|
|
|
// 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.
|
|
|
|
|
|
|
|
#include <cstring>
|
|
|
|
|
|
|
|
#include "options/cf_options.h"
|
|
|
|
#include "options/db_options.h"
|
|
|
|
#include "options/options_helper.h"
|
|
|
|
#include "rocksdb/convenience.h"
|
|
|
|
#include "test_util/testharness.h"
|
|
|
|
|
|
|
|
#ifndef GFLAGS
|
|
|
|
bool FLAGS_enable_print = false;
|
|
|
|
#else
|
|
|
|
#include "util/gflags_compat.h"
|
|
|
|
using GFLAGS_NAMESPACE::ParseCommandLineFlags;
|
|
|
|
DEFINE_bool(enable_print, false, "Print options generated to console.");
|
|
|
|
#endif // GFLAGS
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
// Verify options are settable from options strings.
|
|
|
|
// We take the approach that depends on compiler behavior that copy constructor
|
|
|
|
// won't touch implicit padding bytes, so that the test is fragile.
|
|
|
|
// As a result, we only run the tests to verify new fields in options are
|
|
|
|
// settable through string on limited platforms as it depends on behavior of
|
|
|
|
// compilers.
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
#if defined OS_LINUX || defined OS_WIN
|
|
|
|
#ifndef __clang__
|
|
|
|
#ifndef ROCKSDB_UBSAN_RUN
|
|
|
|
|
|
|
|
class OptionsSettableTest : public testing::Test {
|
|
|
|
public:
|
|
|
|
OptionsSettableTest() {}
|
|
|
|
};
|
|
|
|
|
|
|
|
const char kSpecialChar = 'z';
|
|
|
|
using OffsetGap = std::vector<std::pair<size_t, size_t>>;
|
|
|
|
|
|
|
|
void FillWithSpecialChar(char* start_ptr, size_t total_size,
|
|
|
|
const OffsetGap& excluded,
|
|
|
|
char special_char = kSpecialChar) {
|
|
|
|
size_t offset = 0;
|
|
|
|
// The excluded vector contains pairs of bytes, (first, second).
|
|
|
|
// The first bytes are all set to the special char (represented as 'c' below).
|
|
|
|
// The second bytes are simply skipped (padding bytes).
|
|
|
|
// ccccc[skipped]cccccccc[skiped]cccccccc[skipped]
|
|
|
|
for (auto& pair : excluded) {
|
|
|
|
std::memset(start_ptr + offset, special_char, pair.first - offset);
|
|
|
|
offset = pair.first + pair.second;
|
|
|
|
}
|
|
|
|
// The rest of the structure is filled with the special characters.
|
|
|
|
// ccccc[skipped]cccccccc[skiped]cccccccc[skipped]cccccccccccccccc
|
|
|
|
std::memset(start_ptr + offset, special_char, total_size - offset);
|
|
|
|
}
|
|
|
|
|
|
|
|
int NumUnsetBytes(char* start_ptr, size_t total_size,
|
|
|
|
const OffsetGap& excluded) {
|
|
|
|
int total_unset_bytes_base = 0;
|
|
|
|
size_t offset = 0;
|
|
|
|
for (auto& pair : excluded) {
|
|
|
|
// The first part of the structure contains memory spaces that can be
|
|
|
|
// set (pair.first), and memory spaces that cannot be set (pair.second).
|
|
|
|
// Therefore total_unset_bytes_base only agregates bytes set to kSpecialChar
|
|
|
|
// in the pair.first bytes, but skips the pair.second bytes (padding bytes).
|
|
|
|
for (char* ptr = start_ptr + offset; ptr < start_ptr + pair.first; ptr++) {
|
|
|
|
if (*ptr == kSpecialChar) {
|
|
|
|
total_unset_bytes_base++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
offset = pair.first + pair.second;
|
|
|
|
}
|
|
|
|
// Then total_unset_bytes_base aggregates the bytes
|
|
|
|
// set to kSpecialChar in the rest of the structure
|
|
|
|
for (char* ptr = start_ptr + offset; ptr < start_ptr + total_size; ptr++) {
|
|
|
|
if (*ptr == kSpecialChar) {
|
|
|
|
total_unset_bytes_base++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return total_unset_bytes_base;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Return true iff two structs are the same except excluded fields.
|
|
|
|
bool CompareBytes(char* start_ptr1, char* start_ptr2, size_t total_size,
|
|
|
|
const OffsetGap& excluded) {
|
|
|
|
size_t offset = 0;
|
|
|
|
for (auto& pair : excluded) {
|
|
|
|
for (; offset < pair.first; offset++) {
|
|
|
|
if (*(start_ptr1 + offset) != *(start_ptr2 + offset)) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
offset = pair.first + pair.second;
|
|
|
|
}
|
|
|
|
for (; offset < total_size; offset++) {
|
|
|
|
if (*(start_ptr1 + offset) != *(start_ptr2 + offset)) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If the test fails, likely a new option is added to BlockBasedTableOptions
|
|
|
|
// but it cannot be set through GetBlockBasedTableOptionsFromString(), or the
|
|
|
|
// test is not updated accordingly.
|
|
|
|
// After adding an option, we need to make sure it is settable by
|
|
|
|
// GetBlockBasedTableOptionsFromString() and add the option to the input string
|
|
|
|
// passed to the GetBlockBasedTableOptionsFromString() in this test.
|
|
|
|
// If it is a complicated type, you also need to add the field to
|
|
|
|
// kBbtoExcluded, and maybe add customized verification for it.
|
|
|
|
TEST_F(OptionsSettableTest, BlockBasedTableOptionsAllFieldsSettable) {
|
|
|
|
// Items in the form of <offset, size>. Need to be in ascending order
|
|
|
|
// and not overlapping. Need to update if new option to be excluded is added
|
|
|
|
// (e.g, pointer-type)
|
|
|
|
const OffsetGap kBbtoExcluded = {
|
|
|
|
{offsetof(struct BlockBasedTableOptions, flush_block_policy_factory),
|
|
|
|
sizeof(std::shared_ptr<FlushBlockPolicyFactory>)},
|
|
|
|
{offsetof(struct BlockBasedTableOptions, block_cache),
|
|
|
|
sizeof(std::shared_ptr<Cache>)},
|
|
|
|
{offsetof(struct BlockBasedTableOptions, persistent_cache),
|
|
|
|
sizeof(std::shared_ptr<PersistentCache>)},
|
|
|
|
{offsetof(struct BlockBasedTableOptions, block_cache_compressed),
|
|
|
|
sizeof(std::shared_ptr<Cache>)},
|
|
|
|
{offsetof(struct BlockBasedTableOptions, cache_usage_options),
|
|
|
|
sizeof(CacheUsageOptions)},
|
|
|
|
{offsetof(struct BlockBasedTableOptions, filter_policy),
|
|
|
|
sizeof(std::shared_ptr<const FilterPolicy>)},
|
|
|
|
};
|
|
|
|
|
|
|
|
// In this test, we catch a new option of BlockBasedTableOptions that is not
|
|
|
|
// settable through GetBlockBasedTableOptionsFromString().
|
|
|
|
// We count padding bytes of the option struct, and assert it to be the same
|
|
|
|
// as unset bytes of an option struct initialized by
|
|
|
|
// GetBlockBasedTableOptionsFromString().
|
|
|
|
|
|
|
|
char* bbto_ptr = new char[sizeof(BlockBasedTableOptions)];
|
|
|
|
|
|
|
|
// Count padding bytes by setting all bytes in the memory to a special char,
|
|
|
|
// copy a well constructed struct to this memory and see how many special
|
|
|
|
// bytes left.
|
|
|
|
BlockBasedTableOptions* bbto = new (bbto_ptr) BlockBasedTableOptions();
|
|
|
|
FillWithSpecialChar(bbto_ptr, sizeof(BlockBasedTableOptions), kBbtoExcluded);
|
|
|
|
// It based on the behavior of compiler that padding bytes are not changed
|
|
|
|
// when copying the struct. It's prone to failure when compiler behavior
|
|
|
|
// changes. We verify there is unset bytes to detect the case.
|
|
|
|
*bbto = BlockBasedTableOptions();
|
|
|
|
int unset_bytes_base =
|
|
|
|
NumUnsetBytes(bbto_ptr, sizeof(BlockBasedTableOptions), kBbtoExcluded);
|
|
|
|
ASSERT_GT(unset_bytes_base, 0);
|
|
|
|
bbto->~BlockBasedTableOptions();
|
|
|
|
|
|
|
|
// Construct the base option passed into
|
|
|
|
// GetBlockBasedTableOptionsFromString().
