You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/table/table_properties.cc

361 lines
14 KiB

// 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).
#include "rocksdb/table_properties.h"
#include "port/port.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
Experimental support for SST unique IDs (#8990) Summary: * New public header unique_id.h and function GetUniqueIdFromTableProperties which computes a universally unique identifier based on table properties of table files from recent RocksDB versions. * Generation of DB session IDs is refactored so that they are guaranteed unique in the lifetime of a process running RocksDB. (SemiStructuredUniqueIdGen, new test included.) Along with file numbers, this enables SST unique IDs to be guaranteed unique among SSTs generated in a single process, and "better than random" between processes. See https://github.com/pdillinger/unique_id * In addition to public API producing 'external' unique IDs, there is a function for producing 'internal' unique IDs, with functions for converting between the two. In short, the external ID is "safe" for things people might do with it, and the internal ID enables more "power user" features for the future. Specifically, the external ID goes through a hashing layer so that any subset of bits in the external ID can be used as a hash of the full ID, while also preserving uniqueness guarantees in the first 128 bits (bijective both on first 128 bits and on full 192 bits). Intended follow-up: * Use the internal unique IDs in cache keys. (Avoid conflicts with https://github.com/facebook/rocksdb/issues/8912) (The file offset can be XORed into the third 64-bit value of the unique ID.) * Publish the external unique IDs in FileStorageInfo (https://github.com/facebook/rocksdb/issues/8968) Pull Request resolved: https://github.com/facebook/rocksdb/pull/8990 Test Plan: Unit tests added, and checking of unique ids in stress test. NOTE in stress test we do not generate nearly enough files to thoroughly stress uniqueness, but the test trims off pieces of the ID to check for uniqueness so that we can infer (with some assumptions) stronger properties in the aggregate. Reviewed By: zhichao-cao, mrambacher Differential Revision: D31582865 Pulled By: pdillinger fbshipit-source-id: 1f620c4c86af9abe2a8d177b9ccf2ad2b9f48243
3 years ago
#include "rocksdb/unique_id.h"
#include "table/block_based/block.h"
#include "table/internal_iterator.h"
#include "table/table_properties_internal.h"
Experimental support for SST unique IDs (#8990) Summary: * New public header unique_id.h and function GetUniqueIdFromTableProperties which computes a universally unique identifier based on table properties of table files from recent RocksDB versions. * Generation of DB session IDs is refactored so that they are guaranteed unique in the lifetime of a process running RocksDB. (SemiStructuredUniqueIdGen, new test included.) Along with file numbers, this enables SST unique IDs to be guaranteed unique among SSTs generated in a single process, and "better than random" between processes. See https://github.com/pdillinger/unique_id * In addition to public API producing 'external' unique IDs, there is a function for producing 'internal' unique IDs, with functions for converting between the two. In short, the external ID is "safe" for things people might do with it, and the internal ID enables more "power user" features for the future. Specifically, the external ID goes through a hashing layer so that any subset of bits in the external ID can be used as a hash of the full ID, while also preserving uniqueness guarantees in the first 128 bits (bijective both on first 128 bits and on full 192 bits). Intended follow-up: * Use the internal unique IDs in cache keys. (Avoid conflicts with https://github.com/facebook/rocksdb/issues/8912) (The file offset can be XORed into the third 64-bit value of the unique ID.) * Publish the external unique IDs in FileStorageInfo (https://github.com/facebook/rocksdb/issues/8968) Pull Request resolved: https://github.com/facebook/rocksdb/pull/8990 Test Plan: Unit tests added, and checking of unique ids in stress test. NOTE in stress test we do not generate nearly enough files to thoroughly stress uniqueness, but the test trims off pieces of the ID to check for uniqueness so that we can infer (with some assumptions) stronger properties in the aggregate. Reviewed By: zhichao-cao, mrambacher Differential Revision: D31582865 Pulled By: pdillinger fbshipit-source-id: 1f620c4c86af9abe2a8d177b9ccf2ad2b9f48243
3 years ago
#include "table/unique_id_impl.h"
#include "util/string_util.h"
namespace ROCKSDB_NAMESPACE {
const uint32_t TablePropertiesCollectorFactory::Context::kUnknownColumnFamily =
port::kMaxInt32;
namespace {
void AppendProperty(
std::string& props,
const std::string& key,
const std::string& value,
const std::string& prop_delim,
const std::string& kv_delim) {
props.append(key);
props.append(kv_delim);
props.append(value);
props.append(prop_delim);
}
template <class TValue>
void AppendProperty(
std::string& props,
const std::string& key,
const TValue& value,
const std::string& prop_delim,
const std::string& kv_delim) {
AppendProperty(
props, key, ToString(value), prop_delim, kv_delim
);
}
// Seek to the specified meta block.
