[PATCH] Remove logging every slow request details to monitors

 recent change https://tracker.ceph.com/issues/43975 was made to slow
 request logging to include detail on each operation in the cluster logs.
 With this change, detail for every slow request is always sent to the
 monitors and added to the cluster logs.

 This does not scale. Large, high-throughput clusters can overwhelm
 their monitors with spurious logs in the event of a performance issue.
 Disrupting the monitors can then cause further instability in the
 cluster.

 This SRU reverts the cluster logging of every slow request the osd is
 processing.

 The slow request clog change was added in nautilus (14.2.10) and
 octopus (15.2.0).

Signed-off-by: Gerald Yang <gerald.yang@canonical.com>
Gbp-Pq: Name disable-log-slow-requests.patch

diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc
index f580fb6f5645280c7357ade9585e2e64677f1340..7fed182a99db3e338bb3f0e4f2ef88ea556ee045 100644 (file)
--- a/src/osd/OSD.cc
+++ b/src/osd/OSD.cc
@@ -7758,7 +7758,6 @@ vector<DaemonHealthMetric> OSD::get_health_metrics()
            << " currently "
            << op.state_string();
         lgeneric_subdout(cct,osd,20) << ss.str() << dendl;
-        clog->warn() << ss.str();
        slow++;
        if (!oldest_op || op.get_initiated() < oldest_op->get_initiated()) {
          oldest_op = &op;