|
|
|
|
bbto = new (bbto_ptr) BlockBasedTableOptions();
|
|
|
|
FillWithSpecialChar(bbto_ptr, sizeof(BlockBasedTableOptions), kBbtoExcluded);
|
|
|
|
// This option is not setable:
|
|
|
|
bbto->use_delta_encoding = true;
|
|
|
|
|
|
|
|
char* new_bbto_ptr = new char[sizeof(BlockBasedTableOptions)];
|
|
|
|
BlockBasedTableOptions* new_bbto =
|
|
|
|
new (new_bbto_ptr) BlockBasedTableOptions();
|
|
|
|
FillWithSpecialChar(new_bbto_ptr, sizeof(BlockBasedTableOptions),
|
|
|
|
kBbtoExcluded);
|
|
|
|
|
|
|
|
// Need to update the option string if a new option is added.
|
|
|
|
ASSERT_OK(GetBlockBasedTableOptionsFromString(
|
|
|
|
*bbto,
|
|
|
|
"cache_index_and_filter_blocks=1;"
|
|
|
|
"cache_index_and_filter_blocks_with_high_priority=true;"
|
|
|
|
"metadata_cache_options={top_level_index_pinning=kFallback;"
|
|
|
|
"partition_pinning=kAll;"
|
|
|
|
"unpartitioned_pinning=kFlushedAndSimilar;};"
|
|
|
|
"pin_l0_filter_and_index_blocks_in_cache=1;"
|
|
|
|
"pin_top_level_index_and_filter=1;"
|
|
|
|
"index_type=kHashSearch;"
|
|
|
|
"data_block_index_type=kDataBlockBinaryAndHash;"
|
|
|
|
"index_shortening=kNoShortening;"
|
|
|
|
"data_block_hash_table_util_ratio=0.75;"
|
|
|
|
"checksum=kxxHash;no_block_cache=1;"
|
|
|
|
"block_cache=1M;block_cache_compressed=1k;block_size=1024;"
|
|
|
|
"block_size_deviation=8;block_restart_interval=4; "
|
|
|
|
"metadata_block_size=1024;"
|
|
|
|
"partition_filters=false;"
|
Minimize memory internal fragmentation for Bloom filters (#6427)
Summary:
New experimental option BBTO::optimize_filters_for_memory builds
filters that maximize their use of "usable size" from malloc_usable_size,
which is also used to compute block cache charges.
Rather than always "rounding up," we track state in the
BloomFilterPolicy object to mix essentially "rounding down" and
"rounding up" so that the average FP rate of all generated filters is
the same as without the option. (YMMV as heavily accessed filters might
be unluckily lower accuracy.)
Thus, the option near-minimizes what the block cache considers as
"memory used" for a given target Bloom filter false positive rate and
Bloom filter implementation. There are no forward or backward
compatibility issues with this change, though it only works on the
format_version=5 Bloom filter.
With Jemalloc, we see about 10% reduction in memory footprint (and block
cache charge) for Bloom filters, but 1-2% increase in storage footprint,
due to encoding efficiency losses (FP rate is non-linear with bits/key).
Why not weighted random round up/down rather than state tracking? By
only requiring malloc_usable_size, we don't actually know what the next
larger and next smaller usable sizes for the allocator are. We pick a
requested size, accept and use whatever usable size it has, and use the
difference to inform our next choice. This allows us to narrow in on the
right balance without tracking/predicting usable sizes.
Why not weight history of generated filter false positive rates by
number of keys? This could lead to excess skew in small filters after
generating a large filter.
Results from filter_bench with jemalloc (irrelevant details omitted):
(normal keys/filter, but high variance)
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9
Build avg ns/key: 29.6278
Number of filters: 5516
Total size (MB): 200.046
Reported total allocated memory (MB): 220.597
Reported internal fragmentation: 10.2732%
Bits/key stored: 10.0097
Average FP rate %: 0.965228
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=30000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory
Build avg ns/key: 30.5104
Number of filters: 5464
Total size (MB): 200.015
Reported total allocated memory (MB): 200.322
Reported internal fragmentation: 0.153709%
Bits/key stored: 10.1011
Average FP rate %: 0.966313
(very few keys / filter, optimization not as effective due to ~59 byte
internal fragmentation in blocked Bloom filter representation)
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9
Build avg ns/key: 29.5649
Number of filters: 162950
Total size (MB): 200.001
Reported total allocated memory (MB): 224.624
Reported internal fragmentation: 12.3117%
Bits/key stored: 10.2951
Average FP rate %: 0.821534
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory
Build avg ns/key: 31.8057
Number of filters: 159849
Total size (MB): 200
Reported total allocated memory (MB): 208.846
Reported internal fragmentation: 4.42297%
Bits/key stored: 10.4948
Average FP rate %: 0.811006
(high keys/filter)
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9
Build avg ns/key: 29.7017
Number of filters: 164
Total size (MB): 200.352
Reported total allocated memory (MB): 221.5
Reported internal fragmentation: 10.5552%
Bits/key stored: 10.0003
Average FP rate %: 0.969358
$ ./filter_bench -quick -impl=2 -average_keys_per_filter=1000000 -vary_key_count_ratio=0.9 -optimize_filters_for_memory
Build avg ns/key: 30.7131
Number of filters: 160
Total size (MB): 200.928
Reported total allocated memory (MB): 200.938
Reported internal fragmentation: 0.00448054%
Bits/key stored: 10.1852
Average FP rate %: 0.963387
And from db_bench (block cache) with jemalloc:
$ ./db_bench -db=/dev/shm/dbbench.no_optimize -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false
$ ./db_bench -db=/dev/shm/dbbench -benchmarks=fillrandom -format_version=5 -value_size=90 -bloom_bits=10 -num=2000000 -threads=8 -optimize_filters_for_memory -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false
$ (for FILE in /dev/shm/dbbench.no_optimize/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }'
17063835
$ (for FILE in /dev/shm/dbbench/*.sst; do ./sst_dump --file=$FILE --show_properties | grep 'filter block' ; done) | awk '{ t += $4; } END { print t; }'
17430747
$ #^ 2.1% additional filter storage
$ ./db_bench -db=/dev/shm/dbbench.no_optimize -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000
rocksdb.block.cache.index.add COUNT : 33
rocksdb.block.cache.index.bytes.insert COUNT : 8440400
rocksdb.block.cache.filter.add COUNT : 33
rocksdb.block.cache.filter.bytes.insert COUNT : 21087528
rocksdb.bloom.filter.useful COUNT : 4963889
rocksdb.bloom.filter.full.positive COUNT : 1214081
rocksdb.bloom.filter.full.true.positive COUNT : 1161999
$ #^ 1.04 % observed FP rate
$ ./db_bench -db=/dev/shm/dbbench -use_existing_db -benchmarks=readrandom,stats -statistics -bloom_bits=10 -num=2000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=false -optimize_filters_for_memory -duration=10 -cache_index_and_filter_blocks -cache_size=1000000000
rocksdb.block.cache.index.add COUNT : 33
rocksdb.block.cache.index.bytes.insert COUNT : 8448592
rocksdb.block.cache.filter.add COUNT : 33
rocksdb.block.cache.filter.bytes.insert COUNT : 18220328
rocksdb.bloom.filter.useful COUNT : 5360933
rocksdb.bloom.filter.full.positive COUNT : 1321315
rocksdb.bloom.filter.full.true.positive COUNT : 1262999
$ #^ 1.08 % observed FP rate, 13.6% less memory usage for filters
(Due to specific key density, this example tends to generate filters that are "worse than average" for internal fragmentation. "Better than average" cases can show little or no improvement.)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6427
Test Plan: unit test added, 'make check' with gcc, clang and valgrind
Reviewed By: siying
Differential Revision: D22124374
Pulled By: pdillinger
fbshipit-source-id: f3e3aa152f9043ddf4fae25799e76341d0d8714e
4 years ago
|
|
|
"optimize_filters_for_memory=true;"
|
|
|
|
"index_block_restart_interval=4;"
|
Detect (new) Bloom/Ribbon Filter construction corruption (#9342)
Summary:
Note: rebase on and merge after https://github.com/facebook/rocksdb/pull/9349, https://github.com/facebook/rocksdb/pull/9345, (optional) https://github.com/facebook/rocksdb/pull/9393
**Context:**
(Quoted from pdillinger) Layers of information during new Bloom/Ribbon Filter construction in building block-based tables includes the following:
a) set of keys to add to filter
b) set of hashes to add to filter (64-bit hash applied to each key)
c) set of Bloom indices to set in filter, with duplicates
d) set of Bloom indices to set in filter, deduplicated
e) final filter and its checksum
This PR aims to detect corruption (e.g, unexpected hardware/software corruption on data structures residing in the memory for a long time) from b) to e) and leave a) as future works for application level.