// Return true if it successfully seeks to that block.
Status SeekToMetaBlock(InternalIterator* meta_iter,
const std::string& block_name, bool* is_found,
BlockHandle* block_handle = nullptr) {
if (block_handle != nullptr) {
*block_handle = BlockHandle::NullBlockHandle();
}
*is_found = true;
meta_iter->Seek(block_name);
if (meta_iter->status().ok()) {
if (meta_iter->Valid() && meta_iter->key() == block_name) {
*is_found = true;
if (block_handle) {
Slice v = meta_iter->value();
return block_handle->DecodeFrom(&v);
}
} else {
*is_found = false;
return Status::OK();
}
}
return meta_iter->status();
}
}
std::string TableProperties::ToString(
const std::string& prop_delim,
const std::string& kv_delim) const {
std::string result;
result.reserve(1024);
// Basic Info
AppendProperty(result, "# data blocks", num_data_blocks, prop_delim,
kv_delim);
AppendProperty(result, "# entries", num_entries, prop_delim, kv_delim);
AppendProperty(result, "# deletions", num_deletions, prop_delim, kv_delim);
AppendProperty(result, "# merge operands", num_merge_operands, prop_delim,
kv_delim);
AppendProperty(result, "# range deletions", num_range_deletions, prop_delim,
kv_delim);
AppendProperty(result, "raw key size", raw_key_size, prop_delim, kv_delim);
AppendProperty(result, "raw average key size",
num_entries != 0 ? 1.0 * raw_key_size / num_entries : 0.0,
prop_delim, kv_delim);
AppendProperty(result, "raw value size", raw_value_size, prop_delim,
kv_delim);
AppendProperty(result, "raw average value size",
num_entries != 0 ? 1.0 * raw_value_size / num_entries : 0.0,
prop_delim, kv_delim);
AppendProperty(result, "data block size", data_size, prop_delim, kv_delim);
char index_block_size_str[80];
snprintf(index_block_size_str, sizeof(index_block_size_str),
"index block size (user-key? %d, delta-value? %d)",
static_cast<int>(index_key_is_user_key),
static_cast<int>(index_value_is_delta_encoded));
AppendProperty(result, index_block_size_str, index_size, prop_delim,
kv_delim);
if (index_partitions != 0) {
AppendProperty(result, "# index partitions", index_partitions, prop_delim,
kv_delim);
AppendProperty(result, "top-level index size", top_level_index_size, prop_delim,
kv_delim);
}
AppendProperty(result, "filter block size", filter_size, prop_delim,
kv_delim);
AppendProperty(result, "# entries for filter", num_filter_entries, prop_delim,
kv_delim);
AppendProperty(result, "(estimated) table size",
data_size + index_size + filter_size, prop_delim, kv_delim);
AppendProperty(
result, "filter policy name",
filter_policy_name.empty() ? std::string("N/A") : filter_policy_name,
prop_delim, kv_delim);
AppendProperty(result, "prefix extractor name",
prefix_extractor_name.empty() ? std::string("N/A")
: prefix_extractor_name,
prop_delim, kv_delim);
AppendProperty(result, "column family ID",
column_family_id ==
ROCKSDB_NAMESPACE::TablePropertiesCollectorFactory::
Context::kUnknownColumnFamily
? std::string("N/A")
: ROCKSDB_NAMESPACE::ToString(column_family_id),
prop_delim, kv_delim);
AppendProperty(
result, "column family name",
column_family_name.empty() ? std::string("N/A") : column_family_name,
prop_delim, kv_delim);
AppendProperty(result, "comparator name",
comparator_name.empty() ? std::string("N/A") : comparator_name,
prop_delim, kv_delim);
AppendProperty(
result, "merge operator name",
merge_operator_name.empty() ? std::string("N/A") : merge_operator_name,
prop_delim, kv_delim);
AppendProperty(result, "property collectors names",
property_collectors_names.empty() ? std::string("N/A")
: property_collectors_names,
prop_delim, kv_delim);
AppendProperty(
result, "SST file compression algo",
compression_name.empty() ? std::string("N/A") : compression_name,
prop_delim, kv_delim);
