Commit Graph

961 Commits

Author SHA1 Message Date
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
Igor Canadi
161d9e586b Don't overflow size_t in mac 2014-04-16 15:15:22 -07:00
Igor Canadi
5c12f27791 Remove tautological assert 2014-04-16 09:09:28 -07:00
Igor Canadi
faf7691358 Close DB at the end of DontRollEmptyLogs test 2014-04-15 17:20:56 -07:00
Igor Canadi
1803ed2ccb Fix Mac OS compile 2014-04-15 16:31:49 -07:00
Igor Canadi
7d838856cf Fix compile issues when doing make release 2014-04-15 16:00:10 -07:00
sdong
0f40fe4bc7 When creating a new DB, fail it when wal_dir contains existing log files
Summary: Current behavior of creating new DB is, if there is existing log files, we will go ahead and replay them on top of empty DB. This is a behavior that no user would expect. With this patch, we will fail the creation if a user creates a DB with existing log files.

Test Plan: make all check

Reviewers: haobo, igor, ljin

Reviewed By: haobo

CC: nkg-, yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D17817
2014-04-15 14:01:57 -07:00
Igor Canadi
c166615850 Fix compile issues introduced by RocksDBLite 2014-04-15 13:51:07 -07:00
Igor Canadi
588bca2020 RocksDBLite
Summary:
Introducing RocksDBLite! Removes all the non-essential features and reduces the binary size. This effort should help our adoption on mobile.

Binary size when compiling for IOS (`TARGET_OS=IOS m static_lib`) is down to 9MB from 15MB (without stripping)

Test Plan: compiles :)

Reviewers: dhruba, haobo, ljin, sdong, yhchiang

Reviewed By: yhchiang

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17835
2014-04-15 13:39:26 -07:00
Igor Canadi
dbe0f327ca Set log_empty to false even when options.sync is off [fix tests] 2014-04-15 10:28:34 -07:00
Igor Canadi
e6acb874cd Don't roll empty logs
Summary:
With multiple column families, especially when manual Flush is executed, we might roll the log file, although the current log file is empty (no data has been written to the log).

After the diff, we won't create new log file if current is empty.

Next, I will write an algorithm that will flush column families that reference old log files (i.e., that weren't flushed in a while)

Test Plan: Added an unit test. Confirmed that unit test failes in master

Reviewers: dhruba, haobo, ljin, sdong

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17631
2014-04-15 09:57:25 -07:00
sdong
c87ed0942c Fix db_bench's multireadrandom
Summary: multireadrandom is broken. Fix it

Test Plan: run it and see segfault has gone.

Reviewers: ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17781
2014-04-14 15:43:34 -07:00
Yueh-Hsuan Chiang
118f88d25d Fix compile error in tailing_iter.h
Summary:
Fix the following compile error

  ./db/tailing_iter.h:17:1: error: class 'SuperVersion' was previously declared as a struct [-Werror,-Wmismatched-tags]
  class SuperVersion;
  ^
  ./db/column_family.h:77:8: note: previous use is here
  struct SuperVersion {
         ^
         ./db/tailing_iter.h:17:1: note: did you mean struct here?
         class SuperVersion;
         ^~~~~
         struct
         1 error generated.

Test Plan: make

Reviewers: ljin, igor, haobo, sdong

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17799
2014-04-14 14:05:15 -07:00
Yueh-Hsuan Chiang
327102efa5 Fix merge_test failure due to incorrect assert behavior in the release mode. 2014-04-14 12:06:49 -07:00
Lei Jin
82b37a18bd thread local for tailing iterator
Summary:
replace the super version acquisision in tailing itrator with thread
local

Test Plan: will post results

Reviewers: igor, haobo, sdong, yhchiang, dhruba

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17757
2014-04-14 10:48:01 -07:00
Lei Jin
539dd207df using thread local SuperVersion for NewIterator
Summary:
Similar to GetImp(), use SuperVersion from thread local instead of acquriing mutex.
I don't expect this change will make a dent on NewIterator() performance
because the bottleneck seems to be on the rest part of the API

Test Plan:
make asan_check
will post perf numbers

Reviewers: haobo, igor, sdong, dhruba, yhchiang

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17643
2014-04-14 09:34:59 -07:00
sdong
d5e087b6df db_bench: add a mode to operate multiple DBs
Summary: This patch introduces a new parameter num_multi_db in db_bench. When this parameter is larger than 1, multiple DBs will be created. In all benchmarks, any operation applies to a random DB among them. This is to benchmark the performance of similar applications.

