@nxtedition/rocksdb 11.0.3 → 11.0.5

package/deps/rocksdb/rocksdb/db/write_batch.cc

@@ -929,15 +929,19 @@ Status WriteBatch::Put(ColumnFamilyHandle* column_family, const Slice& key,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::Put(this, cf_id, key, value);
+    s = WriteBatchInternal::Put(this, cf_id, key, value);
+  } else {
+    needs_in_place_update_ts_ = true;
+    has_key_with_ts_ = true;
+    std::string dummy_ts(ts_sz, '\0');
+    std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
+    s = WriteBatchInternal::Put(this, cf_id, SliceParts(key_with_ts.data(), 2),
+                                SliceParts(&value, 1));
   }
-
-  needs_in_place_update_ts_ = true;
-  has_key_with_ts_ = true;
-  std::string dummy_ts(ts_sz, '\0');
-  std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
-  return WriteBatchInternal::Put(this, cf_id, SliceParts(key_with_ts.data(), 2),
-                                 SliceParts(&value, 1));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts_sz);
+  }
+  return s;
 }
 
 Status WriteBatch::TimedPut(ColumnFamilyHandle* column_family, const Slice& key,
@@ -962,7 +966,7 @@ Status WriteBatch::TimedPut(ColumnFamilyHandle* column_family, const Slice& key,
 
 Status WriteBatch::Put(ColumnFamilyHandle* column_family, const Slice& key,
                        const Slice& ts, const Slice& value) {
-  const Status s = CheckColumnFamilyTimestampSize(column_family, ts);
+  Status s = CheckColumnFamilyTimestampSize(column_family, ts);
   if (!s.ok()) {
     return s;
   }
@@ -970,8 +974,12 @@ Status WriteBatch::Put(ColumnFamilyHandle* column_family, const Slice& key,
   assert(column_family);
   uint32_t cf_id = column_family->GetID();
   std::array<Slice, 2> key_with_ts{{key, ts}};
-  return WriteBatchInternal::Put(this, cf_id, SliceParts(key_with_ts.data(), 2),
-                                 SliceParts(&value, 1));
+  s = WriteBatchInternal::Put(this, cf_id, SliceParts(key_with_ts.data(), 2),
+                              SliceParts(&value, 1));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts.size());
+  }
+  return s;
 }
 
 Status WriteBatchInternal::CheckSlicePartsLength(const SliceParts& key,
@@ -1039,7 +1047,11 @@ Status WriteBatch::Put(ColumnFamilyHandle* column_family, const SliceParts& key,
   }
 
   if (ts_sz == 0) {
-    return WriteBatchInternal::Put(this, cf_id, key, value);
+    s = WriteBatchInternal::Put(this, cf_id, key, value);
+    if (s.ok()) {
+      MaybeTrackTimestampSize(cf_id, ts_sz);
+    }
+    return s;
   }
 
   return Status::InvalidArgument(
@@ -1246,20 +1258,24 @@ Status WriteBatch::Delete(ColumnFamilyHandle* column_family, const Slice& key) {
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::Delete(this, cf_id, key);
+    s = WriteBatchInternal::Delete(this, cf_id, key);
+  } else {
+    needs_in_place_update_ts_ = true;
+    has_key_with_ts_ = true;
+    std::string dummy_ts(ts_sz, '\0');
+    std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
+    s = WriteBatchInternal::Delete(this, cf_id,
+                                   SliceParts(key_with_ts.data(), 2));
   }
-
-  needs_in_place_update_ts_ = true;
-  has_key_with_ts_ = true;
-  std::string dummy_ts(ts_sz, '\0');
-  std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
-  return WriteBatchInternal::Delete(this, cf_id,
-                                    SliceParts(key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts_sz);
+  }
+  return s;
 }
 
