Support for block_cache num_shards and other config via option string.

Summary:
Problem: Option string accepts only cache_size as parameter for block_cache which is specified as "block_cache=1M".
It doesn't accept other parameters like num_shards etc.

Changes :
1) ParseBlockBasedTableOption in block_based_table_factory is edited to accept cache options in the format "block_cache=<cache_size>:<num_shard_bits>:<strict_capacity_limit>:<high_pri_pool_ratio>".
Options other than cache_size are optional to maintain backward compatibility. The changes are valid for block_cache_compressed as well.
For example, "block_cache=1M:6:true:0.5", "block_cache=1M:6:true", "block_cache=1M:6" and "block_cache=1M" are all valid option strings.

2) Corresponding unit tests are added.
Closes https://github.com/facebook/rocksdb/pull/3108

Differential Revision: D6420997

Pulled By: sagar0

fbshipit-source-id: cdea8b785688d2802907974af27225ccc1c0cd43

cache/lru_cache.cc

@@ -169,6 +169,11 @@ size_t LRUCacheShard::TEST_GetLRUSize() {
   return lru_size;
 }
 
+double LRUCacheShard::GetHighPriPoolRatio() {
+  MutexLock l(&mutex_);
+  return high_pri_pool_ratio_;
+}
+
 void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   assert(e->next != nullptr);
   assert(e->prev != nullptr);
@@ -513,6 +518,20 @@ size_t LRUCache::TEST_GetLRUSize() {
   return lru_size_of_all_shards;
 }
 
+double LRUCache::GetHighPriPoolRatio() {
+  double result = 0.0;
+  if (num_shards_ > 0) {
+    result = shards_[0].GetHighPriPoolRatio();
+  }
+  return result;
+}
+
+std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
+  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
+                     cache_opts.strict_capacity_limit,
+                     cache_opts.high_pri_pool_ratio);
+}
+
 std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
                                    bool strict_capacity_limit,
                                    double high_pri_pool_ratio) {

cache/lru_cache.h

@@ -202,6 +202,9 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
   //  not threadsafe
   size_t TEST_GetLRUSize();
 
+  //  Retrives high pri pool ratio
+  double GetHighPriPoolRatio();
+
   // Overloading to aligned it to cache line size
   void* operator new(size_t);
 
@@ -293,6 +296,8 @@ class LRUCache : public ShardedCache {
 
   //  Retrieves number of elements in LRU, for unit test purpose only
   size_t TEST_GetLRUSize();
+  //  Retrives high pri pool ratio
+  double GetHighPriPoolRatio();
 
  private:
   LRUCacheShard* shards_;

include/rocksdb/cache.h

@@ -33,6 +33,31 @@ namespace rocksdb {
 
 class Cache;
 
+struct LRUCacheOptions {
+  // Capacity of the cache.
+  size_t capacity = 0;
+
+  // Cache is sharded into 2^num_shard_bits shards,
+  // by hash of key. Refer to NewLRUCache for further
+  // information.
+  int num_shard_bits = -1;
+
+  // If strict_capacity_limit is set,
+  // insert to the cache will fail when cache is full.
+  bool strict_capacity_limit = false;
+
+  // Percentage of cache reserved for high priority entries.
+  double high_pri_pool_ratio = 0.0;
+
+  LRUCacheOptions() {}
+  LRUCacheOptions(size_t _capacity, int _num_shard_bits,
+                  bool _strict_capacity_limit, double _high_pri_pool_ratio)
+      : capacity(_capacity),
+        num_shard_bits(_num_shard_bits),
+        strict_capacity_limit(_strict_capacity_limit),
+        high_pri_pool_ratio(_high_pri_pool_ratio) {}
+};
+
 // Create a new cache with a fixed size capacity. The cache is sharded
 // to 2^num_shard_bits shards, by hash of the key. The total capacity
 // is divided and evenly assigned to each shard. If strict_capacity_limit
@@ -46,6 +71,8 @@ extern std::shared_ptr<Cache> NewLRUCache(size_t capacity,
                                           bool strict_capacity_limit = false,
                                           double high_pri_pool_ratio = 0.0);
 
