Add a blob-specific cache priority (facebook#10461) (tikv#354)

* Add a blob-specific cache priority (facebook#10461) Summary: RocksDB's `Cache` abstraction currently supports two priority levels for items: high (used for frequently accessed/highly valuable SST metablocks like index/filter blocks) and low (used for SST data blocks). Blobs are typically lower-value targets for caching than data blocks, since 1) with BlobDB, data blocks containing blob references conceptually form an index structure which has to be consulted before we can read the blob value, and 2) cached blobs represent only a single key-value, while cached data blocks generally contain multiple KVs. Since we would like to make it possible to use the same backing cache for the block cache and the blob cache, it would make sense to add a new, lower-than-low cache priority level (bottom level) for blobs so data blocks are prioritized over them. This task is a part of facebook#10156 Pull Request resolved: facebook#10461 Reviewed By: siying Differential Revision: D38672823 Pulled By: ltamasi fbshipit-source-id: 90cf7362036563d79891f47be2cc24b827482743 * make format Signed-off-by: Connor1996 <[email protected]> * make format Signed-off-by: Connor1996 <[email protected]> --------- Signed-off-by: Connor1996 <[email protected]> Co-authored-by: Gang Liao <[email protected]>
tonyxuqqi · Feb 1, 2024 · 3dba9fa · 3dba9fa
1 parent dcf2f8d
commit 3dba9fa
Show file tree

Hide file tree

Showing 21 changed files with 1,249 additions and 534 deletions.
diff --git a/HISTORY.md b/HISTORY.md
diff --git a/cache/cache.cc b/cache/cache.cc
@@ -33,6 +33,10 @@ static std::unordered_map<std::string, OptionTypeInfo>
          {offsetof(struct LRUCacheOptions, high_pri_pool_ratio),
           OptionType::kDouble, OptionVerificationType::kNormal,
           OptionTypeFlags::kMutable}},
+        {"low_pri_pool_ratio",
+         {offsetof(struct LRUCacheOptions, low_pri_pool_ratio),
+          OptionType::kDouble, OptionVerificationType::kNormal,
+          OptionTypeFlags::kMutable}},
 };
 #endif  // ROCKSDB_LITE
 

diff --git a/cache/lru_cache.cc b/cache/lru_cache.cc
@@ -111,14 +111,17 @@ void LRUHandleTable::Resize() {
 
 LRUCacheShard::LRUCacheShard(
     size_t capacity, bool strict_capacity_limit, double high_pri_pool_ratio,
-    bool use_adaptive_mutex, CacheMetadataChargePolicy metadata_charge_policy,
-    int max_upper_hash_bits,
+    double low_pri_pool_ratio, bool use_adaptive_mutex,
+    CacheMetadataChargePolicy metadata_charge_policy, int max_upper_hash_bits,
     const std::shared_ptr<SecondaryCache>& secondary_cache)
     : capacity_(0),
       high_pri_pool_usage_(0),
+      low_pri_pool_usage_(0),
       strict_capacity_limit_(strict_capacity_limit),
       high_pri_pool_ratio_(high_pri_pool_ratio),
       high_pri_pool_capacity_(0),
+      low_pri_pool_ratio_(low_pri_pool_ratio),
+      low_pri_pool_capacity_(0),
       table_(max_upper_hash_bits),
       usage_(0),
       lru_usage_(0),
@@ -129,6 +132,7 @@ LRUCacheShard::LRUCacheShard(
   lru_.next = &lru_;
   lru_.prev = &lru_;
   lru_low_pri_ = &lru_;
+  lru_bottom_pri_ = &lru_;
   SetCapacity(capacity);
 }
 
@@ -191,10 +195,12 @@ void LRUCacheShard::ApplyToSomeEntries(
       index_begin, index_end);
 }
 
-void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
+void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri,
+                                    LRUHandle** lru_bottom_pri) {
   MutexLock l(&mutex_);
   *lru = &lru_;
   *lru_low_pri = lru_low_pri_;
+  *lru_bottom_pri = lru_bottom_pri_;
 }
 
 size_t LRUCacheShard::TEST_GetLRUSize() {
@@ -213,12 +219,20 @@ double LRUCacheShard::GetHighPriPoolRatio() {
   return high_pri_pool_ratio_;
 }
 
