2016-02-09 23:12:00 +00:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-15 23:03:42 +00:00
|
|
|
// 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).
|
2014-12-23 21:24:07 +00:00
|
|
|
//
|
|
|
|
// Copyright (c) 2012 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.
|
2015-07-20 18:24:54 +00:00
|
|
|
|
2023-12-01 19:15:17 +00:00
|
|
|
#include <cstdint>
|
2014-12-23 21:24:07 +00:00
|
|
|
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
#include "db/wide/wide_column_serialization.h"
|
2019-09-16 17:31:27 +00:00
|
|
|
#include "file/random_access_file_reader.h"
|
2019-10-09 02:17:39 +00:00
|
|
|
#include "port/stack_trace.h"
|
2021-06-15 10:42:52 +00:00
|
|
|
#include "rocksdb/convenience.h"
|
2014-12-23 21:24:07 +00:00
|
|
|
#include "rocksdb/filter_policy.h"
|
2021-06-15 10:42:52 +00:00
|
|
|
#include "rocksdb/sst_dump_tool.h"
|
2019-05-30 21:47:29 +00:00
|
|
|
#include "table/block_based/block_based_table_factory.h"
|
Fix and defend against FilePrefetchBuffer combined with mmap reads (#12206)
Summary:
FilePrefetchBuffer makes an unchecked assumption about the behavior of RandomAccessFileReader::Read: that it will write to the provided buffer rather than returning the data in an alternate buffer. FilePrefetchBuffer has been quietly incompatible with mmap reads (e.g. allow_mmap_reads / use_mmap_reads) because in that case an alternate buffer is returned (mmapped memory). This incompatibility currently leads to quiet data corruption, as seen in amplified crash test failure in https://github.com/facebook/rocksdb/issues/12200.
In this change,
* Check whether RandomAccessFileReader::Read has the expected behavior, and fail if not. (Assertion failure in debug build, return Corruption in release build.) This will detect future regressions synchronously and precisely, rather than relying on debugging downstream data corruption.
* Why not recover? My understanding is that FilePrefetchBuffer is not intended for use when RandomAccessFileReader::Read uses an alternate buffer, so quietly recovering could lead to undesirable (inefficient) behavior.
* Mention incompatibility with mmap-based readers in the internal API comments for FilePrefetchBuffer
* Fix two cases where FilePrefetchBuffer could be used with mmap, both stemming from SstFileDumper, though one fix is in BlockBasedTableReader. There is currently no way to ask a RandomAccessFileReader whether it's using mmap, so we currently have to rely on other options as clues.
Keeping separate from https://github.com/facebook/rocksdb/issues/12200 in part because this change is more appropriate for backport than that one.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12206
Test Plan:
* Manually verified that the new check aids in debugging.
* Unit test added, that fails if either fix is missed.
* Ran blackbox_crash_test for hours, with and without https://github.com/facebook/rocksdb/issues/12200
Reviewed By: akankshamahajan15
Differential Revision: D52551701
Pulled By: pdillinger
fbshipit-source-id: dea87c5782b7c484a6c6e424585c8832dfc580dc
2024-01-05 02:39:05 +00:00
|
|
|
#include "table/sst_file_dumper.h"
|
2014-12-23 21:24:07 +00:00
|
|
|
#include "table/table_builder.h"
|
2019-05-30 18:21:38 +00:00
|
|
|
#include "test_util/testharness.h"
|
|
|
|
#include "test_util/testutil.h"
|
Fix and defend against FilePrefetchBuffer combined with mmap reads (#12206)
Summary:
FilePrefetchBuffer makes an unchecked assumption about the behavior of RandomAccessFileReader::Read: that it will write to the provided buffer rather than returning the data in an alternate buffer. FilePrefetchBuffer has been quietly incompatible with mmap reads (e.g. allow_mmap_reads / use_mmap_reads) because in that case an alternate buffer is returned (mmapped memory). This incompatibility currently leads to quiet data corruption, as seen in amplified crash test failure in https://github.com/facebook/rocksdb/issues/12200.
In this change,
* Check whether RandomAccessFileReader::Read has the expected behavior, and fail if not. (Assertion failure in debug build, return Corruption in release build.) This will detect future regressions synchronously and precisely, rather than relying on debugging downstream data corruption.
* Why not recover? My understanding is that FilePrefetchBuffer is not intended for use when RandomAccessFileReader::Read uses an alternate buffer, so quietly recovering could lead to undesirable (inefficient) behavior.
* Mention incompatibility with mmap-based readers in the internal API comments for FilePrefetchBuffer
* Fix two cases where FilePrefetchBuffer could be used with mmap, both stemming from SstFileDumper, though one fix is in BlockBasedTableReader. There is currently no way to ask a RandomAccessFileReader whether it's using mmap, so we currently have to rely on other options as clues.
Keeping separate from https://github.com/facebook/rocksdb/issues/12200 in part because this change is more appropriate for backport than that one.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12206
Test Plan:
* Manually verified that the new check aids in debugging.
* Unit test added, that fails if either fix is missed.
