Commit Graph

8692 Commits

Author SHA1 Message Date
Dhruba Borthakur
cd93e82845 Enable SSE when building with fbcode support.
Summary:
fbcode build now support SSE instructions.
Delete older version of the compile-helper fbcode.sh. This is
subsumed by fbcode.gcc471.sh.

Test Plan: run make check

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D6057
2012-10-18 08:43:25 -07:00
Dhruba Borthakur
aa73538f2a The deletion of obsolete files should not occur very frequently.
Summary:
The method DeleteObsolete files is a very costly methind, especially
when the number of files in a system is large. It makes a list of
all live-files and then scans the directory to compute the diff.
By default, this method is executed after every compaction run.

This patch makes it such that DeleteObsolete files is never
invoked twice within a configured period.

Test Plan: run all unit tests

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D6045
2012-10-16 10:26:10 -07:00
Dhruba Borthakur
0230866791 Enhance db_bench to allow setting the number of levels in a database.
Summary: Enhance db_bench to allow setting the number of levels in a database.

Test Plan: run db_bench and look at LOG

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: MarkCallaghan

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D6027
2012-10-15 10:18:49 -07:00
Dhruba Borthakur
5dc784c233 Fix compilation problem with db_stress when using C11 compiler.
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-10-12 17:00:25 -07:00
Asad K Awan
24f7983b1f [tools] Add a tool to stress test concurrent writing to levelDB
Summary:
Created a tool that runs multiple threads that concurrently read and write to levelDB.
All writes to the DB are stored in an in-memory hashtable and verified at the end of the
test. All writes for a given key are serialzied.

Test Plan:
 - Verified by writing only a few keys and logging all writes and verifying that values read and written are correct.
 - Verified correctness of value generator.
 - Ran with various parameters of number of keys, locks, and threads.

Reviewers: dhruba, MarkCallaghan, heyongqiang

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5829
2012-10-10 12:12:55 -07:00
Thawan Kooburat
696b290821 Add LevelDb's JNI wrapper
Summary: This implement the Java interface by using JNI

Test Plan: compile test

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5925
2012-10-05 13:13:49 -07:00
Thawan Kooburat
fc23714f27 Add LevelDb's Java interface
Summary:
See the wiki below
https://our.intern.facebook.com/intern/wiki/index.php/Database/leveldb/Java

Test Plan: compile test

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5919
2012-10-05 13:11:31 -07:00
Dhruba Borthakur
f7975ac733 Implement RowLocks for assoc schema
Summary:
Each assoc is identified by (id1, assocType). This is the rowkey.
Each row has a read/write rowlock. There is statically allocated array
of 2000 read/write locks. A rowkey is murmur-hashed to one of the
read/write locks.

assocPut and assocDelete acquires the rowlock in Write mode.
The key-updates are done within the rowlock with a atomic nosync
batch write to leveldb. Then the rowlock is released and
a write-with-sync is done to sync leveldb transaction log.

Test Plan: added unit test

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5859
2012-10-03 23:19:01 -07:00
Dhruba Borthakur
c1006d4276 An configurable option to write data using write instead of mmap.
Summary:
We have seen that reading data via the pread call (instead of
mmap) is much faster on Linux 2.6.x kernels. This patch makes
an equivalent option to switch off mmaps for the write path
as well.

db_bench --mmap_write=0 will use write() instead of mmap() to
write data to a file.

This change is backward compatible, the default
option is to continue using mmap for writing to a file.

Test Plan: "make check all"

Differential Revision: https://reviews.facebook.net/D5781
2012-10-03 17:08:13 -07:00
Mark Callaghan
e678a5947a Add --stats_interval option to db_bench
Summary:
The option is zero by default and in that case reporting is unchanged.
By unchanged, the interval at which stats are reported is scaled after each
report and newline is not issued after each report so one line is rewritten.
When non-zero it specifies the constant interval (in operations) at which
statistics are reported and the stats include the rate per interval. This
makes it easier to determine whether QPS changes over the duration of the test.

