Allow allocating dynamic bloom, plain table indexes and hash linked list from huge page TLB

Summary: Add an option to allocate a piece of memory from huge page TLB. Add options to trigger it in dynamic bloom, plain table indexes andhash linked list hash table.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: nkg-, dhruba, leveldb, igor, yhchiang

Differential Revision: https://reviews.facebook.net/D18357

include/rocksdb/memtablerep.h

@@ -223,9 +223,14 @@ extern MemTableRepFactory* NewHashSkipListRepFactory(
 // The factory is to create memtables with a hashed linked list:
 // it contains a fixed array of buckets, each pointing to a sorted single
 // linked list (null if the bucket is empty).
-// bucket_count: number of fixed array buckets
+// @bucket_count: number of fixed array buckets
+// @huge_page_tlb_size: if <=0, allocate the hash table bytes from malloc.
+//                      Otherwise from huge page TLB. The user needs to reserve
+//                      huge pages for it to be allocated, like:
+//                          sysctl -w vm.nr_hugepages=20
+//                      See linux doc Documentation/vm/hugetlbpage.txt
 extern MemTableRepFactory* NewHashLinkListRepFactory(
-    size_t bucket_count = 50000);
+    size_t bucket_count = 50000, size_t huge_page_tlb_size = 2 * 1024 * 1024);
 
 // This factory creates a cuckoo-hashing based mem-table representation.
 // Cuckoo-hash is a closed-hash strategy, in which all key/value pairs

include/rocksdb/options.h

@@ -497,6 +497,14 @@ struct ColumnFamilyOptions {
   // number of hash probes per key
   uint32_t memtable_prefix_bloom_probes;
 
+  // Page size for huge page TLB for bloom in memtable. If <=0, not allocate
+  // from huge page TLB but from malloc.
+  // Need to reserve huge pages for it to be allocated. For example:
+  //      sysctl -w vm.nr_hugepages=20
+  // See linux doc Documentation/vm/hugetlbpage.txt
+
+  size_t memtable_prefix_bloom_huge_page_tlb_size;
+
   // Control locality of bloom filter probes to improve cache miss rate.
   // This option only applies to memtable prefix bloom and plaintable
   // prefix bloom. It essentially limits the max number of cache lines each

include/rocksdb/table.h

@@ -96,12 +96,19 @@ extern TableFactory* NewBlockBasedTableFactory(
 //                    in the hash table
 // @index_sparseness: inside each prefix, need to build one index record for how
 //                    many keys for binary search inside each hash bucket.
+// @huge_page_tlb_size: if <=0, allocate hash indexes and blooms from malloc.
+//                      Otherwise from huge page TLB. The user needs to reserve
+//                      huge pages for it to be allocated, like:
+//                          sysctl -w vm.nr_hugepages=20
+//                      See linux doc Documentation/vm/hugetlbpage.txt
+
 const uint32_t kPlainTableVariableLength = 0;
 extern TableFactory* NewPlainTableFactory(uint32_t user_key_len =
                                               kPlainTableVariableLength,
                                           int bloom_bits_per_prefix = 10,
                                           double hash_table_ratio = 0.75,
-                                          size_t index_sparseness = 16);
+                                          size_t index_sparseness = 16,
+                                          size_t huge_page_tlb_size = 0);
 
 // -- Plain Table
 // This factory of plain table ignores Options.prefix_extractor and assumes no
@@ -115,9 +122,15 @@ extern TableFactory* NewPlainTableFactory(uint32_t user_key_len =
 //                  disable it by passing a zero.
 // @index_sparseness: need to build one index record for how many keys for
 //                    binary search.
+// @huge_page_tlb_size: if <=0, allocate hash indexes and blooms from malloc.
+//                      Otherwise from huge page TLB. The user needs to reserve
+//                      huge pages for it to be allocated, like:
+//                          sysctl -w vm.nr_hugepages=20
+//                      See linux doc Documentation/vm/hugetlbpage.txt
 extern TableFactory* NewTotalOrderPlainTableFactory(
     uint32_t user_key_len = kPlainTableVariableLength,
-    int bloom_bits_per_key = 0, size_t index_sparseness = 16);
+    int bloom_bits_per_key = 0, size_t index_sparseness = 16,
+    size_t huge_page_tlb_size = 0);
 
 #endif  // ROCKSDB_LITE