* Ran blackbox_crash_test for hours, with and without https://github.com/facebook/rocksdb/issues/12200
Reviewed By: akankshamahajan15
Differential Revision: D52551701
Pulled By: pdillinger
fbshipit-source-id: dea87c5782b7c484a6c6e424585c8832dfc580dc
2024-01-05 02:39:05 +00:00
|
|
|
#include "util/defer.h"
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2020-05-19 16:20:21 +00:00
|
|
|
const uint32_t kOptLength = 1024;
|
2014-12-23 21:24:07 +00:00
|
|
|
|
|
|
|
namespace {
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
static std::string MakeKey(int i,
|
|
|
|
ValueType value_type = ValueType::kTypeValue) {
|
2014-12-23 21:24:07 +00:00
|
|
|
char buf[100];
|
|
|
|
snprintf(buf, sizeof(buf), "k_%04d", i);
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
InternalKey key(std::string(buf), 0, value_type);
|
2014-12-23 21:24:07 +00:00
|
|
|
return key.Encode().ToString();
|
|
|
|
}
|
|
|
|
|
2022-02-08 20:14:25 +00:00
|
|
|
static std::string MakeKeyWithTimeStamp(int i, uint64_t ts) {
|
|
|
|
char buf[100];
|
|
|
|
snprintf(buf, sizeof(buf), "k_%04d", i);
|
|
|
|
return test::KeyStr(ts, std::string(buf), /*seq=*/0, kTypeValue);
|
|
|
|
}
|
|
|
|
|
2014-12-23 21:24:07 +00:00
|
|
|
static std::string MakeValue(int i) {
|
|
|
|
char buf[100];
|
|
|
|
snprintf(buf, sizeof(buf), "v_%04d", i);
|
|
|
|
InternalKey key(std::string(buf), 0, ValueType::kTypeValue);
|
|
|
|
return key.Encode().ToString();
|
|
|
|
}
|
|
|
|
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
static std::string MakeWideColumn(int i) {
|
|
|
|
std::string val = MakeValue(i);
|
|
|
|
std::string val1 = "attr_1_val_" + val;
|
|
|
|
std::string val2 = "attr_2_val_" + val;
|
|
|
|
WideColumns columns{{"attr_1", val1}, {"attr_2", val2}};
|
|
|
|
std::string entity;
|
|
|
|
EXPECT_OK(WideColumnSerialization::Serialize(columns, entity));
|
|
|
|
return entity;
|
|
|
|
}
|
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
void cleanup(const Options& opts, const std::string& file_name) {
|
|
|
|
Env* env = opts.env;
|
2020-09-05 02:25:20 +00:00
|
|
|
ASSERT_OK(env->DeleteFile(file_name));
|
2014-12-23 21:24:07 +00:00
|
|
|
std::string outfile_name = file_name.substr(0, file_name.length() - 4);
|
|
|
|
outfile_name.append("_dump.txt");
|
2020-09-05 02:25:20 +00:00
|
|
|
env->DeleteFile(outfile_name).PermitUncheckedError();
|
2014-12-23 21:24:07 +00:00
|
|
|
}
|
|
|
|
} // namespace
|
|
|
|
|
|
|
|
// Test for sst dump tool "raw" mode
|
2015-03-17 21:08:00 +00:00
|
|
|
class SSTDumpToolTest : public testing::Test {
|
2019-10-09 02:17:39 +00:00
|
|
|
std::string test_dir_;
|
|
|
|
Env* env_;
|
|
|
|
std::shared_ptr<Env> env_guard_;
|
2018-08-23 17:04:10 +00:00
|
|
|
|
|
|
|
public:
|
2019-10-09 02:17:39 +00:00
|
|
|
SSTDumpToolTest() : env_(Env::Default()) {
|
2021-06-15 10:42:52 +00:00
|
|
|
EXPECT_OK(test::CreateEnvFromSystem(ConfigOptions(), &env_, &env_guard_));
|
2019-10-09 02:17:39 +00:00
|
|
|
test_dir_ = test::PerThreadDBPath(env_, "sst_dump_test_db");
|
|
|
|
Status s = env_->CreateDirIfMissing(test_dir_);
|
|
|
|
EXPECT_OK(s);
|
|
|
|
}
|
|
|
|
|
|
|
|
~SSTDumpToolTest() override {
|
|
|
|
if (getenv("KEEP_DB")) {
|
|
|
|
fprintf(stdout, "Data is still at %s\n", test_dir_.c_str());
|
|
|
|
} else {
|
|
|
|
EXPECT_OK(env_->DeleteDir(test_dir_));
|
|
|
|
}
|
|
|
|
}
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2019-10-09 02:17:39 +00:00
|
|
|
Env* env() { return env_; }
|
2018-08-09 21:21:35 +00:00
|
|
|
|
|
|
|
std::string MakeFilePath(const std::string& file_name) const {
|
2019-10-09 02:17:39 +00:00
|
|
|
std::string path(test_dir_);
|
2018-08-09 21:21:35 +00:00
|
|
|
path.append("/").append(file_name);
|
|
|
|
return path;
|
|
|
|
}
|
|
|
|
|
2018-08-23 17:04:10 +00:00
|
|
|
template <std::size_t N>
|
2018-08-09 21:21:35 +00:00
|
|
|
void PopulateCommandArgs(const std::string& file_path, const char* command,
|
2018-08-23 17:04:10 +00:00
|
|
|
char* (&usage)[N]) const {
|
2018-08-10 02:37:47 +00:00
|
|
|
for (int i = 0; i < static_cast<int>(N); ++i) {
|
2020-05-13 01:21:32 +00:00
|
|
|
usage[i] = new char[kOptLength];
|
2018-08-09 21:21:35 +00:00
|
|
|
}
|
2020-05-13 01:21:32 +00:00
|
|
|
snprintf(usage[0], kOptLength, "./sst_dump");
|
|
|
|
snprintf(usage[1], kOptLength, "%s", command);
|
|
|
|
snprintf(usage[2], kOptLength, "--file=%s", file_path.c_str());
|
2018-08-09 21:21:35 +00:00
|
|
|
}
|
2020-09-05 02:25:20 +00:00
|
|
|
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
void createSST(const Options& opts, const std::string& file_name,
|
2024-02-01 22:35:03 +00:00
|
|
|
uint32_t wide_column_one_in = 0, bool range_del = false) {
|
2020-09-08 19:08:05 +00:00
|
|
|
Env* test_env = opts.env;
|
2021-01-29 06:08:46 +00:00
|
|
|
FileOptions file_options(opts);
|
2020-09-05 02:25:20 +00:00
|
|
|
ReadOptions read_options;
|
2021-05-05 20:59:21 +00:00
|
|
|
