@nxtedition/rocksdb 13.5.12 → 14.0.0

package/deps/rocksdb/rocksdb/db/db_iterator_test.cc

@@ -4142,13 +4142,18 @@ TEST_P(DBIteratorTest, AverageMemtableOpsScanFlushTriggerByOverwrites) {
   ASSERT_EQ(1, NumTableFilesAtLevel(0));
 }
 
-class DBMultiScanIteratorTest : public DBTestBase {
+class DBMultiScanIteratorTest : public DBTestBase,
+                                public ::testing::WithParamInterface<bool> {
  public:
   DBMultiScanIteratorTest()
       : DBTestBase("db_multi_scan_iterator_test", /*env_do_fsync=*/true) {}
 };
 
-TEST_F(DBMultiScanIteratorTest, BasicTest) {
+// Param 0: ReadOptions::fill_cache
+INSTANTIATE_TEST_CASE_P(DBMultiScanIteratorTest, DBMultiScanIteratorTest,
+                        ::testing::Bool());
+
+TEST_P(DBMultiScanIteratorTest, BasicTest) {
   // Create a file
   for (int i = 0; i < 100; ++i) {
     std::stringstream ss;
@@ -4159,9 +4164,10 @@ TEST_F(DBMultiScanIteratorTest, BasicTest) {
 
   std::vector<std::string> key_ranges({"k03", "k10", "k25", "k50"});
   ReadOptions ro;
-  std::vector<ScanOptions> scan_options(
-      {ScanOptions(key_ranges[0], key_ranges[1]),
-       ScanOptions(key_ranges[2], key_ranges[3])});
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
   ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
   std::unique_ptr<MultiScan> iter =
       dbfull()->NewMultiScan(ro, cfh, scan_options);
@@ -4187,23 +4193,48 @@ TEST_F(DBMultiScanIteratorTest, BasicTest) {
     abort();
   }
   iter.reset();
+}
 
-  // Test the overlapping scan case
-  key_ranges[1] = "k30";
-  scan_options[0] = ScanOptions(key_ranges[0], key_ranges[1]);
-  iter = dbfull()->NewMultiScan(ro, cfh, scan_options);
+TEST_P(DBMultiScanIteratorTest, MixedBoundsTest) {
+  // Create a file
+  for (int i = 0; i < 100; ++i) {
+    std::stringstream ss;
+    ss << std::setw(2) << std::setfill('0') << i;
+    ASSERT_OK(Put("k" + ss.str(), "val" + ss.str()));
+  }
+  ASSERT_OK(Flush());
+
+  std::vector<std::string> key_ranges(
+      {"k03", "k10", "k25", "k50", "k75", "k90"});
+  ReadOptions ro;
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2]);
+  scan_options.insert(key_ranges[4], key_ranges[5]);
+  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
+  std::unique_ptr<MultiScan> iter =
+      dbfull()->NewMultiScan(ro, cfh, scan_options);
   try {
     int idx = 0;
     int count = 0;
     for (auto range : *iter) {
       for (auto it : range) {
-        ASSERT_GE(it.first.ToString().compare(key_ranges[idx]), 0);
-        ASSERT_LT(it.first.ToString().compare(key_ranges[idx + 1]), 0);
+        ASSERT_GE(
+            it.first.ToString().compare(
+                scan_options.GetScanRanges()[idx].range.start->ToString()),
+            0);
+        if (scan_options.GetScanRanges()[idx].range.limit) {
+          ASSERT_LT(
+              it.first.ToString().compare(
+                  scan_options.GetScanRanges()[idx].range.limit->ToString()),
+              0);
+        }
         count++;
       }
-      idx += 2;
+      idx++;
     }
-    ASSERT_EQ(count, 52);
+    ASSERT_EQ(count, 97);
   } catch (MultiScanException& ex) {
     // Make sure exception contains the status
     ASSERT_NOK(ex.status());
@@ -4214,25 +4245,31 @@ TEST_F(DBMultiScanIteratorTest, BasicTest) {
     abort();
   }
   iter.reset();
-
-  // Test the no limit scan case
-  scan_options[0] = ScanOptions(key_ranges[0]);
-  scan_options[1] = ScanOptions(key_ranges[2]);
+  scan_options = MultiScanArgs(BytewiseComparator());
+  scan_options.insert(key_ranges[0]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
+  scan_options.insert(key_ranges[4]);
   iter = dbfull()->NewMultiScan(ro, cfh, scan_options);
   try {
     int idx = 0;
     int count = 0;
     for (auto range : *iter) {
       for (auto it : range) {
-        ASSERT_GE(it.first.ToString().compare(key_ranges[idx]), 0);
-        if (it.first.ToString().compare(key_ranges[idx + 1]) == 0) {
-          break;
+        ASSERT_GE(
+            it.first.ToString().compare(
+                scan_options.GetScanRanges()[idx].range.start->ToString()),
+            0);
+        if (scan_options.GetScanRanges()[idx].range.limit) {
+          ASSERT_LT(
+              it.first.ToString().compare(
+                  scan_options.GetScanRanges()[idx].range.limit->ToString()),
+              0);
         }
         count++;
       }
-      idx += 2;
+      idx++;
     }
-    ASSERT_EQ(count, 52);
+    ASSERT_EQ(count, 147);
   } catch (MultiScanException& ex) {
     // Make sure exception contains the status
     ASSERT_NOK(ex.status());
@@ -4245,42 +4282,150 @@ TEST_F(DBMultiScanIteratorTest, BasicTest) {
   iter.reset();
 }
 