add compression options to table properties (#5081) Summary: Since we are planning to use dictionary compression and to use different compression level, it is quite useful to add compression options to TableProperties. For example, in MyRocks, if the feature is available, we can query from information_schema.rocksdb_sst_props to see if all sst files are converted to ZSTD dictionary compressions. Resolves https://github.com/facebook/rocksdb/issues/4992 With this PR, user can query table properties through `GetPropertiesOfAllTables` API and get compression options as std::string: `window_bits=-14; level=32767; strategy=0; max_dict_bytes=0; zstd_max_train_bytes=0; enabled=0;` or table_properties->ToString() will also contain it `# data blocks=1; # entries=13; # deletions=0; # merge operands=0; # range deletions=0; raw key size=143; raw average key size=11.000000; raw value size=39; raw average value size=3.000000; data block size=120; index block size (user-key? 0, delta-value? 0)=27; filter block size=0; (estimated) table size=147; filter policy name=N/A; prefix extractor name=nullptr; column family ID=0; column family name=default; comparator name=leveldb.BytewiseComparator; merge operator name=nullptr; property collectors names=[]; SST file compression algo=Snappy; SST file compression options=window_bits=-14; level=32767; strategy=0; max_dict_bytes=0; zstd_max_train_bytes=0; enabled=0; ; creation time=1552946632; time stamp of earliest key=1552946632;` Pull Request resolved: https://github.com/facebook/rocksdb/pull/5081 Differential Revision: D14716692 Pulled By: miasantreble fbshipit-source-id: 7d2f2cf84e052bff876e71b4212cfdebf5be32dd
6 years ago
AppendProperty(
result, "SST file compression options",
compression_options.empty() ? std::string("N/A") : compression_options,
prop_delim, kv_delim);
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
7 years ago
AppendProperty(result, "creation time", creation_time, prop_delim, kv_delim);
AppendProperty(result, "time stamp of earliest key", oldest_key_time,
prop_delim, kv_delim);
Periodic Compactions (#5166) Summary: Introducing Periodic Compactions. This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold. - Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF. - This works across all levels. - The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used). - Compaction filters, if any, are invoked as usual. - A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS). This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166 Differential Revision: D14884441 Pulled By: sagar0 fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
AppendProperty(result, "file creation time", file_creation_time, prop_delim,
kv_delim);
AppendProperty(result, "slow compression estimated data size",
slow_compression_estimated_data_size, prop_delim, kv_delim);
AppendProperty(result, "fast compression estimated data size",
fast_compression_estimated_data_size, prop_delim, kv_delim);
// DB identity and DB session ID
AppendProperty(result, "DB identity", db_id, prop_delim, kv_delim);
AppendProperty(result, "DB session identity", db_session_id, prop_delim,
kv_delim);
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
3 years ago
AppendProperty(result, "DB host id", db_host_id, prop_delim, kv_delim);
AppendProperty(result, "original file number", orig_file_number, prop_delim,
kv_delim);
Experimental support for SST unique IDs (#8990) Summary: * New public header unique_id.h and function GetUniqueIdFromTableProperties which computes a universally unique identifier based on table properties of table files from recent RocksDB versions. * Generation of DB session IDs is refactored so that they are guaranteed unique in the lifetime of a process running RocksDB. (SemiStructuredUniqueIdGen, new test included.) Along with file numbers, this enables SST unique IDs to be guaranteed unique among SSTs generated in a single process, and "better than random" between processes. See https://github.com/pdillinger/unique_id * In addition to public API producing 'external' unique IDs, there is a function for producing 'internal' unique IDs, with functions for converting between the two. In short, the external ID is "safe" for things people might do with it, and the internal ID enables more "power user" features for the future. Specifically, the external ID goes through a hashing layer so that any subset of bits in