- b)'s corruption is detected by verifying the xor checksum of the hash entries calculated as the entries accumulate before being added to the filter. (i.e, `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()`)
- c) - e)'s corruption is detected by verifying the hash entries indeed exists in the constructed filter by re-querying these hash entries in the filter (i.e, `FilterBitsBuilder::MaybePostVerify()`) after computing the block checksum (except for PartitionFilter, which is done right after each `FilterBitsBuilder::Finish` for impl simplicity - see code comment for more). For this stage of detection, we assume hash entries are not corrupted after checking on b) since the time interval from b) to c) is relatively short IMO.
Option to enable this feature of detection is `BlockBasedTableOptions::detect_filter_construct_corruption` which is false by default.
**Summary:**
- Implemented new functions `XXPH3FilterBitsBuilder::MaybeVerifyHashEntriesChecksum()` and `FilterBitsBuilder::MaybePostVerify()`
- Ensured hash entries, final filter and banding and their [cache reservation ](https://github.com/facebook/rocksdb/issues/9073) are released properly despite corruption
- See [Filter.construction.artifacts.release.point.pdf ](https://github.com/facebook/rocksdb/files/7923487/Design.Filter.construction.artifacts.release.point.pdf) for high-level design
- Bundled and refactored hash entries's related artifact in XXPH3FilterBitsBuilder into `HashEntriesInfo` for better control on lifetime of these artifact during `SwapEntires`, `ResetEntries`
- Ensured RocksDB block-based table builder calls `FilterBitsBuilder::MaybePostVerify()` after constructing the filter by `FilterBitsBuilder::Finish()`
- When encountering such filter construction corruption, stop writing the filter content to files and mark such a block-based table building non-ok by storing the corruption status in the builder.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9342
Test Plan:
- Added new unit test `DBFilterConstructionCorruptionTestWithParam.DetectCorruption`
- Included this new feature in `DBFilterConstructionReserveMemoryTestWithParam.ReserveMemory` as this feature heavily touch ReserveMemory's impl
- For fallback case, I run `./filter_bench -impl=3 -detect_filter_construct_corruption=true -reserve_table_builder_memory=true -strict_capacity_limit=true -quick -runs 10 | grep 'Build avg'` to make sure nothing break.
- Added to `filter_bench`: increased filter construction time by **30%**, mostly by `MaybePostVerify()`
- FastLocalBloom
- Before change: `./filter_bench -impl=2 -quick -runs 10 | grep 'Build avg'`: **28.86643s**
- After change:
- `./filter_bench -impl=2 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless): **27.6644s (-4% perf improvement might be due to now we don't drop bloom hash entry in `AddAllEntries` along iteration but in bulk later, same with the bypassing-MaybePostVerify case below)**
- `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (expect acceptable increase): **34.41159s (+20%)**
- `./filter_bench -impl=2 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'` (by-passing MaybePostVerify, expect minor increase): **27.13431s (-6%)**
- Standard128Ribbon
- Before change: `./filter_bench -impl=3 -quick -runs 10 | grep 'Build avg'`: **122.5384s**
- After change:
- `./filter_bench -impl=3 -detect_filter_construct_corruption=false -quick -runs 10 | grep 'Build avg'` (expect a tiny increase due to MaybePostVerify is always called regardless - verified by removing MaybePostVerify under this case and found only +-1ns difference): **124.3588s (+2%)**
- `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(expect acceptable increase): **159.4946s (+30%)**
- `./filter_bench -impl=3 -detect_filter_construct_corruption=true -quick -runs 10 | grep 'Build avg'`(by-passing MaybePostVerify, expect minor increase) : **125.258s (+2%)**
- Added to `db_stress`: `make crash_test`, `./db_stress --detect_filter_construct_corruption=true`
- Manually smoke-tested: manually corrupted the filter construction in some db level tests with basic PUT and background flush. As expected, the error did get returned to users in subsequent PUT and Flush status.
Reviewed By: pdillinger
Differential Revision: D33746928
Pulled By: hx235
fbshipit-source-id: cb056426be5a7debc1cd16f23bc250f36a08ca57
3 years ago
|
|
|
"filter_policy=bloomfilter:4:true;whole_key_filtering=1;detect_filter_"
|
|
|
|
"construct_corruption=false;"
|
|
|
|
"format_version=1;"
|
|
|
|
"verify_compression=true;read_amp_bytes_per_bit=0;"
|
|
|
|
"enable_index_compression=false;"
|
|
|
|
"block_align=true;"
|
|
|
|
"max_auto_readahead_size=0;"
|
|
|
|
"prepopulate_block_cache=kDisable;"
|
|
|
|
"initial_auto_readahead_size=0;"
|
|
|
|
"num_file_reads_for_auto_readahead=0",
|
|
|
|
new_bbto));
|
|
|
|
|
|
|
|
ASSERT_EQ(unset_bytes_base,
|
|
|
|
NumUnsetBytes(new_bbto_ptr, sizeof(BlockBasedTableOptions),
|
|
|
|
kBbtoExcluded));
|
|
|
|
|
|
|
|
ASSERT_TRUE(new_bbto->block_cache.get() != nullptr);
|
|
|
|
ASSERT_TRUE(new_bbto->block_cache_compressed.get() != nullptr);
|
|
|
|
ASSERT_TRUE(new_bbto->filter_policy.get() != nullptr);
|
|
|
|
|
|
|
|
bbto->~BlockBasedTableOptions();
|
|
|
|
new_bbto->~BlockBasedTableOptions();
|
|
|
|
|
|
|
|
delete[] bbto_ptr;
|
|
|
|
delete[] new_bbto_ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If the test fails, likely a new option is added to DBOptions
|
|
|
|
// but it cannot be set through GetDBOptionsFromString(), or the test is not
|
|
|
|
// updated accordingly.
|
|
|
|
// After adding an option, we need to make sure it is settable by
|
|
|
|
// GetDBOptionsFromString() and add the option to the input string passed to
|
|
|
|
// DBOptionsFromString()in this test.
|
|
|
|
// If it is a complicated type, you also need to add the field to
|
|
|
|
// kDBOptionsExcluded, and maybe add customized verification for it.
|
|
|
|
TEST_F(OptionsSettableTest, DBOptionsAllFieldsSettable) {
|
|
|
|
const OffsetGap kDBOptionsExcluded = {
|
|
|
|
{offsetof(struct DBOptions, env), sizeof(Env*)},
|
|
|
|
{offsetof(struct DBOptions, rate_limiter),
|
|
|
|
sizeof(std::shared_ptr<RateLimiter>)},
|
|
|
|
{offsetof(struct DBOptions, sst_file_manager),
|
|
|
|
sizeof(std::shared_ptr<SstFileManager>)},
|
|
|
|
{offsetof(struct DBOptions, info_log), sizeof(std::shared_ptr<Logger>)},
|
|
|
|
{offsetof(struct DBOptions, statistics),
|
|
|
|
sizeof(std::shared_ptr<Statistics>)},
|
|
|
|
{offsetof(struct DBOptions, db_paths), sizeof(std::vector<DbPath>)},
|
|
|
|
{offsetof(struct DBOptions, db_log_dir), sizeof(std::string)},
|
|
|
|
{offsetof(struct DBOptions, wal_dir), sizeof(std::string)},
|
|
|
|
{offsetof(struct DBOptions, write_buffer_manager),
|
|
|
|
sizeof(std::shared_ptr<WriteBufferManager>)},
|
|
|
|
{offsetof(struct DBOptions, listeners),
|
|
|
|
sizeof(std::vector<std::shared_ptr<EventListener>>)},
|
|
|
|
{offsetof(struct DBOptions, row_cache), sizeof(std::shared_ptr<Cache>)},
|
|
|
|
{offsetof(struct DBOptions, wal_filter), sizeof(const WalFilter*)},
|
|
|
|
{offsetof(struct DBOptions, file_checksum_gen_factory),
|
|
|
|
sizeof(std::shared_ptr<FileChecksumGenFactory>)},
|
|
|
|
{offsetof(struct DBOptions, db_host_id), sizeof(std::string)},
|
|
|
|
{offsetof(struct DBOptions, checksum_handoff_file_types),
|
|
|
|
sizeof(FileTypeSet)},
|
|
|
|
{offsetof(struct DBOptions, compaction_service),
|
|
|
|
sizeof(std::shared_ptr<CompactionService>)},
|
|
|
|
};
|
|
|
|
|
|
|
|
char* options_ptr = new char[sizeof(DBOptions)];
|
|
|
|
|
|
|
|
// Count padding bytes by setting all bytes in the memory to a special char,
|
|
|
|
// copy a well constructed struct to this memory and see how many special
|
|
|
|
// bytes left.
