Commit Graph

957 Commits

Author SHA1 Message Date
Igor Canadi
f4574449e9 Clean up compaction logging
Summary: Cleaned up compaction logging a little bit. Now file sizes are easier to read. Also, removed the trailing space.

Test Plan:
verified that i'm happy with logging output:

        files_size[#33(seq=101,sz=98KB,0) #31(seq=81,sz=159KB,0) #26(seq=0,sz=637KB,0)]

Reviewers: sdong, haobo, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18549
2014-05-14 12:13:50 -07:00
sdong
3e4a9ec241 Arena to inline 2KB of data in it.
Summary:
In order to use arena to a use case that the total allocation size might be small (LogBuffer is already such a case), inline 1KB of data in it, so that it can be mostly in stack or inline in another class.

If always inlining 2KB is a concern, I could make it a template to determine what to inline. However, dependents need to changes. Doesn't go with it for now

Test Plan: make all check.

Reviewers: haobo, igor, yhchiang, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18609
2014-05-14 11:49:01 -07:00
Igor Canadi
26f5dd9a5a TablePropertiesCollectorFactory
Summary:
This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options.

Here's description of task #4296714:
       I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB.

       For example, this table has 3155 entries and 1391828 deleted keys.

The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for.

Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API.

In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe.

Test Plan:
Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one).
Also, all other tests

Reviewers: sdong, dhruba, haobo, kailiu

Reviewed By: kailiu

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18579
2014-05-13 12:30:55 -07:00
Yueh-Hsuan Chiang
1c7799d8aa Fixed a file-not-found issue when a log file is moved to archive.
Summary:
Fixed a file-not-found issue when a log file is moved to archive
by doing a missing retry.

Test Plan:
make db_test
export ROCKSDB_TEST=TransactionLogIteratorRace
./db_test

Reviewers: sdong, haobo

Reviewed By: sdong

CC: igor, leveldb

Differential Revision: https://reviews.facebook.net/D18669
2014-05-12 17:50:21 -07:00
sdong
acd17fd002 Remove unused variable in DBIter
Summary: as title

Test Plan: Still compile

Reviewers: haobo, igor, yhchiang

Reviewed By: igor

CC: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D18603
2014-05-09 13:20:35 -07:00
Igor Canadi
a1068c91a1 Make RocksDB work with newer gflags
Summary:
Newer gflags switched from `google` namespace to `gflags` namespace. See: https://github.com/facebook/rocksdb/issues/139 and https://github.com/facebook/rocksdb/issues/102

Unfortunately, they don't define any macro with their namespace, so we need to actually try to compile gflags with two different namespace to figure out which one is the correct one.

Test Plan: works in fbcode environemnt. I'll also try in ubutnu with newer gflags

Reviewers: dhruba

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18537
2014-05-08 17:25:13 -07:00
Igor Canadi
8e37a29bfb Compaction with zero outputs
Summary: We had a hypothesis in https://reviews.facebook.net/D18507 that empty-string internal keys might have been caused by compaction filter deleting all the entries. I added a unit test for that case. Unforutnately, everything works as expected.

Test Plan: this is a test

Reviewers: dhruba, haobo, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18519
2014-05-08 13:48:39 -07:00
Igor Canadi
768d424dd9 [fix] SIGSEGV when VersionEdit in MANIFEST is corrupted
Summary:
This was reported by our customers in task #4295529.

Cause:
* MANIFEST file contains a VersionEdit, which contains file entries whose 'smallest' and 'largest' internal keys are empty. String with zero characters. Root cause of corruption was not investigated. We should report corruption when this happens. However, we currently SIGSEGV.

Here's what happens:
* VersionEdit encodes zero-strings happily and stores them in smallest and largest InternalKeys. InternalKey::Encode() does assert when `rep_.empty()`, but we don't assert in production environemnts. Also, we should never assert as a result of DB corruption.
* As part of our ConsistencyCheck, we call GetLiveFilesMetaData()
* GetLiveFilesMetadata() calls `file->largest.user_key().ToString()`
* user_key() function does: 1. assert(size > 8) (ooops, no assert), 2. returns `Slice(internal_key.data(), internal_key.size() - 8)`
* since `internal_key.size()` is unsigned int, this call translates to `Slice(whatever, 1298471928561892576182756)`. Bazinga.

