9b51987521
Summary: When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache. What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention. Test Plan: 'export TEST_TMPDIR=/dev/shm/ && DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32' is OK. I didn't run the Java tests, I don't have Java set up on my devserver. Reviewers: sdong Reviewed By: sdong Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D56133
99 lines
4.0 KiB
C++
99 lines
4.0 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under the BSD-style license found in the
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
//
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
#pragma once
|
|
#include <memory>
|
|
|
|
namespace rocksdb {
|
|
|
|
class Iterator;
|
|
struct ParsedInternalKey;
|
|
class Slice;
|
|
class Arena;
|
|
struct ReadOptions;
|
|
struct TableProperties;
|
|
class GetContext;
|
|
class InternalIterator;
|
|
|
|
// A Table is a sorted map from strings to strings. Tables are
|
|
// immutable and persistent. A Table may be safely accessed from
|
|
// multiple threads without external synchronization.
|
|
class TableReader {
|
|
public:
|
|
virtual ~TableReader() {}
|
|
|
|
// Returns a new iterator over the table contents.
|
|
// The result of NewIterator() is initially invalid (caller must
|
|
// call one of the Seek methods on the iterator before using it).
|
|
// arena: If not null, the arena needs to be used to allocate the Iterator.
|
|
// When destroying the iterator, the caller will not call "delete"
|
|
// but Iterator::~Iterator() directly. The destructor needs to destroy
|
|
// all the states but those allocated in arena.
|
|
// skip_filters: disables checking the bloom filters even if they exist. This
|
|
// option is effective only for block-based table format.
|
|
virtual InternalIterator* NewIterator(const ReadOptions&,
|
|
Arena* arena = nullptr,
|
|
bool skip_filters = false) = 0;
|
|
|
|
// Given a key, return an approximate byte offset in the file where
|
|
// the data for that key begins (or would begin if the key were
|
|
// present in the file). The returned value is in terms of file
|
|
// bytes, and so includes effects like compression of the underlying data.
|
|
// E.g., the approximate offset of the last key in the table will
|
|
// be close to the file length.
|
|
virtual uint64_t ApproximateOffsetOf(const Slice& key) = 0;
|
|
|
|
// Set up the table for Compaction. Might change some parameters with
|
|
// posix_fadvise
|
|
virtual void SetupForCompaction() = 0;
|
|
|
|
virtual std::shared_ptr<const TableProperties> GetTableProperties() const = 0;
|
|
|
|
// Prepare work that can be done before the real Get()
|
|
virtual void Prepare(const Slice& target) {}
|
|
|
|
// Report an approximation of how much memory has been used.
|
|
virtual size_t ApproximateMemoryUsage() const = 0;
|
|
|
|
// Calls get_context->SaveValue() repeatedly, starting with
|
|
// the entry found after a call to Seek(key), until it returns false.
|
|
// May not make such a call if filter policy says that key is not present.
|
|
//
|
|
// get_context->MarkKeyMayExist needs to be called when it is configured to be
|
|
// memory only and the key is not found in the block cache.
|
|
//
|
|
// readOptions is the options for the read
|
|
// key is the key to search for
|
|
// skip_filters: disables checking the bloom filters even if they exist. This
|
|
// option is effective only for block-based table format.
|
|
virtual Status Get(const ReadOptions& readOptions, const Slice& key,
|
|
GetContext* get_context, bool skip_filters = false) = 0;
|
|
|
|
// Prefetch data corresponding to a give range of keys
|
|
// Typically this functionality is required for table implementations that
|
|
// persists the data on a non volatile storage medium like disk/SSD
|
|
virtual Status Prefetch(const Slice* begin = nullptr,
|
|
const Slice* end = nullptr) {
|
|
(void) begin;
|
|
(void) end;
|
|
// Default implementation is NOOP.
|
|
// The child class should implement functionality when applicable
|
|
return Status::OK();
|
|
}
|
|
|
|
// convert db file to a human readable form
|
|
virtual Status DumpTable(WritableFile* out_file) {
|
|
return Status::NotSupported("DumpTable() not supported");
|
|
}
|
|
|
|
virtual void Close() {}
|
|
};
|
|
|
|
} // namespace rocksdb
|