Test Plan: run db_bench on both of num_multi_db=0 and more.

Reviewers: haobo, ljin, igor

Reviewed By: igor

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

Differential Revision: https://reviews.facebook.net/D17769
2014-04-11 16:59:08 -07:00
Lei Jin
eba3fc644a make corruption_test:CompactionInputErrorParanoid deterministic
Summary:
it writes ~10M data, default L0 compaction trigger is 4, plus 2 writer
buffer, so that can accommodate ~6M data before compaction happens for
sure. I guess encoding is doing a good job to shrink the data so that
sometime, compaction does not get triggered. I get test failure quite
often.

Test Plan: ran it multiple times and all got pass

Reviewers: igor, sdong

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17775
2014-04-11 12:48:38 -07:00
Igor Canadi
de41357a18 Don't dump rocksdb version on IOS 2014-04-11 10:19:58 -07:00
Lei Jin
0af36d6aa6 SeekRandomWhileWriting
Summary: as title

Test Plan: ran it

Reviewers: igor, haobo, yhchiang

Reviewed By: yhchiang

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17751
2014-04-11 09:47:20 -07:00
Kai Liu
1405232b6d Temporarily disable a test case in db_test
Summary:

Root cause is still under investigation. Just Disable the troubling use case for now.
2014-04-10 17:17:39 -07:00
Igor Canadi
ddef6841b3 Renamed InfoLogLevel::DEBUG to InfoLogLevel::DEBUG_LEVEL
Summary: XCode for some reason injects `#define DEBUG 1` into our code, which makes compile fail because we use `DEBUG` keyword for other stuff. This diff fixes the issue by renaming `DEBUG` to `DEBUG_LEVEL`.

Test Plan: compiles

Reviewers: dhruba, haobo, sdong, yhchiang, ljin

Reviewed By: yhchiang

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17709
2014-04-10 15:27:42 -07:00
Kai Liu
75b59d5146 Enable hash index for block-based table
Summary: Based on previous patches, this diff eventually provides the end-to-end mechanism for users to specify the hash-index.

Test Plan: Wrote several new unit tests.

Reviewers: sdong, haobo, dhruba

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16539
2014-04-10 14:19:43 -07:00
Lei Jin
7a92537fc4 db_bench: add IteratorCreationWhileWriting mode and allow prefix_seek
Summary: as title

Test Plan: ran it

Reviewers: igor, haobo, yhchiang

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17655
2014-04-10 10:15:59 -07:00
Igor Canadi
4daea66343 Turn on -Wmissing-prototypes
Summary: Compiling for iOS has by default turned on -Wmissing-prototypes, which causes rocksdb to fail compiling. This diff turns on -Wmissing-prototypes in our compile options and cleans up all functions with missing prototypes.

Test Plan: compiles

Reviewers: dhruba, haobo, ljin, sdong

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17649
2014-04-09 21:17:14 -07:00
sdong
df2a8b6a1a Polish IterKey and use it in DBImpl::ProcessKeyValueCompaction()
Summary:
1. Polish IterKey a little bit.
2. Turn to use it in local parameter of current_user_key in DBImpl::ProcessKeyValueCompaction(). Our profile showing that DBImpl::ProcessKeyValueCompaction() has about 14% costs in std::string (the base including reading and writing data but excluding compaction filtering), which is higher than it should be. There are two std::string used in DBImpl::ProcessKeyValueCompaction(), compaction_filter_value and current_user_key and it's hard to distinguish the two.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: igor, yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D17613
2014-04-09 20:50:58 -07:00
Igor Canadi
dc55903293 Improved CompressedCache
Summary:
This is testing behavior that was reported in https://github.com/facebook/rocksdb/issues/111

No issue was found, but it still good to commit this and make CompressedCache more robust.