|
|
|
|
DBOptions* options = new (options_ptr) DBOptions();
|
|
|
|
FillWithSpecialChar(options_ptr, sizeof(DBOptions), kDBOptionsExcluded);
|
|
|
|
// It based on the behavior of compiler that padding bytes are not changed
|
|
|
|
// when copying the struct. It's prone to failure when compiler behavior
|
|
|
|
// changes. We verify there is unset bytes to detect the case.
|
|
|
|
*options = DBOptions();
|
|
|
|
int unset_bytes_base =
|
|
|
|
NumUnsetBytes(options_ptr, sizeof(DBOptions), kDBOptionsExcluded);
|
|
|
|
ASSERT_GT(unset_bytes_base, 0);
|
|
|
|
options->~DBOptions();
|
|
|
|
|
|
|
|
options = new (options_ptr) DBOptions();
|
|
|
|
FillWithSpecialChar(options_ptr, sizeof(DBOptions), kDBOptionsExcluded);
|
|
|
|
|
|
|
|
char* new_options_ptr = new char[sizeof(DBOptions)];
|
|
|
|
DBOptions* new_options = new (new_options_ptr) DBOptions();
|
|
|
|
FillWithSpecialChar(new_options_ptr, sizeof(DBOptions), kDBOptionsExcluded);
|
|
|
|
|
|
|
|
// Need to update the option string if a new option is added.
|
|
|
|
ASSERT_OK(
|
|
|
|
GetDBOptionsFromString(*options,
|
|
|
|
"wal_bytes_per_sync=4295048118;"
|
|
|
|
"delete_obsolete_files_period_micros=4294967758;"
|
|
|
|
"WAL_ttl_seconds=4295008036;"
|
|
|
|
"WAL_size_limit_MB=4295036161;"
|
|
|
|
"max_write_batch_group_size_bytes=1048576;"
|
|
|
|
"wal_dir=path/to/wal_dir;"
|
|
|
|
"db_write_buffer_size=2587;"
|
|
|
|
"max_subcompactions=64330;"
|
|
|
|
"table_cache_numshardbits=28;"
|
|
|
|
"max_open_files=72;"
|
|
|
|
"max_file_opening_threads=35;"
|
|
|
|
"max_background_jobs=8;"
|
|
|
|
"max_background_compactions=33;"
|
|
|
|
"use_fsync=true;"
|
|
|
|
"use_adaptive_mutex=false;"
|
|
|
|
"max_total_wal_size=4295005604;"
|
|
|
|
"compaction_readahead_size=0;"
|
|
|
|
"keep_log_file_num=4890;"
|
|
|
|
"skip_stats_update_on_db_open=false;"
|
Add an option to prevent DB::Open() from querying sizes of all sst files (#6353)
Summary:
When paranoid_checks is on, DBImpl::CheckConsistency() iterates over all sst files and calls Env::GetFileSize() for each of them. As far as I could understand, this is pretty arbitrary and doesn't affect correctness - if filesystem doesn't corrupt fsynced files, the file sizes will always match; if it does, it may as well corrupt contents as well as sizes, and rocksdb doesn't check contents on open.
If there are thousands of sst files, getting all their sizes takes a while. If, on top of that, Env is overridden to use some remote storage instead of local filesystem, it can be *really* slow and overload the remote storage service. This PR adds an option to not do GetFileSize(); instead it does GetChildren() for parent directory to check that all the expected sst files are at least present, but doesn't check their sizes.
We can't just disable paranoid_checks instead because paranoid_checks do a few other important things: make the DB read-only on write errors, print error messages on read errors, etc.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6353
Test Plan: ran the added sanity check unit test. Will try it out in a LogDevice test cluster where the GetFileSize() calls are causing a lot of trouble.
Differential Revision: D19656425
Pulled By: al13n321
fbshipit-source-id: c2c421b367633033760d1f56747bad206d1fbf82
5 years ago
|
|
|
"skip_checking_sst_file_sizes_on_db_open=false;"
|
|
|
|
"max_manifest_file_size=4295009941;"
|
|
|
|
"db_log_dir=path/to/db_log_dir;"
|
|
|
|
"writable_file_max_buffer_size=1048576;"
|
|
|
|
"paranoid_checks=true;"
|
|
|
|
"flush_verify_memtable_count=true;"
|
|
|
|
"track_and_verify_wals_in_manifest=true;"
|
|
|
|
"verify_sst_unique_id_in_manifest=true;"
|
|
|
|
"is_fd_close_on_exec=false;"
|
|
|
|
"bytes_per_sync=4295013613;"
|
Optionally wait on bytes_per_sync to smooth I/O (#5183)
Summary:
The existing implementation does not guarantee bytes reach disk every `bytes_per_sync` when writing SST files, or every `wal_bytes_per_sync` when writing WALs. This can cause confusing behavior for users who enable this feature to avoid large syncs during flush and compaction, but then end up hitting them anyways.
My understanding of the existing behavior is we used `sync_file_range` with `SYNC_FILE_RANGE_WRITE` to submit ranges for async writeback, such that we could continue processing the next range of bytes while that I/O is happening. I believe we can preserve that benefit while also limiting how far the processing can get ahead of the I/O, which prevents huge syncs from happening when the file finishes.
Consider this `sync_file_range` usage: `sync_file_range(fd_, 0, static_cast<off_t>(offset + nbytes), SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE)`. Expanding the range to start at 0 and adding the `SYNC_FILE_RANGE_WAIT_BEFORE` flag causes any pending writeback (like from a previous call to `sync_file_range`) to finish before it proceeds to submit the latest `nbytes` for writeback. The latest `nbytes` are still written back asynchronously, unless processing exceeds I/O speed, in which case the following `sync_file_range` will need to wait on it.
There is a second change in this PR to use `fdatasync` when `sync_file_range` is unavailable (determined statically) or has some known problem with the underlying filesystem (determined dynamically).
The above two changes only apply when the user enables a new option, `strict_bytes_per_sync`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5183
Differential Revision: D14953553
Pulled By: siying
fbshipit-source-id: 445c3862e019fb7b470f9c7f314fc231b62706e9
6 years ago
|
|
|
"strict_bytes_per_sync=true;"
|
|
|
|
"enable_thread_tracking=false;"
|
|
|
|
"recycle_log_file_num=0;"
|
|
|
|
"create_missing_column_families=true;"
|
|
|
|
"log_file_time_to_roll=3097;"
|
|
|
|
"max_background_flushes=35;"
|
|
|
|
"create_if_missing=false;"
|
|
|
|
"error_if_exists=true;"
|
|
|
|
"delayed_write_rate=4294976214;"
|
|
|
|
"manifest_preallocation_size=1222;"
|
|
|
|
"allow_mmap_writes=false;"
|
|
|
|
"stats_dump_period_sec=70127;"
|
|
|
|
"stats_persist_period_sec=54321;"
|
|
|
|
"persist_stats_to_disk=true;"
|
|
|
|
"stats_history_buffer_size=14159;"
|
|
|
|
"allow_fallocate=true;"
|
|
|
|
"allow_mmap_reads=false;"
|
|
|
|
"use_direct_reads=false;"
|
|
|
|
"use_direct_io_for_flush_and_compaction=false;"
|
|
|
|
"max_log_file_size=4607;"
|
|
|
|
"random_access_max_buffer_size=1048576;"
|
|
|
|
"advise_random_on_open=true;"
|
|
|
|
"fail_if_options_file_error=false;"
|
|
|
|
"enable_pipelined_write=false;"
|
|
|
|
"unordered_write=false;"
|
|
|
|
"allow_concurrent_memtable_write=true;"
|
|
|
|
"wal_recovery_mode=kPointInTimeRecovery;"
|
|
|
|
"enable_write_thread_adaptive_yield=true;"
|
|
|
|
"write_thread_slow_yield_usec=5;"
|
|
|
|
"write_thread_max_yield_usec=1000;"
|
|
|
|
"access_hint_on_compaction_start=NONE;"
|
|
|
|
"info_log_level=DEBUG_LEVEL;"
|
|
|
|
"dump_malloc_stats=false;"
|
|
|
|
"allow_2pc=false;"
|
|
|
|
"avoid_flush_during_recovery=false;"
|
|
|
|
"avoid_flush_during_shutdown=false;"
|
|
|
|
"allow_ingest_behind=false;"
|
|
|
|
"concurrent_prepare=false;"
|
|
|
|
"two_write_queues=false;"
|
|
|
|
"manual_wal_flush=false;"
|
|
|
|
"wal_compression=kZSTD;"
|
|
|
|
"seq_per_batch=false;"
|
|
|
|
"atomic_flush=false;"
|
|
|
|
"avoid_unnecessary_blocking_io=false;"
|
|
|
|
"log_readahead_size=0;"
|
|
|
|
"write_dbid_to_manifest=false;"
|
|
|
|
"best_efforts_recovery=false;"
|
|
|
|
"max_bgerror_resume_count=2;"
|
|
|
|
"bgerror_resume_retry_interval=1000000;"
|
|
|
|
"db_host_id=hostname;"
|
|
|
|
"lowest_used_cache_tier=kNonVolatileBlockTier;"
|
|
|
|
"allow_data_in_errors=false;"
|
|
|
|
"enforce_single_del_contracts=false;",
|
|
|
|
new_options));
|
|
|
|
|
|
|
|
ASSERT_EQ(unset_bytes_base, NumUnsetBytes(new_options_ptr, sizeof(DBOptions),
|
|
|
|
kDBOptionsExcluded));
|
|
|
|
|
|
|
|
options->~DBOptions();
|
|
|
|
new_options->~DBOptions();
|
|
|
|
|
|
|
|
delete[] options_ptr;
|
|
|
|
delete[] new_options_ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If the test fails, likely a new option is added to ColumnFamilyOptions
|
|
|
|
// but it cannot be set through GetColumnFamilyOptionsFromString(), or the
|
|
|
|
// test is not updated accordingly.
