Split etcd_stats_interval out of etcd_report_interval

docs/config/src/osd.yml

@@ -2,15 +2,28 @@
   type: sec
   default: 5
   info: |
-    Interval at which OSDs report their state to etcd. Affects OSD lease time
+    Interval at which OSDs report their liveness to etcd. Affects OSD lease time
     and thus the failover speed. Lease time is equal to this parameter value
     plus max_etcd_attempts * etcd_quick_timeout because it should be guaranteed
     that every OSD always refreshes its lease in time.
   info_ru: |
-    Интервал, с которым OSD обновляет своё состояние в etcd. Значение параметра
-    влияет на время резервации (lease) OSD и поэтому на скорость переключения
+    Интервал, с которым OSD сообщает о том, что жив, в etcd. Значение параметра
+    влияет на время резервации (lease) OSD и поэтому - на скорость переключения
     при падении OSD. Время lease равняется значению этого параметра плюс
     max_etcd_attempts * etcd_quick_timeout.
+- name: etcd_stats_interval
+  type: sec
+  default: 30
+  info: |
+    Interval at which OSDs report their statistics to etcd. Highly affects the
+    imposed load on etcd, because statistics include a key for every OSD and
+    for every PG. At the same time, low statistic intervals make `vitastor-cli`
+    statistics more responsive.
+  info_ru: |
+    Интервал, с которым OSD обновляет свою статистику в etcd. Сильно влияет на
+    создаваемую нагрузку на etcd, потому что статистика содержит по ключу на
+    каждый OSD и на каждую PG. В то же время низкий интервал делает
+    статистику, печатаемую `vitastor-cli`, отзывчивей.
 - name: run_primary
   type: bool
   default: true

mon/mon.js

@@ -99,6 +99,7 @@ const etcd_tree = {
             etcd_ws_keepalive_interval: 30, // seconds
             // osd
             etcd_report_interval: 5, // seconds
+            etcd_stats_interval: 30, // seconds
             run_primary: true,
             osd_network: null, // "192.168.7.0/24" or an array of masks
             bind_address: "0.0.0.0",

src/osd.cpp

@@ -160,6 +160,9 @@ void osd_t::parse_config(bool init)
         etcd_report_interval = config["etcd_report_interval"].uint64_value();
         if (etcd_report_interval <= 0)
             etcd_report_interval = 5;
+        etcd_stats_interval = config["etcd_stats_interval"].uint64_value();
+        if (etcd_stats_interval <= 0)
+            etcd_stats_interval = 30;
         readonly = json_is_true(config["readonly"]);
         run_primary = !json_is_false(config["run_primary"]);
         allow_test_ops = json_is_true(config["allow_test_ops"]);

src/osd.h

@@ -93,6 +93,7 @@ class osd_t
 
     json11::Json::object cli_config, file_config, etcd_global_config, etcd_osd_config, config;
     int etcd_report_interval = 5;
+    int etcd_stats_interval = 30;
 
     bool readonly = false;
     osd_num_t osd_num = 1; // OSD numbers start with 1

src/osd_cluster.cpp

@@ -429,14 +429,18 @@ void osd_t::acquire_lease()
         create_osd_state();
     });
     printf(
-        "[OSD %lu] reporting to etcd at %s every %d seconds\n", this->osd_num,
+        "[OSD %lu] reporting to etcd at %s every %d seconds (statistics every %d seconds)\n", this->osd_num,
         (config["etcd_address"].is_string() ? config["etcd_address"].string_value() : config["etcd_address"].dump()).c_str(),
-        etcd_report_interval
+        etcd_report_interval, etcd_stats_interval
     );
     tfd->set_timer(etcd_report_interval*1000, true, [this](int timer_id)
     {
         renew_lease(false);
     });
+    tfd->set_timer(etcd_stats_interval*1000, true, [this](int timer_id)
+    {
+        report_statistics();
+    });
 }
 
 // Report "up" state once, then keep it alive using the lease
@@ -541,7 +545,6 @@ void osd_t::renew_lease(bool reload)
         else
         {
             etcd_failed_attempts = 0;
-            report_statistics();
             // Reload PGs
             if (reload && run_primary)
             {

tests/run_3osds.sh

@@ -18,10 +18,10 @@ else
 fi
 
 if [ "$IMMEDIATE_COMMIT" != "" ]; then
-    NO_SAME="--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024 --disable_data_fsync 1 --immediate_commit all --log_level 10"
+    NO_SAME="--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024 --disable_data_fsync 1 --immediate_commit all --log_level 10 --etcd_stats_interval 5"
     $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"osd_out_time":1,"immediate_commit":"all","client_enable_writeback":true}'
 else
-    NO_SAME="--journal_sector_buffer_count 1024 --log_level 10"
+    NO_SAME="--journal_sector_buffer_count 1024 --log_level 10 --etcd_stats_interval 5"
     $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"osd_out_time":1,"client_enable_writeback":true}'
 fi
 

tests/test_move_reappear.sh

@@ -7,7 +7,7 @@ OSD_COUNT=5
 OSD_ARGS="$OSD_ARGS"
 for i in $(seq 1 $OSD_COUNT); do
     dd if=/dev/zero of=./testdata/test_osd$i.bin bs=1024 count=1 seek=$((OSD_SIZE*1024-1))
-    build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 $OSD_ARGS --etcd_address $ETCD_URL $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin 2>/dev/null) >>./testdata/osd$i.log 2>&1 &
+    build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 --etcd_stats_interval 5 $OSD_ARGS --etcd_address $ETCD_URL $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin 2>/dev/null) >>./testdata/osd$i.log 2>&1 &
     eval OSD${i}_PID=$!
 done