Fix:
* VersionEdit checks if InternalKey is valid in `VersionEdit::GetInternalKey()`. If it's invalid, returns corruption.

Lessons learned:
* Always keep in mind that even if you `assert()`, production code will continue execution even if assert fails.
* Never `assert` based on DB corruption. Assert only if the code should guarantee that assert can't fail.

Test Plan: dumped offending manifest. Before: assert. Now: corruption

Reviewers: dhruba, haobo, sdong

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18507
2014-05-07 16:52:12 -07:00
sdong
9efbd85ac9 fsync directory after creating current file in NewDB()
Summary: One of our users reported current file corruption. The machine was rebooted during the time. This is the only think I can think of which could cause current file corruption. Just add this paranoid check.

Test Plan: make all check

Reviewers: haobo, igor

Reviewed By: haobo

CC: yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D18495
2014-05-06 17:51:33 -07:00
sdong
3a171dcb51 Pass logger to memtable rep and TLB page allocation error logged to info logs
Summary:
TLB page allocation errors are now logged to info logs, instead of stderr.
In order to do that, mem table rep's factory functions take a info logger now.

Test Plan: make all check

Reviewers: haobo, igor, yhchiang

Reviewed By: yhchiang

CC: leveldb, yhchiang, dhruba

Differential Revision: https://reviews.facebook.net/D18471
2014-05-05 16:43:37 -07:00
Igor Canadi
15c3991933 Add comment about ValueType 2014-05-05 12:57:47 -07:00
Igor Canadi
d2569fea47 log_and_apply_bench on a new benchmark framework
Summary:
db_test includes Benchmark for LogAndApply. This diff removes it from db_test and puts it into a separate log_and_apply bench. I just wanted to play around with our new benchmark framework and figure out how it works.

I would also like to show you how great it is! I believe right set of microbenchmarks can speed up our productivity a lot and help catch early regressions.

Test Plan: no

Reviewers: dhruba, haobo, sdong, ljin, yhchiang

Reviewed By: yhchiang

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18261
2014-05-05 11:11:48 -07:00
sdong
4a7c747064 Revert "Revert "Allow allocating dynamic bloom, plain table indexes and hash linked list from huge page TLB""
And make the default 0 for hash linked list memtable

This reverts commit d69dc64be7.
2014-05-04 13:56:29 -07:00
Igor Canadi
d69dc64be7 Revert "Allow allocating dynamic bloom, plain table indexes and hash linked list from huge page TLB"
This reverts commit 7dafa3a1d7.
2014-05-04 08:37:09 -07:00
Igor Canadi
0afc8bc29a xxHash
Summary:
Originally: https://github.com/facebook/rocksdb/pull/87/files

I'm taking over to apply some finishing touches

Test Plan: will add tests

Reviewers: dhruba, haobo, sdong, yhchiang, ljin

Reviewed By: yhchiang

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18315
2014-05-01 14:09:32 -04:00
Igor Canadi
096f5be0ed Put column family information in LiveFileMetaData
Summary: As summary

Test Plan: compiles :)

Reviewers: dhruba, haobo, sdong, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18405
2014-04-30 16:24:52 -04:00
Igor Canadi
16f1aa7b2d Fix signed/unsigned compare 2014-04-30 14:38:01 -04:00
Igor Canadi
df70047669 Flush stale column families
Summary:
Added a new option `max_total_wal_size`. Once the total WAL size goes over that, we make an attempt to flush all column families that still have data in the earliest WAL file.

By default, I calculate `max_total_wal_size` dynamically, that should be good-enough for non-advanced customers.

