Remove inline values support (facebook#14270)

mszeszko-meta · meta-codesync[bot] · commit 6b5ccbbec6ba · 2026-01-28T16:08:10.000-08:00
Summary: Pull Request resolved: facebook#14270 Legacy BlobDB's inline values feature (storing small values directly in the LSM tree via `min_blob_size` threshold) is unused in production - all deployments use `min_blob_size = 0`. This removes the functionality entirely. Changes: - Remove `min_blob_size` from `BlobDBOptions` - Remove `IsInlined()` check from compaction filter (dead code path) - Remove inline-related statistics (`BLOB_DB_WRITE_INLINED*`) - Remove `InlineSmallValues` test - Update stale comments referencing inlined data Reviewed By: xingbowang Differential Revision: D91088985 fbshipit-source-id: ec67848ece1a7dc071ca8e8a17faebb435394733
diff --git a/db_stress_tool/db_stress_common.h b/db_stress_tool/db_stress_common.h
@@ -297,7 +297,6 @@ DECLARE_uint32(occ_lock_bucket_count);
 
 // Options for StackableDB-based BlobDB
 DECLARE_bool(use_blob_db);
-DECLARE_uint64(blob_db_min_blob_size);
 DECLARE_uint64(blob_db_bytes_per_sync);
 DECLARE_uint64(blob_db_file_size);
 DECLARE_bool(blob_db_enable_gc);
diff --git a/db_stress_tool/db_stress_gflags.cc b/db_stress_tool/db_stress_gflags.cc
@@ -425,12 +425,6 @@ DEFINE_bool(enable_write_thread_adaptive_yield,
 // Options for StackableDB-based BlobDB
 DEFINE_bool(use_blob_db, false, "[Stacked BlobDB] Use BlobDB.");
 
-DEFINE_uint64(
-    blob_db_min_blob_size,
-    ROCKSDB_NAMESPACE::blob_db::BlobDBOptions().min_blob_size,
-    "[Stacked BlobDB] Smallest blob to store in a file. Blobs "
-    "smaller than this will be inlined with the key in the LSM tree.");
-
 DEFINE_uint64(
     blob_db_bytes_per_sync,
     ROCKSDB_NAMESPACE::blob_db::BlobDBOptions().bytes_per_sync,
diff --git a/db_stress_tool/db_stress_test_base.cc b/db_stress_tool/db_stress_test_base.cc
@@ -3844,7 +3844,6 @@ void StressTest::Open(SharedState* shared, bool reopen) {
         // StackableDB-based BlobDB
         if (FLAGS_use_blob_db) {
           blob_db::BlobDBOptions blob_db_options;
-          blob_db_options.min_blob_size = FLAGS_blob_db_min_blob_size;
           blob_db_options.bytes_per_sync = FLAGS_blob_db_bytes_per_sync;
           blob_db_options.blob_file_size = FLAGS_blob_db_file_size;
           blob_db_options.enable_garbage_collection = FLAGS_blob_db_enable_gc;
diff --git a/include/rocksdb/statistics.h b/include/rocksdb/statistics.h
@@ -326,12 +326,12 @@ enum Tickers : uint32_t {
   // # of bytes (keys + value) read from BlobDB. Only applicable to legacy
   // BlobDB.
   BLOB_DB_BYTES_READ,
-  // # of keys written by BlobDB as non-TTL inlined value. Only applicable to
-  // legacy BlobDB.
-  BLOB_DB_WRITE_INLINED,
-  // # of keys written by BlobDB as TTL inlined value. Only applicable to legacy
-  // BlobDB.
-  BLOB_DB_WRITE_INLINED_TTL,
+  // Deprecated: min_blob_size is no longer configurable. Retained to avoid
+  // shifting enum values.
+  BLOB_DB_WRITE_INLINED_DEPRECATED,
+  // Deprecated: min_blob_size is no longer configurable. Retained to avoid
+  // shifting enum values.
+  BLOB_DB_WRITE_INLINED_TTL_DEPRECATED,
   // # of keys written by BlobDB as non-TTL blob value. Only applicable to
   // legacy BlobDB.
   BLOB_DB_WRITE_BLOB,
diff --git a/java/rocksjni/portal.h b/java/rocksjni/portal.h
@@ -5101,9 +5101,9 @@ class TickerTypeJni {
         return -0x1;
       case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_BYTES_READ:
         return -0x2;
-      case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED:
+      case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_DEPRECATED:
         return -0x3;
-      case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_TTL:
+      case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_TTL_DEPRECATED:
         return -0x4;
       case ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_BLOB:
         return -0x5;
@@ -5594,9 +5594,9 @@ class TickerTypeJni {
       case -0x2:
         return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_BYTES_READ;
       case -0x3:
-        return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED;
+        return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_DEPRECATED;
       case -0x4:
-        return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_TTL;
+        return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_INLINED_TTL_DEPRECATED;
       case -0x5:
         return ROCKSDB_NAMESPACE::Tickers::BLOB_DB_WRITE_BLOB;
       case -0x6:
diff --git a/java/src/main/java/org/rocksdb/TickerType.java b/java/src/main/java/org/rocksdb/TickerType.java
@@ -550,14 +550,14 @@ public enum TickerType {
     BLOB_DB_BYTES_READ((byte) -0x2),
 