const ImmutableOptions imoptions(opts);
|
2020-09-05 02:25:20 +00:00
|
|
|
const MutableCFOptions moptions(opts);
|
|
|
|
ROCKSDB_NAMESPACE::InternalKeyComparator ikc(opts.comparator);
|
|
|
|
std::unique_ptr<TableBuilder> tb;
|
|
|
|
|
2024-02-02 22:14:43 +00:00
|
|
|
InternalTblPropCollFactories internal_tbl_prop_coll_factories;
|
2021-01-29 06:08:46 +00:00
|
|
|
std::unique_ptr<WritableFileWriter> file_writer;
|
|
|
|
ASSERT_OK(WritableFileWriter::Create(test_env->GetFileSystem(), file_name,
|
|
|
|
file_options, &file_writer, nullptr));
|
|
|
|
|
2020-09-05 02:25:20 +00:00
|
|
|
std::string column_family_name;
|
|
|
|
int unknown_level = -1;
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
const WriteOptions write_options;
|
2020-09-05 02:25:20 +00:00
|
|
|
tb.reset(opts.table_factory->NewTableBuilder(
|
|
|
|
TableBuilderOptions(
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
imoptions, moptions, read_options, write_options, ikc,
|
2024-02-02 22:14:43 +00:00
|
|
|
&internal_tbl_prop_coll_factories, CompressionType::kNoCompression,
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
CompressionOptions(),
|
2021-04-29 13:59:53 +00:00
|
|
|
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
|
|
|
|
column_family_name, unknown_level),
|
2020-09-05 02:25:20 +00:00
|
|
|
file_writer.get()));
|
|
|
|
|
|
|
|
// Populate slightly more than 1K keys
|
|
|
|
uint32_t num_keys = kNumKey;
|
2022-02-08 20:14:25 +00:00
|
|
|
const char* comparator_name = ikc.user_comparator()->Name();
|
|
|
|
if (strcmp(comparator_name, ReverseBytewiseComparator()->Name()) == 0) {
|
2024-02-01 22:35:03 +00:00
|
|
|
for (int32_t i = num_keys; i > 0; i--) {
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
if (wide_column_one_in == 0 || i % wide_column_one_in != 0) {
|
|
|
|
tb->Add(MakeKey(i), MakeValue(i));
|
|
|
|
} else {
|
|
|
|
tb->Add(MakeKey(i, ValueType::kTypeWideColumnEntity),
|
|
|
|
MakeWideColumn(i));
|
|
|
|
}
|
2022-02-08 20:14:25 +00:00
|
|
|
}
|
|
|
|
} else if (strcmp(comparator_name,
|
|
|
|
test::BytewiseComparatorWithU64TsWrapper()->Name()) ==
|
|
|
|
0) {
|
|
|
|
for (uint32_t i = 0; i < num_keys; i++) {
|
|
|
|
tb->Add(MakeKeyWithTimeStamp(i, 100 + i), MakeValue(i));
|
|
|
|
}
|
|
|
|
} else {
|
2024-02-01 22:35:03 +00:00
|
|
|
uint32_t i = 0;
|
|
|
|
if (range_del) {
|
|
|
|
tb->Add(MakeKey(i, kTypeRangeDeletion), MakeValue(i + 1));
|
|
|
|
i = 1;
|
|
|
|
}
|
|
|
|
for (; i < num_keys; i++) {
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
if (wide_column_one_in == 0 || i % wide_column_one_in != 0) {
|
|
|
|
tb->Add(MakeKey(i), MakeValue(i));
|
|
|
|
} else {
|
|
|
|
tb->Add(MakeKey(i, ValueType::kTypeWideColumnEntity),
|
|
|
|
MakeWideColumn(i));
|
|
|
|
}
|
2022-02-08 20:14:25 +00:00
|
|
|
}
|
2020-09-05 02:25:20 +00:00
|
|
|
}
|
|
|
|
ASSERT_OK(tb->Finish());
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
ASSERT_OK(file_writer->Close(IOOptions()));
|
2020-09-05 02:25:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
protected:
|
|
|
|
constexpr static int kNumKey = 1024;
|
2014-12-23 21:24:07 +00:00
|
|
|
};
|
|
|
|
|
2020-09-05 02:25:20 +00:00
|
|
|
constexpr int SSTDumpToolTest::kNumKey;
|
|
|
|
|
2020-06-09 17:01:12 +00:00
|
|
|
TEST_F(SSTDumpToolTest, HelpAndVersion) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
|
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
|
|
|
|
|
|
|
static const char* help[] = {"./sst_dump", "--help"};
|
|
|
|
ASSERT_TRUE(!tool.Run(2, help, opts));
|
|
|
|
static const char* version[] = {"./sst_dump", "--version"};
|
|
|
|
ASSERT_TRUE(!tool.Run(2, version, opts));
|
|
|
|
static const char* bad[] = {"./sst_dump", "--not_an_option"};
|
|
|
|
ASSERT_TRUE(tool.Run(2, bad, opts));
|
|
|
|
}
|
|
|
|
|
2015-03-17 21:08:00 +00:00
|
|
|
TEST_F(SSTDumpToolTest, EmptyFilter) {
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = env();
|
2018-08-09 21:21:35 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
createSST(opts, file_path, 10);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 21:21:35 +00:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 21:24:07 +00:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-02-08 20:14:25 +00:00
|
|
|
TEST_F(SSTDumpToolTest, SstDumpReverseBytewiseComparator) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
opts.comparator = ReverseBytewiseComparator();
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
|
|
|
std::string file_path =
|
|
|
|
MakeFilePath("rocksdb_sst_reverse_bytewise_comparator.sst");
|
|
|
|
createSST(opts, file_path);
|
|
|
|
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
|
|
|
|
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, SstDumpComparatorWithU64Ts) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
opts.comparator = test::BytewiseComparatorWithU64TsWrapper();
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