+extern std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts);
+
 // Similar to NewLRUCache, but create a cache based on CLOCK algorithm with
 // better concurrent performance in some cases. See util/clock_cache.cc for
 // more detail.

options/options_helper.cc

@@ -491,6 +491,11 @@ bool ParseOptionHelper(char* opt_address, const OptionType& opt_type,
       }
       return true;
     }
+    case OptionType::kLRUCacheOptions: {
+      return ParseStructOptions<LRUCacheOptions>(value,
+          reinterpret_cast<LRUCacheOptions*>(opt_address),
+          lru_cache_options_type_info);
+    }
     default:
       return false;
   }
@@ -1519,6 +1524,7 @@ std::unordered_map<std::string, InfoLogLevel>
 
 ColumnFamilyOptions OptionsHelper::dummy_cf_options;
 CompactionOptionsFIFO OptionsHelper::dummy_comp_options;
+LRUCacheOptions OptionsHelper::dummy_lru_cache_options;
 
 // offset_of is used to get the offset of a class data member
 // ex: offset_of(&ColumnFamilyOptions::num_levels)
@@ -1544,6 +1550,11 @@ int offset_of(T1 CompactionOptionsFIFO::*member) {
   return int(size_t(&(OptionsHelper::dummy_comp_options.*member)) -
              size_t(&OptionsHelper::dummy_comp_options));
 }
+template <typename T1>
+int offset_of(T1 LRUCacheOptions::*member) {
+  return int(size_t(&(OptionsHelper::dummy_lru_cache_options.*member)) -
+             size_t(&OptionsHelper::dummy_lru_cache_options));
+}
 
 std::unordered_map<std::string, OptionTypeInfo>
     OptionsHelper::cf_options_type_info = {
@@ -1788,6 +1799,23 @@ std::unordered_map<std::string, OptionTypeInfo>
           OptionType::kBoolean, OptionVerificationType::kNormal, true,
           offsetof(struct CompactionOptionsFIFO, allow_compaction)}}};
 
+std::unordered_map<std::string, OptionTypeInfo>
+    OptionsHelper::lru_cache_options_type_info = {
+        {"capacity", {offset_of(&LRUCacheOptions::capacity),
+          OptionType::kSizeT, OptionVerificationType::kNormal, true,
+          offsetof(struct LRUCacheOptions, capacity)}},
+        {"num_shard_bits", {offset_of(&LRUCacheOptions::num_shard_bits),
+          OptionType::kInt, OptionVerificationType::kNormal, true,
+          offsetof(struct LRUCacheOptions, num_shard_bits)}},
+        {"strict_capacity_limit",
+         {offset_of(&LRUCacheOptions::strict_capacity_limit),
+          OptionType::kBoolean, OptionVerificationType::kNormal, true,
+          offsetof(struct LRUCacheOptions, strict_capacity_limit)}},
+        {"high_pri_pool_ratio",
+         {offset_of(&LRUCacheOptions::high_pri_pool_ratio),
+          OptionType::kDouble, OptionVerificationType::kNormal, true,
+          offsetof(struct LRUCacheOptions, high_pri_pool_ratio)}}};
+
 #endif  // !ROCKSDB_LITE
 
 }  // namespace rocksdb

options/options_helper.h

@@ -73,6 +73,7 @@ enum class OptionType {
   kWALRecoveryMode,
   kAccessHint,
   kInfoLogLevel,
+  kLRUCacheOptions,
   kUnknown
 };
 
@@ -145,6 +146,8 @@ struct OptionsHelper {
   static std::unordered_map<std::string, OptionTypeInfo>
       fifo_compaction_options_type_info;
   static std::unordered_map<std::string, OptionTypeInfo> db_options_type_info;
+  static std::unordered_map<std::string, OptionTypeInfo>
+      lru_cache_options_type_info;
   static std::unordered_map<std::string, CompressionType>
       compression_type_string_map;
   static std::unordered_map<std::string, BlockBasedTableOptions::IndexType>
@@ -162,6 +165,7 @@ struct OptionsHelper {
       info_log_level_string_map;
   static ColumnFamilyOptions dummy_cf_options;
   static CompactionOptionsFIFO dummy_comp_options;
+  static LRUCacheOptions dummy_lru_cache_options;
 #endif  // !ROCKSDB_LITE
 };
 