Task ID: #

Blame Rev:

Test Plan:
run db_bench

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: dhruba

Reviewed By: dhruba

CC: heyongqiang

Differential Revision: https://reviews.facebook.net/D5817
2012-10-03 09:54:33 -07:00
Mark Callaghan
d8763abecd Fix the bounds check for the --readwritepercent option
Summary:
see above

Task ID: #

Blame Rev:

Test Plan:
run db_bench with invalid value for option

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: dhruba

Reviewed By: dhruba

CC: heyongqiang

Differential Revision: https://reviews.facebook.net/D5823
2012-10-03 09:52:26 -07:00
Mark Callaghan
98804f914f Fix compiler warnings and errors in ldb.c
Summary:
stdlib.h is needed for exit()
--readhead --> --readahead

Task ID: #

Blame Rev:

Test Plan:
compile

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -
fix compiler warnings & errors

Reviewers: dhruba

Reviewed By: dhruba

CC: heyongqiang

Differential Revision: https://reviews.facebook.net/D5805
2012-10-03 06:46:59 -07:00
Dhruba Borthakur
a58d48de79 Implement ReadWrite locks for leveldb
Summary:
Implement ReadWrite locks for leveldb. These will be helpful
to implement a read-modify-write operation (e.g. atomic increments).

Test Plan: does not modify any existing code

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5787
2012-10-01 22:37:39 -07:00
Abhishek Kona
fec81318b0 Commandline tool to compace LevelDB databases.
Summary:
A simple CLI which calles DB->CompactRange()
Can take String key's as range.

Test Plan:
Inserted data into a table.
Waited for a minute, used compact tool on it. File modification time's
changed so Compact did something on the files.

Existing unit tests work.

Reviewers: heyongqiang, dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5697
2012-10-01 10:49:19 -07:00
Dhruba Borthakur
a321d5be9e Implement assocDelete.
Summary: Implement assocDelete.

Test Plan: unit test attached

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5721
2012-10-01 09:58:26 -07:00
Dhruba Borthakur
72c45c66c6 Print the block cache size in the LOG.
Summary: Print the block cache size in the LOG.

Test Plan: run db_bench and look at LOG. This is helpful while I was debugging one use-case.

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5739
2012-09-29 21:39:19 -07:00
Dhruba Borthakur
c1bb32e1ba Trigger read compaction only if seeks to storage are incurred.
Summary:
In the current code, a Get() call can trigger compaction if it has to look at more than one file. This causes unnecessary compaction because looking at more than one file is a penalty only if the file is not yet in the cache. Also, th current code counts these files before the bloom filter check is applied.

This patch counts a 'seek' only if the file fails the bloom filter
check and has to read in data block(s) from the storage.

This patch also counts a 'seek' if a file is not present in the file-cache, because opening a file means that its index blocks need to be read into cache.

Test Plan: unit test attached. I will probably add one more unti tests.

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5709
2012-09-28 11:10:52 -07:00
gjain
92368ab8a2 Add db_dump tool to dump DB keys
Summary:
Create a tool to iterate through keys and dump values. Current options
as follows:

db_dump --start=[START_KEY] --end=[END_KEY] --max_keys=[NUM] --stats
[PATH]

START_KEY: First key to start at
END_KEY: Key to end at (not inclusive)
NUM: Maximum number of keys to dump
PATH: Path to leveldb DB

The --stats command line argument prints out the DB stats before dumping
the keys.

Test Plan:
- Tested with invalid args
- Tested with invalid path
- Used empty DB
- Used filled DB
- Tried various permutations of command line options

Reviewers: dhruba, heyongqiang

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5643
2012-09-27 09:53:58 -07:00
Dhruba Borthakur
eace74deac Add -fPIC to the shared library builds. Needed by libleveldbjni.
Summary: Add -fPIC to the shared library builds. Needed by libleveldbjni.

Test Plan: build

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5667
2012-09-25 11:07:35 -07:00
Dhruba Borthakur
24eea931ef If ReadCompaction is switched off, then it is better to not even submit background compaction jobs.
Summary:
If ReadCompaction is switched off, then it is better to not even
submit background compaction jobs. I see about 3% increase in
read-throughput on a pure memory database.

Test Plan: run db_bench

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5673
2012-09-25 11:07:01 -07:00
Dhruba Borthakur
26e0ecbd98 Release 1.5.3.fb.
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-09-25 08:30:46 -07:00
Dhruba Borthakur
ae36e509f8 The BackupAPI should also list the length of the manifest file.
Summary:
The GetLiveFiles() api lists the set of sst files and the current
MANIFEST file. But the database continues to append new data to the
MANIFEST file even when the application is backing it up to the
backup location. This means that the database-version that is
stored in the MANIFEST FILE in the backup location
does not correspond to the sst files returned by GetLiveFiles.

