Capture number of snapshots created per day as a metric

apps/spark/src/main/java/com/linkedin/openhouse/jobs/util/TableStatsCollectorUtil.java

@@ -4,7 +4,12 @@
 
 import com.linkedin.openhouse.common.stats.model.IcebergTableStats;
 import java.io.IOException;
+import java.text.SimpleDateFormat;
+import java.util.Date;
+import java.util.LinkedHashMap;
+import java.util.Map;
 import java.util.Optional;
+import java.util.stream.Collectors;
 import java.util.stream.StreamSupport;
 import lombok.extern.slf4j.Slf4j;
 import org.apache.hadoop.fs.FileSystem;
@@ -114,16 +119,42 @@ protected static IcebergTableStats populateStatsForSnapshots(
             .min(Long::compareTo)
             .orElse(null);
 
+    Map<String, Long> snapshotCountByDay =
+        getSnapShotDistributionPerDay(table, spark, MetadataTableType.SNAPSHOTS);
+
     return stats
         .toBuilder()
         .currentSnapshotId(currentSnapshotId)
         .currentSnapshotTimestamp(currentSnapshotTimestamp)
         .oldestSnapshotTimestamp(oldestSnapshotTimestamp)
         .numCurrentSnapshotReferencedDataFiles(countOfDataFiles)
         .totalCurrentSnapshotReferencedDataFilesSizeInBytes(sumOfFileSizeBytes)
+        .snapshotCountByDay(snapshotCountByDay)
         .build();
   }
 
+  /** Get snapshot distribution for a given table by date. */
+  private static Map<String, Long> getSnapshotDistributionPerDay(
+      Table table, SparkSession spark, MetadataTableType metadataTableType) {
+    Dataset<Row> snapShotDistribution =
+        SparkTableUtil.loadMetadataTable(spark, table, metadataTableType)
+            .selectExpr(new String[] {"snapshot_id", "committed_at"})
+            .dropDuplicates("snapshot_id", "committed_at");
+
+    Map<String, Long> snapshotCountByDay =
+        snapShotDistribution.collectAsList().stream()
+            .collect(
+                Collectors.toMap(
+                    row -> {
+                      SimpleDateFormat formatter = new SimpleDateFormat("yyyy-MM-dd");
+                      return formatter.format(new Date(row.getTimestamp(1).getTime()));
+                    },
+                    row -> 1L,
+                    Long::sum,
+                    LinkedHashMap::new));
+    return snapshotCountByDay;
+  }
+
   /**
    * Collect storage stats for a given fully-qualified table name.
    *

apps/spark/src/test/java/com/linkedin/openhouse/jobs/spark/OperationsTest.java

@@ -9,9 +9,12 @@
 import com.linkedin.openhouse.tables.client.model.Retention;
 import com.linkedin.openhouse.tablestest.OpenHouseSparkITest;
 import io.opentelemetry.api.metrics.Meter;
+import java.text.SimpleDateFormat;
 import java.util.ArrayList;
+import java.util.Date;
 import java.util.List;
 import java.util.Map;
+import java.util.concurrent.atomic.AtomicLong;
 import java.util.function.BiFunction;
 import java.util.stream.Collectors;
 import lombok.extern.slf4j.Slf4j;
@@ -566,6 +569,18 @@ public void testCollectTableStats() throws Exception {
               + stats.getNumExistingMetadataJsonFiles()
               + stats.getNumReferencedManifestFiles()
               + stats.getNumReferencedManifestLists());
+      AtomicLong snapShotCount = new AtomicLong();
+
+      table
+          .snapshots()
+          .forEach(
+              snapshot -> {
+                snapShotCount.getAndIncrement();
+              });
+
+      SimpleDateFormat formatter = new SimpleDateFormat("yyyy-MM-dd");
+      Assertions.assertEquals(
+          stats.getSnapshotCountByDay().get(formatter.format(new Date())), snapShotCount.get());
     }
   }
 

services/common/src/main/java/com/linkedin/openhouse/common/stats/model/IcebergTableStats.java

@@ -1,5 +1,6 @@
 package com.linkedin.openhouse.common.stats.model;
 
+import java.util.Map;
 import lombok.AllArgsConstructor;
 import lombok.Getter;
 import lombok.NoArgsConstructor;
@@ -35,4 +36,6 @@ public class IcebergTableStats extends BaseTableMetadata {
   private Long numReferencedManifestFiles;
 
   private Long numReferencedManifestLists;
+
+  private Map<String, Long> snapshotCountByDay;
 }