Test Plan: this is a plan

Reviewers: ljin, dhruba

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17625
2014-04-09 11:43:14 -07:00
Lei Jin
4824014e3b speed up db_bench filluniquerandom mode
Summary:
filluniquerandom is painfully slow due to the naive bitmap check to find
out if a key has been seen before. Majority of time is spent on searching
the last few keys. Split a giant BitSet to smaller ones so that we can
quickly check if a BitSet is full and thus can skip quickly.

It used to take over one hour to filluniquerandom for 100M keys, now it
takes about 10 mins.

Test Plan:
unit test
also verified correctness in db_bench and make sure all keys are
generated

Reviewers: igor, haobo, yhchiang

Reviewed By: igor

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D17607
2014-04-09 11:25:21 -07:00
Igor Canadi
2014915d32 Fix ASAN issue 2014-04-09 10:38:05 -07:00
Igor Canadi
b947fdc89d Column family support for DB::OpenForReadOnly()
Summary: When opening DB in read-only mode, client can choose to only specify a subset of column families ("default" column family can't be omitted, though)

Test Plan: added a unit test in column_family_test

Reviewers: haobo, sdong, ljin, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17565
2014-04-09 09:56:17 -07:00
Igor Canadi
731e55c01c Fix GetProperty() test
Summary:
GetProperty test is flakey.
Before this diff: P8635927
After: P8635945

We need to make sure the thread is done before we destruct sleeping tasks. Otherwise, bad things happen.

Test Plan: See summary

Reviewers: ljin, sdong, haobo, dhruba

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17595
2014-04-08 14:57:00 -07:00
Igor Canadi
34455deb06 Fix Mac OS compile issues 2014-04-08 14:05:53 -07:00
Igor Canadi
5b345b76cb Remove env_ from MergingIterator
Summary: env_ is not used. Compiling for iOS complains.

Test Plan: compiles now

Reviewers: ljin, haobo, sdong, dhruba

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17589
2014-04-08 13:40:42 -07:00
Lei Jin
0c1126d4cf db_bench cleanup
Summary:
clean up the db_bench a little bit. also avoid allocating memory for key
in the loop

Test Plan:
I verified a run with filluniquerandom & readrandom. Iterator seek will be used lot
to measure performance. Will fix whatever comes up

Reviewers: haobo, igor, yhchiang

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17559
2014-04-08 11:21:09 -07:00
Igor Canadi
beeee9dccc Small speedup of CompactionFilterV2
Summary: ToString() is expensive. Profiling shows that most compaction threads are stuck in jemalloc, allocating a new string. This will help out a litte.

Test Plan: make check

Reviewers: haobo, danguo

Reviewed By: danguo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17583
2014-04-08 11:06:39 -07:00
Lei Jin
92c1eb0291 macros for perf_context
Summary: This will allow us to disable them completely for iOS or for better performance

Test Plan: will run make all check

Reviewers: igor, haobo, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17511
2014-04-08 10:58:07 -07:00
sdong
5e2db3b434 PlainTableIterator not to store copied key in std::string
Summary:
Move PlainTableIterator's copied key from std::string local buffer to avoid paying the extra costs in std::string related to sharing. Reuse the same buffer class in DbIter. Move the class to dbformat.h.

This patch improves iterator performance significantly. Running this benchmark:

./table_reader_bench --num_keys2=17 --iterator --plain_table --time_unit=nanosecond

The average latency is improved to about 750 nanoseconds from 1100 nanoseconds.

Test Plan:
Add a unit test.
make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: igor, yhchiang, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D17547
2014-04-07 19:06:09 -07:00
Igor Canadi
664559fe2d Small final fixes before merge 2014-04-07 15:38:53 -07:00
Igor Canadi
d1e2bce42d CallFlushDuringCompaction 2014-04-07 15:03:15 -07:00
Igor Canadi
b42ceb9598 Simplify cleanup of dead (refcount == 0) column families 2014-04-07 14:31:02 -07:00
Igor Canadi
e48348d196 Make flush part of compaction process
This will enable user to use only 1 background thread.
2014-04-07 13:53:08 -07:00
Igor Canadi
2a0917b28e Merge branch 'master' into columnfamilies 2014-04-07 13:04:25 -07:00
Igor Canadi
751e4b1a35 Fix wal_dir sanitizing 2014-04-07 11:36:03 -07:00
Igor Canadi
3d2fe844ab Merge branch 'master' into columnfamilies
Conflicts:
	db/db_impl.cc
	db/db_impl.h
	db/memtable_list.cc
	db/version_set.cc
2014-04-07 11:31:11 -07:00
Igor Canadi
7efdd9ef4d Options::wal_dir shouldn't end in '/'
Summary: If a client specifies wal_dir with trailing '/', we will fail in deleting obsolete log files. See task #4083746