|
|
|
|
// After adding an option, we need to make sure it is settable by
|
|
|
|
// GetColumnFamilyOptionsFromString() and add the option to the input
|
|
|
|
// string passed to GetColumnFamilyOptionsFromString() in this test.
|
|
|
|
// If it is a complicated type, you also need to add the field to
|
|
|
|
// kColumnFamilyOptionsExcluded, and maybe add customized verification
|
|
|
|
// for it.
|
|
|
|
TEST_F(OptionsSettableTest, ColumnFamilyOptionsAllFieldsSettable) {
|
|
|
|
// options in the excluded set need to appear in the same order as in
|
|
|
|
// ColumnFamilyOptions.
|
|
|
|
const OffsetGap kColumnFamilyOptionsExcluded = {
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, inplace_callback),
|
|
|
|
sizeof(UpdateStatus(*)(char*, uint32_t*, Slice, std::string*))},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions,
|
|
|
|
memtable_insert_with_hint_prefix_extractor),
|
|
|
|
sizeof(std::shared_ptr<const SliceTransform>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, compression_per_level),
|
|
|
|
sizeof(std::vector<CompressionType>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions,
|
|
|
|
max_bytes_for_level_multiplier_additional),
|
|
|
|
sizeof(std::vector<int>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, memtable_factory),
|
|
|
|
sizeof(std::shared_ptr<MemTableRepFactory>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions,
|
|
|
|
table_properties_collector_factories),
|
|
|
|
sizeof(ColumnFamilyOptions::TablePropertiesCollectorFactories)},
|
|
|
|
{offsetof(struct ColumnFamilyOptions, preclude_last_level_data_seconds),
|
|
|
|
sizeof(uint64_t)},
|
|
|
|
{offsetof(struct ColumnFamilyOptions, blob_cache),
|
|
|
|
sizeof(std::shared_ptr<Cache>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, comparator), sizeof(Comparator*)},
|
|
|
|
{offsetof(struct ColumnFamilyOptions, merge_operator),
|
|
|
|
sizeof(std::shared_ptr<MergeOperator>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, compaction_filter),
|
|
|
|
sizeof(const CompactionFilter*)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, compaction_filter_factory),
|
|
|
|
sizeof(std::shared_ptr<CompactionFilterFactory>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, prefix_extractor),
|
|
|
|
sizeof(std::shared_ptr<const SliceTransform>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, snap_refresh_nanos),
|
|
|
|
sizeof(uint64_t)},
|
|
|
|
{offsetof(struct ColumnFamilyOptions, table_factory),
|
|
|
|
sizeof(std::shared_ptr<TableFactory>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, cf_paths),
|
|
|
|
sizeof(std::vector<DbPath>)},
|
|
|
|
{offsetof(struct ColumnFamilyOptions, compaction_thread_limiter),
|
Concurrent task limiter for compaction thread control (#4332)
Summary:
The PR is targeting to resolve the issue of:
https://github.com/facebook/rocksdb/issues/3972#issue-330771918
We have a rocksdb created with leveled-compaction with multiple column families (CFs), some of CFs are using HDD to store big and less frequently accessed data and others are using SSD.
When there are continuously write traffics going on to all CFs, the compaction thread pool is mostly occupied by those slow HDD compactions, which blocks fully utilize SSD bandwidth.
Since atomic write and transaction is needed across CFs, so splitting it to multiple rocksdb instance is not an option for us.
With the compaction thread control, we got 30%+ HDD write throughput gain, and also a lot smooth SSD write since less write stall happening.
ConcurrentTaskLimiter can be shared with multi-CFs across rocksdb instances, so the feature does not only work for multi-CFs scenarios, but also for multi-rocksdbs scenarios, who need disk IO resource control per tenant.
The usage is straight forward:
e.g.:
//
// Enable compaction thread limiter thru ColumnFamilyOptions
//
std::shared_ptr<ConcurrentTaskLimiter> ctl(NewConcurrentTaskLimiter("foo_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = ctl;
...
//
// Compaction thread limiter can be tuned or disabled on-the-fly
//
ctl->SetMaxOutstandingTask(12); // enlarge to 12 tasks
...
ctl->ResetMaxOutstandingTask(); // disable (bypass) thread limiter
ctl->SetMaxOutstandingTask(-1); // Same as above
...
ctl->SetMaxOutstandingTask(0); // full throttle (0 task)
//
// Sharing compaction thread limiter among CFs (to resolve multiple storage perf issue)
//
std::shared_ptr<ConcurrentTaskLimiter> ctl_ssd(NewConcurrentTaskLimiter("ssd_limiter", 8));
std::shared_ptr<ConcurrentTaskLimiter> ctl_hdd(NewConcurrentTaskLimiter("hdd_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt_ssd1(options);
ColumnFamilyOptions cf_opt_ssd2(options);
ColumnFamilyOptions cf_opt_hdd1(options);
ColumnFamilyOptions cf_opt_hdd2(options);
ColumnFamilyOptions cf_opt_hdd3(options);
// SSD CFs
cf_opt_ssd1.compaction_thread_limiter = ctl_ssd;
cf_opt_ssd2.compaction_thread_limiter = ctl_ssd;
// HDD CFs
cf_opt_hdd1.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd2.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd3.compaction_thread_limiter = ctl_hdd;
...
//
// The limiter is disabled by default (or set to nullptr explicitly)
//
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = nullptr;
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4332
Differential Revision: D13226590
Pulled By: siying
fbshipit-source-id: 14307aec55b8bd59c8223d04aa6db3c03d1b0c1d
6 years ago
|
|
|
sizeof(std::shared_ptr<ConcurrentTaskLimiter>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct ColumnFamilyOptions, sst_partitioner_factory),
|
|
|
|
sizeof(std::shared_ptr<SstPartitionerFactory>)},
|
|
|
|
};
|
|
|
|
|
|
|
|
char* options_ptr = new char[sizeof(ColumnFamilyOptions)];
|
|
|
|
|
|
|
|
// Count padding bytes by setting all bytes in the memory to a special char,
|
|
|
|
// copy a well constructed struct to this memory and see how many special
|
|
|
|
// bytes left.
|
|
|
|
FillWithSpecialChar(options_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded);
|
|
|
|
|
Limit buffering for collecting samples for compression dictionary (#7970)
Summary:
For dictionary compression, we need to collect some representative samples of the data to be compressed, which we use to either generate or train (when `CompressionOptions::zstd_max_train_bytes > 0`) a dictionary. Previously, the strategy was to buffer all the data blocks during flush, and up to the target file size during compaction. That strategy allowed us to randomly pick samples from as wide a range as possible that'd be guaranteed to land in a single output file.
However, some users try to make huge files in memory-constrained environments, where this strategy can cause OOM. This PR introduces an option, `CompressionOptions::max_dict_buffer_bytes`, that limits how much data blocks are buffered before we switch to unbuffered mode (which means creating the per-SST dictionary, writing out the buffered data, and compressing/writing new blocks as soon as they are built). It is not strict as we currently buffer more than just data blocks -- also keys are buffered. But it does make a step towards giving users predictable memory usage.
Related changes include:
- Changed sampling for dictionary compression to select unique data blocks when there is limited availability of data blocks
- Made use of `BlockBuilder::SwapAndReset()` to save an allocation+memcpy when buffering data blocks for building a dictionary
- Changed `ParseBoolean()` to accept an input containing characters after the boolean. This is necessary since, with this PR, a value for `CompressionOptions::enabled` is no longer necessarily the final component in the `CompressionOptions` string.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7970
Test Plan:
- updated `CompressionOptions` unit tests to verify limit is respected (to the extent expected in the current implementation) in various scenarios of flush/compaction to bottommost/non-bottommost level
- looked at jemalloc heap profiles right before and after switching to unbuffered mode during flush/compaction. Verified memory usage in buffering is proportional to the limit set.
