[ceph] include bluefs db size in "osdfull" calculation (#983)

Closes: #973

Signed-off-by: Ponnuvel Palaniyappan <[email protected]>

hotsos/core/plugins/storage/ceph/cluster.py

@@ -656,6 +656,25 @@ def ssds_using_bcache(self):
 
         return sorted(ssd_osds_using_bcache)
 
+    @staticmethod
+    def _get_db_size_of_osd(osd_id):
+        """
+        Returns the bluefs DB size of the given OSD.
+        Returned size is in bytes.
+        """
+
+        report = CLIHelper().ceph_report_json_decoded()
+        if report:
+            for osd in report['osd_metadata']:
+                if osd['id'] == osd_id:
+                    try:
+                        return int(osd['bluefs_db_size'])
+                    except KeyError:
+                        # older versions do not output bluefs_db_size
+                        return 0
+
+        return 0
+
     @cached_property
     def osd_raw_usage_higher_than_data(self):
         _bad_osds = []
@@ -664,10 +683,12 @@ def osd_raw_usage_higher_than_data(self):
             return _bad_osds
 
         for osd in self.osd_df_tree['nodes']:
-            if osd['id'] >= 0:
+            osd_id = osd['id']
+            if osd_id >= 0:
                 raw_usage = osd['kb_used']
+                db_size_kb = self._get_db_size_of_osd(osd_id) / 1024.0
                 total_usage = osd['kb_used_data'] + osd['kb_used_omap'] + \
-                    osd['kb_used_meta']
+                    osd['kb_used_meta'] + db_size_kb
                 # There's always some additional space used by OSDs that's not
                 # by data/omap/meta for journaling, internal structures, etc.
                 # Thus we allow 5% discrepancy.

hotsos/defs/scenarios/storage/ceph/ceph-mon/osd_unusual_raw.yaml

@@ -9,9 +9,9 @@ conclusions:
     raises:
       type: CephOSDWarning
       message: >-
-        Found OSD(s) {bad_osds} with larger raw usage size than data+meta+omap
+        Found OSD(s) {bad_osds} with larger raw usage size than data+meta+omap+bluefs
         combined. While a discrepancy is to be expected due to Ceph using space
-        not accounted by data+meta+omap columns, usage is greater than {limit}%
+        not accounted by data+meta+omap+bluefs columns, usage is greater than {limit}%
         and likely indicates high discard ops sent to disk which is often
         the case for workloads with frequent rewrites.
 

hotsos/defs/tests/scenarios/storage/ceph/ceph-mon/osd_unusual_raw.yaml

@@ -115,9 +115,9 @@ data-root:
     - sos_commands/systemd/systemctl_list-unit-files
 raised-issues:
   CephOSDWarning: >-
-    Found OSD(s) osd.2 with larger raw usage size than data+meta+omap
+    Found OSD(s) osd.2 with larger raw usage size than data+meta+omap+bluefs
     combined. While a discrepancy is to be expected due to Ceph using space
-    not accounted by data+meta+omap columns, usage is greater than 5%
+    not accounted by data+meta+omap+bluefs columns, usage is greater than 5%
     and likely indicates high discard ops sent to disk which is often
     the case for workloads with frequent rewrites.