 Status WriteBatch::Delete(ColumnFamilyHandle* column_family, const Slice& key,
                           const Slice& ts) {
-  const Status s = CheckColumnFamilyTimestampSize(column_family, ts);
+  Status s = CheckColumnFamilyTimestampSize(column_family, ts);
   if (!s.ok()) {
     return s;
   }
@@ -1267,8 +1283,12 @@ Status WriteBatch::Delete(ColumnFamilyHandle* column_family, const Slice& key,
   has_key_with_ts_ = true;
   uint32_t cf_id = column_family->GetID();
   std::array<Slice, 2> key_with_ts{{key, ts}};
-  return WriteBatchInternal::Delete(this, cf_id,
-                                    SliceParts(key_with_ts.data(), 2));
+  s = WriteBatchInternal::Delete(this, cf_id,
+                                 SliceParts(key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts.size());
+  }
+  return s;
 }
 
 Status WriteBatchInternal::Delete(WriteBatch* b, uint32_t column_family_id,
@@ -1313,7 +1333,11 @@ Status WriteBatch::Delete(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::Delete(this, cf_id, key);
+    s = WriteBatchInternal::Delete(this, cf_id, key);
+    if (s.ok()) {
+      MaybeTrackTimestampSize(cf_id, ts_sz);
+    }
+    return s;
   }
 
   return Status::InvalidArgument(
@@ -1361,20 +1385,24 @@ Status WriteBatch::SingleDelete(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::SingleDelete(this, cf_id, key);
+    s = WriteBatchInternal::SingleDelete(this, cf_id, key);
+  } else {
+    needs_in_place_update_ts_ = true;
+    has_key_with_ts_ = true;
+    std::string dummy_ts(ts_sz, '\0');
+    std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
+    s = WriteBatchInternal::SingleDelete(this, cf_id,
+                                         SliceParts(key_with_ts.data(), 2));
   }
-
-  needs_in_place_update_ts_ = true;
-  has_key_with_ts_ = true;
-  std::string dummy_ts(ts_sz, '\0');
-  std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
-  return WriteBatchInternal::SingleDelete(this, cf_id,
-                                          SliceParts(key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts_sz);
+  }
+  return s;
 }
 
 Status WriteBatch::SingleDelete(ColumnFamilyHandle* column_family,
                                 const Slice& key, const Slice& ts) {
-  const Status s = CheckColumnFamilyTimestampSize(column_family, ts);
+  Status s = CheckColumnFamilyTimestampSize(column_family, ts);
   if (!s.ok()) {
     return s;
   }
@@ -1382,8 +1410,12 @@ Status WriteBatch::SingleDelete(ColumnFamilyHandle* column_family,
   assert(column_family);
   uint32_t cf_id = column_family->GetID();
   std::array<Slice, 2> key_with_ts{{key, ts}};
-  return WriteBatchInternal::SingleDelete(this, cf_id,
-                                          SliceParts(key_with_ts.data(), 2));
+  s = WriteBatchInternal::SingleDelete(this, cf_id,
+                                       SliceParts(key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts.size());
+  }
+  return s;
 }
 
 Status WriteBatchInternal::SingleDelete(WriteBatch* b,
@@ -1430,7 +1462,11 @@ Status WriteBatch::SingleDelete(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::SingleDelete(this, cf_id, key);
+    s = WriteBatchInternal::SingleDelete(this, cf_id, key);
+    if (s.ok()) {
+      MaybeTrackTimestampSize(cf_id, ts_sz);
+    }
+    return s;
   }
 
   return Status::InvalidArgument(
@@ -1480,23 +1516,27 @@ Status WriteBatch::DeleteRange(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::DeleteRange(this, cf_id, begin_key, end_key);
+    s = WriteBatchInternal::DeleteRange(this, cf_id, begin_key, end_key);
+  } else {
+    needs_in_place_update_ts_ = true;
+    has_key_with_ts_ = true;
+    std::string dummy_ts(ts_sz, '\0');
+    std::array<Slice, 2> begin_key_with_ts{{begin_key, dummy_ts}};
+    std::array<Slice, 2> end_key_with_ts{{end_key, dummy_ts}};
+    s = WriteBatchInternal::DeleteRange(this, cf_id,
+                                        SliceParts(begin_key_with_ts.data(), 2),
+                                        SliceParts(end_key_with_ts.data(), 2));
   }
-
-  needs_in_place_update_ts_ = true;
-  has_key_with_ts_ = true;
-  std::string dummy_ts(ts_sz, '\0');
-  std::array<Slice, 2> begin_key_with_ts{{begin_key, dummy_ts}};
-  std::array<Slice, 2> end_key_with_ts{{end_key, dummy_ts}};
-  return WriteBatchInternal::DeleteRange(
-      this, cf_id, SliceParts(begin_key_with_ts.data(), 2),
-      SliceParts(end_key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts_sz);
+  }
+  return s;
 }
 
