osd: add osd_fast_shutdown option (default true)

qa/suites/fs/verify/validater/valgrind.yaml

@@ -17,6 +17,8 @@ overrides:
         mds heartbeat grace: 60
       mon:
         mon osd crush smoke test: false
+      osd:
+        osd fast shutdown: false
     valgrind:
       mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes]
       osd: [--tool=memcheck]

qa/suites/rados/singleton-flat/valgrind-leaks.yaml

@@ -23,6 +23,8 @@ overrides:
         osd max object namespace len: 64
       mon:
         mon osd crush smoke test: false
+      osd:
+        osd fast shutdown: false
     valgrind:
       mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes]
       osd: [--tool=memcheck]

qa/suites/rados/verify/validater/valgrind.yaml

@@ -13,6 +13,8 @@ overrides:
         debug refs: 5
       mon:
         mon osd crush smoke test: false
+      osd:
+        osd fast shutdown: false
     log-whitelist:
       - overall HEALTH_
 # valgrind is slow.. we might get PGs stuck peering etc

qa/suites/rgw/multisite/valgrind.yaml

@@ -11,6 +11,8 @@ overrides:
         osd heartbeat grace: 40
       mon:
         mon osd crush smoke test: false
+      osd:
+        osd fast shutdown: false
     valgrind:
       mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes]
       osd: [--tool=memcheck]

qa/suites/rgw/verify/validater/valgrind.yaml

@@ -12,6 +12,8 @@ overrides:
         osd heartbeat grace: 40
       mon:
         mon osd crush smoke test: false
+      osd:
+        osd fast shutdown: false
     valgrind:
       mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes]
       osd: [--tool=memcheck]

src/common/legacy_config_opts.h

@@ -764,6 +764,7 @@ OPTION(osd_op_history_slow_op_size, OPT_U32)           // Max number of slow ops
 OPTION(osd_op_history_slow_op_threshold, OPT_DOUBLE) // track the op if over this threshold
 OPTION(osd_target_transaction_size, OPT_INT)     // to adjust various transactions that batch smaller items
 OPTION(osd_failsafe_full_ratio, OPT_FLOAT) // what % full makes an OSD "full" (failsafe)
+OPTION(osd_fast_shutdown, OPT_BOOL)
 OPTION(osd_fast_fail_on_connection_refused, OPT_BOOL) // immediately mark OSDs as down once they refuse to accept connections
 
 OPTION(osd_pg_object_context_cache_count, OPT_INT)

src/common/options.cc

@@ -3498,6 +3498,11 @@ std::vector<Option> get_global_options() {
     .set_default(.97)
     .set_description(""),
 
+    Option("osd_fast_shutdown", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
+    .set_default(true)
+    .set_description("Fast, immediate shutdown")
+    .set_long_description("Setting this to false makes the OSD do a slower teardown of all state when it receives a SIGINT or SIGTERM or when shutting down for any other reason.  That slow shutdown is primarilyy useful for doing memory leak checking with valgrind."),
+
     Option("osd_fast_fail_on_connection_refused", Option::TYPE_BOOL, Option::LEVEL_ADVANCED)
     .set_default(true)
     .set_description(""),

src/osd/OSD.cc

@@ -4016,6 +4016,12 @@ void OSD::create_recoverystate_perf()
 
 int OSD::shutdown()
 {
+  if (cct->_conf->osd_fast_shutdown) {
+    derr << "*** Immediate shutdown (osd_fast_shutdown=true) ***" << dendl;
+    cct->_log->flush();
+    _exit(0);
+  }
+
   if (!service.prepare_to_stop())
     return 0; // already shutting down
   osd_lock.lock();

src/vstart.sh

@@ -710,6 +710,7 @@ $DAEMONOPTS
         osd class dir = $OBJCLASS_PATH
         osd class load list = *
         osd class default list = *
+        osd fast shutdown = false
 
         filestore wbthrottle xfs ios start flusher = 10
         filestore wbthrottle xfs ios hard limit = 20