Hi Alban,
On Friday 16 December 2016 05:44 PM, Alban Crequy wrote:
Hi,
Currently, there is no trivial mechanism to analyze events based on
containers. perf -G can be used, but it will not filter events for the
containers created after perf is invoked, making it difficult to assess/
analyze performance issues of multiple containers at once.
This patch-set overcomes this limitation by using cgroup identifier as
container unique identifier. A new PERF_RECORD_NAMESPACES event that
records namespaces related info is introduced, from which the cgroup
namespace's device & inode numbers are used as cgroup identifier. This
is based on the assumption that each container is created with it's own
cgroup namespace allowing assessment/analysis of multiple containers
using cgroup identifier.
The first patch introduces PERF_RECORD_NAMESPACES in kernel while the
second patch makes the corresponding changes in perf tool to read this
PERF_RECORD_NAMESPACES events. The third patch adds a cgroup identifier
column in perf report, which contains the cgroup namespace's device and
inode numbers.
I have a question for the pid namespace: does the new perf event gives
the pid namespace of the task, or the pid_ns_for_children from the
nsproxy? From my limited understanding, v4 seems to do the former, as
opposed to v3.
Ah! How did I miss that?!
When synthesizing events from /proc/$PID/ns/pid, it cannot take the
pid_ns_for_children, so I wanted to make sure it is consistent.
So, eventually this version sounds like the right way of doing it..?
Thanks
Hari
_______________________________________________
Containers mailing list
Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/containers