|
|
|
std::string file_path =
|
|
|
|
MakeFilePath("rocksdb_sst_comparator_with_u64_ts.sst");
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
createSST(opts, file_path, 10);
|
2022-02-08 20:14:25 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
|
|
|
|
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-17 21:08:00 +00:00
|
|
|
TEST_F(SSTDumpToolTest, FilterBlock) {
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = env();
|
2019-01-03 19:11:09 +00:00
|
|
|
BlockBasedTableOptions table_opts;
|
2020-02-20 20:07:53 +00:00
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, true));
|
2019-01-03 19:11:09 +00:00
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 21:21:35 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
createSST(opts, file_path, 10);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 21:21:35 +00:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 21:24:07 +00:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-17 21:08:00 +00:00
|
|
|
TEST_F(SSTDumpToolTest, FullFilterBlock) {
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = env();
|
2019-01-03 19:11:09 +00:00
|
|
|
BlockBasedTableOptions table_opts;
|
2020-02-20 20:07:53 +00:00
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
|
2019-01-03 19:11:09 +00:00
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 21:21:35 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 19:11:09 +00:00
|
|
|
createSST(opts, file_path);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 21:21:35 +00:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 21:24:07 +00:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2015-02-26 00:34:26 +00:00
|
|
|
|
2015-03-17 21:08:00 +00:00
|
|
|
TEST_F(SSTDumpToolTest, GetProperties) {
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = env();
|
2019-01-03 19:11:09 +00:00
|
|
|
BlockBasedTableOptions table_opts;
|
2020-02-20 20:07:53 +00:00
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
|
2019-01-03 19:11:09 +00:00
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 21:21:35 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 19:11:09 +00:00
|
|
|
createSST(opts, file_path);
|
2015-02-26 00:34:26 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 21:21:35 +00:00
|
|
|
PopulateCommandArgs(file_path, "--show_properties", usage);
|
2015-02-26 00:34:26 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2015-02-26 00:34:26 +00:00
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
cleanup(opts, file_path);
|
2015-02-26 00:34:26 +00:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2015-07-24 00:05:33 +00:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, CompressedSizes) {
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = env();
|
2019-01-03 19:11:09 +00:00
|
|
|
BlockBasedTableOptions table_opts;
|
2020-02-20 20:07:53 +00:00
|
|
|
table_opts.filter_policy.reset(
|
|
|
|
ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
|
2019-01-03 19:11:09 +00:00
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 21:21:35 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
createSST(opts, file_path, 10);
|
2015-07-24 00:05:33 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 21:21:35 +00:00
|
|
|
PopulateCommandArgs(file_path, "--command=recompress", usage);
|
2015-07-24 00:05:33 +00:00
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2015-07-24 00:05:33 +00:00
|
|
|
|
2019-01-03 19:11:09 +00:00
|
|
|
cleanup(opts, file_path);
|
2015-07-24 00:05:33 +00:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2019-01-03 19:11:09 +00:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, MemEnv) {
|
2019-10-09 02:17:39 +00:00
|
|
|
std::unique_ptr<Env> mem_env(NewMemEnv(env()));
|
2019-01-03 19:11:09 +00:00
|
|
|
Options opts;
|
2019-10-09 02:17:39 +00:00
|
|
|
opts.env = mem_env.get();
|
2019-01-03 19:11:09 +00:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
createSST(opts, file_path);
|
|
|
|
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "--command=verify_checksum", usage);
|
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
2019-01-03 19:11:09 +00:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-05-13 01:21:32 +00:00
|
|
|
TEST_F(SSTDumpToolTest, ReadaheadSize) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
createSST(opts, file_path);
|
|
|
|
|
|
|
|
char* usage[4];
|
|
|
|
PopulateCommandArgs(file_path, "--command=verify", usage);
|
|
|
|
snprintf(usage[3], kOptLength, "--readahead_size=4000000");
|
|
|
|
|
|
|
|
int num_reads = 0;
|
|
|
|
SyncPoint::GetInstance()->SetCallBack("RandomAccessFileReader::Read",
|
|
|
|
[&](void*) { num_reads++; });
|
|
|
|
SyncPoint::GetInstance()->EnableProcessing();
|
|
|
|
|
|
|
|
SSTDumpTool tool;
|
|
|
|
ASSERT_TRUE(!tool.Run(4, usage, opts));
|
|
|
|
|
|
|
|
// The file is approximately 10MB. Readahead is 4MB.