Reviewed By: pdillinger
Differential Revision: D26467994
Pulled By: ajkr
fbshipit-source-id: 3da4ef9fba59974e4ef40e40c01611002c861465
4 years ago
|
|
|
// Invoke a user-defined constructor in the hope that it does not overwrite
|
|
|
|
// padding bytes. Note that previously we relied on the implicitly-defined
|
|
|
|
// copy-assignment operator (i.e., `*options = ColumnFamilyOptions();`) here,
|
|
|
|
// which did in fact modify padding bytes.
|
|
|
|
ColumnFamilyOptions* options = new (options_ptr) ColumnFamilyOptions();
|
|
|
|
|
|
|
|
int unset_bytes_base = NumUnsetBytes(options_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded);
|
|
|
|
ASSERT_GT(unset_bytes_base, 0);
|
|
|
|
options->~ColumnFamilyOptions();
|
|
|
|
|
|
|
|
options = new (options_ptr) ColumnFamilyOptions();
|
|
|
|
FillWithSpecialChar(options_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded);
|
|
|
|
|
|
|
|
// Following options are not settable through
|
|
|
|
// GetColumnFamilyOptionsFromString():
|
|
|
|
options->compaction_options_universal = CompactionOptionsUniversal();
|
|
|
|
options->num_levels = 42; // Initialize options for MutableCF
|
Concurrent task limiter for compaction thread control (#4332)
Summary:
The PR is targeting to resolve the issue of:
https://github.com/facebook/rocksdb/issues/3972#issue-330771918
We have a rocksdb created with leveled-compaction with multiple column families (CFs), some of CFs are using HDD to store big and less frequently accessed data and others are using SSD.
When there are continuously write traffics going on to all CFs, the compaction thread pool is mostly occupied by those slow HDD compactions, which blocks fully utilize SSD bandwidth.
Since atomic write and transaction is needed across CFs, so splitting it to multiple rocksdb instance is not an option for us.
With the compaction thread control, we got 30%+ HDD write throughput gain, and also a lot smooth SSD write since less write stall happening.
ConcurrentTaskLimiter can be shared with multi-CFs across rocksdb instances, so the feature does not only work for multi-CFs scenarios, but also for multi-rocksdbs scenarios, who need disk IO resource control per tenant.
The usage is straight forward:
e.g.:
//
// Enable compaction thread limiter thru ColumnFamilyOptions
//
std::shared_ptr<ConcurrentTaskLimiter> ctl(NewConcurrentTaskLimiter("foo_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = ctl;
...
//
// Compaction thread limiter can be tuned or disabled on-the-fly
//
ctl->SetMaxOutstandingTask(12); // enlarge to 12 tasks
...
ctl->ResetMaxOutstandingTask(); // disable (bypass) thread limiter
ctl->SetMaxOutstandingTask(-1); // Same as above
...
ctl->SetMaxOutstandingTask(0); // full throttle (0 task)
//
// Sharing compaction thread limiter among CFs (to resolve multiple storage perf issue)
//
std::shared_ptr<ConcurrentTaskLimiter> ctl_ssd(NewConcurrentTaskLimiter("ssd_limiter", 8));
std::shared_ptr<ConcurrentTaskLimiter> ctl_hdd(NewConcurrentTaskLimiter("hdd_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt_ssd1(options);
ColumnFamilyOptions cf_opt_ssd2(options);
ColumnFamilyOptions cf_opt_hdd1(options);
ColumnFamilyOptions cf_opt_hdd2(options);
ColumnFamilyOptions cf_opt_hdd3(options);
// SSD CFs
cf_opt_ssd1.compaction_thread_limiter = ctl_ssd;
cf_opt_ssd2.compaction_thread_limiter = ctl_ssd;
// HDD CFs
cf_opt_hdd1.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd2.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd3.compaction_thread_limiter = ctl_hdd;
...
//
// The limiter is disabled by default (or set to nullptr explicitly)
//
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = nullptr;
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4332
Differential Revision: D13226590
Pulled By: siying
fbshipit-source-id: 14307aec55b8bd59c8223d04aa6db3c03d1b0c1d
6 years ago
|
|
|
options->compaction_filter = nullptr;
|
|
|
|
options->sst_partitioner_factory = nullptr;
|
|
|
|
|
|
|
|
char* new_options_ptr = new char[sizeof(ColumnFamilyOptions)];
|
|
|
|
ColumnFamilyOptions* new_options =
|
|
|
|
new (new_options_ptr) ColumnFamilyOptions();
|
|
|
|
FillWithSpecialChar(new_options_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded);
|
|
|
|
|
|
|
|
// Need to update the option string if a new option is added.
|
|
|
|
ASSERT_OK(GetColumnFamilyOptionsFromString(
|
|
|
|
*options,
|
|
|
|
"compaction_filter_factory=mpudlojcujCompactionFilterFactory;"
|
|
|
|
"table_factory=PlainTable;"
|
|
|
|
"prefix_extractor=rocksdb.CappedPrefix.13;"
|
|
|
|
"comparator=leveldb.BytewiseComparator;"
|
|
|
|
"compression_per_level=kBZip2Compression:kBZip2Compression:"
|
|
|
|
"kBZip2Compression:kNoCompression:kZlibCompression:kBZip2Compression:"
|
|
|
|
"kSnappyCompression;"
|
|
|
|
"max_bytes_for_level_base=986;"
|
|
|
|
"bloom_locality=8016;"
|
|
|
|
"target_file_size_base=4294976376;"
|
|
|
|
"memtable_huge_page_size=2557;"
|
|
|
|
"max_successive_merges=5497;"
|
|
|
|
"max_sequential_skip_in_iterations=4294971408;"
|
|
|
|
"arena_block_size=1893;"
|
|
|
|
"target_file_size_multiplier=35;"
|
|
|
|
"min_write_buffer_number_to_merge=9;"
|
|
|
|
"max_write_buffer_number=84;"
|
|
|
|
"write_buffer_size=1653;"
|
|
|
|
"max_compaction_bytes=64;"
|
|
|
|
"max_bytes_for_level_multiplier=60;"
|
|
|
|
"memtable_factory=SkipListFactory;"
|
|
|
|
"compression=kNoCompression;"
|
Support using ZDICT_finalizeDictionary to generate zstd dictionary (#9857)
Summary:
An untrained dictionary is currently simply the concatenation of several samples. The ZSTD API, ZDICT_finalizeDictionary(), can improve such a dictionary's effectiveness at low cost. This PR changes how dictionary is created by calling the ZSTD ZDICT_finalizeDictionary() API instead of creating raw content dictionary (when max_dict_buffer_bytes > 0), and pass in all buffered uncompressed data blocks as samples.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9857
Test Plan:
#### db_bench test for cpu/memory of compression+decompression and space saving on synthetic data:
Set up: change the parameter [here](https://github.com/facebook/rocksdb/blob/fb9a167a55e0970b1ef6f67c1600c8d9c4c6114f/tools/db_bench_tool.cc#L1766) to 16384 to make synthetic data more compressible.
```
# linked local ZSTD with version 1.5.2
# DEBUG_LEVEL=0 ROCKSDB_NO_FBCODE=1 ROCKSDB_DISABLE_ZSTD=1 EXTRA_CXXFLAGS="-DZSTD_STATIC_LINKING_ONLY -DZSTD -I/data/users/changyubi/install/include/" EXTRA_LDFLAGS="-L/data/users/changyubi/install/lib/ -l:libzstd.a" make -j32 db_bench
dict_bytes=16384
train_bytes=1048576
echo "========== No Dictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=0 -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total
echo "========== Raw Content Dictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench_main -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench_main -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total
echo "========== FinalizeDictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total
echo "========== TrainDictionary =========="
TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=filluniquerandom,compact -num=10000000 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 -max_background_jobs=24 -memtablerep=vector -allow_concurrent_memtable_write=false -disable_wal=true -max_write_buffer_number=8 >/dev/null 2>&1
TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -use_existing_db=true -benchmarks=compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -block_size=4096 2>&1 | grep elapsed
du -hc /dev/shm/dbbench/*sst | grep total
# Result: TrainDictionary is much better on space saving, but FinalizeDictionary seems to use less memory.
# before compression data size: 1.2GB
dict_bytes=16384
max_dict_buffer_bytes = 1048576
space cpu/memory
No Dictionary 468M 14.93user 1.00system 0:15.92elapsed 100%CPU (0avgtext+0avgdata 23904maxresident)k
Raw Dictionary 251M 15.81user 0.80system 0:16.56elapsed 100%CPU (0avgtext+0avgdata 156808maxresident)k
FinalizeDictionary 236M 11.93user 0.64system 0:12.56elapsed 100%CPU (0avgtext+0avgdata 89548maxresident)k
TrainDictionary 84M 7.29user 0.45system 0:07.75elapsed 100%CPU (0avgtext+0avgdata 97288maxresident)k
```
#### Benchmark on 10 sample SST files for spacing saving and CPU time on compression:
FinalizeDictionary is comparable to TrainDictionary in terms of space saving, and takes less time in compression.
