Commit Graph

22 Commits

Author SHA1 Message Date
Siying Dong
f35574a16d RangeSync() should work with ROCKSDB_FALLOCATE_PRESENT not set
Summary: Closes https://github.com/facebook/rocksdb/pull/1824

Differential Revision: D4493862

Pulled By: siying

fbshipit-source-id: c168446
2017-02-23 11:34:45 -08:00
Yi Wu
62a1c55418 Remove fadvise with direct IO read
Summary:
Remove the logic since we don't use buffer cache with direct IO. Resolve
read regression we currently have.
Closes https://github.com/facebook/rocksdb/pull/1782

Differential Revision: D4430408

Pulled By: yiwu-arbug

fbshipit-source-id: 5557bba
2017-01-18 15:51:54 -08:00
Aaron Gao
3e6899d116 change UseDirectIO() to use_direct_io()
Summary:
also change variable name `direct_io_` to `use_direct_io_` in WritableFile to make it consistent with read path.
Closes https://github.com/facebook/rocksdb/pull/1770

Differential Revision: D4416435

Pulled By: lightmark

fbshipit-source-id: 4143c53
2017-01-13 12:09:15 -08:00
Aaron Gao
d4e07a8459 fix warning of unused direct io helper functions
Summary:
add build guard
Closes https://github.com/facebook/rocksdb/pull/1771

Differential Revision: D4410779

Pulled By: siying

fbshipit-source-id: 3796c30
2017-01-12 12:39:14 -08:00
Aaron Gao
dc2584eea0 direct reads refactor
Summary:
direct IO reads refactoring
remove unnecessary classes and unified interfaces
tested with db_bench

need more change for options and ON/OFF for different files.
Since disabled is default, it should be fine now
Closes https://github.com/facebook/rocksdb/pull/1636

Differential Revision: D4307189

Pulled By: lightmark

fbshipit-source-id: 6991e22
2017-01-11 16:54:12 -08:00
Anirban Rahut
62384ebe9c Guarding extra fallocate call with TRAVIS because its not working pro…
Summary:
…perly on travis

 There is some old code in PosixWritableFile::Close(), which
truncates the file to the measured size and then does an extra fallocate
with KEEP_SIZE. This is commented as a failsafe because in some
cases ftruncate doesn't do the right job (I don't know of an instance of
this btw). However doing an fallocate with KEEP_SIZE should not increase
the file size. However on Travis Worker which is Docker (likely AUFS )
its not working. There are comments on web that show that the AUFS
author had initially not implemented fallocate, and then did it later.
So not sure what is the quality of the implementation.
Closes https://github.com/facebook/rocksdb/pull/1765

