mon/osdmonitor: fix incorrect output of "osd df" due to osd out

If an osd is automatically marked as out, the output of "osd df"
is not right, as follow:

-5 10.00999        -  5586G  2989G  2596G     0    0     host ceph192-9-9-8
11  0.90999  1.00000   931G   542G   388G 58.25 0.99         osd.11
14  0.90999  1.00000   931G   530G   400G 56.97 0.97         osd.14
20  0.90999  1.00000   931G   716G   214G 76.99 1.31         osd.20
22  0.90999  1.00000   931G   477G   453G 51.29 0.87         osd.22
26  0.90999        0      0      0      0     0    0         osd.26
28  0.90999  1.00000   931G   587G   343G 63.09 1.07         osd.28
30  0.90999  1.00000   931G   602G   328G 64.75 1.10         osd.30
16  0.90999  1.00000   931G   589G   341G 63.34 1.08         osd.16
18  0.90999  1.00000   931G   530G   400G 56.93 0.97         osd.18
24  0.90999  1.00000   931G   202G   728G 21.77 0.37         osd.24
32  0.90999  1.00000   931G   477G   454G 51.23 0.87         osd.32

Two problems are identified from the above output:

1. the total capacity(total, total used, total avial)
only includes osd.32, osd.24, osd.18, osd.16, osd.30, osd.28, and other
healthy osds such as osd.11, osd.14 etc. are excluded.

2. the average utilization/deviation are forced resetted.

Fixes: http://tracker.ceph.com/issues/16706
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>

diff --git a/src/mon/OSDMonitor.cc b/src/mon/OSDMonitor.cc
index 0b6237554b76acf3335630d55e6f821c8f15c90d..d65e20f7d0c611f1833e2a0a502db5604962509a 100644 (file)
--- a/src/mon/OSDMonitor.cc
+++ b/src/mon/OSDMonitor.cc
@@ -808,8 +808,15 @@ protected:
 
   bool get_bucket_utilization(int id, int64_t* kb, int64_t* kb_used,
                              int64_t* kb_avail) const {
-    if (id >= 0)
+    if (id >= 0) {
+      if (osdmap->is_out(id)) {
+        *kb = 0;
+        *kb_used = 0;
+        *kb_avail = 0;
+        return true;
+      }
       return get_osd_utilization(id, kb, kb_used, kb_avail);
+    }
 
     *kb = 0;
     *kb_used = 0;