Test Plan: make check

Reviewers: haobo, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17535
2014-04-07 10:25:38 -07:00
sdong
ea0198fe9a Create log::Writer out of DB Mutex
Summary: Our measurement shows that sometimes new log::Write's constructor can take hundreds of milliseconds. It's unclear why but just simply move it out of DB mutex.

Test Plan: make all check

Reviewers: haobo, ljin, igor

Reviewed By: haobo

CC: nkg-, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17487
2014-04-04 15:46:28 -07:00
Lei Jin
c90d446ee7 make hash_link_list Node's key space consecutively followed at the end
Summary: per sdong's request, this will help processor prefetch on n->key case.

Test Plan: make all check

Reviewers: sdong, haobo, igor

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17415
2014-04-04 15:37:28 -07:00
sdong
99c756f0fe Flush Buffered Info Logs Before Doing Compaction (one line change)
Summary: Flushing log buffer earlier to avoid confusion of time holding the locks.

Test Plan: Should be safe as long as several related db test passes

Reviewers: haobo, igor, ljin

Reviewed By: igor

CC: nkg-, leveldb

Differential Revision: https://reviews.facebook.net/D17493
2014-04-04 10:58:30 -07:00
Igor Canadi
040657aec9 Fix MacOS errors 2014-04-03 16:04:34 -07:00
Igor Canadi
f76e4027ca initialize candidate count 2014-04-03 11:45:44 -07:00
sdong
b9767d0e09 Move several more logging inside DB mutex to log buffer
Summary: Move several some common logging still in DB mutex to log buffer.

Test Plan: make all check

Reviewers: haobo, igor, ljin, nkg-

Reviewed By: nkg-

CC: nkg-, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17439
2014-04-03 10:47:18 -07:00
Thomas Adam
98422cba77 [C-API] implemented more options 2014-04-03 10:47:37 +02:00
Thomas Adam
3a30b5b0be [C-API] added "rocksdb_options_set_plain_table_factory" to make it possible to use plain table factory 2014-04-03 10:47:37 +02:00
Haobo Xu
48bc0c6ad3 [RocksDB] Fix a race condition in GetSortedWalFiles
Summary: This patch fixed a race condition where a log file is moved to archived dir in the middle of GetSortedWalFiles. Without the fix, the log file would be missed in the result, which leads to transaction log iterator gap. A test utility SyncPoint is added to help reproducing the race condition.

Test Plan: TransactionLogIteratorRace; make check

Reviewers: dhruba, ljin

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17121
2014-04-02 22:12:29 -07:00
Igor Canadi
d1d19f5db3 Fix valgrind error in c_test 2014-04-02 17:24:30 -07:00
sdong
158845ba9a Move a info logging out of DB Mutex
Summary: As we know, logging can be slow, or even hang for some file systems. Move one more logging out of DB mutex.

Test Plan: make all check

Reviewers: haobo, igor, ljin

Reviewed By: igor

CC: yhchiang, nkg-, leveldb

Differential Revision: https://reviews.facebook.net/D17427
2014-04-02 16:48:32 -07:00
sdong
4af1954fd6 Compaction Filter V1 to use old context struct to keep backward compatible
Summary: The previous change D15087 changed existing compaction filter, which makes the commonly used class not backward compatible. Revert the older interface. Use a new interface for V2 instead.