```
dict_bytes=16384
train_bytes=1048576
for sst_file in `ls ../temp/myrock-sst/`
do
echo "********** $sst_file **********"
echo "========== No Dictionary =========="
./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD
echo "========== Raw Content Dictionary =========="
./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes
echo "========== FinalizeDictionary =========="
./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes --compression_use_zstd_finalize_dict
echo "========== TrainDictionary =========="
./sst_dump --file="../temp/myrock-sst/$sst_file" --command=recompress --compression_level_from=6 --compression_level_to=6 --compression_types=kZSTD --compression_max_dict_bytes=$dict_bytes --compression_zstd_max_train_bytes=$train_bytes
done
010240.sst (Size/Time) 011029.sst 013184.sst 021552.sst 185054.sst 185137.sst 191666.sst 7560381.sst 7604174.sst 7635312.sst
No Dictionary 28165569 / 2614419 32899411 / 2976832 32977848 / 3055542 31966329 / 2004590 33614351 / 1755877 33429029 / 1717042 33611933 / 1776936 33634045 / 2771417 33789721 / 2205414 33592194 / 388254
Raw Content Dictionary 28019950 / 2697961 33748665 / 3572422 33896373 / 3534701 26418431 / 2259658 28560825 / 1839168 28455030 / 1846039 28494319 / 1861349 32391599 / 3095649 33772142 / 2407843 33592230 / 474523
FinalizeDictionary 27896012 / 2650029 33763886 / 3719427 33904283 / 3552793 26008225 / 2198033 28111872 / 1869530 28014374 / 1789771 28047706 / 1848300 32296254 / 3204027 33698698 / 2381468 33592344 / 517433
TrainDictionary 28046089 / 2740037 33706480 / 3679019 33885741 / 3629351 25087123 / 2204558 27194353 / 1970207 27234229 / 1896811 27166710 / 1903119 32011041 / 3322315 32730692 / 2406146 33608631 / 570593
```
#### Decompression/Read test:
With FinalizeDictionary/TrainDictionary, some data structure used for decompression are in stored in dictionary, so they are expected to be faster in terms of decompression/reads.
```
dict_bytes=16384
train_bytes=1048576
echo "No Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=0 > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=0 2>&1 | grep MB/s
echo "Raw Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes 2>&1 | grep MB/s
echo "FinalizeDict"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes -compression_use_zstd_dict_trainer=false 2>&1 | grep MB/s
echo "Train Dictionary"
TEST_TMPDIR=/dev/shm/ ./db_bench -benchmarks=filluniquerandom,compact -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes > /dev/null 2>&1
TEST_TMPDIR=/dev/shm/ ./db_bench -use_existing_db=true -benchmarks=readrandom -cache_size=0 -compression_type=zstd -compression_max_dict_bytes=$dict_bytes -compression_zstd_max_train_bytes=$train_bytes 2>&1 | grep MB/s
No Dictionary
readrandom : 12.183 micros/op 82082 ops/sec 12.183 seconds 1000000 operations; 9.1 MB/s (1000000 of 1000000 found)
Raw Dictionary
readrandom : 12.314 micros/op 81205 ops/sec 12.314 seconds 1000000 operations; 9.0 MB/s (1000000 of 1000000 found)
FinalizeDict
readrandom : 9.787 micros/op 102180 ops/sec 9.787 seconds 1000000 operations; 11.3 MB/s (1000000 of 1000000 found)
Train Dictionary
readrandom : 9.698 micros/op 103108 ops/sec 9.699 seconds 1000000 operations; 11.4 MB/s (1000000 of 1000000 found)
```
Reviewed By: ajkr
Differential Revision: D35720026
Pulled By: cbi42
fbshipit-source-id: 24d230fdff0fd28a1bb650658798f00dfcfb2a1f
3 years ago
|
|
|
"compression_opts=5:6:7:8:9:10:true:11:false;"
|
|
|
|
"bottommost_compression_opts=4:5:6:7:8:9:true:10:true;"
|
|
|
|
"bottommost_compression=kDisableCompressionOption;"
|
|
|
|
"level0_stop_writes_trigger=33;"
|
|
|
|
"num_levels=99;"
|
|
|
|
"level0_slowdown_writes_trigger=22;"
|
|
|
|
"level0_file_num_compaction_trigger=14;"
|
|
|
|
"compaction_filter=urxcqstuwnCompactionFilter;"
|
|
|
|
"soft_pending_compaction_bytes_limit=0;"
|
|
|
|
"max_write_buffer_number_to_maintain=84;"
|
Refactor trimming logic for immutable memtables (#5022)
Summary:
MyRocks currently sets `max_write_buffer_number_to_maintain` in order to maintain enough history for transaction conflict checking. The effectiveness of this approach depends on the size of memtables. When memtables are small, it may not keep enough history; when memtables are large, this may consume too much memory.
We are proposing a new way to configure memtable list history: by limiting the memory usage of immutable memtables. The new option is `max_write_buffer_size_to_maintain` and it will take precedence over the old `max_write_buffer_number_to_maintain` if they are both set to non-zero values. The new option accounts for the total memory usage of flushed immutable memtables and mutable memtable. When the total usage exceeds the limit, RocksDB may start dropping immutable memtables (which is also called trimming history), starting from the oldest one.
The semantics of the old option actually works both as an upper bound and lower bound. History trimming will start if number of immutable memtables exceeds the limit, but it will never go below (limit-1) due to history trimming.
In order the mimic the behavior with the new option, history trimming will stop if dropping the next immutable memtable causes the total memory usage go below the size limit. For example, assuming the size limit is set to 64MB, and there are 3 immutable memtables with sizes of 20, 30, 30. Although the total memory usage is 80MB > 64MB, dropping the oldest memtable will reduce the memory usage to 60MB < 64MB, so in this case no memtable will be dropped.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5022
Differential Revision: D14394062
Pulled By: miasantreble
fbshipit-source-id: 60457a509c6af89d0993f988c9b5c2aa9e45f5c5
5 years ago
|
|
|
"max_write_buffer_size_to_maintain=2147483648;"
|
|
|
|
"merge_operator=aabcxehazrMergeOperator;"
|
|
|
|
"memtable_prefix_bloom_size_ratio=0.4642;"
|
|
|
|
"memtable_whole_key_filtering=true;"
|
|
|
|
"memtable_insert_with_hint_prefix_extractor=rocksdb.CappedPrefix.13;"
|
|
|
|
"check_flush_compaction_key_order=false;"
|
|
|
|
"paranoid_file_checks=true;"
|
|
|
|
"force_consistency_checks=true;"
|
|
|
|
"inplace_update_num_locks=7429;"
|
|
|
|
"experimental_mempurge_threshold=0.0001;"
|
|
|
|
"optimize_filters_for_hits=false;"
|
|
|
|
"level_compaction_dynamic_level_bytes=false;"
|
Align compaction output file boundaries to the next level ones (#10655)
Summary:
Try to align the compaction output file boundaries to the next level ones
(grandparent level), to reduce the level compaction write-amplification.
In level compaction, there are "wasted" data at the beginning and end of the
output level files. Align the file boundary can avoid such "wasted" compaction.
With this PR, it tries to align the non-bottommost level file boundaries to its
next level ones. It may cut file when the file size is large enough (at least
50% of target_file_size) and not too large (2x target_file_size).
db_bench shows about 12.56% compaction reduction:
```
TEST_TMPDIR=/data/dbbench2 ./db_bench --benchmarks=fillrandom,readrandom -max_background_jobs=12 -num=400000000 -target_file_size_base=33554432
# baseline:
Flush(GB): cumulative 25.882, interval 7.216
Cumulative compaction: 285.90 GB write, 162.36 MB/s write, 269.68 GB read, 153.15 MB/s read, 2926.7 seconds
# with this change:
Flush(GB): cumulative 25.882, interval 7.753
Cumulative compaction: 249.97 GB write, 141.96 MB/s write, 233.74 GB read, 132.74 MB/s read, 2534.9 seconds
```
The compaction simulator shows a similar result (14% with 100G random data).