|
|
|
|
// We usually need 3 reads + one metadata read.
|
|
|
|
// One extra read is needed before opening the file for metadata.
|
|
|
|
ASSERT_EQ(5, num_reads);
|
|
|
|
|
|
|
|
SyncPoint::GetInstance()->ClearAllCallBacks();
|
|
|
|
SyncPoint::GetInstance()->DisableProcessing();
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 4; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-06-04 18:38:34 +00:00
|
|
|
TEST_F(SSTDumpToolTest, NoSstFile) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
std::string file_path = MakeFilePath("no_such_file.sst");
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "", usage);
|
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
|
|
|
for (const auto& command :
|
|
|
|
{"--command=check", "--command=dump", "--command=raw",
|
|
|
|
"--command=verify", "--command=recompress", "--command=verify_checksum",
|
|
|
|
"--show_properties"}) {
|
|
|
|
snprintf(usage[1], kOptLength, "%s", command);
|
2020-06-08 20:56:22 +00:00
|
|
|
ASSERT_TRUE(tool.Run(3, usage, opts));
|
2020-06-04 18:38:34 +00:00
|
|
|
}
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-06-08 20:56:22 +00:00
|
|
|
TEST_F(SSTDumpToolTest, ValidSSTPath) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs("", "", usage);
|
|
|
|
SSTDumpTool tool;
|
|
|
|
std::string file_not_exists = MakeFilePath("file_not_exists.sst");
|
|
|
|
std::string sst_file = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
createSST(opts, sst_file);
|
|
|
|
std::string text_file = MakeFilePath("text_file");
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
ASSERT_OK(WriteStringToFile(opts.env, "Hello World!", text_file, false));
|
2020-06-08 20:56:22 +00:00
|
|
|
std::string fake_sst = MakeFilePath("fake_sst.sst");
|
Group SST write in flush, compaction and db open with new stats (#11910)
Summary:
## Context/Summary
Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity.
For that, this PR does the following:
- Tag different write IOs by passing down and converting WriteOptions to IOOptions
- Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS
Some related code refactory to make implementation cleaner:
- Blob stats
- Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info.
- Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write.
- Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority
- Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification
- Build table
- TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables
- Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder.
