Merge pull request #28755 from dzafman/wip-network

feature: Health warnings on long network ping times, add "dump_osd_network" to get a report

Reviewed-by: Neha Ojha <nojha@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>

diff --cc doc/rados/configuration/mon-config-ref.rst
index a9152b73416cef362da2d5152b97b2737622301a,b167a8e1aef11c2980fef52d55db8dc1c25501af..e40b53ff96be07f650788c4dd8f7276ec188a545
--- 1/doc/rados/configuration/mon-config-ref.rst
--- 2/doc/rados/configuration/mon-config-ref.rst
+++ b/doc/rados/configuration/mon-config-ref.rst
@@@ -396,11 -389,29 +396,30 @@@ by setting it in the ``[mon]`` section 
                to figure out what's going wrong with clusters without the
                ``noout`` flag set but acting like that just the same, so we
                report a warning in this case.
 +
  :Type: Boolean
 -:Default: True
 +:Default: ``True``
  
  
+ ``mon warn on slow ping ratio``
+ 
+ :Description: Issue a ``HEALTH_WARN`` in cluster log if any heartbeat
+               between OSDs exceeds ``mon warn on slow ping ratio``
+               of ``osd heartbeat grace``.  The default is 5%.
+ :Type: Float
+ :Default: ``0.05``
+ 
+ 
+ ``mon warn on slow ping time``
+ 
+ :Description: Override ``mon warn on slow ping ratio`` with a specific value.
+               Issue a ``HEALTH_WARN`` in cluster log if any heartbeat
+               between OSDs exceeds ``mon warn on slow ping time``
+               milliseconds.  The default is 0 (disabled).
+ :Type: Integer
+ :Default: ``0``
+ 
+ 
  ``mon cache target full warn ratio``
  
  :Description: Position between pool's ``cache_target_full`` and

diff --cc src/common/options.cc
Simple merge

diff --cc src/mgr/DaemonServer.cc
Simple merge

diff --cc src/osd/OSD.cc
Simple merge

diff --cc src/osd/OSD.h
Simple merge

diff --cc src/osd/osd_types.cc
Simple merge

diff --cc src/osd/osd_types.h
Simple merge