add property "rocksdb.obsolete-sst-files-size" (facebook#11533)

Summary: See "unreleased_history/new_features/obsolete_sst_files_size.md" for description Pull Request resolved: facebook#11533 Test Plan: updated unit test Reviewed By: jowlyzhang Differential Revision: D46703152 Pulled By: ajkr fbshipit-source-id: ea5e31cd6293eccc154130c13e66b5271f57c102
wxing1292 · Jun 13, 2023 · cac3240 · cac3240
1 parent e178f9e
commit cac3240
Show file tree

Hide file tree

Showing 9 changed files with 70 additions and 4 deletions.
diff --git a/db/db_impl/db_impl.h b/db/db_impl/db_impl.h
@@ -811,6 +811,8 @@ class DBImpl : public DB {
   // being deleted.
   uint64_t MinObsoleteSstNumberToKeep();
 
+  uint64_t GetObsoleteSstFilesSize();
+
   // Returns the list of live files in 'live' and the list
   // of all files in the filesystem in 'candidate_files'.
   // If force == false and the last call was less than

diff --git a/db/db_impl/db_impl_files.cc b/db/db_impl/db_impl_files.cc
@@ -35,6 +35,11 @@ uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
   return std::numeric_limits<uint64_t>::max();
 }
 
+uint64_t DBImpl::GetObsoleteSstFilesSize() {
+  mutex_.AssertHeld();
+  return versions_->GetObsoleteSstFilesSize();
+}
+
 Status DBImpl::DisableFileDeletions() {
   Status s;
   int my_disable_delete_obsolete_files;

diff --git a/db/db_properties_test.cc b/db/db_properties_test.cc
@@ -1715,14 +1715,35 @@ TEST_F(DBPropertiesTest, SstFilesSize) {
     ASSERT_OK(Delete("key" + std::to_string(i)));
   }
   ASSERT_OK(Flush());
+
   uint64_t sst_size;
-  bool ok = db_->GetIntProperty(DB::Properties::kTotalSstFilesSize, &sst_size);
-  ASSERT_TRUE(ok);
+  ASSERT_TRUE(
+      db_->GetIntProperty(DB::Properties::kTotalSstFilesSize, &sst_size));
   ASSERT_GT(sst_size, 0);
   listener->size_before_compaction = sst_size;
+
+  uint64_t obsolete_sst_size;
+  ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kObsoleteSstFilesSize,
+                                  &obsolete_sst_size));
+  ASSERT_EQ(obsolete_sst_size, 0);
+
+  // Hold files from being deleted so we can test property for size of obsolete
+  // SST files.
+  ASSERT_OK(db_->DisableFileDeletions());
+
   // Compact to clean all keys and trigger listener.
   ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
   ASSERT_TRUE(listener->callback_triggered);
+
+  ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kObsoleteSstFilesSize,
+                                  &obsolete_sst_size));
+  ASSERT_EQ(obsolete_sst_size, sst_size);
+
+  // Let the obsolete files be deleted.
+  ASSERT_OK(db_->EnableFileDeletions());
+  ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kObsoleteSstFilesSize,
+                                  &obsolete_sst_size));
+  ASSERT_EQ(obsolete_sst_size, 0);
 }
 
 TEST_F(DBPropertiesTest, MinObsoleteSstNumberToKeep) {

diff --git a/db/internal_stats.cc b/db/internal_stats.cc
@@ -291,6 +291,7 @@ static const std::string min_obsolete_sst_number_to_keep_str =
 static const std::string base_level_str = "base-level";
 static const std::string total_sst_files_size = "total-sst-files-size";
 static const std::string live_sst_files_size = "live-sst-files-size";
+static const std::string obsolete_sst_files_size = "obsolete-sst-files-size";
 static const std::string live_sst_files_size_at_temperature =
     "live-sst-files-size-at-temperature";
 static const std::string estimate_pending_comp_bytes =
@@ -394,6 +395,8 @@ const std::string DB::Properties::kTotalSstFilesSize =
     rocksdb_prefix + total_sst_files_size;
 const std::string DB::Properties::kLiveSstFilesSize =
     rocksdb_prefix + live_sst_files_size;
+const std::string DB::Properties::kObsoleteSstFilesSize =
+    rocksdb_prefix + obsolete_sst_files_size;
 const std::string DB::Properties::kBaseLevel = rocksdb_prefix + base_level_str;
 const std::string DB::Properties::kEstimatePendingCompactionBytes =
     rocksdb_prefix + estimate_pending_comp_bytes;
@@ -565,6 +568,9 @@ const UnorderedMap<std::string, DBPropertyInfo>
         {DB::Properties::kLiveSstFilesSizeAtTemperature,
          {false, &InternalStats::HandleLiveSstFilesSizeAtTemperature, nullptr,
           nullptr, nullptr}},
+        {DB::Properties::kObsoleteSstFilesSize,
+         {false, nullptr, &InternalStats::HandleObsoleteSstFilesSize, nullptr,
+          nullptr}},
         {DB::Properties::kEstimatePendingCompactionBytes,
          {false, nullptr, &InternalStats::HandleEstimatePendingCompactionBytes,
           nullptr, nullptr}},
@@ -1395,6 +1401,12 @@ bool InternalStats::HandleLiveSstFilesSize(uint64_t* value, DBImpl* /*db*/,
   return true;
 }
 