Test Plan: make all check

Reviewers: haobo, yhchiang, igor

CC: danguo, dhruba, ljin, igor, leveldb

Differential Revision: https://reviews.facebook.net/D17223
2014-04-02 14:57:51 -07:00
sdong
284c365b77 Fix valgrind error caused by FileMetaData as two level iterator's index block handle
Summary: It is a regression valgrind bug caused by using FileMetaData as index block handle. One of the fields of FileMetaData is not initialized after being contructed and copied, but I'm not able to find which one. Also, I realized that it's not a good idea to use FileMetaData as in TwoLevelIterator::InitDataBlock(), a copied FileMetaData can be compared with the one in version set byte by byte, but the refs can be changed. Also comparing such a large structure is slightly more expensive. Use a simpler structure instead

Test Plan:
Run the failing valgrind test (Harness.RandomizedLongDB)
make all check

Reviewers: igor, haobo, ljin

Reviewed By: igor

CC: yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17409
2014-04-02 14:38:28 -07:00
Igor Canadi
8555ce2dec Merge branch 'master' into columnfamilies 2014-04-02 10:48:05 -07:00
sdong
e0a87c4cf1 DBIter to use static allocated char array for saved_key_ (if it is not too long)
Summary: DBIter now uses a std::string for saved_key. Based on some profiling, it could be more expensive than we though. Optimize it with the same technique as LookupKey -- if it is short, we copy it to a static allocated char. Otherwise, dynamically allocate memory for it.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: haobo

CC: dhruba, igor, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17289
2014-04-01 16:43:11 -07:00
sdong
d50619a559 PlainTableIterator::Seek() shouldn't check bloom filter in total order mode
Summary:
In total order mode, iterator's seek() shouldn't check total order.

Also some cleaning up about checking null for shared pointers. I don't know the behavior before it.

This bug was reported by @igor.

Test Plan: test plain_table_db_test

Reviewers: ljin, haobo, igor

Reviewed By: igor

CC: yhchiang, dhruba, igor, leveldb

Differential Revision: https://reviews.facebook.net/D17391
2014-04-01 15:05:16 -07:00
Thomas Adam
38dc5ef45f [C-API] added the possiblity to create a HashSkipList or HashLinkedList to support prefix seeks 2014-04-01 12:44:27 +02:00
Igor Canadi
ddbd1ece88 Merge branch 'master' into columnfamilies
Conflicts:
	db/db_impl.cc
	db/db_test.cc
	db/internal_stats.cc
	db/internal_stats.h
	db/version_edit.cc
	db/version_edit.h
	db/version_set.cc
	include/rocksdb/options.h
	util/options.cc
2014-03-31 13:39:24 -07:00
Igor Canadi
577556d5f9 Don't store version number in MANIFEST
Summary: Talked to <insert internal project name> folks and they found it really scary that they won't be able to roll back once they upgrade to 2.8. We should fix this.

Test Plan: make check

Reviewers: haobo, ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17343
2014-03-31 11:33:09 -07:00
Igor Canadi
8a139a054c More valgrind issues!
Summary: Fix some more CompactionFilterV2 valgrind issues. Maybe it would make sense for CompactionFilterV2 to delete its prefix_extractor?

Test Plan: ran CompactionFilterV2* tests with valgrind. issues before patch -> no issues after

Reviewers: haobo, sdong, ljin, dhruba

Reviewed By: dhruba

CC: leveldb, danguo

Differential Revision: https://reviews.facebook.net/D17337
2014-03-29 10:34:47 -07:00
sdong
43a593a6d9 Change default value of some Options
Summary: Since we are optimizing for server workloads, some default values are not optimized any more. We change some of those values that I feel it's less prone to regression bugs.

Test Plan: make all check

Reviewers: dhruba, haobo, ljin, igor, yhchiang

Reviewed By: igor

CC: leveldb, MarkCallaghan

Differential Revision: https://reviews.facebook.net/D16995
2014-03-28 17:09:28 -07:00
sdong
2d3468c293 MemTableIterator not to reference Memtable
Summary: In one of the perf, I shows 10%-25% CPU costs of MemTableIterator.Seek(), when doing dynamic prefix seek, are spent on checking whether we need to do bloom filter check or finding out the prefix extractor. Seems that  more level of pointer checking makes CPU cache miss more likely. This patch makes things slightly simpler by copying pointer of bloom of prefix extractor into the iterator.

