Optimize noisy kernel logs

Author: Caideyipi

iotdb-core/datanode/src/main/java/org/apache/iotdb/db/queryengine/plan/scheduler/FixedRateFragInsStateTracker.java

@@ -156,6 +156,11 @@ private void fetchStateAndUpdate() {
           if (metrics.reachMaxRetryCount()) {
             // if reach max retry count, we think that the DN is down, and FI in that node won't
             // exist
+            logger.warn(
+                "Failed to fetch state for FragmentInstance {} after {} retries, mark it as no such instance",
+                instance.getId(),
+                InstanceStateMetrics.MAX_STATE_FETCH_RETRY_COUNT,
+                e);
             FragmentInstanceInfo instanceInfo = new FragmentInstanceInfo(NO_SUCH_INSTANCE);
             instanceInfo.setMessage(
                 String.format(
@@ -165,7 +170,12 @@ private void fetchStateAndUpdate() {
           } else {
             // if not reaching max retry count, add retry count, and wait for next fetching schedule
             metrics.addRetryCount();
-            logger.warn(DataNodeQueryMessages.ERROR_HAPPENED_WHILE_FETCHING_QUERY_STATE, e);
+            logger.debug(
+                "Failed to fetch state for FragmentInstance {}, retry {}/{}",
+                instance.getId(),
+                metrics.retryCount,
+                InstanceStateMetrics.MAX_STATE_FETCH_RETRY_COUNT,
+                e);
           }
         }
       }

iotdb-core/datanode/src/main/java/org/apache/iotdb/db/storageengine/dataregion/compaction/schedule/CompactionScheduler.java

@@ -47,6 +47,8 @@
 import java.util.Collections;
 import java.util.List;
 import java.util.concurrent.Phaser;
+import java.util.concurrent.TimeUnit;
+import java.util.concurrent.atomic.AtomicLong;
 import java.util.concurrent.locks.ReadWriteLock;
 import java.util.concurrent.locks.ReentrantReadWriteLock;
 import java.util.stream.Collectors;
@@ -65,6 +67,9 @@ public class CompactionScheduler {
   private static final Logger LOGGER =
       LoggerFactory.getLogger(IoTDBConstant.COMPACTION_LOGGER_NAME);
   private static final IoTDBConfig config = IoTDBDescriptor.getInstance().getConfig();
+  private static final long DISK_SPACE_CHECK_FAIL_LOG_INTERVAL_MS = TimeUnit.MINUTES.toMillis(1);
+  private static final AtomicLong LAST_DISK_SPACE_CHECK_FAIL_LOG_TIME = new AtomicLong(0);
+  private static final AtomicLong SUPPRESSED_DISK_SPACE_CHECK_FAIL_LOG_COUNT = new AtomicLong(0);
 
   private CompactionScheduler() {}
 
@@ -207,13 +212,32 @@ private static boolean canAddTaskToWaitingQueue(AbstractCompactionTask task)
     }
     // check disk space
     if (!task.isDiskSpaceCheckPassed()) {
-      LOGGER.info(
-          "Compaction task start check failed because disk free ratio is less than disk_space_warning_threshold");
+      logDiskSpaceCheckFailure(task);
       return false;
     }
     return true;
   }
 
+  private static void logDiskSpaceCheckFailure(AbstractCompactionTask task) {
+    long now = System.currentTimeMillis();
+    long lastLogTime = LAST_DISK_SPACE_CHECK_FAIL_LOG_TIME.get();
+    if (now - lastLogTime >= DISK_SPACE_CHECK_FAIL_LOG_INTERVAL_MS
+        && LAST_DISK_SPACE_CHECK_FAIL_LOG_TIME.compareAndSet(lastLogTime, now)) {
+      long suppressedCount = SUPPRESSED_DISK_SPACE_CHECK_FAIL_LOG_COUNT.getAndSet(0);
+      LOGGER.info(
+          "Skip compaction task because disk free ratio is less than disk_space_warning_threshold, "
+              + "taskType={}, storageGroup={}, dataRegion={}, timePartition={}, processedFileNum={}, suppressedSimilarLogs={}",
+          task.getCompactionTaskType(),
+          task.getStorageGroupName(),
+          task.getDataRegionId(),
+          task.getTimePartition(),
+          task.getProcessedFileNum(),
+          suppressedCount);
+    } else {
+      SUPPRESSED_DISK_SPACE_CHECK_FAIL_LOG_COUNT.incrementAndGet();
+    }
+  }
+
   public static int scheduleInsertionCompaction(
       TsFileManager tsFileManager, long timePartition, CompactionScheduleContext context)
       throws InterruptedException {