Test Plan: Added a test

Reviewers: dhruba, haobo, sdong, ljin, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18345
2014-04-30 14:33:40 -04:00
sdong
7dafa3a1d7 Allow allocating dynamic bloom, plain table indexes and hash linked list from huge page TLB
Summary: Add an option to allocate a piece of memory from huge page TLB. Add options to trigger it in dynamic bloom, plain table indexes andhash linked list hash table.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: nkg-, dhruba, leveldb, igor, yhchiang

Differential Revision: https://reviews.facebook.net/D18357
2014-04-30 11:02:26 -07:00
Igor Canadi
66f88c43a5 Some fixes as preparation for release 2014-04-30 09:03:24 -07:00
Igor Canadi
d6d67c0efe More s/us fixes 2014-04-30 07:04:36 -07:00
Yueh-Hsuan Chiang
9d9d2965cb Add a new mem-table representation based on cuckoo hash.
Summary:
= Major Changes =
* Add a new mem-table representation, HashCuckooRep, which is based cuckoo hash.
  Cuckoo hash uses multiple hash functions.  This allows each key to have multiple
  possible locations in the mem-table.

  - Put: When insert a key, it will try to find whether one of its possible
    locations is vacant and store the key.  If none of its possible
    locations are available, then it will kick out a victim key and
    store at that location.  The kicked-out victim key will then be
    stored at a vacant space of its possible locations or kick-out
    another victim.  In this diff, the kick-out path (known as
    cuckoo-path) is found using BFS, which guarantees to be the shortest.

 - Get: Simply tries all possible locations of a key --- this guarantees
   worst-case constant time complexity.

 - Time complexity: O(1) for Get, and average O(1) for Put if the
   fullness of the mem-table is below 80%.

 - Default using two hash functions, the number of hash functions used
   by the cuckoo-hash may dynamically increase if it fails to find a
   short-enough kick-out path.

 - Currently, HashCuckooRep does not support iteration and snapshots,
   as our current main purpose of this is to optimize point access.

= Minor Changes =
* Add IsSnapshotSupported() to DB to indicate whether the current DB
  supports snapshots.  If it returns false, then DB::GetSnapshot() will
  always return nullptr.

Test Plan:
Run existing tests.  Will develop a test specifically for cuckoo hash in
the next diff.

Reviewers: sdong, haobo

Reviewed By: sdong

CC: leveldb, dhruba, igor

Differential Revision: https://reviews.facebook.net/D16155
2014-04-29 17:13:46 -07:00
Igor Canadi
f1c9aa6ebe More unsigned/signed compare fixes 2014-04-29 13:01:06 -07:00
Igor Canadi
38693d99c4 Fix more signed/unsigned comparsions 2014-04-29 12:40:18 -07:00
Igor Canadi
dd9eb7a7d5 Cache result of ReadFirstRecord()
Summary:
ReadFirstRecord() reads the actual log file from disk on every call. This diff introduces a cache layer on top of ReadFirstRecord(), which should significantly speed up repeated calls to GetUpdatesSince().

I also cleaned up some stuff, but the whole TransactionLogIterator could use some refactoring, especially if we see increased usage.

Test Plan: make check

Reviewers: haobo, sdong, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18387
2014-04-29 13:27:58 -04:00
Igor Canadi
91ef2eae23 Use new DBWithTTL API in tests 2014-04-28 23:46:24 -04:00
Igor Canadi
72ff275e3c Fix TransactionLogIterator EOF caching
Summary:
When TransactionLogIterator comes to EOF, it calls UnmarkEOF and continues reading. However, if glibc cached the EOF status of the file, it will get EOF again, even though the new data might have been written to it.

This has been causing errors in Mac OS.

Test Plan: test passes, was failing before

Reviewers: dhruba, haobo, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18381
2014-04-28 23:30:27 -04:00
Donovan Hide
4f9fae9bb7 Add rocksdb_open_for_read_only to C API 2014-04-27 20:57:10 +01:00
Igor Canadi
c489499a2b Fix OSX compile 2014-04-26 17:15:43 -04:00
Lei Jin
ccaca59bee avoid calling FindFile twice in TwoLevelIterator for PlainTable
Summary:
this is to reclaim the regression introduced in
https://reviews.facebook.net/D17853

Test Plan: make all check

Reviewers: igor, haobo, sdong, dhruba, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17985
2014-04-25 12:23:07 -07:00
Lei Jin
d642c60bdc Check PrefixMayMatch on Seek()
Summary:
As a follow-up diff for https://reviews.facebook.net/D17805, add
optimization to check PrefixMayMatch on Seek()