This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more
- Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority
## Test
### db bench
Flush
```
./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100
rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377
rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
```
compaction, db oopen
```
Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279
rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0
rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213
rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66
```
blob stats - just to make sure they aren't broken by this PR
```
Integrated Blob DB
Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600
rocksdb.blobdb.blob.file.synced COUNT : 1
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same)
```
```
Stacked Blob DB
Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench
pre-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876
rocksdb.blobdb.blob.file.synced COUNT : 8
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445
post-PR:
rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924
- COUNT is higher and values are smaller as it includes header and footer write
- COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164
rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same)
rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same)
```
### Rehearsal CI stress test
Trigger 3 full runs of all our CI stress tests
### Performance
Flush
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark; enable_statistics = true
Pre-pr: avg 507515519.3 ns
497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908,
Post-pr: avg 511971266.5 ns, regressed 0.88%
502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408,
```
Compaction
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 495346098.30 ns
492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846
Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97%
502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007
```
Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats)
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000
-- default: 1 thread is used to run benchmark
Pre-pr: avg 3848.10 ns
3814,3838,3839,3848,3854,3854,3854,3860,3860,3860
Post-pr: avg 3874.20 ns, regressed 0.68%
3863,3867,3871,3874,3875,3877,3877,3877,3880,3881
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910
Reviewed By: ajkr
Differential Revision: D49788060
Pulled By: hx235
fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
|
|
|
ASSERT_OK(WriteStringToFile(opts.env, "Not an SST file!", fake_sst, false));
|
2020-06-08 20:56:22 +00:00
|
|
|
|
|
|
|
for (const auto& command_arg : {"--command=verify", "--command=identify"}) {
|
|
|
|
snprintf(usage[1], kOptLength, "%s", command_arg);
|
|
|
|
|
|
|
|
snprintf(usage[2], kOptLength, "--file=%s", file_not_exists.c_str());
|
|
|
|
ASSERT_TRUE(tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
snprintf(usage[2], kOptLength, "--file=%s", sst_file.c_str());
|
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
snprintf(usage[2], kOptLength, "--file=%s", text_file.c_str());
|
|
|
|
ASSERT_TRUE(tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
snprintf(usage[2], kOptLength, "--file=%s", fake_sst.c_str());
|
|
|
|
ASSERT_TRUE(tool.Run(3, usage, opts));
|
|
|
|
}
|
|
|
|
ASSERT_OK(opts.env->DeleteFile(sst_file));
|
|
|
|
ASSERT_OK(opts.env->DeleteFile(text_file));
|
|
|
|
ASSERT_OK(opts.env->DeleteFile(fake_sst));
|
|
|
|
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2020-09-05 02:25:20 +00:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, RawOutput) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
Wide Column support in ldb (#11754)
Summary:
wide_columns can now be pretty-printed in the following commands
- `./ldb dump_wal`
- `./ldb dump`
- `./ldb idump`
- `./ldb dump_live_files`
- `./ldb scan`
- `./sst_dump --command=scan`
There are opportunities to refactor to reduce some nearly identical code. This PR is initial change to add wide column support in `ldb` and `sst_dump` tool. More PRs to come for the refactor.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11754
Test Plan:
**New Tests added**
- `WideColumnsHelperTest::DumpWideColumns`
- `WideColumnsHelperTest::DumpSliceAsWideColumns`
**Changes added to existing tests**
- `ExternalSSTFileTest::BasicMixed` added to cover mixed case (This test should have been added in https://github.com/facebook/rocksdb/issues/11688). This test does not verify the ldb or sst_dump output. This test was used to create test SST files having some rows with wide columns and some without and the generated SST files were used to manually test sst_dump_tool.
- `createSST()` in `sst_dump_test` now takes `wide_column_one_in` to add wide column value in SST
**dump_wal**
```
./ldb dump_wal --walfile=/tmp/rocksdbtest-226125/db_wide_basic_test_2675429_2308393776696827948/000004.log --print_value --header
```
```
Sequence,Count,ByteSize,Physical Offset,Key(s) : value
1,1,59,0,PUT_ENTITY(0) : 0x:0x68656C6C6F 0x617474725F6E616D6531:0x666F6F 0x617474725F6E616D6532:0x626172
2,1,34,42,PUT_ENTITY(0) : 0x617474725F6F6E65:0x74776F 0x617474725F7468726565:0x666F7572
3,1,17,7d,PUT(0) : 0x7468697264 : 0x62617A
```
**idump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ idump
```
```
'first' seq:1, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:2, type:22 => attr_one:two attr_three:four
'third' seq:3, type:1 => baz
Internal keys in range: 3
```
**SST Dump from dump_live_files**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ compact
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump_live_files
```
```
...
==============================
SST Files
==============================
/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst level:1
------------------------------
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
...
```
**dump**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ dump
```
```
first ==> :hello attr_name1:foo attr_name2:bar
second ==> attr_one:two attr_three:four
third ==> baz
Keys in range: 3
```
**scan**
```
./ldb --db=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/ scan
```
```
first : :hello attr_name1:foo attr_name2:bar
second : attr_one:two attr_three:four
third : baz
```
**sst_dump**
```
./sst_dump --file=/tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst --command=scan
```
```
options.env is 0x7ff54b296000
Process /tmp/rocksdbtest-226125/db_wide_basic_test_3481961_2308393776696827948/000013.sst
Sst file format: block-based
from [] to []
'first' seq:0, type:22 => :hello attr_name1:foo attr_name2:bar
'second' seq:0, type:22 => attr_one:two attr_three:four
'third' seq:0, type:1 => baz
```
Reviewed By: ltamasi
Differential Revision: D48837999
Pulled By: jaykorean
fbshipit-source-id: b0280f0589d2b9716bb9b50530ffcabb397d140f
2023-08-30 19:45:52 +00:00
|
|
|
createSST(opts, file_path, 10);
|
2020-09-05 02:25:20 +00:00
|
|
|
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
|
|
|
|
|
|
|
ROCKSDB_NAMESPACE::SSTDumpTool tool;
|
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
const std::string raw_path = MakeFilePath("rocksdb_sst_test_dump.txt");
|
|
|
|
std::ifstream raw_file(raw_path);
|
|
|
|
|
|
|
|
std::string tp;
|
|
|
|
bool is_data_block = false;
|
|
|
|
int key_count = 0;
|
|
|
|
while (getline(raw_file, tp)) {
|
|
|
|
if (tp.find("Data Block #") != std::string::npos) {
|
|
|
|
is_data_block = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (is_data_block && tp.find("HEX") != std::string::npos) {
|
|
|
|
key_count++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
ASSERT_EQ(kNumKey, key_count);
|
|
|
|
|
Fix testcase failures on windows (#7992)
Summary:
Fixed 5 test case failures found on Windows 10/Windows Server 2016
1. In `flush_job_test`, the DestroyDir function fails in deconstructor because some file handles are still being held by VersionSet. This happens on Windows Server 2016, so need to manually reset versions_ pointer to release all file handles.