As a side effect, with this PR, the SST file size can exceed the
target_file_size, but is capped at 2x target_file_size. And there will be
smaller files. Here are file size statistics when loading 100GB with the target
file size 32MB:
```
baseline this_PR
count 1.656000e+03 1.705000e+03
mean 3.116062e+07 3.028076e+07
std 7.145242e+06 8.046139e+06
```
The feature is enabled by default, to revert to the old behavior disable it
with `AdvancedColumnFamilyOptions.level_compaction_dynamic_file_size = false`
Also includes https://github.com/facebook/rocksdb/issues/1963 to cut file before skippable grandparent file. Which is for
use case like user adding 2 or more non-overlapping data range at the same
time, it can reduce the overlapping of 2 datasets in the lower levels.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10655
Reviewed By: cbi42
Differential Revision: D39552321
Pulled By: jay-zhuang
fbshipit-source-id: 640d15f159ab0cd973f2426cfc3af266fc8bdde2
2 years ago
|
|
|
"level_compaction_dynamic_file_size=true;"
|
|
|
|
"inplace_update_support=false;"
|
|
|
|
"compaction_style=kCompactionStyleFIFO;"
|
|
|
|
"compaction_pri=kMinOverlappingRatio;"
|
|
|
|
"hard_pending_compaction_bytes_limit=0;"
|
|
|
|
"disable_auto_compactions=false;"
|
|
|
|
"report_bg_io_stats=true;"
|
|
|
|
"ttl=60;"
|
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
|
|
|
"periodic_compaction_seconds=3600;"
|
|
|
|
"sample_for_compression=0;"
|
|
|
|
"enable_blob_files=true;"
|
|
|
|
"min_blob_size=256;"
|
|
|
|
"blob_file_size=1000000;"
|
|
|
|
"blob_compression_type=kBZip2Compression;"
|
|
|
|
"enable_blob_garbage_collection=true;"
|
|
|
|
"blob_garbage_collection_age_cutoff=0.5;"
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
"blob_garbage_collection_force_threshold=0.75;"
|
|
|
|
"blob_compaction_readahead_size=262144;"
|
|
|
|
"blob_file_starting_level=1;"
|
|
|
|
"prepopulate_blob_cache=kDisable;"
|
|
|
|
"bottommost_temperature=kWarm;"
|
|
|
|
"last_level_temperature=kWarm;"
|
|
|
|
"preclude_last_level_data_seconds=86400;"
|
|
|
|
"compaction_options_fifo={max_table_files_size=3;allow_"
|
|
|
|
"compaction=false;age_for_warm=1;};"
|
|
|
|
"blob_cache=1M;"
|
|
|
|
"memtable_protection_bytes_per_key=2;",
|
|
|
|
new_options));
|
|
|
|
|
|
|
|
ASSERT_NE(new_options->blob_cache.get(), nullptr);
|
|
|
|
|
|
|
|
ASSERT_EQ(unset_bytes_base,
|
|
|
|
NumUnsetBytes(new_options_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded));
|
|
|
|
|
|
|
|
ColumnFamilyOptions rnd_filled_options = *new_options;
|
|
|
|
|
|
|
|
options->~ColumnFamilyOptions();
|
|
|
|
new_options->~ColumnFamilyOptions();
|
|
|
|
|
|
|
|
delete[] options_ptr;
|
|
|
|
delete[] new_options_ptr;
|
|
|
|
|
|
|
|
// Test copying to mutabable and immutable options and copy back the mutable
|
|
|
|
// part.
|
|
|
|
const OffsetGap kMutableCFOptionsExcluded = {
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct MutableCFOptions, prefix_extractor),
|
|
|
|
sizeof(std::shared_ptr<const SliceTransform>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct MutableCFOptions,
|
|
|
|
max_bytes_for_level_multiplier_additional),
|
|
|
|
sizeof(std::vector<int>)},
|
|
|
|
{offsetof(struct MutableCFOptions, compression_per_level),
|
|
|
|
sizeof(std::vector<CompressionType>)},
|
Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563)
Summary:
After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some
warnings-as-error in some internal builds like this:
```
stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error:
offset of on non-standard-layout type 'struct CompactionServiceResult'
[-Werror,-Winvalid-offsetof]
{offsetof(struct CompactionServiceResult, status),
^ ~~~~~~
```
I see three potential solutions to resolving this:
* Expand our use of an idiom that works around the warning (see offset_of
functions removed in this change, inspired by
https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However,
this construction is invoking undefined behavior that assumes consistent
layout with no compiler-introduced indirection. A compiler incompatible
with our assumptions will likely compile the code and exhibit undefined
behavior.
* Migrate to something in place of offset, like a function mapping
CompactionServiceResult* to Status* (for the `status` field). This might
be required in the long term.
* **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way
when the compiler allows it. From a comment on
https://gist.github.com/graphitemaster/494f21190bb2c63c5516:
> A final note: in C++17, offsetof is conditionally supported, which
> means that you can use it on any type (not just standard layout
> types) and the compiler will error if it can't compile it correctly.
> That appears to be the best option if you can live with C++17 and
> don't need constexpr support.
The C++17 semantics are confirmed on
https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the
warning as long as we accept that we might run into a compiler that
rejects the code, and at that point we will find a solution, such as
the more intrusive "migrate" solution above.
Although this is currently only showing in our buck build, it will
surely show up also with make and cmake, so I have updated those
configurations as well.
Also in the buck build, -Wno-expansion-to-defined does not appear to be
needed anymore (both current compiler configurations) so I
removed it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563
Test Plan: Tried out buck builds with both current compiler configurations
Reviewed By: riversand963
Differential Revision: D34220931
Pulled By: pdillinger
fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f
3 years ago
|
|
|
{offsetof(struct MutableCFOptions, max_file_size),
|
|
|
|
sizeof(std::vector<uint64_t>)},
|
|
|
|
};
|
|
|
|
|
|
|
|
// For all memory used for options, pre-fill every char. Otherwise, the
|
|
|
|
// padding bytes might be different so that byte-wise comparison doesn't
|
|
|
|
// general equal results even if objects are equal.
|
|
|
|
const char kMySpecialChar = 'x';
|
|
|
|
char* mcfo1_ptr = new char[sizeof(MutableCFOptions)];
|
|
|
|
FillWithSpecialChar(mcfo1_ptr, sizeof(MutableCFOptions),
|
|
|
|
kMutableCFOptionsExcluded, kMySpecialChar);
|
|
|
|
char* mcfo2_ptr = new char[sizeof(MutableCFOptions)];
|
|
|
|
FillWithSpecialChar(mcfo2_ptr, sizeof(MutableCFOptions),
|
|
|
|
kMutableCFOptionsExcluded, kMySpecialChar);
|
|
|
|
|
|
|
|
// A clean column family options is constructed after filling the same special
|
|
|
|
// char as the initial one. So that the padding bytes are the same.
|
|
|
|
char* cfo_clean_ptr = new char[sizeof(ColumnFamilyOptions)];
|
|
|
|
FillWithSpecialChar(cfo_clean_ptr, sizeof(ColumnFamilyOptions),
|
|
|
|
kColumnFamilyOptionsExcluded);
|
|
|
|
rnd_filled_options.num_levels = 66;
|
|
|
|
ColumnFamilyOptions* cfo_clean = new (cfo_clean_ptr) ColumnFamilyOptions();
|
|
|
|
|
|
|
|
MutableCFOptions* mcfo1 =
|
|
|
|
new (mcfo1_ptr) MutableCFOptions(rnd_filled_options);
|
|
|
|
ColumnFamilyOptions cfo_back = BuildColumnFamilyOptions(*cfo_clean, *mcfo1);
|
|
|
|
MutableCFOptions* mcfo2 = new (mcfo2_ptr) MutableCFOptions(cfo_back);
|
|
|
|
|
|
|
|
ASSERT_TRUE(CompareBytes(mcfo1_ptr, mcfo2_ptr, sizeof(MutableCFOptions),
|
|
|
|
kMutableCFOptionsExcluded));
|
|
|
|
|
|
|
|
cfo_clean->~ColumnFamilyOptions();
|
|
|
|
mcfo1->~MutableCFOptions();
|
|
|
|
mcfo2->~MutableCFOptions();
|
|
|
|
delete[] mcfo1_ptr;
|
|
|
|
delete[] mcfo2_ptr;
|
|
|
|
delete[] cfo_clean_ptr;
|
|
|
|
}
|
|
|
|
#endif // !ROCKSDB_UBSAN_RUN
|
|
|
|
#endif // !__clang__
|
|
|
|
#endif // OS_LINUX || OS_WIN
|
|
|
|
#endif // !ROCKSDB_LITE
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
|
|
|
|
int main(int argc, char** argv) {
|
|
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
|
|
#ifdef GFLAGS
|
|
|
|
ParseCommandLineFlags(&argc, &argv, true);
|
|
|
|
#endif // GFLAGS
|
|
|
|
return RUN_ALL_TESTS();
|
|
|
|
}
|