Test Plan: make all check

Reviewers: igor, haobo, sdong, yhchiang, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17853
2014-04-25 12:22:23 -07:00
Lei Jin
3995e801ab kill ReadOptions.prefix and .prefix_seek
Summary:
also add an override option total_order_iteration if you want to use full
iterator with prefix_extractor

Test Plan: make all check

Reviewers: igor, haobo, sdong, yhchiang

Reviewed By: haobo

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D17805
2014-04-25 12:21:34 -07:00
Igor Canadi
8ce5492623 Delete superversion and log outside of mutex
Summary: As summary. Add two autovectors that get filled up in MakeRoomForWrite and they get deleted outside of mutex

Test Plan: make check

Reviewers: dhruba, haobo, ljin, sdong

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18249
2014-04-25 14:58:02 -04:00
Igor Canadi
ad3cd39ccd Column family logging
Summary:
Now that we have column families involved, we need to add extra context to every log message. They now start with "[column family name] log message"

Also added some logging that I think would be useful, like level summary after every flush (I often needed that when going through the logs).

Test Plan: make check + ran db_bench to confirm I'm happy with log output

Reviewers: dhruba, haobo, ljin, yhchiang, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18303
2014-04-25 09:51:16 -04:00
Igor Canadi
4cd9f58c04 Fix corruption test 2014-04-24 14:56:41 -04:00
Igor Canadi
478990c81b Make CompactionInputErrorParanoid less flakey
Summary:
I'm getting lots of e-mails with CompactionInputErrorParanoid failing. Most recent example early morning today was: http://ci-builds.fb.com/job/rocksdb_valgrind/562/consoleFull

I'm putting a stop to these e-mails. I investigated why the test is flakey and it turns out it's because of non-determinsim of compaction scheduling. If there is a compaction after the last flush, CorruptFile will corrupt the compacted file instead of file at level 0 (as it assumes). That makes `Check(9, 9)` fail big time.

I also saw some errors with table file getting outputed to >= 1 levels instead of 0. Also fixed that.

Test Plan: Ran corruption_test 100 times without a failure. Previously it usually failed at 10th occurrence.

Reviewers: dhruba, haobo, ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18285
2014-04-24 11:13:28 -07:00
sdong
4de5b84ee0 Fix a bug in IterKey
Summary: IterKey set buffer_size_ to a wrong initial value, causing it to always allocate values from heap instead of stack if the key size is smaller. Fix it.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: igor, dhruba, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D18279
2014-04-23 19:45:22 -07:00
Igor Canadi
f9f8965e96 Print out stack trace in mac, too
Summary: While debugging Mac-only issue with ThreadLocalPtr, this was very useful. Let's print out stack trace in MAC OS, too.

Test Plan: Verified that somewhat useful stack trace was generated on mac. Will run PrintStack() on linux, too.

Reviewers: ljin, haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18189
2014-04-23 09:11:35 -04:00
sdong
a570740727 Expose number of entries in mem tables to users
Summary: In this patch, two new DB properties are defined: rocksdb.num-immutable-mem-table and rocksdb.num-entries-imm-mem-tables, from where number of entries in mem tables can be exposed to users

Test Plan:
Cover the codes in db_test
make all check

Reviewers: haobo, ljin, igor

Reviewed By: igor

CC: nkg-, igor, yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D18207
2014-04-22 22:13:21 -07:00
Lei Jin
5f1daf7ae3 get rid of shared_ptr in memtable.cc
Summary: Get rid of the devil. Probably won't impact anything on the perf side.

Test Plan: make all check

Reviewers: igor, haobo, sdong, yhchiang

Reviewed By: haobo

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D18153
2014-04-22 21:14:25 -07:00
sdong
86a0133d05 PlainTableReader to expose index size to users
Summary:
This is a temp solution to expose index sizes to users from PlainTableReader before we persistent them to files.
In this patch, the memory consumption of indexes used by PlainTableReader will be reported as two user defined properties, so that users can monitor them.

Test Plan:
Add a unit test.
make all check`

Reviewers: haobo, ljin

Reviewed By: haobo

CC: nkg-, yhchiang, igor, ljin, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D18195
2014-04-22 19:29:05 -07:00
Igor Canadi
1068d2fa60 Revert "Better port::Mutex::AssertHeld() and AssertNotHeld()"
This reverts commit ddafceb6c2.
2014-04-22 18:38:10 -07:00
Igor Canadi
ddafceb6c2 Better port::Mutex::AssertHeld() and AssertNotHeld()
Summary:
Using ThreadLocalPtr as a flag to determine if a mutex is locked or not enables us to implement AssertNotHeld(). It also makes AssertHeld() actually correct.