2. In `StatsHistoryTest.InMemoryStatsHistoryPurging` test, the capping memory cost of stats_history_size on Windows becomes 14000 bytes with latest changes, not just 13000 bytes.
3. In `SSTDumpToolTest.RawOutput` test, the output file handle is not closed at the end.
4. In `FullBloomTest.OptimizeForMemory` test, ROCKSDB_MALLOC_USABLE_SIZE is undefined on windows so `total_mem` is always equal to `total_size`. The internal memory fragmentation assertion does not apply in this case.
5. In `BlockFetcherTest.FetchAndUncompressCompressedDataBlock` test, XPRESS cannot reach 87.5% compression ratio with original CreateTable method, so I append extra zeros to the string value to enhance compression ratio. Beside, since XPRESS allocates memory internally, thus does not support for custom allocator verification, we will skip the allocator verification for XPRESS
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7992
Reviewed By: jay-zhuang
Differential Revision: D26615283
Pulled By: ajkr
fbshipit-source-id: 3632612f84b99e2b9c77c403b112b6bedf3b125d
2021-02-23 22:31:50 +00:00
|
|
|
raw_file.close();
|
|
|
|
|
2020-09-05 02:25:20 +00:00
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
Fix and defend against FilePrefetchBuffer combined with mmap reads (#12206)
Summary:
FilePrefetchBuffer makes an unchecked assumption about the behavior of RandomAccessFileReader::Read: that it will write to the provided buffer rather than returning the data in an alternate buffer. FilePrefetchBuffer has been quietly incompatible with mmap reads (e.g. allow_mmap_reads / use_mmap_reads) because in that case an alternate buffer is returned (mmapped memory). This incompatibility currently leads to quiet data corruption, as seen in amplified crash test failure in https://github.com/facebook/rocksdb/issues/12200.
In this change,
* Check whether RandomAccessFileReader::Read has the expected behavior, and fail if not. (Assertion failure in debug build, return Corruption in release build.) This will detect future regressions synchronously and precisely, rather than relying on debugging downstream data corruption.
* Why not recover? My understanding is that FilePrefetchBuffer is not intended for use when RandomAccessFileReader::Read uses an alternate buffer, so quietly recovering could lead to undesirable (inefficient) behavior.
* Mention incompatibility with mmap-based readers in the internal API comments for FilePrefetchBuffer
* Fix two cases where FilePrefetchBuffer could be used with mmap, both stemming from SstFileDumper, though one fix is in BlockBasedTableReader. There is currently no way to ask a RandomAccessFileReader whether it's using mmap, so we currently have to rely on other options as clues.
Keeping separate from https://github.com/facebook/rocksdb/issues/12200 in part because this change is more appropriate for backport than that one.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/12206
Test Plan:
* Manually verified that the new check aids in debugging.
* Unit test added, that fails if either fix is missed.
* Ran blackbox_crash_test for hours, with and without https://github.com/facebook/rocksdb/issues/12200
Reviewed By: akankshamahajan15
Differential Revision: D52551701
Pulled By: pdillinger
fbshipit-source-id: dea87c5782b7c484a6c6e424585c8832dfc580dc
2024-01-05 02:39:05 +00:00
|
|
|
TEST_F(SSTDumpToolTest, SstFileDumperMmapReads) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
createSST(opts, file_path, 10);
|
|
|
|
|
|
|
|
EnvOptions env_opts;
|
|
|
|
uint64_t data_size = 0;
|
|
|
|
|
|
|
|
// Test all combinations of mmap read options
|
|
|
|
for (int i = 0; i < 4; ++i) {
|
|
|
|
SaveAndRestore<bool> sar_opts(&opts.allow_mmap_reads, (i & 1) != 0);
|
|
|
|
SaveAndRestore<bool> sar_env_opts(&env_opts.use_mmap_reads, (i & 2) != 0);
|
|
|
|
|
|
|
|
SstFileDumper dumper(opts, file_path, Temperature::kUnknown,
|
|
|
|
1024 /*readahead_size*/, true /*verify_checksum*/,
|
|
|
|
false /*output_hex*/, false /*decode_blob_index*/,
|
|
|
|
env_opts);
|
|
|
|
ASSERT_OK(dumper.getStatus());
|
|
|
|
std::shared_ptr<const TableProperties> tp;
|
|
|
|
ASSERT_OK(dumper.ReadTableProperties(&tp));
|
|
|
|
ASSERT_NE(tp.get(), nullptr);
|
|
|
|