 Status WriteBatch::DeleteRange(ColumnFamilyHandle* column_family,
                                const Slice& begin_key, const Slice& end_key,
                                const Slice& ts) {
-  const Status s = CheckColumnFamilyTimestampSize(column_family, ts);
+  Status s = CheckColumnFamilyTimestampSize(column_family, ts);
   if (!s.ok()) {
     return s;
   }
@@ -1505,9 +1545,13 @@ Status WriteBatch::DeleteRange(ColumnFamilyHandle* column_family,
   uint32_t cf_id = column_family->GetID();
   std::array<Slice, 2> key_with_ts{{begin_key, ts}};
   std::array<Slice, 2> end_key_with_ts{{end_key, ts}};
-  return WriteBatchInternal::DeleteRange(this, cf_id,
-                                         SliceParts(key_with_ts.data(), 2),
-                                         SliceParts(end_key_with_ts.data(), 2));
+  s = WriteBatchInternal::DeleteRange(this, cf_id,
+                                      SliceParts(key_with_ts.data(), 2),
+                                      SliceParts(end_key_with_ts.data(), 2));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts.size());
+  }
+  return s;
 }
 
 Status WriteBatchInternal::DeleteRange(WriteBatch* b, uint32_t column_family_id,
@@ -1554,7 +1598,11 @@ Status WriteBatch::DeleteRange(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::DeleteRange(this, cf_id, begin_key, end_key);
+    s = WriteBatchInternal::DeleteRange(this, cf_id, begin_key, end_key);
+    if (s.ok()) {
+      MaybeTrackTimestampSize(cf_id, ts_sz);
+    }
+    return s;
   }
 
   return Status::InvalidArgument(
@@ -1608,21 +1656,25 @@ Status WriteBatch::Merge(ColumnFamilyHandle* column_family, const Slice& key,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::Merge(this, cf_id, key, value);
-  }
-
-  needs_in_place_update_ts_ = true;
-  has_key_with_ts_ = true;
-  std::string dummy_ts(ts_sz, '\0');
-  std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
+    s = WriteBatchInternal::Merge(this, cf_id, key, value);
+  } else {
+    needs_in_place_update_ts_ = true;
+    has_key_with_ts_ = true;
+    std::string dummy_ts(ts_sz, '\0');
+    std::array<Slice, 2> key_with_ts{{key, dummy_ts}};
 
-  return WriteBatchInternal::Merge(
-      this, cf_id, SliceParts(key_with_ts.data(), 2), SliceParts(&value, 1));
+    s = WriteBatchInternal::Merge(
+        this, cf_id, SliceParts(key_with_ts.data(), 2), SliceParts(&value, 1));
+  }
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts_sz);
+  }
+  return s;
 }
 
 Status WriteBatch::Merge(ColumnFamilyHandle* column_family, const Slice& key,
                          const Slice& ts, const Slice& value) {
-  const Status s = CheckColumnFamilyTimestampSize(column_family, ts);
+  Status s = CheckColumnFamilyTimestampSize(column_family, ts);
   if (!s.ok()) {
     return s;
   }
@@ -1630,8 +1682,12 @@ Status WriteBatch::Merge(ColumnFamilyHandle* column_family, const Slice& key,
   assert(column_family);
   uint32_t cf_id = column_family->GetID();
   std::array<Slice, 2> key_with_ts{{key, ts}};
-  return WriteBatchInternal::Merge(
-      this, cf_id, SliceParts(key_with_ts.data(), 2), SliceParts(&value, 1));
+  s = WriteBatchInternal::Merge(this, cf_id, SliceParts(key_with_ts.data(), 2),
+                                SliceParts(&value, 1));
+  if (s.ok()) {
+    MaybeTrackTimestampSize(cf_id, ts.size());
+  }
+  return s;
 }
 