@@ -177,6 +181,8 @@ static auto& cf_options_type_info = OptionsHelper::cf_options_type_info;
 static auto& fifo_compaction_options_type_info =
     OptionsHelper::fifo_compaction_options_type_info;
 static auto& db_options_type_info = OptionsHelper::db_options_type_info;
+static auto& lru_cache_options_type_info =
+    OptionsHelper::lru_cache_options_type_info;
 static auto& compression_type_string_map =
     OptionsHelper::compression_type_string_map;
 static auto& block_base_table_index_type_string_map =

options/options_test.cc

@@ -16,6 +16,8 @@
 #include <unordered_map>
 #include <inttypes.h>
 
+#include "cache/lru_cache.h"
+#include "cache/sharded_cache.h"
 #include "options/options_helper.h"
 #include "options/options_parser.h"
 #include "options/options_sanity_check.h"
@@ -529,6 +531,101 @@ TEST_F(OptionsTest, GetBlockBasedTableOptionsFromString) {
   ASSERT_EQ(table_opt.cache_index_and_filter_blocks,
             new_opt.cache_index_and_filter_blocks);
   ASSERT_EQ(table_opt.filter_policy, new_opt.filter_policy);
+
+  // Check block cache options are overwritten when specified
+  // in new format as a struct.
+  ASSERT_OK(GetBlockBasedTableOptionsFromString(table_opt,
+             "block_cache={capacity=1M;num_shard_bits=4;"
+             "strict_capacity_limit=true;high_pri_pool_ratio=0.5;};"
+             "block_cache_compressed={capacity=1M;num_shard_bits=4;"
+             "strict_capacity_limit=true;high_pri_pool_ratio=0.5;}",
+             &new_opt));
+  ASSERT_TRUE(new_opt.block_cache != nullptr);
+  ASSERT_EQ(new_opt.block_cache->GetCapacity(), 1024UL*1024UL);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache)->GetNumShardBits(), 4);
+  ASSERT_EQ(new_opt.block_cache->HasStrictCapacityLimit(), true);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache)->GetHighPriPoolRatio(), 0.5);
+  ASSERT_TRUE(new_opt.block_cache_compressed != nullptr);
+  ASSERT_EQ(new_opt.block_cache_compressed->GetCapacity(), 1024UL*1024UL);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache_compressed)->GetNumShardBits(), 4);
+  ASSERT_EQ(new_opt.block_cache_compressed->HasStrictCapacityLimit(), true);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache_compressed)->GetHighPriPoolRatio(),
+                0.5);
+
+  // Set only block cache capacity. Check other values are
+  // reset to default values.
+  ASSERT_OK(GetBlockBasedTableOptionsFromString(table_opt,
+             "block_cache={capacity=2M};"
+             "block_cache_compressed={capacity=2M}",
+             &new_opt));
+  ASSERT_TRUE(new_opt.block_cache != nullptr);
+  ASSERT_EQ(new_opt.block_cache->GetCapacity(), 2*1024UL*1024UL);
+  // Default values
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache)->GetNumShardBits(),
+                GetDefaultCacheShardBits(new_opt.block_cache->GetCapacity()));
+  ASSERT_EQ(new_opt.block_cache->HasStrictCapacityLimit(), false);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache)->GetHighPriPoolRatio(), 0.0);
+  ASSERT_TRUE(new_opt.block_cache_compressed != nullptr);
+  ASSERT_EQ(new_opt.block_cache_compressed->GetCapacity(), 2*1024UL*1024UL);
+  // Default values
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache_compressed)->GetNumShardBits(),
+                GetDefaultCacheShardBits(
+                    new_opt.block_cache_compressed->GetCapacity()));
+  ASSERT_EQ(new_opt.block_cache_compressed->HasStrictCapacityLimit(), false);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache_compressed)->GetHighPriPoolRatio(),
+                0.0);
+
+  // Set couple of block cache options.
+  ASSERT_OK(GetBlockBasedTableOptionsFromString(table_opt,
+             "block_cache={num_shard_bits=5;high_pri_pool_ratio=0.5;};"
+             "block_cache_compressed={num_shard_bits=5;"
+             "high_pri_pool_ratio=0.5;}",
+             &new_opt));
+  ASSERT_EQ(new_opt.block_cache->GetCapacity(), 0);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache)->GetNumShardBits(), 5);
+  ASSERT_EQ(new_opt.block_cache->HasStrictCapacityLimit(), false);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache)->GetHighPriPoolRatio(), 0.5);
+  ASSERT_TRUE(new_opt.block_cache_compressed != nullptr);
+  ASSERT_EQ(new_opt.block_cache_compressed->GetCapacity(), 0);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache_compressed)->GetNumShardBits(), 5);
+  ASSERT_EQ(new_opt.block_cache_compressed->HasStrictCapacityLimit(), false);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache_compressed)->GetHighPriPoolRatio(),
+                0.5);
+
+  // Set couple of block cache options.
+  ASSERT_OK(GetBlockBasedTableOptionsFromString(table_opt,
+             "block_cache={capacity=1M;num_shard_bits=4;"
+             "strict_capacity_limit=true;};"
+             "block_cache_compressed={capacity=1M;num_shard_bits=4;"
+             "strict_capacity_limit=true;}",
+             &new_opt));
+  ASSERT_TRUE(new_opt.block_cache != nullptr);
+  ASSERT_EQ(new_opt.block_cache->GetCapacity(), 1024UL*1024UL);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache)->GetNumShardBits(), 4);
+  ASSERT_EQ(new_opt.block_cache->HasStrictCapacityLimit(), true);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache)->GetHighPriPoolRatio(), 0.0);
+  ASSERT_TRUE(new_opt.block_cache_compressed != nullptr);
+  ASSERT_EQ(new_opt.block_cache_compressed->GetCapacity(), 1024UL*1024UL);
+  ASSERT_EQ(std::dynamic_pointer_cast<ShardedCache>(
+                new_opt.block_cache_compressed)->GetNumShardBits(), 4);
+  ASSERT_EQ(new_opt.block_cache_compressed->HasStrictCapacityLimit(), true);
+  ASSERT_EQ(std::dynamic_pointer_cast<LRUCache>(
+                new_opt.block_cache_compressed)->GetHighPriPoolRatio(),
+                0.0);
 }
 #endif  // !ROCKSDB_LITE
 