     /**
-     * # of keys written by BlobDB as non-TTL inlined value.
+     * Deprecated and unused. Retained to avoid shifting enum values.
      */
-    BLOB_DB_WRITE_INLINED((byte) -0x3),
+    @Deprecated BLOB_DB_WRITE_INLINED((byte) -0x3),
 
     /**
-     * # of keys written by BlobDB as TTL inlined value.
+     * Deprecated and unused. Retained to avoid shifting enum values.
      */
-    BLOB_DB_WRITE_INLINED_TTL((byte) -0x4),
+    @Deprecated BLOB_DB_WRITE_INLINED_TTL((byte) -0x4),
 
     /**
      * # of keys written by BlobDB as non-TTL blob value.
diff --git a/monitoring/statistics.cc b/monitoring/statistics.cc
@@ -169,8 +169,8 @@ const std::vector<std::pair<Tickers, std::string>> TickersNameMap = {
     {BLOB_DB_NUM_KEYS_READ, "rocksdb.blobdb.num.keys.read"},
     {BLOB_DB_BYTES_WRITTEN, "rocksdb.blobdb.bytes.written"},
     {BLOB_DB_BYTES_READ, "rocksdb.blobdb.bytes.read"},
-    {BLOB_DB_WRITE_INLINED, "rocksdb.blobdb.write.inlined"},
-    {BLOB_DB_WRITE_INLINED_TTL, "rocksdb.blobdb.write.inlined.ttl"},
+    {BLOB_DB_WRITE_INLINED_DEPRECATED, "rocksdb.blobdb.write.inlined"},
+    {BLOB_DB_WRITE_INLINED_TTL_DEPRECATED, "rocksdb.blobdb.write.inlined.ttl"},
     {BLOB_DB_WRITE_BLOB, "rocksdb.blobdb.write.blob"},
     {BLOB_DB_WRITE_BLOB_TTL, "rocksdb.blobdb.write.blob.ttl"},
     {BLOB_DB_BLOB_FILE_BYTES_WRITTEN, "rocksdb.blobdb.blob.file.bytes.written"},
diff --git a/tools/db_bench_tool.cc b/tools/db_bench_tool.cc
@@ -1069,12 +1069,6 @@ DEFINE_uint64(
     ROCKSDB_NAMESPACE::blob_db::BlobDBOptions().ttl_range_secs,
     "[Stacked BlobDB] TTL bucket size to use when creating blob files.");
 
-DEFINE_uint64(
-    blob_db_min_blob_size,
-    ROCKSDB_NAMESPACE::blob_db::BlobDBOptions().min_blob_size,
-    "[Stacked BlobDB] Smallest blob to store in a file. Blobs "
-    "smaller than this will be inlined with the key in the LSM tree.");
-
 DEFINE_uint64(blob_db_bytes_per_sync,
               ROCKSDB_NAMESPACE::blob_db::BlobDBOptions().bytes_per_sync,
               "[Stacked BlobDB] Bytes to sync blob file at.");
@@ -5190,7 +5184,6 @@ class Benchmark {
       blob_db_options.garbage_collection_cutoff = FLAGS_blob_db_gc_cutoff;
       blob_db_options.max_db_size = FLAGS_blob_db_max_db_size;
       blob_db_options.ttl_range_secs = FLAGS_blob_db_ttl_range_secs;
-      blob_db_options.min_blob_size = FLAGS_blob_db_min_blob_size;
       blob_db_options.bytes_per_sync = FLAGS_blob_db_bytes_per_sync;
       blob_db_options.blob_file_size = FLAGS_blob_db_file_size;
       blob_db::BlobDB* ptr = nullptr;
diff --git a/utilities/blob_db/blob_compaction_filter.cc b/utilities/blob_db/blob_compaction_filter.cc
@@ -32,7 +32,7 @@ CompactionFilter::Decision BlobIndexCompactionFilterBase::FilterV2(
     if (ucf == nullptr) {
       return Decision::kKeep;
     }
-    // Apply user compaction filter for inlined data.
+    // Apply user compaction filter for non-blob data.
     CompactionFilter::Decision decision =
         ucf->FilterV2(level, key, value_type, value, new_value, skip_until);
     if (decision == Decision::kChangeValue) {
@@ -52,8 +52,7 @@ CompactionFilter::Decision BlobIndexCompactionFilterBase::FilterV2(
     expired_size_ += key.size() + value.size();
     return Decision::kRemove;
   }
-  if (!blob_index.IsInlined() &&
-      blob_index.file_number() < context_.next_file_number &&
+  if (blob_index.file_number() < context_.next_file_number &&
       context_.current_blob_files.count(blob_index.file_number()) == 0) {
     evicted_count_++;
     evicted_size_ += key.size() + value.size();
@@ -88,13 +87,6 @@ CompactionFilter::Decision BlobIndexCompactionFilterBase::FilterV2(
 