+double LRUCacheShard::GetLowPriPoolRatio() {
+  MutexLock l(&mutex_);
+  return low_pri_pool_ratio_;
+}
+
 void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   assert(e->next != nullptr);
   assert(e->prev != nullptr);
   if (lru_low_pri_ == e) {
     lru_low_pri_ = e->prev;
   }
+  if (lru_bottom_pri_ == e) {
+    lru_bottom_pri_ = e->prev;
+  }
   e->next->prev = e->prev;
   e->prev->next = e->next;
   e->prev = e->next = nullptr;
@@ -228,6 +242,9 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   if (e->InHighPriPool()) {
     assert(high_pri_pool_usage_ >= total_charge);
     high_pri_pool_usage_ -= total_charge;
+  } else if (e->InLowPriPool()) {
+    assert(low_pri_pool_usage_ >= total_charge);
+    low_pri_pool_usage_ -= total_charge;
   }
 }
 
@@ -242,17 +259,34 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->prev->next = e;
     e->next->prev = e;
     e->SetInHighPriPool(true);
+    e->SetInLowPriPool(false);
     high_pri_pool_usage_ += total_charge;
     MaintainPoolSize();
-  } else {
-    // Insert "e" to the head of low-pri pool. Note that when
-    // high_pri_pool_ratio is 0, head of low-pri pool is also head of LRU list.
+  } else if (low_pri_pool_ratio_ > 0 &&
+             (e->IsHighPri() || e->IsLowPri() || e->HasHit())) {
+    // Insert "e" to the head of low-pri pool.
     e->next = lru_low_pri_->next;
     e->prev = lru_low_pri_;
     e->prev->next = e;
     e->next->prev = e;
     e->SetInHighPriPool(false);
+    e->SetInLowPriPool(true);
+    low_pri_pool_usage_ += total_charge;
+    MaintainPoolSize();
     lru_low_pri_ = e;
+  } else {
+    // Insert "e" to the head of bottom-pri pool.
+    e->next = lru_bottom_pri_->next;
+    e->prev = lru_bottom_pri_;
+    e->prev->next = e;
+    e->next->prev = e;
+    e->SetInHighPriPool(false);
+    e->SetInLowPriPool(false);
+    // if the low-pri pool is empty, lru_low_pri_ also needs to be updated.
+    if (lru_bottom_pri_ == lru_low_pri_) {
+      lru_low_pri_ = e;
+    }
+    lru_bottom_pri_ = e;
   }
   lru_usage_ += total_charge;
 }
@@ -263,10 +297,24 @@ void LRUCacheShard::MaintainPoolSize() {
     lru_low_pri_ = lru_low_pri_->next;
     assert(lru_low_pri_ != &lru_);
     lru_low_pri_->SetInHighPriPool(false);
+    lru_low_pri_->SetInLowPriPool(true);
     size_t total_charge =
         lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
     assert(high_pri_pool_usage_ >= total_charge);
     high_pri_pool_usage_ -= total_charge;
+    low_pri_pool_usage_ += total_charge;
+  }
+
+  while (low_pri_pool_usage_ > low_pri_pool_capacity_) {
+    // Overflow last entry in low-pri pool to bottom-pri pool.
+    lru_bottom_pri_ = lru_bottom_pri_->next;
+    assert(lru_bottom_pri_ != &lru_);
+    lru_bottom_pri_->SetInHighPriPool(false);
+    lru_bottom_pri_->SetInLowPriPool(false);
+    size_t total_charge =
+        lru_bottom_pri_->CalcTotalCharge(metadata_charge_policy_);
+    assert(low_pri_pool_usage_ >= total_charge);
+    low_pri_pool_usage_ -= total_charge;
   }
 }
 
@@ -292,6 +340,7 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
     MutexLock l(&mutex_);
     capacity_ = capacity;
     high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
+    low_pri_pool_capacity_ = capacity_ * low_pri_pool_ratio_;
     EvictFromLRU(0, &last_reference_list);
   }
 