-TEST_F(DBMultiScanIteratorTest, MixedBoundsTest) {
+TEST_P(DBMultiScanIteratorTest, RangeAcrossFiles) {
+  auto options = CurrentOptions();
+  options.target_file_size_base = 100 << 10;  // 20KB
+  options.compaction_style = kCompactionStyleUniversal;
+  options.num_levels = 50;
+  options.compression = kNoCompression;
+  DestroyAndReopen(options);
+
+  auto rnd = Random::GetTLSInstance();
+  // Write ~200KB data
+  for (int i = 0; i < 100; ++i) {
+    ASSERT_OK(Put(Key(i), rnd->RandomString(2 << 10)));
+  }
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
+  ASSERT_EQ(2, NumTableFilesAtLevel(49));
+  std::vector<std::string> key_ranges({Key(10), Key(90)});
+  ReadOptions ro;
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
+  std::unique_ptr<MultiScan> iter =
+      dbfull()->NewMultiScan(ro, cfh, scan_options);
+  try {
+    int i = 10;
+    for (auto range : *iter) {
+      for (auto it : range) {
+        ASSERT_EQ(it.first.ToString(), Key(i));
+        ++i;
+      }
+    }
+    ASSERT_EQ(i, 90);
+  } catch (MultiScanException& ex) {
+    // Make sure exception contains the status
+    ASSERT_NOK(ex.status());
+    std::cerr << "Iterator returned status " << ex.what();
+    abort();
+  } catch (std::logic_error& ex) {
+    std::cerr << "Iterator returned logic error " << ex.what();
+    abort();
+  }
+  iter.reset();
+}
+
+TEST_P(DBMultiScanIteratorTest, FailureTest) {
+  auto options = CurrentOptions();
+  options.compression = kNoCompression;
+  DestroyAndReopen(options);
+
+  Random rnd(301);
   // Create a file
   for (int i = 0; i < 100; ++i) {
     std::stringstream ss;
     ss << std::setw(2) << std::setfill('0') << i;
-    ASSERT_OK(Put("k" + ss.str(), "val" + ss.str()));
+    ASSERT_OK(Put("k" + ss.str(), rnd.RandomString(1024)));
   }
   ASSERT_OK(Flush());
 
