osd: osd_mon_report_interval_min -> osd_mon_report_interval, kill _max

The _max isn't used.  Drop the _min suffix.

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

diff --git a/PendingReleaseNotes b/PendingReleaseNotes
index 4f1d6e417838799b7836179bf4a204c53e68bcd2..3661008bbdcefd2ab9431af9f92c73088284a5e0 100644 (file)
--- a/PendingReleaseNotes
+++ b/PendingReleaseNotes
@@ -109,3 +109,12 @@ method. See http://docs.ceph.com/docs/luminous/mgr/restful for details.
   now reflects the source of each config option (e.g., default, config file,
   command line) as well as the final (active) value.
 
+13.0.3
+------
+
+* The ``osd_mon_report_interval_min`` option has been renamed to
+  ``osd_mon_report_interval``, and the ``osd_mon_report_interval_max``
+  (unused) has been eliminated.  If this value has been customized on
+  your cluster then your configuration should be adjusted in order to
+  avoid reverting to the default value.
+

diff --git a/doc/rados/configuration/mon-osd-interaction.rst b/doc/rados/configuration/mon-osd-interaction.rst
index e335ff070587ce9ed5aea0e181d81f5a28d84ecb..e2c24771481489ca733149b25279952267d02a5f 100644 (file)
--- a/doc/rados/configuration/mon-osd-interaction.rst
+++ b/doc/rados/configuration/mon-osd-interaction.rst
@@ -154,7 +154,7 @@ consider the Ceph OSD Daemon ``down`` after the  ``mon osd report timeout``
 elapses. A Ceph OSD Daemon sends a report to a Ceph Monitor when a reportable
 event such as a failure, a change in placement group stats, a change in
 ``up_thru`` or when it boots within 5 seconds. You can change the Ceph OSD
-Daemon minimum report interval by adding an ``osd mon report interval min``
+Daemon minimum report interval by adding an ``osd mon report interval``
 setting under the ``[osd]`` section of your Ceph configuration file, or by
 setting the value at runtime. A Ceph OSD Daemon sends a report to a Ceph
 Monitor every 120 seconds irrespective of whether any notable changes occur.
@@ -379,24 +379,14 @@ OSD Settings
 :Default: ``30``
 
 
-``osd mon report interval max``
+``osd mon report interval``
 
-:Description: The maximum time in seconds that a Ceph OSD Daemon can wait before
-              it must report to a Ceph Monitor.
-
-:Type: 32-bit Integer
-:Default: ``120``
-
-
-``osd mon report interval min``
-
-:Description: The minimum number of seconds a Ceph OSD Daemon may wait
+:Description: The number of seconds a Ceph OSD Daemon may wait
               from startup or another reportable event before reporting
               to a Ceph Monitor.
 
 :Type: 32-bit Integer
 :Default: ``5``
-:Valid Range: Should be less than ``osd mon report interval max``
 
 
 ``osd mon ack timeout``

diff --git a/qa/suites/fs/basic_functional/tasks/mds-full.yaml b/qa/suites/fs/basic_functional/tasks/mds-full.yaml
index eab120590bcfdf762818f70dc8fea272c3703a6f..7e57dc6b124926ce7bbdf29c99d9ed157179d5d1 100644 (file)
--- a/qa/suites/fs/basic_functional/tasks/mds-full.yaml
+++ b/qa/suites/fs/basic_functional/tasks/mds-full.yaml
@@ -18,7 +18,7 @@ overrides:
         mon osd backfillfull ratio: 0.6
         mon osd full ratio: 0.7
       osd:
-        osd mon report interval max: 5
+        osd mon report interval: 5
         osd objectstore: memstore
         osd failsafe full ratio: 1.0
         memstore device bytes: 200000000

diff --git a/qa/suites/kcephfs/recovery/tasks/mds-full.yaml b/qa/suites/kcephfs/recovery/tasks/mds-full.yaml
index 77a0a83e5eb266ee4a00a2a2beba825edf28f254..e9744e7199e582a90b552d3fd77f083fcdda0e0b 100644 (file)
--- a/qa/suites/kcephfs/recovery/tasks/mds-full.yaml
+++ b/qa/suites/kcephfs/recovery/tasks/mds-full.yaml
@@ -18,7 +18,7 @@ overrides:
         mon osd backfillfull ratio: 0.6
         mon osd full ratio: 0.7
       osd:
-        osd mon report interval max: 5
+        osd mon report interval: 5
         osd objectstore: memstore
         osd failsafe full ratio: 1.0
         memstore device bytes: 200000000