This API adds a new parameter to GetLiveFiles. This new parmeter
returns the current size of the MANIFEST file.

Test Plan: Unit test attached.

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5631
2012-09-25 03:13:25 -07:00
Dhruba Borthakur
dd45b8cd8c Keep symbols even for production release.
Summary:
Keeping symbols in the binary increases the size of the library but makes
it easier to debug. The optimization level is still -O2, so this should
have no impact on performance.

Test Plan: make all

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: MarkCallaghan

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5601
2012-09-21 15:57:47 -07:00
Dhruba Borthakur
653add3c66 Release 1.5.2.fb
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-09-21 11:01:33 -07:00
Dhruba Borthakur
bb2dcd2457 Segfault in DoCompactionWork caused by buffer overflow
Summary:
The code was allocating 200 bytes on the stack but it
writes 256 bytes into the array.

x8a8ea5 std::_Rb_tree<>::erase()
    @     0x7f134bee7eb0 (unknown)
    @           0x8a8ea5 std::_Rb_tree<>::erase()
    @           0x8a35d6 leveldb::DBImpl::CleanupCompaction()
    @           0x8a7810 leveldb::DBImpl::BackgroundCompaction()
    @           0x8a804d leveldb::DBImpl::BackgroundCall()
    @           0x8c4eff leveldb::(anonymous namespace)::PosixEnv::BGThreadWrapper()
    @     0x7f134b3c010d start_thread
    @     0x7f134bf9f10d clone

Test Plan: run db_bench with overwrite option

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5595
2012-09-21 10:55:38 -07:00
Dhruba Borthakur
9e84834eb4 Allow a configurable number of background threads.
Summary:
The background threads are necessary for compaction.
For slower storage, it might be necessary to have more than
one compaction thread per DB. This patch allows creating
a configurable number of worker threads.
The default reamins at 1 (to maintain backward compatibility).

Test Plan:
run all unit tests. changes to db-bench coming in
a separate patch.

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5559
2012-09-19 15:51:08 -07:00
Dhruba Borthakur
fb4b381a0c Print out the compile version in the LOG.
Summary: Print out the compile version in the LOG.

Test Plan: run dbbench and verify LOG

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5529
2012-09-18 13:24:32 -07:00
heyongqiang
3662c2976a improve comments about target_file_size_base, target_file_size_multiplier, max_bytes_for_level_base, max_bytes_for_level_multiplier Summary:
Summary: as subject

Test Plan: compile

Reviewers: MarkCallaghan, dhruba

Differential Revision: https://reviews.facebook.net/D5499
2012-09-17 15:56:11 -07:00
Dhruba Borthakur
aa0426f124 Use correct version of jemalloc.
Summary: Use correct version of jemalloc.

Test Plan: run unit tests

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5487
2012-09-17 15:00:19 -07:00
heyongqiang
a8464ed820 add an option to disable seek compaction
Summary:
as subject. This diff should be good for benchmarking.

will send another diff to make it better in the case the seek compaction is enable.
In that coming diff, will not count a seek if the bloomfilter filters.

Test Plan: build

Reviewers: dhruba, MarkCallaghan

Reviewed By: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5481
2012-09-17 13:59:57 -07:00
Dhruba Borthakur
906f2ee1f1 New release 1.5.1.fb
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-09-17 11:35:06 -07:00
Dhruba Borthakur
1f7850cf4c Build with gcc-4.7.1-glibc-2.14.1.
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-09-17 10:56:26 -07:00
heyongqiang
b5263428ab use 20d3328ac30f633840ce819ad03019f415267a86 as builder Summary:
Summary: as subject

Test Plan: build

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5475
2012-09-17 10:53:52 -07:00
Dhruba Borthakur
ba55d77b5d Ability to take a file-lvel snapshot from leveldb.
Summary:
A set of apis that allows an application to backup data from the
leveldb database based on a set of files.

Test Plan: unint test attached. more coming soon.

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5439
2012-09-17 09:14:50 -07:00
heyongqiang
b85cdca690 add a global var leveldb::useMmapRead to enable mmap Summary:
Summary:
as subject. this can be used for benchmarking.
If we want it for some cases, we can do more changes to make this part of the option.