-  std::vector<std::string> key_ranges(
-      {"k03", "k10", "k25", "k50", "k75", "k90"});
+  std::vector<std::string> key_ranges({"k04", "k06", "k12", "k14"});
+  ReadOptions ro;
+  Slice ub;
+  ro.iterate_upper_bound = &ub;
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
+  scan_options.max_prefetch_size = 4500;
+  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
+  std::unique_ptr<Iterator> iter(dbfull()->NewIterator(ro, cfh));
+  ASSERT_NE(iter, nullptr);
+  iter->Prepare(scan_options);
+  int count = 0;
+  ub = key_ranges[1];
+  iter->Seek(key_ranges[0]);
+  while (iter->status().ok() && iter->Valid()) {
+    ASSERT_GE(iter->key().compare(key_ranges[0]), 0);
+    ASSERT_LT(iter->key().compare(key_ranges[1]), 0);
+    count++;
+    iter->Next();
+  }
+  ASSERT_OK(iter->status()) << iter->status().ToString();
+  ASSERT_EQ(count, 2);
+
+  // Second seek should hit the max_prefetch_size limit
+  ub = key_ranges[3];
+  iter->Seek(key_ranges[2]);
+  ASSERT_NOK(iter->status());
+  iter.reset();
+
+  // Test the case of unexpected Seek key
+  iter.reset(dbfull()->NewIterator(ro, cfh));
+  ASSERT_NE(iter, nullptr);
+  scan_options.max_prefetch_size = 0;
+  iter->Prepare(scan_options);
+  ub = key_ranges[3];
+  iter->Seek(key_ranges[2]);
+  ASSERT_NOK(iter->status());
+  iter.reset();
+}
+
+TEST_P(DBMultiScanIteratorTest, RangeBetweenFiles) {
+  auto options = CurrentOptions();
+  options.target_file_size_base = 100 << 10;  // 20KB
+  options.compaction_style = kCompactionStyleUniversal;
+  options.num_levels = 50;
+  options.compression = kNoCompression;
+  DestroyAndReopen(options);
+
+  auto rnd = Random::GetTLSInstance();
+  // Write ~200KB data
+  for (int i = 0; i < 100; ++i) {
+    ASSERT_OK(Put(Key(i), rnd->RandomString(2 << 10)));
+  }
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
+  ASSERT_EQ(2, NumTableFilesAtLevel(49));
+
+  // Test with a scan range that overlaps an entire file, with upper bound
+  // between 2 files
+  std::vector<LiveFileMetaData> file_meta;
+  dbfull()->GetLiveFilesMetaData(&file_meta);
+  ASSERT_EQ(file_meta.size(), 2);
+  std::vector<std::string> key_ranges(4);
+  key_ranges[0] = file_meta[0].smallestkey;
+  key_ranges[1] = file_meta[0].largestkey + "0";
+  key_ranges[2] = file_meta[1].smallestkey + "0";
+  key_ranges[3] = file_meta[1].largestkey;
   ReadOptions ro;
-  std::vector<ScanOptions> scan_options(
-      {ScanOptions(key_ranges[0], key_ranges[1]), ScanOptions(key_ranges[2]),
-       ScanOptions(key_ranges[4], key_ranges[5])});
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
   ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
   std::unique_ptr<MultiScan> iter =
       dbfull()->NewMultiScan(ro, cfh, scan_options);
   try {
-    int idx = 0;
-    int count = 0;
     for (auto range : *iter) {
       for (auto it : range) {
-        ASSERT_GE(it.first.ToString().compare(
-                      scan_options[idx].range.start->ToString()),
-                  0);
-        if (scan_options[idx].range.limit) {
-          ASSERT_LT(it.first.ToString().compare(
-                        scan_options[idx].range.limit->ToString()),
-                    0);
-        }
-        count++;
+        ASSERT_GE(it.first.ToString(), key_ranges[0]);
       }
-      idx++;
     }
-    ASSERT_EQ(count, 97);
   } catch (MultiScanException& ex) {
     // Make sure exception contains the status
     ASSERT_NOK(ex.status());
@@ -4292,28 +4437,21 @@ TEST_F(DBMultiScanIteratorTest, MixedBoundsTest) {
   }
   iter.reset();
 