@@ -507,6 +556,13 @@ void LRUCacheShard::SetHighPriorityPoolRatio(double high_pri_pool_ratio) {
   MaintainPoolSize();
 }
 
+void LRUCacheShard::SetLowPriorityPoolRatio(double low_pri_pool_ratio) {
+  MutexLock l(&mutex_);
+  low_pri_pool_ratio_ = low_pri_pool_ratio;
+  low_pri_pool_capacity_ = capacity_ * low_pri_pool_ratio_;
+  MaintainPoolSize();
+}
+
 bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
   if (handle == nullptr) {
     return false;
@@ -640,12 +696,15 @@ std::string LRUCacheShard::GetPrintableOptions() const {
     MutexLock l(&mutex_);
     snprintf(buffer, kBufferSize, "    high_pri_pool_ratio: %.3lf\n",
              high_pri_pool_ratio_);
+    snprintf(buffer + strlen(buffer), kBufferSize - strlen(buffer),
+             "    low_pri_pool_ratio: %.3lf\n", low_pri_pool_ratio_);
   }
   return std::string(buffer);
 }
 
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
                    bool strict_capacity_limit, double high_pri_pool_ratio,
+                   double low_pri_pool_ratio,
                    std::shared_ptr<MemoryAllocator> allocator,
                    bool use_adaptive_mutex,
                    CacheMetadataChargePolicy metadata_charge_policy,
@@ -659,7 +718,7 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
   for (int i = 0; i < num_shards_; i++) {
     new (&shards_[i]) LRUCacheShard(
         per_shard, strict_capacity_limit, high_pri_pool_ratio,
-        use_adaptive_mutex, metadata_charge_policy,
+        low_pri_pool_ratio, use_adaptive_mutex, metadata_charge_policy,
         /* max_upper_hash_bits */ 32 - num_shard_bits, secondary_cache);
   }
   secondary_cache_ = secondary_cache;
@@ -763,38 +822,49 @@ std::shared_ptr<Cache> NewLRUCache(
     double high_pri_pool_ratio,
     std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
     CacheMetadataChargePolicy metadata_charge_policy,
-    const std::shared_ptr<SecondaryCache>& secondary_cache) {
+    const std::shared_ptr<SecondaryCache>& secondary_cache,
+    double low_pri_pool_ratio) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
   if (high_pri_pool_ratio < 0.0 || high_pri_pool_ratio > 1.0) {
     // invalid high_pri_pool_ratio
     return nullptr;
   }
+  if (low_pri_pool_ratio < 0.0 || low_pri_pool_ratio > 1.0) {
+    // Invalid high_pri_pool_ratio
+    return nullptr;
+  }
+  if (low_pri_pool_ratio + high_pri_pool_ratio > 1.0) {
+    // Invalid high_pri_pool_ratio and low_pri_pool_ratio combination
+    return nullptr;
+  }
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
   return std::make_shared<LRUCache>(
       capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      std::move(memory_allocator), use_adaptive_mutex, metadata_charge_policy,
-      secondary_cache);
+      low_pri_pool_ratio, std::move(memory_allocator), use_adaptive_mutex,
+      metadata_charge_policy, secondary_cache);
 }
 
 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,
-      cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-      cache_opts.metadata_charge_policy, cache_opts.secondary_cache);
+  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
+                     cache_opts.strict_capacity_limit,
+                     cache_opts.high_pri_pool_ratio,
+                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
+                     cache_opts.metadata_charge_policy,
+                     cache_opts.secondary_cache, cache_opts.low_pri_pool_ratio);
 }
 
 std::shared_ptr<Cache> NewLRUCache(
     size_t capacity, int num_shard_bits, bool strict_capacity_limit,
     double high_pri_pool_ratio,
     std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+    CacheMetadataChargePolicy metadata_charge_policy,
+    double low_pri_pool_ratio) {
   return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
                      high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                     metadata_charge_policy, nullptr);
+                     metadata_charge_policy, nullptr, low_pri_pool_ratio);
 }
 }  // namespace ROCKSDB_NAMESPACE