the external ID can be used as a hash of the full ID, while also preserving uniqueness guarantees in the first 128 bits (bijective both on first 128 bits and on full 192 bits). Intended follow-up: * Use the internal unique IDs in cache keys. (Avoid conflicts with https://github.com/facebook/rocksdb/issues/8912) (The file offset can be XORed into the third 64-bit value of the unique ID.) * Publish the external unique IDs in FileStorageInfo (https://github.com/facebook/rocksdb/issues/8968) Pull Request resolved: https://github.com/facebook/rocksdb/pull/8990 Test Plan: Unit tests added, and checking of unique ids in stress test. NOTE in stress test we do not generate nearly enough files to thoroughly stress uniqueness, but the test trims off pieces of the ID to check for uniqueness so that we can infer (with some assumptions) stronger properties in the aggregate. Reviewed By: zhichao-cao, mrambacher Differential Revision: D31582865 Pulled By: pdillinger fbshipit-source-id: 1f620c4c86af9abe2a8d177b9ccf2ad2b9f48243
3 years ago
// Unique ID, when available
std::string id;
Status s = GetUniqueIdFromTableProperties(*this, &id);
AppendProperty(result, "unique ID",
s.ok() ? UniqueIdToHumanString(id) : "N/A", prop_delim,
kv_delim);
return result;
}
void TableProperties::Add(const TableProperties& tp) {
data_size += tp.data_size;
index_size += tp.index_size;
index_partitions += tp.index_partitions;
top_level_index_size += tp.top_level_index_size;
index_key_is_user_key += tp.index_key_is_user_key;
index_value_is_delta_encoded += tp.index_value_is_delta_encoded;
filter_size += tp.filter_size;
raw_key_size += tp.raw_key_size;
raw_value_size += tp.raw_value_size;
num_data_blocks += tp.num_data_blocks;
num_entries += tp.num_entries;
num_filter_entries += tp.num_filter_entries;
num_deletions += tp.num_deletions;
num_merge_operands += tp.num_merge_operands;
num_range_deletions += tp.num_range_deletions;
slow_compression_estimated_data_size +=
tp.slow_compression_estimated_data_size;
fast_compression_estimated_data_size +=
tp.fast_compression_estimated_data_size;
}
aggregated-table-properties with GetMapProperty (#7779) Summary: So that we can more easily get aggregate live table data such as total filter, index, and data sizes. Also adds ldb support for getting properties Also fixed some missing/inaccurate related comments in db.h For example: $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties rocksdb.aggregated-table-properties.data_size: 102871 rocksdb.aggregated-table-properties.filter_size: 0 rocksdb.aggregated-table-properties.index_partitions: 0 rocksdb.aggregated-table-properties.index_size: 2232 rocksdb.aggregated-table-properties.num_data_blocks: 100 rocksdb.aggregated-table-properties.num_deletions: 0 rocksdb.aggregated-table-properties.num_entries: 15000 rocksdb.aggregated-table-properties.num_merge_operands: 0 rocksdb.aggregated-table-properties.num_range_deletions: 0 rocksdb.aggregated-table-properties.raw_key_size: 288890 rocksdb.aggregated-table-properties.raw_value_size: 198890 rocksdb.aggregated-table-properties.top_level_index_size: 0 $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties-at-level1 rocksdb.aggregated-table-properties-at-level1.data_size: 80909 rocksdb.aggregated-table-properties-at-level1.filter_size: 0 rocksdb.aggregated-table-properties-at-level1.index_partitions: 0 rocksdb.aggregated-table-properties-at-level1.index_size: 1787 rocksdb.aggregated-table-properties-at-level1.num_data_blocks: 81 rocksdb.aggregated-table-properties-at-level1.num_deletions: 0 rocksdb.aggregated-table-properties-at-level1.num_entries: 12466 rocksdb.aggregated-table-properties-at-level1.num_merge_operands: 0 rocksdb.aggregated-table-properties-at-level1.num_range_deletions: 0 rocksdb.aggregated-table-properties-at-level1.raw_key_size: 238210 rocksdb.aggregated-table-properties-at-level1.raw_value_size: 163414 rocksdb.aggregated-table-properties-at-level1.top_level_index_size: 0 $ Pull Request resolved: https://github.com/facebook/rocksdb/pull/7779 Test Plan: Added a test to ldb_test.py Reviewed By: jay-zhuang Differential Revision: D25653103 Pulled By: pdillinger fbshipit-source-id: 2905469a08a64dd6b5510cbd7be2e64d3234d6d3