 CompactionFilter::Decision BlobIndexCompactionFilterBase::HandleValueChange(
     const Slice& key, std::string* new_value) const {
-  BlobDBImpl* const blob_db_impl = context_.blob_db_impl;
-  assert(blob_db_impl);
-
-  if (new_value->size() < blob_db_impl->bdb_options_.min_blob_size) {
-    // Keep new_value inlined.
-    return Decision::kChangeValue;
-  }
   if (!OpenNewBlobFileIfNeeded()) {
     return Decision::kIOError;
   }
@@ -295,12 +287,6 @@ CompactionFilter::BlobDecision BlobIndexCompactionFilterGC::PrepareBlobOutput(
     return BlobDecision::kCorruption;
   }
 
-  if (blob_index.IsInlined()) {
-    gc_stats_.AddBlob(blob_index.value().size());
-
-    return BlobDecision::kKeep;
-  }
-
   gc_stats_.AddBlob(blob_index.size());
 
   if (blob_index.HasTTL()) {
diff --git a/utilities/blob_db/blob_db.cc b/utilities/blob_db/blob_db.cc
@@ -80,9 +80,6 @@ void BlobDBOptions::Dump(Logger* log) const {
   ROCKS_LOG_HEADER(
       log, "                            BlobDBOptions.ttl_range_secs: %" PRIu64,
       ttl_range_secs);
-  ROCKS_LOG_HEADER(
-      log, "                             BlobDBOptions.min_blob_size: %" PRIu64,
-      min_blob_size);
   ROCKS_LOG_HEADER(
       log, "                            BlobDBOptions.bytes_per_sync: %" PRIu64,
       bytes_per_sync);
diff --git a/utilities/blob_db/blob_db.h b/utilities/blob_db/blob_db.h
@@ -48,10 +48,6 @@ struct BlobDBOptions {
   // and so on
   uint64_t ttl_range_secs = 3600;
 
-  // The smallest value to store in blob log. Values smaller than this threshold
-  // will be inlined in base DB together with the key.
-  uint64_t min_blob_size = 0;
-
   // Allows OS to incrementally sync blob files to disk for every
   // bytes_per_sync bytes written. Users shouldn't rely on it for
   // persistency guarantee.
diff --git a/utilities/blob_db/blob_db_impl.cc b/utilities/blob_db/blob_db_impl.cc
@@ -1071,69 +1071,54 @@ Status BlobDBImpl::PutBlobValue(const WriteOptions& write_options,
                                 const Slice& key, const Slice& value,
                                 uint64_t expiration, WriteBatch* batch) {
   write_mutex_.AssertHeld();
-  Status s;
-  std::string index_entry;
-  uint32_t column_family_id =
-      static_cast_with_check<ColumnFamilyHandleImpl>(DefaultColumnFamily())
-          ->GetID();
-  if (value.size() < bdb_options_.min_blob_size) {
-    if (expiration == kNoExpiration) {
-      // Put as normal value
-      s = batch->Put(key, value);
-      RecordTick(statistics_, BLOB_DB_WRITE_INLINED);
-    } else {
-      // Inlined with TTL
-      BlobIndex::EncodeInlinedTTL(&index_entry, expiration, value);
-      s = WriteBatchInternal::PutBlobIndex(batch, column_family_id, key,
-                                           index_entry);
-      RecordTick(statistics_, BLOB_DB_WRITE_INLINED_TTL);
-    }
-  } else {
-    std::string headerbuf;
-    BlobLogWriter::ConstructBlobHeader(&headerbuf, key, value, expiration);
+  std::string headerbuf;
+  BlobLogWriter::ConstructBlobHeader(&headerbuf, key, value, expiration);
 