 Status WriteBatchInternal::Merge(WriteBatch* b, uint32_t column_family_id,
@@ -1680,7 +1736,11 @@ Status WriteBatch::Merge(ColumnFamilyHandle* column_family,
   }
 
   if (0 == ts_sz) {
-    return WriteBatchInternal::Merge(this, cf_id, key, value);
+    s = WriteBatchInternal::Merge(this, cf_id, key, value);
+    if (s.ok()) {
+      MaybeTrackTimestampSize(cf_id, ts_sz);
+    }
+    return s;
   }
 
   return Status::InvalidArgument(

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_common.h

@@ -125,7 +125,6 @@ DECLARE_int32(level0_stop_writes_trigger);
 DECLARE_int32(block_size);
 DECLARE_int32(format_version);
 DECLARE_int32(index_block_restart_interval);
-DECLARE_bool(disable_auto_compactions);
 DECLARE_int32(max_background_compactions);
 DECLARE_int32(num_bottom_pri_threads);
 DECLARE_int32(compaction_thread_pool_adjust_interval);
@@ -151,6 +150,7 @@ DECLARE_bool(charge_filter_construction);
 DECLARE_bool(charge_table_reader);
 DECLARE_bool(charge_file_metadata);
 DECLARE_bool(charge_blob_cache);
+DECLARE_bool(decouple_partitioned_filters);
 DECLARE_int32(top_level_index_pinning);
 DECLARE_int32(partition_pinning);
 DECLARE_int32(unpartitioned_pinning);
@@ -197,7 +197,6 @@ DECLARE_int64(target_file_size_base);
 DECLARE_int32(target_file_size_multiplier);
 DECLARE_uint64(max_bytes_for_level_base);
 DECLARE_double(max_bytes_for_level_multiplier);
-DECLARE_int32(range_deletion_width);
 DECLARE_uint64(rate_limiter_bytes_per_sec);
 DECLARE_bool(rate_limit_bg_reads);
 DECLARE_bool(rate_limit_user_ops);
@@ -275,6 +274,7 @@ DECLARE_bool(verification_only);
 DECLARE_string(last_level_temperature);
 DECLARE_string(default_write_temperature);
 DECLARE_string(default_temperature);
+DECLARE_bool(paranoid_memory_checks);
 
 // Options for transaction dbs.
 // Use TransactionDB (a.k.a. Pessimistic Transaction DB)
@@ -319,7 +319,6 @@ DECLARE_int32(prepopulate_blob_cache);
 DECLARE_int32(approximate_size_one_in);
 DECLARE_bool(best_efforts_recovery);
 DECLARE_bool(skip_verifydb);
-DECLARE_bool(enable_compaction_filter);
 DECLARE_bool(paranoid_file_checks);
 DECLARE_bool(fail_if_options_file_error);
 DECLARE_uint64(batch_protection_bytes_per_key);

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_compaction_filter.h

@@ -49,7 +49,7 @@ class DbStressCompactionFilter : public CompactionFilter {
       return Decision::kKeep;
     }
     // Reaching here means we acquired the lock.
-
+    key_mutex->AssertHeld();
     bool key_exists = state_->Exists(cf_id_, key_num);
     const bool allow_overwrite = state_->AllowsOverwrite(key_num);
 

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_driver.cc

@@ -167,7 +167,10 @@ bool RunStressTestImpl(SharedState* shared) {
               {FileType::kWalFile});
         }
       }
-      now = clock->NowMicros();
+      if (ShouldDisableAutoCompactionsBeforeVerifyDb()) {
+        Status s = stress->EnableAutoCompaction();
+        assert(s.ok());
+      }
       fprintf(stdout, "%s Starting database operations\n",
               clock->TimeToString(now / 1000000).c_str());
 

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_gflags.cc

@@ -380,6 +380,11 @@ DEFINE_bool(charge_blob_cache, false,
             "CacheEntryRoleOptions::charged of "
             "kBlobCache");
 
+DEFINE_bool(
+    decouple_partitioned_filters,
+    ROCKSDB_NAMESPACE::BlockBasedTableOptions().decouple_partitioned_filters,
+    "Decouple filter partitioning from index partitioning.");
+
 DEFINE_int32(
     top_level_index_pinning,
     static_cast<int32_t>(ROCKSDB_NAMESPACE::PinningTier::kFallback),
@@ -1443,4 +1448,8 @@ DEFINE_uint32(uncache_aggressiveness,
               "obsolete. 0 = disabled, 1 = minimum, 100 = moderate, 10000 = "
               "normal max");
 