4 years ago
std::map<std::string, uint64_t>
TableProperties::GetAggregatablePropertiesAsMap() const {
std::map<std::string, uint64_t> rv;
rv["data_size"] = data_size;
rv["index_size"] = index_size;
rv["index_partitions"] = index_partitions;
rv["top_level_index_size"] = top_level_index_size;
rv["filter_size"] = filter_size;
rv["raw_key_size"] = raw_key_size;
rv["raw_value_size"] = raw_value_size;
rv["num_data_blocks"] = num_data_blocks;
rv["num_entries"] = num_entries;
rv["num_filter_entries"] = num_filter_entries;
aggregated-table-properties with GetMapProperty (#7779) Summary: So that we can more easily get aggregate live table data such as total filter, index, and data sizes. Also adds ldb support for getting properties Also fixed some missing/inaccurate related comments in db.h For example: $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties rocksdb.aggregated-table-properties.data_size: 102871 rocksdb.aggregated-table-properties.filter_size: 0 rocksdb.aggregated-table-properties.index_partitions: 0 rocksdb.aggregated-table-properties.index_size: 2232 rocksdb.aggregated-table-properties.num_data_blocks: 100 rocksdb.aggregated-table-properties.num_deletions: 0 rocksdb.aggregated-table-properties.num_entries: 15000 rocksdb.aggregated-table-properties.num_merge_operands: 0 rocksdb.aggregated-table-properties.num_range_deletions: 0 rocksdb.aggregated-table-properties.raw_key_size: 288890 rocksdb.aggregated-table-properties.raw_value_size: 198890 rocksdb.aggregated-table-properties.top_level_index_size: 0 $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties-at-level1 rocksdb.aggregated-table-properties-at-level1.data_size: 80909 rocksdb.aggregated-table-properties-at-level1.filter_size: 0 rocksdb.aggregated-table-properties-at-level1.index_partitions: 0 rocksdb.aggregated-table-properties-at-level1.index_size: 1787 rocksdb.aggregated-table-properties-at-level1.num_data_blocks: 81 rocksdb.aggregated-table-properties-at-level1.num_deletions: 0 rocksdb.aggregated-table-properties-at-level1.num_entries: 12466 rocksdb.aggregated-table-properties-at-level1.num_merge_operands: 0 rocksdb.aggregated-table-properties-at-level1.num_range_deletions: 0 rocksdb.aggregated-table-properties-at-level1.raw_key_size: 238210 rocksdb.aggregated-table-properties-at-level1.raw_value_size: 163414 rocksdb.aggregated-table-properties-at-level1.top_level_index_size: 0 $ Pull Request resolved: https://github.com/facebook/rocksdb/pull/7779 Test Plan: Added a test to ldb_test.py Reviewed By: jay-zhuang Differential Revision: D25653103 Pulled By: pdillinger fbshipit-source-id: 2905469a08a64dd6b5510cbd7be2e64d3234d6d3
4 years ago
rv["num_deletions"] = num_deletions;
rv["num_merge_operands"] = num_merge_operands;
rv["num_range_deletions"] = num_range_deletions;
rv["slow_compression_estimated_data_size"] =
slow_compression_estimated_data_size;
rv["fast_compression_estimated_data_size"] =
fast_compression_estimated_data_size;
aggregated-table-properties with GetMapProperty (#7779) Summary: So that we can more easily get aggregate live table data such as total filter, index, and data sizes. Also adds ldb support for getting properties Also fixed some missing/inaccurate related comments in db.h For example: $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties rocksdb.aggregated-table-properties.data_size: 102871 rocksdb.aggregated-table-properties.filter_size: 0 rocksdb.aggregated-table-properties.index_partitions: 0 rocksdb.aggregated-table-properties.index_size: 2232 rocksdb.aggregated-table-properties.num_data_blocks: 100 rocksdb.aggregated-table-properties.num_deletions: 0 rocksdb.aggregated-table-properties.num_entries: 15000 rocksdb.aggregated-table-properties.num_merge_operands: 0 rocksdb.aggregated-table-properties.num_range_deletions: 0 rocksdb.aggregated-table-properties.raw_key_size: 288890 rocksdb.aggregated-table-properties.raw_value_size: 