-  scan_options[0] = ScanOptions(key_ranges[0]);
-  scan_options[1] = ScanOptions(key_ranges[2], key_ranges[3]);
-  scan_options[2] = ScanOptions(key_ranges[4]);
+  // Test multiscan with a range entirely between adjacent files
+  key_ranges[0] = file_meta[0].largestkey + "0";
+  key_ranges[1] = file_meta[0].largestkey + "1";
+  key_ranges[2] = file_meta[1].smallestkey + "0";
+  key_ranges[3] = file_meta[1].largestkey;
+  (*scan_options).clear();
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
   iter = dbfull()->NewMultiScan(ro, cfh, scan_options);
   try {
-    int idx = 0;
-    int count = 0;
     for (auto range : *iter) {
       for (auto it : range) {
-        ASSERT_GE(it.first.ToString().compare(
-                      scan_options[idx].range.start->ToString()),
-                  0);
-        if (scan_options[idx].range.limit) {
-          ASSERT_LT(it.first.ToString().compare(
-                        scan_options[idx].range.limit->ToString()),
-                    0);
-        }
-        count++;
+        ASSERT_GE(it.first.ToString(), key_ranges[0]);
       }
-      idx++;
     }
-    ASSERT_EQ(count, 147);
   } catch (MultiScanException& ex) {
     // Make sure exception contains the status
     ASSERT_NOK(ex.status());
@@ -4325,6 +4463,141 @@ TEST_F(DBMultiScanIteratorTest, MixedBoundsTest) {
   }
   iter.reset();
 }
+
+// This test case tests multiscan in the presence of fragmented range
+// tombstones in the LSM.
+TEST_P(DBMultiScanIteratorTest, FragmentedRangeTombstones) {
+  auto options = CurrentOptions();
+  // Compaction may create files 2x the target_file_size_base,
+  // so set this to 50KB so we atleast end up with 2 files of
+  // 100KB
+  options.target_file_size_base = 50 << 10;  // 50KB
+  options.compaction_style = kCompactionStyleUniversal;
+  options.num_levels = 50;
+  options.compression = kNoCompression;
+  DestroyAndReopen(options);
+
+  // Setup the LSM as follows -
+  // 1. Ingest a file with 100 keys
+  // 2. Ingest a file with one overlapping key
+  // 3. Do a Put and flush a file to L0 with one overlapping key
+  // 4. Ingest a standalone delete range file that covers the full key space
+  //    and a file with the same 100 keys with new values. This will ingest
+  //    into L0 due to the presence of an existing file in L0
+  // The final LSM will have an SST in Lmax with 100 keys, and 2 SST files
+  // in Lmax-1 with half the keys each and completely overlapping delete ranges
+  std::unordered_map<std::string, std::string> kvs;
+  auto rnd = Random::GetTLSInstance();
+  auto create_ingestion_data_file_and_update_key_value =
+      [&](const std::string& filename, int start_key, int end_key) {
+        std::unique_ptr<SstFileWriter> writer;
+        writer.reset(new SstFileWriter(EnvOptions(), options));
+        ASSERT_OK(writer->Open(filename));
+        for (int i = start_key; i < end_key; ++i) {
+          auto kiter = kvs.find(Key(i));
+          if (kiter != kvs.end()) {
+            kvs.erase(kiter);
+          }
+          auto res =
+              kvs.emplace(std::make_pair(Key(i), rnd->RandomString(2 << 10)));
+          ASSERT_OK(writer->Put(res.first->first, res.first->second));