+bool InternalStats::HandleObsoleteSstFilesSize(uint64_t* value, DBImpl* db,
+                                               Version* /*version*/) {
+  *value = db->GetObsoleteSstFilesSize();
+  return true;
+}
+
 bool InternalStats::HandleEstimatePendingCompactionBytes(uint64_t* value,
                                                          DBImpl* /*db*/,
                                                          Version* /*version*/) {

diff --git a/db/internal_stats.h b/db/internal_stats.h
@@ -819,6 +819,8 @@ class InternalStats {
   bool HandleBaseLevel(uint64_t* value, DBImpl* db, Version* version);
   bool HandleTotalSstFilesSize(uint64_t* value, DBImpl* db, Version* version);
   bool HandleLiveSstFilesSize(uint64_t* value, DBImpl* db, Version* version);
+  bool HandleObsoleteSstFilesSize(uint64_t* value, DBImpl* db,
+                                  Version* version);
   bool HandleEstimatePendingCompactionBytes(uint64_t* value, DBImpl* db,
                                             Version* version);
   bool HandleEstimateTableReadersMem(uint64_t* value, DBImpl* db,

diff --git a/db/version_set.cc b/db/version_set.cc
@@ -7003,6 +7003,16 @@ void VersionSet::GetObsoleteFiles(std::vector<ObsoleteFileInfo>* files,
   obsolete_manifests_.swap(*manifest_filenames);
 }
 
+uint64_t VersionSet::GetObsoleteSstFilesSize() const {
+  uint64_t ret = 0;
+  for (auto& f : obsolete_files_) {
+    if (f.metadata != nullptr) {
+      ret += f.metadata->fd.GetFileSize();
+    }
+  }
+  return ret;
+}
+
 ColumnFamilyData* VersionSet::CreateColumnFamily(
     const ColumnFamilyOptions& cf_options, const ReadOptions& read_options,
     const VersionEdit* edit) {

diff --git a/db/version_set.h b/db/version_set.h
@@ -1466,6 +1466,9 @@ class VersionSet {
                         std::vector<std::string>* manifest_filenames,
                         uint64_t min_pending_output);
 
+  // REQUIRES: DB mutex held
+  uint64_t GetObsoleteSstFilesSize() const;
+
   ColumnFamilySet* GetColumnFamilySet() { return column_family_set_.get(); }
 
   const UnorderedMap<uint32_t, size_t>& GetRunningColumnFamiliesTimestampSize()

diff --git a/include/rocksdb/db.h b/include/rocksdb/db.h
@@ -1097,14 +1097,23 @@ class DB {
     static const std::string kMinObsoleteSstNumberToKeep;
 
     //  "rocksdb.total-sst-files-size" - returns total size (bytes) of all SST
-    //      files.
+    //      files belonging to any of the CF's versions.
     //  WARNING: may slow down online queries if there are too many files.
     static const std::string kTotalSstFilesSize;
 
     //  "rocksdb.live-sst-files-size" - returns total size (bytes) of all SST
-    //      files belong to the latest LSM tree.
+    //      files belong to the CF's current version.
     static const std::string kLiveSstFilesSize;
 
+    //  "rocksdb.obsolete-sst-files-size" - returns total size (bytes) of all
+    //      SST files that became obsolete but have not yet been deleted or
+    //      scheduled for deletion. SST files can end up in this state when
+    //      using `DisableFileDeletions()`, for example.
+    //
+    //      N.B. Unlike the other "*SstFilesSize" properties, this property
+    //      includes SST files that originated in any of the DB's CFs.
+    static const std::string kObsoleteSstFilesSize;
+
     // "rocksdb.live_sst_files_size_at_temperature" - returns total size (bytes)
     //      of SST files at all certain file temperature
     static const std::string kLiveSstFilesSizeAtTemperature;
@@ -1238,6 +1247,7 @@ class DB {
   //  "rocksdb.min-obsolete-sst-number-to-keep"
   //  "rocksdb.total-sst-files-size"
   //  "rocksdb.live-sst-files-size"
+  //  "rocksdb.obsolete-sst-files-size"
   //  "rocksdb.base-level"
   //  "rocksdb.estimate-pending-compaction-bytes"
   //  "rocksdb.num-running-compactions"

diff --git a/unreleased_history/new_features/obsolete_sst_files_size.md b/unreleased_history/new_features/obsolete_sst_files_size.md
@@ -0,0 +1 @@
+Added new property "rocksdb.obsolete-sst-files-size-property" that reports the size of SST files that have become obsolete but have not yet been deleted or scheduled for deletion
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Added new property "rocksdb.obsolete-sst-files-size-property" that reports the size of SST files that have become obsolete but have not yet been deleted or scheduled for deletion