Revision 1f32dc7d2b6721a1fe13eb515d52e5cd6f110f59 authored by Andrew Kryczka on 14 June 2018, 00:28:31 UTC, committed by Facebook Github Bot on 14 June 2018, 00:32:04 UTC
Summary:
Rebased and resubmitting #1831 on behalf of stevelittle.

The problem is when a single process attempts to open the same DB twice, the second attempt fails due to LOCK file held. If the second attempt had opened the LOCK file, it'll now need to close it, and closing causes the file to be unlocked. Then, any subsequent attempt to open the DB will succeed, which is the wrong behavior.

The solution was to track which files a process has locked in PosixEnv, and check those before opening a LOCK file.

Fixes #1780.
Closes https://github.com/facebook/rocksdb/pull/3993

Differential Revision: D8398984

Pulled By: ajkr

fbshipit-source-id: 2755fe66950a0c9de63075f932f9e15768041918
1 parent 7497f99
Raw File
table_cache.h
//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
//  This source code is licensed under both the GPLv2 (found in the
//  COPYING file in the root directory) and Apache 2.0 License
//  (found in the LICENSE.Apache file in the root 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.
//
// Thread-safe (provides internal synchronization)

#pragma once
#include <string>
#include <vector>
#include <stdint.h>

#include "db/dbformat.h"
#include "db/range_del_aggregator.h"
#include "options/cf_options.h"
#include "port/port.h"
#include "rocksdb/cache.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/table_reader.h"

namespace rocksdb {

class Env;
class Arena;
struct FileDescriptor;
class GetContext;
class HistogramImpl;
class InternalIterator;

class TableCache {
 public:
  TableCache(const ImmutableCFOptions& ioptions,
             const EnvOptions& storage_options, Cache* cache);
  ~TableCache();

  // Return an iterator for the specified file number (the corresponding
  // file length must be exactly "file_size" bytes).  If "tableptr" is
  // non-nullptr, also sets "*tableptr" to point to the Table object
  // underlying the returned iterator, or nullptr if no Table object underlies
  // the returned iterator.  The returned "*tableptr" object is owned by
  // the cache and should not be deleted, and is valid for as long as the
  // returned iterator is live.
  // @param range_del_agg If non-nullptr, adds range deletions to the
  //    aggregator. If an error occurs, returns it in a NewErrorInternalIterator
  // @param skip_filters Disables loading/accessing the filter block
  // @param level The level this table is at, -1 for "not set / don't know"
  InternalIterator* NewIterator(
      const ReadOptions& options, const EnvOptions& toptions,
      const InternalKeyComparator& internal_comparator,
      const FileDescriptor& file_fd, RangeDelAggregator* range_del_agg,
      const SliceTransform* prefix_extractor = nullptr,
      TableReader** table_reader_ptr = nullptr,
      HistogramImpl* file_read_hist = nullptr, bool for_compaction = false,
      Arena* arena = nullptr, bool skip_filters = false, int level = -1);

  InternalIterator* NewRangeTombstoneIterator(
      const ReadOptions& options, const EnvOptions& toptions,
      const InternalKeyComparator& internal_comparator,
      const FileDescriptor& file_fd, HistogramImpl* file_read_hist,
      bool skip_filters, int level,
      const SliceTransform* prefix_extractor = nullptr);

  // If a seek to internal key "k" in specified file finds an entry,
  // call (*handle_result)(arg, found_key, found_value) repeatedly until
  // it returns false.
  // @param get_context State for get operation. If its range_del_agg() returns
  //    non-nullptr, adds range deletions to the aggregator. If an error occurs,
  //    returns non-ok status.
  // @param skip_filters Disables loading/accessing the filter block
  // @param level The level this table is at, -1 for "not set / don't know"
  Status Get(const ReadOptions& options,
             const InternalKeyComparator& internal_comparator,
             const FileDescriptor& file_fd, const Slice& k,
             GetContext* get_context,
             const SliceTransform* prefix_extractor = nullptr,
             HistogramImpl* file_read_hist = nullptr, bool skip_filters = false,
             int level = -1);

  // Evict any entry for the specified file number
  static void Evict(Cache* cache, uint64_t file_number);

  // Clean table handle and erase it from the table cache
  // Used in DB close, or the file is not live anymore.
  void EraseHandle(const FileDescriptor& fd, Cache::Handle* handle);

  // Find table reader
  // @param skip_filters Disables loading/accessing the filter block
  // @param level == -1 means not specified
  Status FindTable(const EnvOptions& toptions,
                   const InternalKeyComparator& internal_comparator,
                   const FileDescriptor& file_fd, Cache::Handle**,
                   const SliceTransform* prefix_extractor = nullptr,
                   const bool no_io = false, bool record_read_stats = true,
                   HistogramImpl* file_read_hist = nullptr,
                   bool skip_filters = false, int level = -1,
                   bool prefetch_index_and_filter_in_cache = true);

  // Get TableReader from a cache handle.
  TableReader* GetTableReaderFromHandle(Cache::Handle* handle);

  // Get the table properties of a given table.
  // @no_io: indicates if we should load table to the cache if it is not present
  //         in table cache yet.
  // @returns: `properties` will be reset on success. Please note that we will
  //            return Status::Incomplete() if table is not present in cache and
  //            we set `no_io` to be true.
  Status GetTableProperties(const EnvOptions& toptions,
                            const InternalKeyComparator& internal_comparator,
                            const FileDescriptor& file_meta,
                            std::shared_ptr<const TableProperties>* properties,
                            const SliceTransform* prefix_extractor = nullptr,
                            bool no_io = false);

  // Return total memory usage of the table reader of the file.
  // 0 if table reader of the file is not loaded.
  size_t GetMemoryUsageByTableReader(
      const EnvOptions& toptions,
      const InternalKeyComparator& internal_comparator,
      const FileDescriptor& fd,
      const SliceTransform* prefix_extractor = nullptr);

  // Release the handle from a cache
  void ReleaseHandle(Cache::Handle* handle);

  // Capacity of the backing Cache that indicates inifinite TableCache capacity.
  // For example when max_open_files is -1 we set the backing Cache to this.
  static const int kInfiniteCapacity = 0x400000;

 private:
  // Build a table reader
  Status GetTableReader(const EnvOptions& env_options,
                        const InternalKeyComparator& internal_comparator,
                        const FileDescriptor& fd, bool sequential_mode,
                        size_t readahead, bool record_read_stats,
                        HistogramImpl* file_read_hist,
                        unique_ptr<TableReader>* table_reader,
                        const SliceTransform* prefix_extractor = nullptr,
                        bool skip_filters = false, int level = -1,
                        bool prefetch_index_and_filter_in_cache = true,
                        bool for_compaction = false);

  const ImmutableCFOptions& ioptions_;
  const EnvOptions& env_options_;
  Cache* const cache_;
  std::string row_cache_id_;
};

}  // namespace rocksdb
back to top