diff --git a/qa/tasks/ceph_manager.py b/qa/tasks/ceph_manager.py
index 5407873a669ddbde8e135242483e470d2449ed53..4042f1cf47be41b7d529e78a5e4899159c6f76e9 100644 (file)
--- a/qa/tasks/ceph_manager.py
+++ b/qa/tasks/ceph_manager.py
@@ -1384,7 +1384,7 @@ class CephManager:
         assert False
 
     def wait_for_pg_stats(func):
-        # both osd_mon_report_interval_min and mgr_stats_period are 5 seconds
+        # both osd_mon_report_interval and mgr_stats_period are 5 seconds
         # by default, and take the faulty injection in ms into consideration,
         # 12 seconds are more than enough
         delays = [1, 1, 2, 3, 5, 8, 13]

diff --git a/qa/tasks/cephfs/test_full.py b/qa/tasks/cephfs/test_full.py
index 9395612e48f44cdf94da8f2680bcf2ac987a3336..24a5b67c9440f43487dbeb3e5d8c7d5753ef9c50 100644 (file)
--- a/qa/tasks/cephfs/test_full.py
+++ b/qa/tasks/cephfs/test_full.py
@@ -134,7 +134,7 @@ class FullnessTestCase(CephFSTestCase):
                           the failed write.
         """
 
-        osd_mon_report_interval_max = int(self.fs.get_config("osd_mon_report_interval_max", service_type='osd'))
+        osd_mon_report_interval = int(self.fs.get_config("osd_mon_report_inverval", service_type='osd'))
 
         log.info("Writing {0}MB should fill this cluster".format(self.fill_mb))
 
@@ -149,7 +149,7 @@ class FullnessTestCase(CephFSTestCase):
         else:
             log.info("Writing file B succeeded (full status will happen soon)")
             self.wait_until_true(lambda: self.is_full(),
-                                 timeout=osd_mon_report_interval_max * 5)
+                                 timeout=osd_mon_report_interval * 5)
 
         # Attempting to write more data should give me ENOSPC
         with self.assertRaises(CommandFailedError) as ar:
@@ -184,7 +184,7 @@ class FullnessTestCase(CephFSTestCase):
         # * The MDS to purge the stray folder and execute object deletions
         #  * The OSDs to inform the mon that they are no longer full
         self.wait_until_true(lambda: not self.is_full(),
-                             timeout=osd_mon_report_interval_max * 5)
+                             timeout=osd_mon_report_interval * 5)
 
         # Wait for the MDS to see the latest OSD map so that it will reliably
         # be applying the free space policy
@@ -212,7 +212,7 @@ class FullnessTestCase(CephFSTestCase):
         file_path = os.path.join(self.mount_a.mountpoint, "full_test_file")
 
         # Enough to trip the full flag
-        osd_mon_report_interval_max = int(self.fs.get_config("osd_mon_report_interval_max", service_type='osd'))
+        osd_mon_report_interval = int(self.fs.get_config("osd_mon_report_interval", service_type='osd'))
         mon_tick_interval = int(self.fs.get_config("mon_tick_interval", service_type="mon"))
 
         # Sufficient data to cause RADOS cluster to go 'full'
@@ -222,13 +222,13 @@ class FullnessTestCase(CephFSTestCase):
         # (report_interval for mon to learn PG stats, tick interval for it to update OSD map,
         #  factor of 1.5 for I/O + network latency in committing OSD map and distributing it
         #  to the OSDs)
-        full_wait = (osd_mon_report_interval_max + mon_tick_interval) * 1.5
+        full_wait = (osd_mon_report_interval + mon_tick_interval) * 1.5
 
         # Configs for this test should bring this setting down in order to
         # run reasonably quickly
-        if osd_mon_report_interval_max > 10:
+        if osd_mon_report_interval > 10:
             log.warn("This test may run rather slowly unless you decrease"
-                     "osd_mon_report_interval_max (5 is a good setting)!")
+                     "osd_mon_report_interval (5 is a good setting)!")
 
         self.mount_a.run_python(template.format(
             fill_mb=self.fill_mb,

diff --git a/qa/tasks/vstart_runner.py b/qa/tasks/vstart_runner.py
index 15428080f0d6eb6f6685cf7fe0ab6dede23248e3..048376f5acf8fe70199cdbddc15bbb8b3cc41fc6 100644 (file)
--- a/qa/tasks/vstart_runner.py
+++ b/qa/tasks/vstart_runner.py
@@ -954,8 +954,8 @@ def exec_test():
 