198890 rocksdb.aggregated-table-properties.top_level_index_size: 0 $ ./ldb --db=testdb get_property rocksdb.aggregated-table-properties-at-level1 rocksdb.aggregated-table-properties-at-level1.data_size: 80909 rocksdb.aggregated-table-properties-at-level1.filter_size: 0 rocksdb.aggregated-table-properties-at-level1.index_partitions: 0 rocksdb.aggregated-table-properties-at-level1.index_size: 1787 rocksdb.aggregated-table-properties-at-level1.num_data_blocks: 81 rocksdb.aggregated-table-properties-at-level1.num_deletions: 0 rocksdb.aggregated-table-properties-at-level1.num_entries: 12466 rocksdb.aggregated-table-properties-at-level1.num_merge_operands: 0 rocksdb.aggregated-table-properties-at-level1.num_range_deletions: 0 rocksdb.aggregated-table-properties-at-level1.raw_key_size: 238210 rocksdb.aggregated-table-properties-at-level1.raw_value_size: 163414 rocksdb.aggregated-table-properties-at-level1.top_level_index_size: 0 $ Pull Request resolved: https://github.com/facebook/rocksdb/pull/7779 Test Plan: Added a test to ldb_test.py Reviewed By: jay-zhuang Differential Revision: D25653103 Pulled By: pdillinger fbshipit-source-id: 2905469a08a64dd6b5510cbd7be2e64d3234d6d3
4 years ago
return rv;
}
const std::string TablePropertiesNames::kDbId = "rocksdb.creating.db.identity";
const std::string TablePropertiesNames::kDbSessionId =
"rocksdb.creating.session.identity";
const std::string TablePropertiesNames::kDbHostId =
"rocksdb.creating.host.identity";
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
3 years ago
const std::string TablePropertiesNames::kOriginalFileNumber =
"rocksdb.original.file.number";
const std::string TablePropertiesNames::kDataSize =
"rocksdb.data.size";
const std::string TablePropertiesNames::kIndexSize =
"rocksdb.index.size";
const std::string TablePropertiesNames::kIndexPartitions =
"rocksdb.index.partitions";
const std::string TablePropertiesNames::kTopLevelIndexSize =
"rocksdb.top-level.index.size";
const std::string TablePropertiesNames::kIndexKeyIsUserKey =
"rocksdb.index.key.is.user.key";
const std::string TablePropertiesNames::kIndexValueIsDeltaEncoded =
"rocksdb.index.value.is.delta.encoded";
const std::string TablePropertiesNames::kFilterSize =
"rocksdb.filter.size";
const std::string TablePropertiesNames::kRawKeySize =
"rocksdb.raw.key.size";
const std::string TablePropertiesNames::kRawValueSize =
"rocksdb.raw.value.size";
const std::string TablePropertiesNames::kNumDataBlocks =
"rocksdb.num.data.blocks";
const std::string TablePropertiesNames::kNumEntries =
"rocksdb.num.entries";
const std::string TablePropertiesNames::kNumFilterEntries =
"rocksdb.num.filter_entries";
const std::string TablePropertiesNames::kDeletedKeys = "rocksdb.deleted.keys";
const std::string TablePropertiesNames::kMergeOperands =
"rocksdb.merge.operands";
const std::string TablePropertiesNames::kNumRangeDeletions =
"rocksdb.num.range-deletions";
const std::string TablePropertiesNames::kFilterPolicy =
"rocksdb.filter.policy";
const std::string TablePropertiesNames::kFormatVersion =
"rocksdb.format.version";
const std::string TablePropertiesNames::kFixedKeyLen =
"rocksdb.fixed.key.length";
const std::string TablePropertiesNames::kColumnFamilyId =
"rocksdb.column.family.id";
const std::string TablePropertiesNames::kColumnFamilyName =
"rocksdb.column.family.name";
const std::string TablePropertiesNames::kComparator = "rocksdb.comparator";
const std::string TablePropertiesNames::kMergeOperator =
"rocksdb.merge.operator";
