbols with perf

You are using an old version of perf which do not support -g dwarf but only -g (without argument) i.e. it does not support DWARF unwinding.

Best way to test a custom kernel for hardware performance counters

I found a solution : KVM + QEMU emulator.

To use PMU, I changed this parameter in the VM parameters (XML format) :

<cpu mode='host-passthrough'/>

Or you can add this option in cmd line :

-cpu host

I followed in part this page for building the kernel on qemu and for the counters this page.

How to read instructions retired using the perf-interface inside a LKM?

The /proc/kallsyms file shows all kernel symbols defined in the source. Right, the capital T indicates a global symbol in the text section of the kernel binary, but the meaning of "global" here is according to the C language. That is, it can be used in other files of the kernel itself. You can't call a kernel function from a kernel module just because it's global.

Kernel modules can only use kernel symbols that are exported with EXPORT_SYMBOL in the kernel source code. Since kernel 2.6.0, none of the system calls are exported, so you can't call any of them from a kernel module, including sys_perf_event_open. System calls are really designed to be called from user space. What this all means is that you can't use the perf_event subsystem from within a kernel module.

That said, I think you can modify the kernel to add EXPORT_SYMBOL to sys_perf_event_open. That will make it an exported symbol, which means it can be used from a kernel module.

---

Related Topics