Test Plan: make all check

Reviewers: haobo, ljin

Reviewed By: ljin

CC: igor, dhruba, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17247
2014-03-28 16:46:25 -07:00
Lei Jin
0d755fff14 cache friendly blocked bloomfilter
Summary:
By constraining the probes within cache line(s), we can improve the
cache miss rate thus performance. This probably only makes sense for
in-memory workload so defaults the option to off.

Numbers and comparision can be found in wiki:
https://our.intern.facebook.com/intern/wiki/index.php/Ljin/rocksdb_perf/2014_03_17#Bloom_Filter_Study

Test Plan: benchmarked this change substantially. Will run make all check as well

Reviewers: haobo, igor, dhruba, sdong, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17133
2014-03-28 09:21:20 -07:00
Yueh-Hsuan Chiang
10cebec79e Fix the bug in MergeUtil which causes mixing values of different keys.
Summary: Fix the bug in MergeUtil which causes mixing values of different keys.

Test Plan:
stringappend_test
make all check

Reviewers: haobo, igor

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17235
2014-03-27 16:15:25 -07:00
Haobo Xu
a92194e5b2 [RocksDB] Add db property "rocksdb.cur-size-active-mem-table"
Summary: as title

Test Plan: db_test

Reviewers: sdong

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17217
2014-03-27 15:14:04 -07:00
Igor Canadi
1c9f8f0884 Fix valgrind issues
Summary:
NewFixedPrefixTransform is leaked in default options. Broken by b47812fba6

Also included in the diff some code cleanup

Test Plan:
valgrind env_test
also make check

Reviewers: haobo, danguo, yhchiang

Reviewed By: danguo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17211
2014-03-27 08:22:59 -07:00
sdong
d556200264 Some small cleaning up to make some compiling environment happy
Summary: Compiler complains some errors when building using our internal build settings. Fix them.

Test Plan: rebuild

Reviewers: haobo, dhruba, igor, yhchiang, ljin

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17199
2014-03-26 18:11:41 -07:00
Igor Canadi
6a08bc042a Fix no return warning in FileComparator 2014-03-26 14:46:07 -07:00
Igor Canadi
1e9621d4e5 Sort files correctly in Builder::SaveTo
Summary:
Previously, we used to sort all files by BySmallestFirst comparator and then re-sort level0 files in the Finalize() (recently moved to end of SaveTo).

In this diff, I chose the correct comparator at the beginning and sort the files correctly in Builder::SaveTo.

I also added a verification that all files are sorted correctly in CheckConsistency()

NOTE: This diff depends on D17037

Test Plan: make check. Will also run db_stress

Reviewers: dhruba, haobo, sdong, ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17049
2014-03-26 13:30:14 -07:00
Igor Canadi
954679bb0f AssertHeld() should do things
Summary:
AssertHeld() was a no-op before. Now it does things.

Also, this change caught a bad bug in SuperVersion::Init(). The method is calling db->mutex.AssertHeld(), but db variable is not initialized yet! I also fixed that issue.

Test Plan: make check

Reviewers: dhruba, haobo, ljin, sdong, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17193
2014-03-26 11:24:52 -07:00
Igor Canadi
ad9a39c9b4 [RocksDB] Preallocate new MANIFEST files
Summary: We don't preallocate MANIFEST file, even though we have an option for that. This diff preallocates manifest file every time we create it

Test Plan: make check

Reviewers: dhruba, haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17163
2014-03-26 09:37:53 -07:00
sdong
6b2e7a2a01 When Options.max_num_files=-1, non level0 files also by pass table cache
Summary:
This is the part that was not finished when doing the Options.max_num_files=-1 feature. For iterating non level0 SST files (which was done using two level iterator), table cache is not bypassed. With this patch, the leftover feature is done.

Test Plan: make all check; change Options.max_num_files=-1 in one of the tests to cover the codes.

Reviewers: haobo, igor, dhruba, ljin, yhchiang

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17001
2014-03-25 18:40:52 -07:00
Igor Canadi
e86d7dffd7 Merge branch 'master' into columnfamilies 2014-03-25 15:24:02 -07:00
Yueh-Hsuan Chiang
b9ce156e38 Add assert to MergeOperator::PartialMergeMulti to check # of operands.
Summary:
Add assert(operands_list.size() >= 2) in MergeOperator::PartialMergeMulti
to ensure it's only be called when we have at least two merge operands.