store prefix_extractor_name in table Summary: Make sure prefix extractor name is stored in SST files and if DB is opened with a prefix extractor of a different name, prefix bloom is skipped when read the file. Also add unit tests for that. Test Plan: before change: ``` Note: Google Test filter = BlockBasedTableTest.SkipPrefixBloomFilter [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from BlockBasedTableTest [ RUN ] BlockBasedTableTest.SkipPrefixBloomFilter table/table_test.cc:1421: Failure Value of: db_iter->Valid() Actual: false Expected: true [ FAILED ] BlockBasedTableTest.SkipPrefixBloomFilter (1 ms) [----------] 1 test from BlockBasedTableTest (1 ms total) [----------] Global test environment tear-down [==========] 1 test from 1 test case ran. (1 ms total) [ PASSED ] 0 tests. [ FAILED ] 1 test, listed below: [ FAILED ] BlockBasedTableTest.SkipPrefixBloomFilter 1 FAILED TEST ``` after: ``` Note: Google Test filter = BlockBasedTableTest.SkipPrefixBloomFilter [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from BlockBasedTableTest [ RUN ] BlockBasedTableTest.SkipPrefixBloomFilter [ OK ] BlockBasedTableTest.SkipPrefixBloomFilter (0 ms) [----------] 1 test from BlockBasedTableTest (0 ms total) [----------] Global test environment tear-down [==========] 1 test from 1 test case ran. (0 ms total) [ PASSED ] 1 test. ``` Reviewers: sdong, andrewkr, yiwu, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D61215
8 years ago
const std::string TablePropertiesNames::kPrefixExtractorName =
"rocksdb.prefix.extractor.name";
const std::string TablePropertiesNames::kPropertyCollectors =
"rocksdb.property.collectors";
const std::string TablePropertiesNames::kCompression = "rocksdb.compression";
add compression options to table properties (#5081) Summary: Since we are planning to use dictionary compression and to use different compression level, it is quite useful to add compression options to TableProperties. For example, in MyRocks, if the feature is available, we can query from information_schema.rocksdb_sst_props to see if all sst files are converted to ZSTD dictionary compressions. Resolves https://github.com/facebook/rocksdb/issues/4992 With this PR, user can query table properties through `GetPropertiesOfAllTables` API and get compression options as std::string: `window_bits=-14; level=32767; strategy=0; max_dict_bytes=0; zstd_max_train_bytes=0; enabled=0;` or table_properties->ToString() will also contain it `# data blocks=1; # entries=13; # deletions=0; # merge operands=0; # range deletions=0; raw key size=143; raw average key size=11.000000; raw value size=39; raw average value size=3.000000; data block size=120; index block size (user-key? 0, delta-value? 0)=27; filter block size=0; (estimated) table size=147; filter policy name=N/A; prefix extractor name=nullptr; column family ID=0; column family name=default; comparator name=leveldb.BytewiseComparator; merge operator name=nullptr; property collectors names=[]; SST file compression algo=Snappy; SST file compression options=window_bits=-14; level=32767; strategy=0; max_dict_bytes=0; zstd_max_train_bytes=0; enabled=0; ; creation time=1552946632; time stamp of earliest key=1552946632;` Pull Request resolved: https://github.com/facebook/rocksdb/pull/5081 Differential Revision: D14716692 Pulled By: miasantreble fbshipit-source-id: 7d2f2cf84e052bff876e71b4212cfdebf5be32dd
6 years ago
const std::string TablePropertiesNames::kCompressionOptions =
"rocksdb.compression_options";
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
7 years ago
const std::string TablePropertiesNames::kCreationTime = "rocksdb.creation.time";
const std::string TablePropertiesNames::kOldestKeyTime =
"rocksdb.oldest.key.time";
Periodic Compactions (#5166) Summary: Introducing Periodic Compactions. This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold. - Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF. - This works across all levels. - The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used). - Compaction filters, if any, are invoked as usual. - A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS). This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166 Differential Revision: D14884441 Pulled By: sagar0 fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
const std::string TablePropertiesNames::kFileCreationTime =
"rocksdb.file.creation.time";
const std::string TablePropertiesNames::kSlowCompressionEstimatedDataSize =
"rocksdb.sample_for_compression.slow.data.size";
const std::string TablePropertiesNames::kFastCompressionEstimatedDataSize =
"rocksdb.sample_for_compression.fast.data.size";