     # For the benefit of polling tests like test_full -- in teuthology land we set this
     # in a .yaml, here it's just a hardcoded thing for the developer's pleasure.
-    remote.run(args=[os.path.join(BIN_PREFIX, "ceph"), "tell", "osd.*", "injectargs", "--osd-mon-report-interval-max", "5"])
-    ceph_cluster.set_ceph_conf("osd", "osd_mon_report_interval_max", "5")
+    remote.run(args=[os.path.join(BIN_PREFIX, "ceph"), "tell", "osd.*", "injectargs", "--osd-mon-report-interval", "5"])
+    ceph_cluster.set_ceph_conf("osd", "osd_mon_report_interval", "5")
 
     # Vstart defaults to two segments, which very easily gets a "behind on trimming" health warning
     # from normal IO latency.  Increase it for running teests.

diff --git a/src/common/legacy_config_opts.h b/src/common/legacy_config_opts.h
index a491ec7616815347435608d112fbf751072d1fbd..18b2058a90118f35aa091f06815f1c6d5a846e23 100644 (file)
--- a/src/common/legacy_config_opts.h
+++ b/src/common/legacy_config_opts.h
@@ -699,8 +699,7 @@ OPTION(osd_max_trimming_pgs, OPT_U64)
 OPTION(osd_heartbeat_min_healthy_ratio, OPT_FLOAT)
 
 OPTION(osd_mon_heartbeat_interval, OPT_INT)  // (seconds) how often to ping monitor if no peers
-OPTION(osd_mon_report_interval_max, OPT_INT)
-OPTION(osd_mon_report_interval_min, OPT_INT)  // pg stats, failures, up_thru, boot.
+OPTION(osd_mon_report_interval, OPT_INT)  // failures, up_thru, boot.
 OPTION(osd_mon_report_max_in_flight, OPT_INT)  // max updates in flight
 OPTION(osd_beacon_report_interval, OPT_INT)       // (second) how often to send beacon message to monitor
 OPTION(osd_pg_stat_report_interval_max, OPT_INT)  // report pg stats for any given pg at least this often

diff --git a/src/common/options.cc b/src/common/options.cc
index 3da6dd7bfa584ab7106bd47ed7cd6f3b54110faa..6b880ea0ab9f72084379a3b5ec18e35f0b4574d1 100644 (file)
--- a/src/common/options.cc
+++ b/src/common/options.cc
@@ -2912,13 +2912,9 @@ std::vector<Option> get_global_options() {
     .set_default(30)
     .set_description(""),
 
-    Option("osd_mon_report_interval_max", Option::TYPE_INT, Option::LEVEL_ADVANCED)
-    .set_default(600)
-    .set_description(""),
-
-    Option("osd_mon_report_interval_min", Option::TYPE_INT, Option::LEVEL_ADVANCED)
+    Option("osd_mon_report_interval", Option::TYPE_INT, Option::LEVEL_ADVANCED)
     .set_default(5)
-    .set_description(""),
+    .set_description("Frequency of OSD reports to mon for peer failures, fullness status changes"),
 
     Option("osd_mon_report_max_in_flight", Option::TYPE_INT, Option::LEVEL_ADVANCED)
     .set_default(2)

diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc
index 73921cfbc3515308b1e3e84e62b93ed9f8507a2c..b4e33c0f2b079d5ad4e21c00b0786a2542c9c385 100644 (file)
--- a/src/osd/OSD.cc
+++ b/src/osd/OSD.cc
@@ -4963,7 +4963,7 @@ void OSD::tick_without_osd_lock()
     // mon report?
     utime_t now = ceph_clock_now();
     if (service.need_fullness_update() ||
-       now - last_mon_report > cct->_conf->osd_mon_report_interval_min) {
+       now - last_mon_report > cct->_conf->osd_mon_report_interval) {
       last_mon_report = now;
       send_full_update();
       send_failures();

diff --git a/src/test/test_lost.sh b/src/test/test_lost.sh
index 43959bb887d596ff9452993d914e760e625787e0..d8246b27327b6f3243ac7976dc5d3a9cae5f2f7d 100755 (executable)
--- a/src/test/test_lost.sh
+++ b/src/test/test_lost.sh
@@ -223,8 +223,7 @@ all_osds_die_impl() {
 }
 
 all_osds_die() {
-       setup 3 'osd mon report interval max = 60
-       osd mon report interval min = 3
+       setup 3 'osd mon report interval = 3
        mon osd report timeout = 60'
 
        all_osds_die_impl