+        }
+        ASSERT_OK(writer->Finish());
+        writer.reset();
+      };
+
+  CreateColumnFamilies({"new_cf"}, options);
+  std::string ingest_file = dbname_ + "test.sst";
+  // Write ~200KB data
+  create_ingestion_data_file_and_update_key_value(ingest_file + "_0", 0, 100);
+  create_ingestion_data_file_and_update_key_value(ingest_file + "_1", 50, 51);
+  ColumnFamilyHandle* cfh = handles_[0];
+  IngestExternalFileOptions ifo;
+  Status s = dbfull()->IngestExternalFile(
+      cfh, {ingest_file + "_0", ingest_file + "_1"}, ifo);
+  ASSERT_OK(s);
+
+  ASSERT_OK(Put(0, Key(50), rnd->RandomString(2 << 10)));
+  ASSERT_OK(Flush());
+
+  {
+    std::unique_ptr<SstFileWriter> writer;
+    writer.reset(new SstFileWriter(EnvOptions(), options));
+    ASSERT_OK(writer->Open(ingest_file + "_2"));
+    ASSERT_OK(writer->DeleteRange("a", "z"));
+    ASSERT_OK(writer->Finish());
+    writer.reset();
+  }
+  create_ingestion_data_file_and_update_key_value(ingest_file + "_3", 0, 100);
+  s = dbfull()->IngestExternalFile(
+      cfh, {ingest_file + "_2", ingest_file + "_3"}, ifo);
+  ASSERT_OK(s);
+
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  // The first scan range overlaps the DB key range, while the second extends
+  // beyond but overlaps the delete range
+  std::vector<std::string> key_ranges({"key000085", "key000090", "l", "n"});
+  ReadOptions ro;
+  ro.fill_cache = GetParam();
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
+  std::unique_ptr<MultiScan> iter =
+      dbfull()->NewMultiScan(ro, cfh, scan_options);
+  try {
+    int i = 0;
+    int count = 0;
+    for (auto range : *iter) {
+      for (auto it : range) {
+        ASSERT_GE(it.first.ToString(), key_ranges[i]);
+        ASSERT_LT(it.first.ToString(), key_ranges[i + 1]);
+        auto kiter = kvs.find(it.first.ToString());
+        ASSERT_NE(kiter, kvs.end());
+        ASSERT_EQ(kiter->second, it.second.ToString());
+        count++;
+      }
+      i += 2;
+    }
+    ASSERT_EQ(i, 4);
+    ASSERT_EQ(count, 5);
+  } catch (MultiScanException& ex) {
+    ASSERT_OK(ex.status());
+  }
+  iter.reset();
+
+  // The second scan range start overlaps the delete range in the first file
+  // in Lmax-1, while the end overlaps the keys in the second file
+  (*scan_options).clear();
+  key_ranges[0] = "key000010";
+  key_ranges[1] = "key000020";
+  key_ranges[2] = "key0000500";
+  key_ranges[3] = "key000060";
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+  scan_options.insert(key_ranges[2], key_ranges[3]);
+  iter = dbfull()->NewMultiScan(ro, cfh, scan_options);
+  try {
+    int i = 0;
+    int count = 0;
+    for (auto range : *iter) {
+      for (auto it : range) {
+        ASSERT_GE(it.first.ToString(), key_ranges[i]);
+        ASSERT_LT(it.first.ToString(), key_ranges[i + 1]);
+        auto kiter = kvs.find(it.first.ToString());
+        ASSERT_NE(kiter, kvs.end());
+        ASSERT_EQ(kiter->second, it.second.ToString());
+        count++;
+      }
+      i += 2;
+    }
+    ASSERT_EQ(i, 4);
+    ASSERT_EQ(count, 19);
+  } catch (MultiScanException& ex) {
+    ASSERT_OK(ex.status());
+  }
+  iter.reset();
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