I had to remove port::Mutex as a dependency for util/thread_local.h, but that's fine since we can just use std::mutex :)

Test Plan: make check

Reviewers: ljin, dhruba, haobo, sdong, yhchiang

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18171
2014-04-22 17:26:21 -07:00
Igor Canadi
3992aec8fa Support for column families in TTL DB
Summary:
This will enable people using TTL DB to do so with multiple column families. They can also specify different TTLs for each one.

TODO: Implement CreateColumnFamily() in TTL world.

Test Plan: Added a very simple sanity test.

Reviewers: dhruba, haobo, ljin, sdong, yhchiang

Reviewed By: haobo

CC: leveldb, alberts

Differential Revision: https://reviews.facebook.net/D17859
2014-04-22 11:27:33 -07:00
Igor Canadi
8dc34364d2 Rename "benchmark" back to "bench".
Also, make `benchharness.cc` not compiled into rocksdb library.
2014-04-21 13:12:15 -07:00
Pratyush Seth
ff1b5df4c6 Added benchmark functionality on the lines of folly/Benchmark.h
Summary: Added benchmark functionality on the lines of folly/Benchmark.h

Test Plan: Added unit tests

Reviewers: igor, haobo, sdong, ljin, yhchiang, dhruba

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17973
2014-04-21 12:29:55 -07:00
Igor Canadi
f813279da5 Remove TransactionLogIteratorRace when -DNDEBUG 2014-04-21 11:08:30 -07:00
Lei Jin
0f2d768191 hints for narrowing down FindFile range and avoiding checking unrelevant L0 files
Summary:
The file tree structure in Version is prebuilt and the range of each file is known.
On the Get() code path, we do binary search in FindFile() by comparing
target key with each file's largest key and also check the range for each L0 file.
With some pre-calculated knowledge, each key comparision that has been done can serve
as a hint to narrow down further searches:
(1) If a key falls within a L0 file's range, we can safely skip the next
file if its range does not overlap with the current one.
(2) If a key falls within a file's range in level L0 - Ln-1, we should only
need to binary search in the next level for files that overlap with the current one.

(1) will be able to skip some files depending one the key distribution.
(2) can greatly reduce the range of binary search, especially for bottom
levels, given that one file most likely only overlaps with N files from
the level below (where N is max_bytes_for_level_multiplier). So on level
L, we will only look at ~N files instead of N^L files.

Some inital results: measured with 500M key DB, when write is light (10k/s = 1.2M/s), this
improves QPS ~7% on top of blocked bloom. When write is heavier (80k/s =
9.6M/s), it gives us ~13% improvement.

Test Plan: make all check

Reviewers: haobo, igor, dhruba, sdong, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17205
2014-04-21 09:10:12 -07:00
sdong
651792251a Fix bugs introduced by D17961
Summary:
D17961 has two bugs:
(1) two level iterator fails to populate FileMetaData.table_reader, causing performance regression.
(2) table cache handle the !status.ok() case in the wrong place, causing seg fault which shouldn't happen.

Test Plan: make all check

Reviewers: ljin, igor, haobo

Reviewed By: ljin

CC: yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D17991
2014-04-17 17:25:28 -07:00
sdong
fa430bfd04 Minimize accessing multiple objects in Version::Get()
Summary:
One of our profilings shows that Version::Get() sometimes is slow when getting pointer of user comparators or other global objects. In this patch:
(1) we keep pointers of immutable objects in Version to avoid accesses them though option objects or cfd objects
(2) table_reader is directly cached in FileMetaData so that table cache don't have to go through handle first to fetch it
(3) If level 0 has less than 3 files, skip the filtering logic based on SST tables' key range. Smallest and largest key are stored in separated memory locations, which has potential cache misses

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: igor, yhchiang, nkg-, leveldb

Differential Revision: https://reviews.facebook.net/D17739
2014-04-17 14:14:00 -07:00