Test Plan: db_test

Reviewers: dhruba

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5451
2012-09-16 22:07:35 -07:00
heyongqiang
dcbd6be340 remove boost
Summary: as subject

Test Plan: build

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D5469
2012-09-16 19:33:43 -07:00
Mark Callaghan
33323f2111 Remove use of mmap for random reads
Summary:
Reads via mmap on concurrent workloads are much slower than pread.
For example on a 24-core server with storage that can do 100k IOPS or more
I can get no more than 10k IOPS with mmap reads and 32+ threads.

Test Plan: db_bench benchmarks

Reviewers: dhruba, heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5433
2012-09-14 16:43:50 -07:00
Mark Callaghan
fa29f82548 scan a long for FLAGS_cache_size to fix a compiler warning
Summary:
FLAGS_cache_size is a long, no need to scan %lld into a size_t
for it (which generates a compiler warning)

Test Plan: run db_bench

Reviewers: dhruba, heyongqiang

Reviewed By: heyongqiang

CC: heyongqiang

Differential Revision: https://reviews.facebook.net/D5427
2012-09-14 12:45:42 -07:00
Mark Callaghan
837113908c Add --compression_type=X option with valid values: snappy (default) none bzip2 zlib
Summary:
This adds an option to db_bench to specify the compression algorithm to
use for LevelDB

Test Plan: ran db_bench

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5421
2012-09-14 12:28:21 -07:00
Dhruba Borthakur
93f4952089 Ability to switch off filesystem read-aheads
Summary:
Ability to switch off filesystem read-aheads. This change is
backward-compatible: the default setting is to allow file
system read-aheads.

Test Plan: run benchmarks

Reviewers: heyongqiang, adsharma

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5391
2012-09-13 12:09:56 -07:00
Dhruba Borthakur
4028ae7d31 Do not cache readahead-pages in the OS cache.
Summary:
When posix_fadvise(offset, offset) is usedm it frees up only those
pages in that specified range. But the filesystem could have done some
read-aheads and those get cached in the OS cache.

Do not cache readahead-pages in the OS cache.

Test Plan: run db_bench benchmark.

Reviewers: vamsi, heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5379
2012-09-13 10:56:02 -07:00
Dhruba Borthakur
7ecc5d4ad5 Enable db_bench to specify block size.
Summary: Enable db_bench to specify block size.

Test Plan: compile and run

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5373
2012-09-13 10:22:43 -07:00
Dhruba Borthakur
407727b75f Fix compiler warnings. Use uint64_t instead of uint.
Summary: Fix compiler warnings. Use uint64_t instead of uint.

Test Plan: build using -Wall

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5355
2012-09-12 14:42:36 -07:00
heyongqiang
0f43aa474e put log in a seperate dir
Summary: added a new option db_log_dir, which points the log dir. Inside that dir, in order to make log names unique, the log file name is prefixed with the leveldb data dir absolute path.

Test Plan: db_test

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5205
2012-09-06 17:52:08 -07:00
heyongqiang
afb5f2210f build scribe with thrift lib Summary:
Summary: as subject

Test Plan: test build

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5145
2012-09-06 17:41:53 -07:00
Dhruba Borthakur
536ca698ba The ReadnRandomWriteRandom was always looping FLAGS_num of times.
Summary: If none of reads or writes are specified by user, then pick the FLAGS_NUM as the number of iterations in the ReadRandomWriteRandom test. If either reads or writes are defined, then use their maximum.

Test Plan: run benchmark

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5217
2012-09-06 09:13:24 -07:00
Dhruba Borthakur
354a9ea089 Compile leveldb with gcc 4.7.1
Test Plan: run unit tests

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5163
2012-09-05 00:11:35 -07:00
Dhruba Borthakur
7112c93c9b Do not use scribe for release builds.
Summary: Do not use scribe for release builds.

Test Plan: build fbcode

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5139
2012-09-04 16:33:49 -07:00
Dhruba Borthakur
94208a7881 Benchmark with both reads and writes at the same time.
Summary:
This patch enables the db_bench benchmark to issue both random reads and random writes at the same time. This options can be trigged via
./db_bench --benchmarks=readrandomwriterandom

The default percetage of reads is 90.

One can change the percentage of reads by specifying the --readwritepercent.
./db_bench --benchmarks=readrandomwriterandom=50

This is a feature request from Jeffro asking for leveldb performance with a 90:10 read:write ratio.

Test Plan: run on test machine.

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5067
2012-09-04 12:06:26 -07:00
Dhruba Borthakur
8bab05687e Release 1.5.0.fb.
Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-08-29 15:29:30 -07:00