package/deps/rocksdb/rocksdb/db/db_memtable_test.cc

@@ -339,6 +339,135 @@ TEST_F(DBMemTableTest, ColumnFamilyId) {
   }
 }
 
+class DBMemTableTestForSeek : public DBMemTableTest,
+                              virtual public ::testing::WithParamInterface<
+                                  std::tuple<bool, bool, bool>> {};
+
+TEST_P(DBMemTableTestForSeek, IntegrityChecks) {
+  // Validate key corruption could be detected during seek.
+  // We insert many keys into skiplist. Then we corrupt the each key one at a
+  // time. With memtable_veirfy_per_key_checksum_on_seek enabled, when the
+  // corrupted key is searched, the checksum of every key visited during the
+  // seek is validated. It will report data corruption. Otherwise seek returns
+  // not found.
+  auto allow_data_in_error = std::get<0>(GetParam());
+  Options options = CurrentOptions();
+  options.allow_data_in_errors = allow_data_in_error;
+  options.paranoid_memory_checks = std::get<1>(GetParam());
+  options.memtable_veirfy_per_key_checksum_on_seek = std::get<2>(GetParam());
+  options.memtable_protection_bytes_per_key = 8;
+  DestroyAndReopen(options);
+
+  // capture the data pointer of all of the keys
+  std::vector<char*> raw_data_pointer;
+
+  // Insert enough keys, so memtable would create multiple levels.
+  auto key_count = 100;
+  for (int i = 0; i < key_count; i++) {
+    // The last digit of the key will be corrupted from value 0 to value 5
+    ASSERT_OK(Put(Key(i * 10), "val0"));
+  }
+
+  ReadOptions rops;
+
+  // Iterate all the keys to get key pointers
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->SetCallBack("InlineSkipList::Iterator::Next::key",
+                                        [&raw_data_pointer](void* key) {
+                                          auto p = static_cast<char*>(key);
+                                          raw_data_pointer.push_back(p);
+                                        });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  {
+    std::unique_ptr<Iterator> iter{db_->NewIterator(rops)};
+    iter->Seek(Key(0));
+    while (iter->Valid()) {
+      ASSERT_OK(iter->status());
+      iter->Next();
+    }
+    // check status after valid returned false.
+    auto status = iter->status();
+    ASSERT_TRUE(status.ok());
+  }
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  ASSERT_EQ(raw_data_pointer.size(), key_count);
+
+  bool enable_key_validation_on_seek =
+      options.memtable_veirfy_per_key_checksum_on_seek;
+
+  // For each key, corrupt it, validate corruption is detected correctly, then
+  // revert it.
+  for (int i = 0; i < key_count; i++) {
+    std::string key_to_corrupt = Key(i * 10);
+    raw_data_pointer[i][key_to_corrupt.size()] = '5';
+
+    auto corrupted_key = key_to_corrupt;
+    corrupted_key.data()[key_to_corrupt.size() - 1] = '5';
+    auto corrupted_key_slice =
+        Slice(corrupted_key.data(), corrupted_key.length());
+    auto corrupted_key_hex = corrupted_key_slice.ToString(/*hex=*/true);
+
+    {
+      // Test Get API
+      std::string val;
+      auto status = db_->Get(rops, key_to_corrupt, &val);
+      if (enable_key_validation_on_seek) {
+        ASSERT_TRUE(status.IsCorruption()) << key_to_corrupt;
+        ASSERT_EQ(
+            status.ToString().find(corrupted_key_hex) != std::string::npos,
+            allow_data_in_error)
+            << status.ToString() << "\n"
+            << corrupted_key_hex;
+      } else {
+        ASSERT_TRUE(status.IsNotFound());
+      }
+    }
+
+    {
+      // Test MultiGet API
+      std::vector<std::string> vals;
+      std::vector<Status> statuses = db_->MultiGet(
+          rops, {db_->DefaultColumnFamily()}, {key_to_corrupt}, &vals, nullptr);
+      if (enable_key_validation_on_seek) {
+        ASSERT_TRUE(statuses[0].IsCorruption());
+        ASSERT_EQ(
+            statuses[0].ToString().find(corrupted_key_hex) != std::string::npos,
+            allow_data_in_error);
+      } else {
+        ASSERT_TRUE(statuses[0].IsNotFound());
+      }
+    }
+
+    {
+      // Test Iterator Seek API
+      std::unique_ptr<Iterator> iter{db_->NewIterator(rops)};
+      ASSERT_OK(iter->status());
+      iter->Seek(key_to_corrupt);
+      auto status = iter->status();
+      if (enable_key_validation_on_seek) {
+        ASSERT_TRUE(status.IsCorruption());
+        ASSERT_EQ(
+            status.ToString().find(corrupted_key_hex) != std::string::npos,
+            allow_data_in_error);
+      } else {
+        ASSERT_FALSE(iter->Valid());
+        ASSERT_FALSE(status.ok());
+      }
+    }
+
+    // revert the key corruption.
+    raw_data_pointer[i][key_to_corrupt.size()] = '0';
+  }
+}
+
+INSTANTIATE_TEST_CASE_P(DBMemTableTestForSeek, DBMemTableTestForSeek,
+                        ::testing::Combine(::testing::Bool(), ::testing::Bool(),
+                                           ::testing::Bool()));
+
 TEST_F(DBMemTableTest, IntegrityChecks) {
   // We insert keys key000000, key000001 and key000002 into skiplist at fixed
   // height 1 (smallest height). Then we corrupt the second key to aey000001 to