-    // Check DB size limit before selecting blob file.
-    s = CheckDbSizeLimit(headerbuf.size() + key.size() + value.size());
-    if (!s.ok()) {
-      return s;
-    }
+  // Check DB size limit before selecting blob file.
+  Status s = CheckDbSizeLimit(headerbuf.size() + key.size() + value.size());
+  if (!s.ok()) {
+    return s;
+  }
 
-    std::shared_ptr<BlobFile> blob_file;
+  std::shared_ptr<BlobFile> blob_file;
+  if (expiration != kNoExpiration) {
+    s = SelectBlobFileTTL(write_options, expiration, &blob_file);
+  } else {
+    s = SelectBlobFile(write_options, &blob_file);
+  }
+  std::string index_entry;
+  if (s.ok()) {
+    assert(blob_file != nullptr);
+    s = AppendBlob(write_options, blob_file, headerbuf, key, value, expiration,
+                   &index_entry);
+  }
+  if (s.ok()) {
     if (expiration != kNoExpiration) {
-      s = SelectBlobFileTTL(write_options, expiration, &blob_file);
-    } else {
-      s = SelectBlobFile(write_options, &blob_file);
-    }
-    if (s.ok()) {
-      assert(blob_file != nullptr);
-      s = AppendBlob(write_options, blob_file, headerbuf, key, value,
-                     expiration, &index_entry);
-    }
-    if (s.ok()) {
-      if (expiration != kNoExpiration) {
-        WriteLock file_lock(&blob_file->mutex_);
-        blob_file->ExtendExpirationRange(expiration);
-      }
-      s = CloseBlobFileIfNeeded(write_options, blob_file);
-    }
-    if (s.ok()) {
-      s = WriteBatchInternal::PutBlobIndex(batch, column_family_id, key,
-                                           index_entry);
+      WriteLock file_lock(&blob_file->mutex_);
+      blob_file->ExtendExpirationRange(expiration);
     }
-    if (s.ok()) {
-      if (expiration == kNoExpiration) {
-        RecordTick(statistics_, BLOB_DB_WRITE_BLOB);
-      } else {
-        RecordTick(statistics_, BLOB_DB_WRITE_BLOB_TTL);
-      }
+    s = CloseBlobFileIfNeeded(write_options, blob_file);
+  }
+  if (s.ok()) {
+    const uint32_t column_family_id =
+        static_cast_with_check<ColumnFamilyHandleImpl>(DefaultColumnFamily())
+            ->GetID();
+    s = WriteBatchInternal::PutBlobIndex(batch, column_family_id, key,
+                                         index_entry);
+  }
+  if (s.ok()) {
+    if (expiration == kNoExpiration) {
+      RecordTick(statistics_, BLOB_DB_WRITE_BLOB);
     } else {
-      ROCKS_LOG_ERROR(
-          db_options_.info_log,
-          "Failed to append blob to FILE: %s: KEY: %s VALSZ: %" ROCKSDB_PRIszt
-          " status: '%s' blob_file: '%s'",
-          blob_file->PathName().c_str(), key.ToString().c_str(), value.size(),
-          s.ToString().c_str(), blob_file->DumpState().c_str());
+      RecordTick(statistics_, BLOB_DB_WRITE_BLOB_TTL);
     }
+  } else {
+    ROCKS_LOG_ERROR(
+        db_options_.info_log,
+        "Failed to append blob to FILE: %s: KEY: %s VALSZ: %" ROCKSDB_PRIszt
+        " status: '%s' blob_file: '%s'",
+        blob_file->PathName().c_str(), key.ToString().c_str(), value.size(),
+        s.ToString().c_str(), blob_file->DumpState().c_str());
   }
 
   RecordTick(statistics_, BLOB_DB_NUM_KEYS_WRITTEN);
@@ -1366,13 +1351,6 @@ Status BlobDBImpl::GetBlobValue(const Slice& key, const Slice& index_entry,
     }
   }
 
-  if (blob_index.IsInlined()) {
-    // TODO(yiwu): If index_entry is a PinnableSlice, we can also pin the same
-    // memory buffer to avoid extra copy.
-    value->PinSelf(blob_index.value());
-    return Status::OK();
-  }
-
   return GetRawBlobFromFile(key, blob_index.file_number(), blob_index.offset(),
                             blob_index.size(), value);
 }
diff --git a/utilities/blob_db/blob_db_test.cc b/utilities/blob_db/blob_db_test.cc
