Improve the "table stats"

Summary:
The primary motivation of the changes is to make it easier to figure out the inside of the tables.

* rename "table stats" to "table properties" since now we have more than "integers" to store in the property block.
* Add filter block size to the basic table properties.
* Whenever a table is built, we'll log the table properties (the sample output is in Test Plan).
* Make an api to expose deleted keys.

Test Plan:
Passed all existing test. and the sample output of table stats:

    ==================================================================
        Basic Properties
    ------------------------------------------------------------------
                  # data blocks: 1
                      # entries: 1

                   raw key size: 9
           raw average key size: 9
                 raw value size: 9
         raw average value size: 0

                data block size: 25
               index block size: 27
              filter block size: 18
         (estimated) table size: 70

                  filter policy: rocksdb.BuiltinBloomFilter
    ==================================================================
        User collected properties: InternalKeyPropertiesCollector
    ------------------------------------------------------------------
                    kDeletedKeys: 1
    ==================================================================

Reviewers: dhruba, haobo

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D14187
This commit is contained in:
kailiu
2013-11-19 16:29:42 -08:00
parent f045871f1c
commit 1415f8820d
17 changed files with 589 additions and 372 deletions

View File

@@ -21,7 +21,7 @@
#include "rocksdb/slice_transform.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/statistics.h"
#include "rocksdb/table_stats.h"
#include "rocksdb/table_properties.h"
#include "rocksdb/universal_compaction.h"
namespace rocksdb {
@@ -619,7 +619,8 @@ struct Options {
// the tables.
// Default: emtpy vector -- no user-defined statistics collection will be
// performed.
std::vector<std::shared_ptr<TableStatsCollector>> table_stats_collectors;
std::vector<std::shared_ptr<TablePropertiesCollector>>
table_properties_collectors;
// Allows thread-safe inplace updates. Requires Updates iff
// * key exists in current memtable

View File

@@ -12,7 +12,7 @@
#include <stdint.h>
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/table_stats.h"
#include "rocksdb/table_properties.h"
#include "rocksdb/options.h"
namespace rocksdb {
@@ -98,7 +98,7 @@ class TableReader {
// posix_fadvise
virtual void SetupForCompaction() = 0;
virtual TableStats& GetTableStats() = 0;
virtual TableProperties& GetTableProperties() = 0;
// Calls (*result_handler)(handle_context, ...) repeatedly, starting with
// the entry found after a call to Seek(key), until result_handler returns

View File

@@ -0,0 +1,90 @@
// Copyright (c) 2013, 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.
#pragma once
#include <string>
#include <unordered_map>
#include "rocksdb/status.h"
namespace rocksdb {
// TableProperties contains a bunch of read-only properties of its associated
// table.
struct TableProperties {
public:
// Other than basic table properties, each table may also have the user
// collected properties.
// The value of the user-collected properties are encoded as raw bytes --
// users have to interprete these values by themselves.
typedef
std::unordered_map<std::string, std::string>
UserCollectedProperties;
// the total size of all data blocks.
uint64_t data_size = 0;
// the size of index block.
uint64_t index_size = 0;
// the size of filter block.
uint64_t filter_size = 0;
// total raw key size
uint64_t raw_key_size = 0;
// total raw value size
uint64_t raw_value_size = 0;
// the number of blocks in this table
uint64_t num_data_blocks = 0;
// the number of entries in this table
uint64_t num_entries = 0;
// The name of the filter policy used in this table.
// If no filter policy is used, `filter_policy_name` will be an empty string.
std::string filter_policy_name;
// user collected properties
UserCollectedProperties user_collected_properties;
// convert this object to a human readable form
// @prop_delim: delimiter for each property.
std::string ToString(
const std::string& prop_delim = "; ",
const std::string& kv_delim = "=") const;
};
// `TablePropertiesCollector` provides the mechanism for users to collect
// their own interested properties. This class is essentially a collection
// of callback functions that will be invoked during table building.
class TablePropertiesCollector {
public:
virtual ~TablePropertiesCollector() { }
// Add() will be called when a new key/value pair is inserted into the table.
// @params key the original key that is inserted into the table.
// @params value the original value that is inserted into the table.
virtual Status Add(const Slice& key, const Slice& value) = 0;
// Finish() will be called when a table has already been built and is ready
// for writing the properties block.
// @params properties User will add their collected statistics to
// `properties`.
virtual Status Finish(
TableProperties::UserCollectedProperties* properties) = 0;
// The name of the properties collector can be used for debugging purpose.
virtual const char* Name() const = 0;
// Return the human-readable properties, where the key is property name and
// the value is the human-readable form of value.
virtual TableProperties::UserCollectedProperties
GetReadableProperties() const = 0;
};
// Extra properties
// Below is a list of non-basic properties that are collected by database
// itself. Especially some properties regarding to the internal keys (which
// is unknown to `table`).
extern uint64_t GetDeletedKeys(
const TableProperties::UserCollectedProperties& props);
} // namespace rocksdb

View File

@@ -1,67 +0,0 @@
// Copyright (c) 2013, 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.
#pragma once
#include <string>
#include <unordered_map>
#include "rocksdb/status.h"
namespace rocksdb {
// TableStats contains a bunch of read-only stats of its associated
// table.
struct TableStats {
public:
// Other than basic table stats, each table may also have the user
// collected stats.
// The value of the user-collected stats are encoded as raw bytes --
// users have to interprete these values by themselves.
typedef
std::unordered_map<std::string, std::string>
UserCollectedStats;
// the total size of all data blocks.
uint64_t data_size = 0;
// the total size of all index blocks.
uint64_t index_size = 0;
// total raw key size
uint64_t raw_key_size = 0;
// total raw value size
uint64_t raw_value_size = 0;
// the number of blocks in this table
uint64_t num_data_blocks = 0;
// the number of entries in this table
uint64_t num_entries = 0;
// The name of the filter policy used in this table.
// If no filter policy is used, `filter_policy_name` will be an empty string.
std::string filter_policy_name;
// user collected stats
UserCollectedStats user_collected_stats;
};
// `TableStatsCollector` provides the mechanism for users to collect their own
// interested stats. This class is essentially a collection of callback
// functions that will be invoked during table building.
class TableStatsCollector {
public:
virtual ~TableStatsCollector() { }
// Add() will be called when a new key/value pair is inserted into the table.
// @params key the original key that is inserted into the table.
// @params value the original value that is inserted into the table.
virtual Status Add(const Slice& key, const Slice& value) = 0;
// Finish() will be called when a table has already been built and is ready
// for writing the stats block.
// @params stats User will add their collected statistics to `stats`.
virtual Status Finish(TableStats::UserCollectedStats* stats) = 0;
// The name of the stats collector can be used for debugging purpose.
virtual const char* Name() const = 0;
};
} // namespace rocksdb