package/deps/rocksdb/rocksdb/db/db_sst_test.cc

@@ -1937,6 +1937,70 @@ TEST_F(DBSSTTest, DBWithSFMForBlobFilesAtomicFlush) {
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
+TEST_F(DBSSTTest, SstGetFileSizeFails) {
+  // Build an SST file
+  ASSERT_OK(Put("x", "zaphod"));
+  ASSERT_OK(Flush());
+  std::vector<LiveFileMetaData> metadata;
+  db_->GetLiveFilesMetaData(&metadata);
+  ASSERT_EQ(1U, metadata.size());
+  std::string filename = dbname_ + metadata[0].name;
+
+  // Prepare for fault injection
+  std::shared_ptr<FaultInjectionTestFS> fault_fs =
+      std::make_shared<FaultInjectionTestFS>(
+          CurrentOptions().env->GetFileSystem());
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.env = fault_fs_env.get();
+  options.paranoid_checks = false;  // don't check file sizes on open
+
+  for (int i = 0; i < 4; i++) {
+    SCOPED_TRACE("Iteration = " + std::to_string(i));
+    fault_fs->SetFailRandomAccessGetFileSizeSst(false);
+    fault_fs->SetFailFilesystemGetFileSizeSst(false);
+    Close();
+
+    if (i == 1) {
+      // Just FSRandomAccessFile::GetFileSize fails, which should be worked
+      // around
+      fault_fs->SetFailRandomAccessGetFileSizeSst(true);
+    } else if (i == 2) {
+      // FileSystem::GetFileSize fails, which should be worked around if
+      // FSRandomAccessFile::GetFileSize is supported
+      fault_fs->SetFailFilesystemGetFileSizeSst(true);
+    } else if (i == 3) {
+      // Both GetFileSize APIs fail with an IOError
+      fault_fs->SetFailRandomAccessGetFileSizeSst(true);
+      fault_fs->SetFailFilesystemGetFileSizeSst(true);
+    }
+
+    ASSERT_OK(TryReopen(options));
+    std::string value;
+    Status get_status = db_->Get({}, "x", &value);
+    if (i < 2) {
+      ASSERT_OK(get_status);
+    } else if (i == 2) {
+      if (encrypted_env_) {
+        // Can't recover because RandomAccessFile::GetFileSize is not supported
+        // on EncryptedEnv
+        // Fail with propagated IOError. (Not Corruption nor NotSupported!)
+        ASSERT_EQ(get_status.code(), Status::Code::kIOError);
+        ASSERT_STREQ(get_status.getState(), "FileSystem::GetFileSize failed");
+      } else {
+        // Never sees the FileSystem::GetFileSize failure
+        ASSERT_OK(get_status);
+      }
+    } else {
+      ASSERT_EQ(i, 3);
+      // Fail with propagated IOError. (Not Corruption nor NotSupported!)
+      ASSERT_EQ(get_status.code(), Status::Code::kIOError);
+      ASSERT_STREQ(get_status.getState(), "FileSystem::GetFileSize failed");
+    }
+  }
+  Close();
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {