Summary:
The compaction process deletes a large number of files. This takes
quite a bit of time and is best done outside the mutex lock.

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

Summary:
Leveldb code already calculates checksums for each block. There
is no need to generate checksums inside zlib. This patch switches-off checksum generation/checking in zlib library.

(The Inno support for zlib uses windowsBits=14 as well.)

pfabricator marks this file as binary. But here is the diff

diff --git a/port/port_posix.h b/port/port_posix.h
index 86a0927..db4e0b8 100644
--- a/port/port_posix.h
+++ b/port/port_posix.h
@@ -163,7 +163,7 @@ inline bool Snappy_Uncompress(const char* input, size_t length,
 }

 inline bool Zlib_Compress(const char* input, size_t length,
-    ::std::string* output, int windowBits = 15, int level = -1,
+    ::std::string* output, int windowBits = -14, int level = -1,
      int strategy = 0) {
 #ifdef ZLIB
   // The memLevel parameter specifies how much memory should be allocated for
@@ -223,7 +223,7 @@ inline bool Zlib_Compress(const char* input, size_t length,
 }

 inline char* Zlib_Uncompress(const char* input_data, size_t input_length,
-    int* decompress_size, int windowBits = 15) {
+    int* decompress_size, int windowBits = -14) {
 #ifdef ZLIB
   z_stream _stream;
   memset(&_stream, 0, sizeof(z_stream));

Test Plan: run db_bench with zlib compression.

Reviewers: heyongqiang, MarkCallaghan

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D6105

Summary:
The parameter delete_obsolete_files_period_micros controls the
periodicity of deleting obsolete files. db_bench was reading in
this parameter intoa local variable called 'l' but was incorrectly
using another local variable called 'n' while setting it in the
db.options data structure.
This patch also logs the value of delete_obsolete_files_period_micros
in the LOG file at db startup time.

I am hoping that this will improve the overall write throughput drastically.

Test Plan: run db_bench

Reviewers: MarkCallaghan, heyongqiang

Reviewed By: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D6099

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

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

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

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

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

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

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

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

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

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

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

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

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

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

Summary: Implement assocDelete.

Test Plan: unit test attached

Reviewers: heyongqiang

Reviewed By: heyongqiang

CC: MarkCallaghan

Differential Revision: https://reviews.facebook.net/D5721

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

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

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

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

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

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

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

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

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

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

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

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

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

Summary: Use correct version of jemalloc.

Test Plan: run unit tests

Reviewers: heyongqiang

Reviewed By: heyongqiang

Differential Revision: https://reviews.facebook.net/D5487

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

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

Summary:

Test Plan:

Reviewers:

CC:

Task ID: #

Blame Rev:

Summary: as subject

Test Plan: build

Reviewers: dhruba

Reviewed By: dhruba

Differential Revision: https://reviews.facebook.net/D5475

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

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

Summary: as subject

Test Plan: build

Reviewers: dhruba

Differential Revision: https://reviews.facebook.net/D5469

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