+DEFINE_bool(paranoid_memory_checks,
+            ROCKSDB_NAMESPACE::Options().paranoid_memory_checks,
+            "Sets CF option paranoid_memory_checks.");
+
 #endif  // GFLAGS

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_listener.h

@@ -72,14 +72,7 @@ class DbStressListener : public EventListener {
     // pretending doing some work here
     RandomSleep();
     if (fault_fs_guard) {
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kWrite);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataWrite);
+      fault_fs_guard->DisableAllThreadLocalErrorInjection();
     }
   }
 
@@ -180,14 +173,7 @@ class DbStressListener : public EventListener {
 
   void OnSubcompactionCompleted(const SubcompactionJobInfo& /* si */) override {
     if (fault_fs_guard) {
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kWrite);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataWrite);
+      fault_fs_guard->DisableAllThreadLocalErrorInjection();
     }
   }
 
@@ -274,14 +260,7 @@ class DbStressListener : public EventListener {
                             bool* /* auto_recovery */) override {
     RandomSleep();
     if (FLAGS_error_recovery_with_no_fault_injection && fault_fs_guard) {
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kWrite);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataWrite);
+      fault_fs_guard->DisableAllThreadLocalErrorInjection();
       // TODO(hx235): only exempt the flush thread during error recovery instead
       // of all the flush threads from error injection
       fault_fs_guard->SetIOActivtiesExcludedFromFaultInjection(
@@ -293,14 +272,7 @@ class DbStressListener : public EventListener {
       const BackgroundErrorRecoveryInfo& /*info*/) override {
     RandomSleep();
     if (FLAGS_error_recovery_with_no_fault_injection && fault_fs_guard) {
-      fault_fs_guard->EnableThreadLocalErrorInjection(
-          FaultInjectionIOType::kRead);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
-          FaultInjectionIOType::kWrite);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
-          FaultInjectionIOType::kMetadataWrite);
+      fault_fs_guard->EnableAllThreadLocalErrorInjection();
       fault_fs_guard->SetIOActivtiesExcludedFromFaultInjection({});
     }
   }

package/deps/rocksdb/rocksdb/db_stress_tool/db_stress_shared_state.h

@@ -31,6 +31,7 @@ DECLARE_int32(compaction_thread_pool_adjust_interval);
 DECLARE_int32(continuous_verification_interval);
 DECLARE_bool(error_recovery_with_no_fault_injection);
 DECLARE_bool(sync_fault_injection);
+DECLARE_int32(range_deletion_width);
 DECLARE_bool(disable_wal);
 DECLARE_int32(manual_wal_flush_one_in);
 DECLARE_int32(metadata_read_fault_one_in);
@@ -44,6 +45,8 @@ DECLARE_int32(open_write_fault_one_in);
 DECLARE_int32(open_read_fault_one_in);
 
 DECLARE_int32(inject_error_severity);
+DECLARE_bool(disable_auto_compactions);
+DECLARE_bool(enable_compaction_filter);
 
 namespace ROCKSDB_NAMESPACE {
 class StressTest;
@@ -147,7 +150,8 @@ class SharedState {
 
   ~SharedState() {
 #ifndef NDEBUG
-    if (FLAGS_read_fault_one_in) {
+    if (FLAGS_read_fault_one_in || FLAGS_write_fault_one_in ||
+        FLAGS_metadata_write_fault_one_in) {
       SyncPoint::GetInstance()->ClearAllCallBacks();
       SyncPoint::GetInstance()->DisableProcessing();
     }
@@ -260,8 +264,8 @@ class SharedState {
   // This is useful for crash-recovery testing when the process may crash
   // before updating the corresponding expected value
   //
-  // Requires external locking covering `key` in `cf` to prevent concurrent
-  // write or delete to the same `key`.
+  // Requires external locking covering `key` in `cf` to prevent
+  // concurrent write or delete to the same `key`.
   PendingExpectedValue PreparePut(int cf, int64_t key) {
     return expected_state_manager_->PreparePut(cf, key);
   }