Commit Graph

3671 Commits

Author SHA1 Message Date
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
Dhruba Borthakur
f0b1654ff2 Add libhdfs.a to the build process.
Fix compilcation error for hdfs build.

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:
2012-08-29 15:21:56 -07:00
Dhruba Borthakur
fe93631678 Clean up compiler warnings generated by -Wall option.
Summary:
Clean up compiler warnings generated by -Wall option.
make clean all OPT=-Wall

This is a pre-requisite before making a new release.

Test Plan: compile and run unit tests

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5019
2012-08-29 14:24:51 -07:00
Dhruba Borthakur
e5fe80e4e3 The sharding of the block cache is limited to 2*20 pieces.
Summary:
The numbers of shards that the block cache is divided into is
configurable. However, if the user specifies that he/she wants
the block cache to be divided into more than 2**20 pieces, then
the system will rey to allocate a huge array of that size) that
could fail.

It is better to limit the sharding of the block cache to an
upper bound. The default sharding is 16 shards (i.e. 2**4)
and the maximum is now 2 million shards (i.e. 2**20).

Also, fixed a bug with the LRUCache where the numShardBits
should be a private member of the LRUCache object rather than
a static variable.

Test Plan:
run db_bench with --cache_numshardbits=64.

Task ID: #

Blame Rev:

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5013
2012-08-29 12:17:59 -07:00
heyongqiang
a4f9b8b49e merge 1.5
Summary:

as subject

Test Plan:

db_test table_test

Reviewers: dhruba
2012-08-28 11:43:33 -07:00
heyongqiang
6fee5a74f5 Do not spin in a tight loop attempting compactions if there is a compaction error
Summary: as subject. ported the change from google code leveldb 1.5

Test Plan: run db_test

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D4839
2012-08-28 11:43:33 -07:00
heyongqiang
935fdd030b fix filename_test
Summary: as subject

Test Plan: run filename_test

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D4965
2012-08-28 11:42:42 -07:00
heyongqiang
690bf88682 in db_stats_logger.cc, hold mutex_ while accessing versions_
Summary:

as subject

Test Plan:db_test

Reviewers: dhruba
2012-08-28 11:29:30 -07:00
heyongqiang
d3759ca121 fix db_test error with scribe logger turned on
Summary: as subject

Test Plan: db_test

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D4929
2012-08-28 11:22:58 -07:00
Dhruba Borthakur
fc20273e73 Introduce a new method Env->Fsync() that issues fsync (instead of fdatasync).
Summary:
Introduce a new method Env->Fsync() that issues fsync (instead of fdatasync).
This is needed for data durability when running on ext3 filesystems.
Added options to the benchmark db_bench to generate performance numbers
with either fsync or fdatasync enabled.

Cleaned up Makefile to build leveldb_shell only when building the thrift
leveldb server.

Test Plan: build and run benchmark

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D4911
2012-08-27 21:24:17 -07:00
heyongqiang
e675351ad7 number to read is not resepected
Summary: as subject

Test Plan: sst_dump --command=scan --file=

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D4887
2012-08-24 18:29:40 -07:00
heyongqiang
7cd644021e Merge branch 'master' of https://github.com/facebook/leveldb 2012-08-24 15:22:47 -07:00
heyongqiang
1de83cc2ac add more logs
Summary:
as subject

add a tool to read sst file

as subject.

./sst_reader --command=check --file=
./sst_reader --command=scan --file=

Test Plan:
db_test

run this command

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D4881
2012-08-24 15:20:49 -07:00
heyongqiang
64219276f0 sst_dump tool
Summary:
as subject

add a tool to read sst file

as subject.

./sst_reader --command=check --file=
./sst_reader --command=scan --file=

Test Plan:
db_test

run this command

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D4881
2012-08-24 15:18:43 -07:00
heyongqiang
1c99b0a6b3 add more logs
Summary:

as subject

Test Plan:db_test

Reviewers: dhruba
2012-08-24 15:18:43 -07:00
Dhruba Borthakur
5d96f290b3 Record the version of the source repository that was used to build the leveldb library.
Summary: Record the version of the source that we are compiling. We keep a record of the git revision in util/version.cc. This source file is then built as a regular source file as part of the compilation process. One can run "strings executable_filename | grep _build_" to find the version of the source that we used to build the executable file.