extern const std::string kPropertiesBlock = "rocksdb.properties";
// Old property block name for backward compatibility
extern const std::string kPropertiesBlockOldName = "rocksdb.stats";
extern const std::string kCompressionDictBlock = "rocksdb.compression_dict";
extern const std::string kRangeDelBlock = "rocksdb.range_del";
Experimental support for SST unique IDs (#8990) Summary: * New public header unique_id.h and function GetUniqueIdFromTableProperties which computes a universally unique identifier based on table properties of table files from recent RocksDB versions. * Generation of DB session IDs is refactored so that they are guaranteed unique in the lifetime of a process running RocksDB. (SemiStructuredUniqueIdGen, new test included.) Along with file numbers, this enables SST unique IDs to be guaranteed unique among SSTs generated in a single process, and "better than random" between processes. See https://github.com/pdillinger/unique_id * In addition to public API producing 'external' unique IDs, there is a function for producing 'internal' unique IDs, with functions for converting between the two. In short, the external ID is "safe" for things people might do with it, and the internal ID enables more "power user" features for the future. Specifically, the external ID goes through a hashing layer so that any subset of bits in the external ID can be used as a hash of the full ID, while also preserving uniqueness guarantees in the first 128 bits (bijective both on first 128 bits and on full 192 bits). Intended follow-up: * Use the internal unique IDs in cache keys. (Avoid conflicts with https://github.com/facebook/rocksdb/issues/8912) (The file offset can be XORed into the third 64-bit value of the unique ID.) * Publish the external unique IDs in FileStorageInfo (https://github.com/facebook/rocksdb/issues/8968) Pull Request resolved: https://github.com/facebook/rocksdb/pull/8990 Test Plan: Unit tests added, and checking of unique ids in stress test. NOTE in stress test we do not generate nearly enough files to thoroughly stress uniqueness, but the test trims off pieces of the ID to check for uniqueness so that we can infer (with some assumptions) stronger properties in the aggregate. Reviewed By: zhichao-cao, mrambacher Differential Revision: D31582865 Pulled By: pdillinger fbshipit-source-id: 1f620c4c86af9abe2a8d177b9ccf2ad2b9f48243
3 years ago
#ifndef NDEBUG
void TEST_SetRandomTableProperties(TableProperties* props) {
Random* r = Random::GetTLSInstance();
// For now, TableProperties is composed of a number of uint64_t followed by
// a number of std::string, followed by some extras starting with
// user_collected_properties.
uint64_t* pu = &props->orig_file_number;
assert(static_cast<void*>(pu) == static_cast<void*>(props));
std::string* ps = &props->db_id;
const uint64_t* const pu_end = reinterpret_cast<const uint64_t*>(ps);
const std::string* const ps_end =
reinterpret_cast<const std::string*>(&props->user_collected_properties);
for (; pu < pu_end; ++pu) {
*pu = r->Next64();
}
assert(static_cast<void*>(pu) == static_cast<void*>(ps));
for (; ps < ps_end; ++ps) {
*ps = r->RandomBinaryString(13);
}
}
#endif
// Seek to the properties block.
// Return true if it successfully seeks to the properties block.
Status SeekToPropertiesBlock(InternalIterator* meta_iter, bool* is_found) {
Status status = SeekToMetaBlock(meta_iter, kPropertiesBlock, is_found);
if (!*is_found && status.ok()) {
status = SeekToMetaBlock(meta_iter, kPropertiesBlockOldName, is_found);
}
return status;
}
// Seek to the compression dictionary block.
// Return true if it successfully seeks to that block.
Status SeekToCompressionDictBlock(InternalIterator* meta_iter, bool* is_found,
BlockHandle* block_handle) {
return SeekToMetaBlock(meta_iter, kCompressionDictBlock, is_found, block_handle);
}
Status SeekToRangeDelBlock(InternalIterator* meta_iter, bool* is_found,
BlockHandle* block_handle = nullptr) {
return SeekToMetaBlock(meta_iter, kRangeDelBlock, is_found, block_handle);
}
} // namespace ROCKSDB_NAMESPACE