Differential Revision: D4401340

Pulled By: anirbanr-fb

fbshipit-source-id: e2d8100
2017-01-11 14:24:13 -08:00
Aaron Gao
972f96b3fb direct io write support
Summary:
rocksdb direct io support

```
[gzh@dev11575.prn2 ~/rocksdb] ./db_bench -benchmarks=fillseq --num=1000000
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
RocksDB:    version 5.0
Date:       Wed Nov 23 13:17:43 2016
CPU:        40 * Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz
CPUCache:   25600 KB
Keys:       16 bytes each
Values:     100 bytes each (50 bytes after compression)
Entries:    1000000
Prefix:    0 bytes
Keys per prefix:    0
RawSize:    110.6 MB (estimated)
FileSize:   62.9 MB (estimated)
Write rate: 0 bytes/second
Compression: Snappy
Memtablerep: skip_list
Perf Level: 1
WARNING: Assertions are enabled; benchmarks unnecessarily slow
------------------------------------------------
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
DB path: [/tmp/rocksdbtest-112628/dbbench]
fillseq      :       4.393 micros/op 227639 ops/sec;   25.2 MB/s

[gzh@dev11575.prn2 ~/roc
Closes https://github.com/facebook/rocksdb/pull/1564

Differential Revision: D4241093

Pulled By: lightmark

fbshipit-source-id: 98c29e3
2016-12-22 13:09:19 -08:00
Siying Dong
73843aa636 Direct I/O Reads Handle the last sector correctly.
Summary:
Currently, in the Direct I/O read mode, the last sector of the file, if not full, is not handled correctly. If the return value of pread is not multiplier of kSectorSize, we still go ahead and continue reading, even if the buffer is not aligned. With the commit, if the return value is not multiplier of kSectorSize, and all but the last sector has been read, we simply return.
Closes https://github.com/facebook/rocksdb/pull/1550

Differential Revision: D4209609

Pulled By: lightmark

fbshipit-source-id: cb0b439
2016-11-18 19:24:13 -08:00
Maysam Yabandeh
9d60151b04 Implement PositionedAppend for PosixWritableFile
Summary:
This patch clarifies the contract of PositionedAppend with some unit
tests and also implements it for PosixWritableFile. (Tasks: 14524071)
Closes https://github.com/facebook/rocksdb/pull/1514

Differential Revision: D4204907

Pulled By: maysamyabandeh

fbshipit-source-id: 06eabd2
2016-11-18 17:24:13 -08:00
Islam AbdelRahman
ba65c816bb Support POSIX RandomRWFile
Summary:
Add Env::RandomRWFile in env.h and implement it for POSIX
RandomRWFile is a file that allow us to read from / write to random offsets in the file

I will implement it for other Envs later after finishing the whole task for AddFile()

Test Plan: unit tests

Reviewers: andrewkr, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D62433
2016-09-13 12:08:22 -07:00
krad
c116b47804 Persistent Read Cache (part 6) Block Cache Tier Implementation
Summary:
The patch is a continuation of part 5. It glues the abstraction for
file layout and metadata, and flush out the implementation of the API. It
adds unit tests for the implementation.

Test Plan: Run unit tests

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D57549
2016-08-01 14:15:14 -07:00
krad
f89caa127b Direct IO capability for RocksDB
Summary:
This patch adds direct IO capability to RocksDB Env.

The direct IO capability is required for persistent cache since NVM is best
accessed as 4K direct IO. SSDs can leverage direct IO for reading.

Direct IO requires the offset and size be sector size aligned, and memory to
be kernel page aligned. Since neither RocksDB/Persistent read cache data
layout is aligned to sector size, the code can accommodate reading unaligned IO size
(or unaligned memory) at the cost of an alloc/copy.

The write code path expects the size and memory to be aligned.

Test Plan: Run RocksDB unit tests

Reviewers: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D57393
2016-05-23 12:27:27 -07:00
krad
bb98ca3c80 Implement GetUniqueId for Mac
Summary:
Persistent read cache relies on the accuracy of the GetUniqueIdFromFile
to generate a unique key for a given block of data. Currently we don't have an
implementation for Mac.

This patch adds an implementation.

Test Plan: Run unit tests

Reviewers: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D58413
2016-05-19 16:34:31 -07:00
krad
a08c8c851a Added PersistentCache abstraction
Summary:
Added a new abstraction to cache page to RocksDB designed for the read
cache use.

RocksDB current block cache is more of an object cache. For the persistent read cache
project, what we need is a page cache equivalent. This changes adds a cache
abstraction to RocksDB to cache pages called PersistentCache. PersistentCache can cache
uncompressed pages or raw pages (content as in filesystem). The user can
choose to operate PersistentCache either in  COMPRESSED or UNCOMPRESSED mode.

Blame Rev:

Test Plan: Run unit tests

Reviewers: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D55707
2016-05-15 22:17:18 -07:00
Baraa Hamodi
21e95811d1 Updated all copyright headers to the new format. 2016-02-09 15:12:00 -08:00
Dmitri Smirnov
5270b33bd3 Make use of portable uint64_t type to make possible file access
in 64-bit.

  Currently, a signed off_t type is being used for the following
  interfaces for both offset and the length in bytes:
  * `Allocate`
  * `RangeSync`

  On Linux `off_t` is automatically either 32 or 64-bit depending on
  the platform. On Windows it is always a 32-bit signed long which
  limits file access and in particular space pre-allocation
  to effectively 2 Gb.

  Proposal is to replace off_t with uint64_t as a portable type
  always access files with 64-bit interfaces.

  May need to modify posix code but lack resources to test it.
2015-11-10 17:03:42 -08:00
sdong
47414c6cd6 Move include/posix/io_posix.h to util/io_posix.h
Summary: include/posix/io_posix.h is not a public API. Although include/posix/ is not a public header directory, it is confusing to put non-public headers to under include/. Move it to util/ to be clearer.

Test Plan: Run all tests

Reviewers: rven, IslamAbdelRahman, anthony, kradhakrishnan, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D49611
2015-10-28 12:15:51 -07:00
sdong
2889df84cb Revert "Avoid to reply on ROCKSDB_FALLOCATE_PRESENT in include/posix/io_posix.h"
This reverts commit c37223c083.
2015-10-28 11:55:20 -07:00
sdong
c37223c083 Avoid to reply on ROCKSDB_FALLOCATE_PRESENT in include/posix/io_posix.h
Summary: include/posix/io_posix.h should not depend on ROCKSDB_FALLOCATE_PRESENT. Remove it.

Test Plan: Build it with both of ROCKSDB_FALLOCATE_PRESENT defined and not defined.

Reviewers: rven, yhchiang, anthony, kradhakrishnan, IslamAbdelRahman, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D49563
2015-10-27 16:48:40 -07:00
sdong
d6219e4d9b Mac build break caused by include/posix/io_posix.h not declearing errno,
Summary: Mac build breaks as include/posix/io_posix.h doesn't include errno. Move the exact function declaration to io_posix.cc

Test Plan: Run all test. Will run on Mac

Reviewers: rven, anthony, yhchiang, IslamAbdelRahman, igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D49551
2015-10-27 14:16:19 -07:00
sdong
44d4057d78 Avoid some includes in io_posix.h
Summary: IO Posix depends on too many .h files. Move most of them to .cc files.

Test Plan: make all

Reviewers: anthony, rven, IslamAbdelRahman, yhchiang, kradhakrishnan, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D49479
2015-10-26 17:00:25 -07:00
Javier González
6e6dd5f6f9 Split posix storage backend into Env and library
Summary: This patch splits the posix storage backend into Env and
the actual *File implementations. The motivation is to allow other Envs
to use posix as a library. This enables a storage backend different from
posix to split its secondary storage between a normal file system
partition managed by posix, and it own media.

Test Plan: No new functionality is added to posix Env or the library,
thus the current tests should suffice.
2015-10-22 17:31:31 +02:00