Test Plan: none

Differential Revision: https://reviews.facebook.net/D4785
2012-08-24 15:18:43 -07:00
Dhruba Borthakur
d41316bc0f Prevent concurrent multiple opens of leveldb database.
Summary:
The fcntl call cannot detect lock conflicts when invoked multiple times
from the same thread.
Use a static lockedFile Set to record the paths that are locked.
A lockfile request checks to see if htis filename already exists in
lockedFiles, if so, then it triggers an error. Otherwise, it inserts
the filename in the lockedFiles Set.
A unlock file request verifies that the filename is in the lockedFiles
set and removes it from lockedFiles set.

Test Plan: unit test attached

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D4755
2012-08-24 15:18:01 -07:00
Dhruba Borthakur
f3ee54526f Utility to dump manifest contents.
Summary:
./manifest_dump --file=/tmp/dbbench/MANIFEST-000002

Output looks like

manifest_file_number 30 next_file_number 31 last_sequence 388082 log_number 28  prev_log_number 0
--- level 0 ---
--- level 1 ---
--- level 2 ---
 5:3244155['0000000000000000' @ 1 : 1 .. '0000000000028220' @ 28221 : 1]
 7:3244177['0000000000028221' @ 28222 : 1 .. '0000000000056441' @ 56442 : 1]
 9:3244156['0000000000056442' @ 56443 : 1 .. '0000000000084662' @ 84663 : 1]
 11:3244178['0000000000084663' @ 84664 : 1 .. '0000000000112883' @ 112884 : 1]
 13:3244158['0000000000112884' @ 112885 : 1 .. '0000000000141104' @ 141105 : 1]
 15:3244176['0000000000141105' @ 141106 : 1 .. '0000000000169325' @ 169326 : 1]
 17:3244156['0000000000169326' @ 169327 : 1 .. '0000000000197546' @ 197547 : 1]
 19:3244178['0000000000197547' @ 197548 : 1 .. '0000000000225767' @ 225768 : 1]
 21:3244155['0000000000225768' @ 225769 : 1 .. '0000000000253988' @ 253989 : 1]
 23:3244179['0000000000253989' @ 253990 : 1 .. '0000000000282209' @ 282210 : 1]
 25:3244157['0000000000282210' @ 282211 : 1 .. '0000000000310430' @ 310431 : 1]
 27:3244176['0000000000310431' @ 310432 : 1 .. '0000000000338651' @ 338652 : 1]
 29:3244156['0000000000338652' @ 338653 : 1 .. '0000000000366872' @ 366873 : 1]
--- level 3 ---
--- level 4 ---
--- level 5 ---
--- level 6 ---

Test Plan: run on test directory created by dbbench

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: hustliubo

Differential Revision: https://reviews.facebook.net/D4743
2012-08-24 15:17:09 -07:00
heyongqiang
e3bf8f0a96 Merge branch 'master' of https://github.com/facebook/leveldb 2012-08-24 13:09:48 -07:00
bol
89f0c25360 Merge remote-tracking branch 'origin/master' into task1181723
Conflicts:
	Makefile
2012-08-24 03:34:55 -07:00
Dhruba Borthakur
2b443ba887 Titile: a command line shell to read/write data from a leveldb thrift server
Summary: implemented a commond line shell to talk with leveldb thrift server, which is based on state pattern and can be easily extended.

Test Plan: build and run

Reviewers: dhruba, zshao, heyongqiang

Differential Revision: https://reviews.facebook.net/D4713
2012-08-23 09:41:05 -07:00
Dhruba Borthakur
e5a7c8e580 Log the open-options to the LOG.
Summary: Log the open-options to the LOG. Use options_ instead of options because SanitizeOptions could modify the max_file_open limit.

Test Plan: num db_bench

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D4833
2012-08-22 12:22:12 -07:00