mon: adjust or decay laggy probabilities on osd boot

On each osd boot, determine whether the osd was laggy (wrongly marked down)
or newly booted.  Either update the laggy probability and interval or
decay the values, as appropriate.

Signed-off-by: Sage Weil <sage@inktank.com>

diff --git a/src/mon/OSDMonitor.cc b/src/mon/OSDMonitor.cc
index 21e4e6588f4ef8b55f0932aee18262a37e001a35..d44873a5d0eb6d381167a5b4d0bab481e460617b 100644 (file)
--- a/src/mon/OSDMonitor.cc
+++ b/src/mon/OSDMonitor.cc
@@ -886,6 +886,21 @@ bool OSDMonitor::prepare_boot(MOSDBoot *m)
       pending_inc.new_last_clean_interval[from] = pair<epoch_t,epoch_t>(begin, end);
     }
 
+    osd_xinfo_t xi = osdmap.get_xinfo(from);
+    if (m->boot_epoch == 0) {
+      xi.laggy_probability = xi.laggy_probability / 3;
+      xi.laggy_interval = xi.laggy_interval / 3;
+      dout(10) << " not laggy, new xi " << xi << dendl;
+    } else {
+      if (xi.down_stamp.sec()) {
+       int interval = ceph_clock_now(g_ceph_context).sec() - xi.down_stamp.sec();
+       xi.laggy_interval = (xi.laggy_interval * 2 + interval) / 3;
+      }
+      xi.laggy_probability = ((long long)xi.laggy_probability * 2ull + 0xffffffffull) / 3;
+      dout(10) << " laggy, now xi " << xi << dendl;
+    }
+    pending_inc.new_xinfo[from] = xi;
+
     // wait
     paxos->wait_for_commit(new C_Booted(this, m));
   }