Test Plan: run merge_test and stringappend_test.

Reviewers: haobo, igor

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17169
2014-03-25 13:39:17 -07:00
Danny Guo
d9ca83df28 [rocksdb] make init prefix more robust
Summary:
Currently if client uses kNULLString as the prefix, it will confuse
compaction filter v2. This diff added a bool to indicate if the prefix
has been intialized. I also added a unit test to cover this case and
make sure the new code path is hit.

Test Plan: db_test

Reviewers: igor, haobo

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17151
2014-03-25 11:59:40 -07:00
Yueh-Hsuan Chiang
34f9da1cef Fix the failure of stringappend_test caused by PartialMergeMulti.
Summary:
Fix a bug that PartialMergeMulti will try to merge the first operand
with an empty slice.

Test Plan: run stringappend_test and merge_test.

Reviewers: haobo, igor

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17157
2014-03-25 11:50:09 -07:00
Igor Canadi
e8168382c4 Merge branch 'master' into columnfamilies
Conflicts:
	db/db_impl.cc
	include/rocksdb/options.h
	util/options.cc
2014-03-25 11:09:40 -07:00
Danny Guo
b47812fba6 [rocksdb] new CompactionFilterV2 API
Summary:
This diff adds a new CompactionFilterV2 API that roll up the
decisions of kv pairs during compactions. These kv pairs must share the
same key prefix. They are buffered inside the db.

    typedef std::vector<Slice> SliceVector;
    virtual std::vector<bool> Filter(int level,
                                 const SliceVector& keys,
                                 const SliceVector& existing_values,
                                 std::vector<std::string>* new_values,
                                 std::vector<bool>* values_changed
                                 ) const = 0;

Application can override the Filter() function to operate
on the buffered kv pairs. More details in the inline documentation.

Test Plan:
make check. Added unit tests to make sure Keep, Delete,
Change all works.

Reviewers: haobo

CCs: leveldb

Differential Revision: https://reviews.facebook.net/D15087
2014-03-24 20:47:53 -07:00
Yueh-Hsuan Chiang
cda4006e87 Enhance partial merge to support multiple arguments
Summary:
* PartialMerge api now takes a list of operands instead of two operands.
* Add min_pertial_merge_operands to Options, indicating the minimum
  number of operands to trigger partial merge.
* This diff is based on Schalk's previous diff (D14601), but it also
  includes necessary changes such as updating the pure C api for
  partial merge.

Test Plan:
* make check all
* develop tests for cases where partial merge takes more than two
  operands.

TODOs (from Schalk):
* Add test with min_partial_merge_operands > 2.
* Perform benchmarks to measure the performance improvements (can probably
  use results of task #2837810.)
* Add description of problem to doc/index.html.
* Change wiki pages to reflect the interface changes.

Reviewers: haobo, igor, vamsi

Reviewed By: haobo

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D16815
2014-03-24 17:57:13 -07:00
Igor Canadi
ac328a86b9 Merge branch 'master' into columnfamilies
Conflicts:
	db/db_impl.cc
	db/db_test.cc
2014-03-20 14:41:37 -07:00
Igor Canadi
c21ce14fa5 Fix double-free in corruption_test 2014-03-20 14:37:30 -07:00
Igor Canadi
e67241f0b9 Sanity check on Open
Summary:
Everytime a client opens a DB, we do a sanity check that:
* checks the existance of all the necessary files
* verifies that file sizes are correct

Some of the code was stolen from https://reviews.facebook.net/D16935

Test Plan: added a unit test

Reviewers: dhruba, haobo, sdong

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17097
2014-03-20 14:18:29 -07:00
Yiting Li
7981a43274 Consistency Check Function
Summary: Added a function/command to check the consistency of live files' meta data

Test Plan:
Manual test (size mismatch, file not exist).
Command test script.

Reviewers: haobo

Reviewed By: haobo

CC: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D16935
2014-03-20 13:42:45 -07:00
Igor Canadi
8ea3cb621e If paranoid_checks -- Mark DB read-only on any IOError
Summary:
Whenever we get an IOError from GetImpl() or NewIterator(), we should immediatelly mark the DB read-only. The same check already exists in Write() and Compaction().