table/block_based_table_factory.cc

@@ -291,11 +291,31 @@ std::string ParseBlockBasedTableOption(const std::string& name,
   if (!input_strings_escaped) {
     // if the input string is not escaped, it means this function is
     // invoked from SetOptions, which takes the old format.
-    if (name == "block_cache") {
+    if (name == "block_cache" || name == "block_cache_compressed") {
-      new_options->block_cache = NewLRUCache(ParseSizeT(value));
+      // cache options can be specified in the following format
-      return "";
+      //   "block_cache={capacity=1M;num_shard_bits=4;
-    } else if (name == "block_cache_compressed") {
+      //    strict_capacity_limit=true;high_pri_pool_ratio=0.5;}"
-      new_options->block_cache_compressed = NewLRUCache(ParseSizeT(value));
+      // To support backward compatibility, the following format
+      // is also supported.
+      //   "block_cache=1M"
+      std::shared_ptr<Cache> cache;
+      // block_cache is specified in format block_cache=<cache_size>.
+      if (value.find('=') == std::string::npos) {
+        cache = NewLRUCache(ParseSizeT(value));
+      } else {
+        LRUCacheOptions cache_opts;
+        if(!ParseOptionHelper(reinterpret_cast<char*>(&cache_opts),
+                              OptionType::kLRUCacheOptions, value)) {
+          return "Invalid cache options";
+        }
+        cache = NewLRUCache(cache_opts);
+      }
+
+      if (name == "block_cache") {
+        new_options->block_cache = cache;
+      } else {
+        new_options->block_cache_compressed = cache;
+      }
       return "";
     } else if (name == "filter_policy") {
       // Expect the following format