if (i == 0) {
|
|
|
|
// Verify consistency of a populated field with some entropy
|
|
|
|
data_size = tp->data_size;
|
|
|
|
ASSERT_GT(data_size, 0);
|
|
|
|
} else {
|
|
|
|
ASSERT_EQ(data_size, tp->data_size);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
}
|
2024-02-01 22:35:03 +00:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, SstFileDumperVerifyNumRecords) {
|
|
|
|
Options opts;
|
|
|
|
opts.env = env();
|
|
|
|
|
|
|
|
EnvOptions env_opts;
|
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
{
|
|
|
|
createSST(opts, file_path, 10);
|
|
|
|
SstFileDumper dumper(opts, file_path, Temperature::kUnknown,
|
|
|
|
1024 /*readahead_size*/, true /*verify_checksum*/,
|
|
|
|
false /*output_hex*/, false /*decode_blob_index*/,
|
|
|
|
env_opts, /*silent=*/true);
|
|
|
|
ASSERT_OK(dumper.getStatus());
|
|
|
|
ASSERT_OK(dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false,
|
|
|
|
/*read_num_limit=*/std::numeric_limits<uint64_t>::max(),
|
|
|
|
/*has_from=*/false, /*from_key=*/"",
|
|
|
|
/*has_to=*/false, /*to_key=*/""));
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
}
|
|
|
|
|
|
|
|
{
|
|
|
|
// Test with range del
|
|
|
|
createSST(opts, file_path, 10, /*range_del=*/true);
|
|
|
|
SstFileDumper dumper(opts, file_path, Temperature::kUnknown,
|
|
|
|
1024 /*readahead_size*/, true /*verify_checksum*/,
|
|
|
|
false /*output_hex*/, false /*decode_blob_index*/,
|
|
|
|
env_opts, /*silent=*/true);
|
|
|
|
ASSERT_OK(dumper.getStatus());
|
|
|
|
ASSERT_OK(dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false,
|
|
|
|
/*read_num_limit=*/std::numeric_limits<uint64_t>::max(),
|
|
|
|
/*has_from=*/false, /*from_key=*/"",
|
|
|
|
/*has_to=*/false, /*to_key=*/""));
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
}
|
|
|
|
|
|
|
|
{
|
|
|
|
SyncPoint::GetInstance()->SetCallBack(
|
|
|
|
"PropertyBlockBuilder::AddTableProperty:Start", [&](void* arg) {
|
|
|
|
TableProperties* props = reinterpret_cast<TableProperties*>(arg);
|
|
|
|
props->num_entries = kNumKey + 2;
|
|
|
|
});
|
|
|
|
SyncPoint::GetInstance()->EnableProcessing();
|
|
|
|
createSST(opts, file_path, 10);
|
|
|
|
SstFileDumper dumper(opts, file_path, Temperature::kUnknown,
|
|
|
|
1024 /*readahead_size*/, true /*verify_checksum*/,
|
|
|
|
false /*output_hex*/, false /*decode_blob_index*/,
|
|
|
|
env_opts, /*silent=*/true);
|
|
|
|
ASSERT_OK(dumper.getStatus());
|
|
|
|
Status s = dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false,
|
|
|
|
/*read_num_limit==*/std::numeric_limits<uint64_t>::max(),
|
|
|
|
/*has_from=*/false, /*from_key=*/"",
|
|
|
|
/*has_to=*/false, /*to_key=*/"");
|
|
|
|
ASSERT_TRUE(s.IsCorruption());
|
|
|
|
ASSERT_TRUE(
|
2024-03-12 18:05:20 +00:00
|
|
|
std::strstr("Table property expects 1026 entries when excluding range "
|
|
|
|
"deletions, but scanning the table returned 1024 entries",
|
2024-02-01 22:35:03 +00:00
|
|
|
s.getState()));
|
|
|
|
|
|
|
|
// Validation is not performed when read_num, has_from, has_to are set
|
|
|
|
ASSERT_OK(dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false, /*read_num_limit=*/10,
|
|
|
|
/*has_from=*/false, /*from_key=*/"",
|
|
|
|
/*has_to=*/false, /*to_key=*/""));
|
|
|
|
|
|
|
|
ASSERT_OK(dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false,
|
|
|
|
/*read_num_limit=*/std::numeric_limits<uint64_t>::max(),
|
|
|
|
/*has_from=*/true, /*from_key=*/MakeKey(100),
|
|
|
|
/*has_to=*/false, /*to_key=*/""));
|
|
|
|
|
|
|
|
ASSERT_OK(dumper.ReadSequential(
|
|
|
|
/*print_kv=*/false,
|
|
|
|
/*read_num_limit=*/std::numeric_limits<uint64_t>::max(),
|
|
|
|
/*has_from=*/false, /*from_key=*/"",
|
|
|
|
/*has_to=*/true, /*to_key=*/MakeKey(100)));
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-02-20 20:07:53 +00:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
2014-12-23 21:24:07 +00:00
|
|
|
|
2015-03-17 21:08:00 +00:00
|
|
|
int main(int argc, char** argv) {
|
2020-02-20 20:07:53 +00:00
|
|
|
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
|
2015-03-17 21:08:00 +00:00
|
|
|
::testing::InitGoogleTest(&argc, argv);
|
2019-10-09 02:17:39 +00:00
|
|
|
RegisterCustomObjects(argc, argv);
|
2015-03-17 21:08:00 +00:00
|
|
|
return RUN_ALL_TESTS();
|
|
|
|
}
|