Hello and thanks for RocksDB,
 
When log_write_bench is run with the -bytes_per_sync option, the option does not influence any *sync* behaviour.
 
> strace -e trace=write,sync_file_range ./log_write_bench -record_interval 0 -record_size 1048576 -num_records 11 -bytes_per_sync 2097152 2>&1 | egrep '^(sync|write.*XXXX)'
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
 
I suspect that this is because the bytes_per_sync option now needs to be using a `WritableFileWriter` and not a `WritableFile`.
 
With the diff below applied, it changes to:
 
> strace -e trace=write,sync_file_range ./log_write_bench -record_interval 0 -record_size 1048576 -num_records 11 -bytes_per_sync 2097152 2>&1 | egrep '^(sync|write.*XXXX)'
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
sync_file_range(0x3, 0, 0x200000, 0x2)  = 0
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
sync_file_range(0x3, 0x200000, 0x200000, 0x2) = 0
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
sync_file_range(0x3, 0x400000, 0x200000, 0x2) = 0
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
sync_file_range(0x3, 0x600000, 0x200000, 0x2) = 0
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 1048576) = 1048576
sync_file_range(0x3, 0x800000, 0x200000, 0x2) = 0
 
( Note that the first 1MB is not synced as mentioned in util/file_reader_writer.cc::WritableFileWriter::Flush() )
 
This diff also includes the fix from https://github.com/facebook/rocksdb/pull/1373
 
> diff -du util/log_write_bench.cc.orig util/log_write_bench.cc
--- util/log_write_bench.cc.orig        2016-10-04 12:06:29.115122580 -0400
+++ util/log_write_bench.cc     2016-10-05 07:24:09.677037576 -0400
@@ -14,6 +14,7 @@
 #include <gflags/gflags.h>

 #include "rocksdb/env.h"
+#include "util/file_reader_writer.h"
 #include "util/histogram.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
@@ -38,19 +39,21 @@
   env_options.bytes_per_sync = FLAGS_bytes_per_sync;
   unique_ptr<WritableFile> file;
   env->NewWritableFile(file_name, &file, env_options);
+  unique_ptr<WritableFileWriter> writer;
+  writer.reset(new WritableFileWriter(std::move(file), env_options));

   std::string record;
-  record.assign('X', FLAGS_record_size);
+  record.assign(FLAGS_record_size, 'X');

   HistogramImpl hist;

   uint64_t start_time = env->NowMicros();
   for (int i = 0; i < FLAGS_num_records; i++) {
     uint64_t start_nanos = env->NowNanos();
-    file->Append(record);
-    file->Flush();
+    writer->Append(record);
+    writer->Flush();
     if (FLAGS_enable_sync) {
-      file->Sync();
+      writer->Sync(false);
     }
     hist.Add(env->NowNanos() - start_nanos);

Summary: makes Transaction::GetState() a const function.

Test Plan: compiles.

Reviewers: mung

Reviewed By: mung

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D64929

Summary:
1) The previous solution for Prev() prefix support is not clean.
Since I add api SeekForPrev(), now the Prev() can be symmetric to Next().
and we do not need SeekToLast() to be called in Prev() any more.

Also, Next() will Seek(prefix_seek_key_) to solve the problem of possible inconsistency between db_iter and merge_iter when
there is merge_operator. And prefix_seek_key is only refreshed when change direction to forward.

2) This diff also solves the bug of Iterator::SeekToLast() with iterate_upper_bound_ with prefix extractor.

add test cases for the above two cases.

There are some tests for the SeekToLast() in Prev(), I will clean them later.

Test Plan: make all check

Reviewers: IslamAbdelRahman, andrewkr, yiwu, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D63933

Summary: Adding several missing block cache tickers.

Test Plan:
  make all check

Reviewers: IslamAbdelRahman, yhchiang, lightmark

Reviewed By: lightmark

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D64881

Summary: A convience method to atomically get and reset ticker count. I'm wanting to use it to have a thin wrapper to the statistics object to export ticker counts to ODS for LogDevice (since they don't even use fb303).

Test Plan:
test in LogDevice shadow cluster.
https://fburl.com/461868822

Reviewers: andrewkr, yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D64869

Signed-off-by: NBassam Tabbara <bassam.tabbara@quantum.com>

Summary:
We always run consistency checks when compiling in debug mode
allow users to set Options::force_consistency_checks to true to be able to run such checks even when compiling in release mode

Test Plan:
make check -j64
make release

Reviewers: lightmark, sdong, yiwu

Reviewed By: yiwu

Subscribers: hermanlee4, andrewkr, yoshinorim, jkedgar, dhruba

Differential Revision: https://reviews.facebook.net/D64701

Summary:
I saw this exception thrown because sometimes we may resize with -ve value
if we have empty max_bytes_for_level_multiplier_additional vector

Test Plan: run the tests

Reviewers: yiwu

Reviewed By: yiwu

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D64791

Summary: Modifies the lock info export test to test multiple column families after I was experiencing a bug while developing the MyRocks front-end for this.

Test Plan: is test.

Reviewers: mung

Reviewed By: mung

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D64725

This reverts commit ab01da54.

Summary:
- Deprecated RateLimiterConfig and GenericRateLimiterConfig
- Introduced RateLimiter

It is now possible to use all C++ related methods also in RocksJava.
A noteable method is setBytesPerSecond which can change the allowed
number of bytes per second at runtime.

Test Plan:
make rocksdbjava
make jtest

Reviewers: adamretter, yhchiang, ankgup87

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D35715

Summary:
This exposes a transactions state through a public api rather than through a public member variable. I also do some name refactoring.
ExecutionStatus => TransactionState
exec_status_ => trx_state_

Test Plan: It compiles and transaction_test passes.