This should help with clients that are somehow missing a file.

Test Plan: make check

Reviewers: dhruba, haobo, sdong, ljin

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17061
2014-03-20 13:10:02 -07:00
sdong
f681030c80 Fix DBTest.UniversalCompactionTrigger failure caused by D17067
Summary: D17067 breaks DBTest.UniversalCompactionTrigger because of wrong location of the checking. Fix it.

Test Plan: Run the test and make sure it passes.

Reviewers: igor, haobo

Reviewed By: igor

CC: dhruba, ljin, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D17079
2014-03-20 11:10:11 -07:00
sdong
752ec46cd5 Add a unit test to verify compaction filter context
Summary: Add unit tests to make sure CompactionFilterContext::is_manual_compaction_ and CompactionFilterContext::is_full_compaction_ are set correctly.

Test Plan: run the new tests.

Reviewers: haobo, igor, dhruba, yhchiang, ljin

Reviewed By: haobo

CC: nkg-, leveldb

Differential Revision: https://reviews.facebook.net/D17067
2014-03-19 18:10:48 -07:00
Igor Canadi
e20fa3f8a4 Merge branch 'master' into columnfamilies
Conflicts:
	db/db_impl.cc
	db/internal_stats.cc
	db/internal_stats.h
	db/version_set.cc
2014-03-19 17:22:20 -07:00
Igor Canadi
fcd5c5e828 ComputeCompactionScore in CompactionPicker
Summary:
As it turns out, we need the call to ComputeCompactionScore (previously: Finalize) in CompactionPicker.

The issue caused a deadlock in db_stress: http://ci-builds.fb.com/job/rocksdb_crashtest/290/console

The last two lines before a deadlock were:
2014/03/18-22:43:41.481029 7facafbee700 (Original Log Time 2014/03/18-22:43:41.480989) Compaction nothing to do
2014/03/18-22:43:41.481041 7faccf7fc700 wait for fewer level0 files...

"Compaction nothing to do" and other thread waiting for fewer level0 files. Hm hm.

I moved the pre-sorting to SaveTo, which should fix both the original and the new issue.

Test Plan: make check for now, will run db_stress in jenkins

Reviewers: dhruba, haobo, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17037
2014-03-19 16:52:26 -07:00
Igor Canadi
e493f2f54e Don't compact with zero input files
Summary:
We have an issue with internal service trying to run compaction with zero input files:
2014/02/07-02:26:58.386531 7f79117ec700 Compaction start summary: Base version 1420 Base level 3, seek compaction:0, inputs:[ϛ~^Qy^?],[]
2014/02/07-02:26:58.386539 7f79117ec700 Compacted 0@3 + 0@4 files => 0 bytes

There are two issues:
* inputsummary is printing out junk
* it's constantly retrying (since I guess madeProgress is true), so it prints out a lot of data in the LOG file (40GB in one day).

I read through the Level compaction picker and added some failure condition if input[0] is empty. I think PickCompaction() should not return compaction with zero input files with this change. I'm not confident enough to add an assertion though :)

Test Plan: make check

Reviewers: dhruba, haobo, sdong, kailiu

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16005
2014-03-19 16:01:25 -07:00
Igor Canadi
22507aff6c Fix compile issue in Mac OS
Summary:
Compile issues are:
* Unused variable env_
* Unused fallocate_with_keep_size_

Test Plan: compiles

Reviewers: dhruba, haobo, sdong

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17043
2014-03-19 15:40:12 -07:00
Lei Jin
6dc940d4c9 avoid shared_ptr assignment in Version::Get()
Summary:
This is a 500ns operation while the whole Get() call takes only a few
micro!

Test Plan: ran db_bench, for a DB with 50M keys, QPS jumps from 5.2M/s to 7.2M/s

Reviewers: haobo, igor, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17007
2014-03-19 10:54:32 -07:00
sdong
71e6a34271 Add a DB property to indicate number of background errors encountered
Summary: Add a property to calculate number of background errors encountered to help users build their monitoring

Test Plan: Add a unit test. make all check

Reviewers: haobo, igor, dhruba

Reviewed By: igor

CC: ljin, nkg-, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D16959
2014-03-18 14:28:30 -07:00