Reviewers: IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, mung, dhruba, sdong

Differential Revision: https://reviews.facebook.net/D64689

Summary:
When constructing a write batch a client may now call MarkWalTerminationPoint() on that batch. No batch operations after this call will be added written to the WAL but will still be inserted into the Memtable. This facility is used to remove one of the three WriteImpl calls in 2PC transactions. This produces a ~1% perf improvement.

```
RocksDB - unoptimized 2pc, sync_binlog=1, disable_2pc=off
INFO 2016-08-31 14:30:38,814 [main]: REQUEST PHASE COMPLETED. 75000000 requests done in 2619 seconds. Requests/second = 28628

RocksDB - optimized 2pc , sync_binlog=1, disable_2pc=off
INFO 2016-08-31 16:26:59,442 [main]: REQUEST PHASE COMPLETED. 75000000 requests done in 2581 seconds. Requests/second = 29054
```

Test Plan: Two unit tests added.

Reviewers: sdong, yiwu, IslamAbdelRahman

Reviewed By: yiwu

Subscribers: hermanlee4, dhruba, andrewkr

Differential Revision: https://reviews.facebook.net/D64599

Hello and thank you for RocksDB,
 
I noticed when using log_write_bench that writes were always 88 bytes:
 
> strace -e trace=write ./log_write_bench -num_records 2 2>&1 | head -n 2
write(3, "\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371"..., 88) = 88
write(3, "\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371\371"..., 88) = 88

> strace -e trace=write ./log_write_bench -record_size 4096 -num_records 2 2>&1 | head -n 2
write(3, "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 88) = 88
write(3, "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 88) = 88
 
I think this should be:

<<    record.assign('X', FLAGS_record_size);
>>    record.assign(FLAGS_record_size, 'X');

So fill and not buffer. Otherwise I always see writes of size 88 (the decimal value for chr "X").

string& assign (const char* s, size_t n);
buffer - Copies the first n characters from the array of characters pointed by s.

string& assign (size_t n, char c);
fill   - Replaces the current value by n consecutive copies of character c.

perl -le 'print ord "X"'
88
 
With the change:
 
> strace -e trace=write ./log_write_bench -record_size 4096 -num_records 2 2>&1 | head -n 2
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 4096) = 4096
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 4096) = 4096
 
> strace -e trace=write ./log_write_bench -num_records 2 2>&1 | head -n 2
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 249) = 249
write(3, "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"..., 249) = 249

Thanks.

https://github.com/facebook/rocksdb/commit/01c27be5fb42524c5052b4b4a23e05501e1d1421
https://reviews.facebook.net/D16239

* env_mirror: fix leak from LockFile
Signed-off-by: NSage Weil <sage@redhat.com>

* env_mirror: instruct EnvMirror whether mirrored Envs should be destroyed

The lifecycle rules for Env are frustrating and undocumented.  Notably,
Env::Default() should *not* be freed, but any Env instances we created
should be.

Explicitly instruct EnvMirror whether to clean up child Env instances.
Default to false so that we do not affect existing callers.
Signed-off-by: NSage Weil <sage@redhat.com>

Added rocksdb_options_set_memtable_prefix_bloom_size_ratio function implemented in c.cc but not exported via c.h

Blog sidebar shows all the posts, not just the most recent ones.

.... if they do not exist

Now the author associated with fbid will be shown at top of blog post

Summary:
- Update SstFileWriter to include a property for a global sequence number in the SST file `rocksdb.external_sst_file.global_seqno`
- Update TableProperties to be aware of the offset of each property in the file
- Update BlockBasedTableReader and Block to be able to honor the sequence number in `rocksdb.external_sst_file.global_seqno` property and use it to overwrite all sequence number in the file

Something worth mentioning is that we don't update the seqno in the index block since and when doing a binary search, the reason for that is that it's guaranteed that SST files with global seqno will have only one user_key and each key will have seqno=0 encoded in it, This mean that this key is greater than any other key with seqno> 0. That mean that we can actually keep the current logic for these blocks

Test Plan: unit tests

Reviewers: andrewkr, yhchiang, yiwu, sdong

Reviewed By: sdong

Subscribers: hcz, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D62523

Summary:
Currently there is no mechanism to create persistent cache from
headers. Adding a simple factory method to create a simple persistent cache with
default or NVM optimized settings.

note: Any idea to test this factory is appreciated.

Test Plan: None

Reviewers: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D64527

Summary:
This diff does 3 things:

Expose TransactionID so that we can identify transactions when we retrieve locking and lock wait information. This is exposed as `Transaction::GetID`.

Expose lock state information by locking all stripes in all column families and copying their contents to a data structure. This is exposed as `TransactionDB::GetLockStatusData`.

Adds support for tracking the transaction and the key being waited on, and exposes this as `Transaction::GetWaitingTxn`.

Test Plan: unit tests

Reviewers: horuff, sdong

Reviewed By: sdong

Subscribers: vasilep, hermanlee4, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D64413

Summary:
- Store range tombstones in a separate MemTableRep instantiated with ColumnFamilyOptions::memtable_factory
- MemTable::NewRangeTombstoneIterator() returns a MemTableIterator over the separate MemTableRep
- Part of the read path is not implemented yet (i.e., MemTable::Get())

Test Plan: see unit tests

Reviewers: wanning

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62217

Use size hint for HashMap in multiGet. Similar to https://github.com/facebook/rocksdb/pull/1344 (#1367)

Add Java API for SstFileWriter. Closes https://github.com/facebook/rocksdb/issues/1248

Summary: delete unused variable

Test Plan: make check

Reviewers: sdong, andrewkr, IslamAbdelRahman, tianx

Reviewed By: tianx

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D64509