Commit Graph

2642 Commits

Author SHA1 Message Date
Shu Zhang
756c5924e6 Allow adding external v1 sst file with no global seqno support
Summary:
This is a follow up fix for https://github.com/facebook/rocksdb/pull/1783. After it, we should be able to ingest external v1 sst files with no global seqno field.
Closes https://github.com/facebook/rocksdb/pull/1874

Differential Revision: D4576194

Pulled By: IslamAbdelRahman

fbshipit-source-id: 5b34a3e
2017-02-16 17:09:12 -08:00
Aaron Gao
db2b4eb50e avoid direct io in rocksdb_lite
Summary:
fix lite bugs
disable direct io in lite mode
Closes https://github.com/facebook/rocksdb/pull/1870

Differential Revision: D4559866

Pulled By: yiwu-arbug

fbshipit-source-id: 3761c51
2017-02-16 10:39:13 -08:00
Andrew Kryczka
43e9f01c20 Fix repair_test on ROCKSDB_LITE
Summary:
RepairDB isn't included in rocksdb lite, so don't test it.
Closes https://github.com/facebook/rocksdb/pull/1873

Differential Revision: D4565094

Pulled By: ajkr

fbshipit-source-id: 8cc0898
2017-02-15 11:24:12 -08:00
Xiaofei Du
7106a994fe Use monotonic time points in write_controller.cc and rate_limiter.cc
Summary:
NowMicros() provides non-monotonic time. When wall clock is
synchronized or changed, the non-monotonicity time points will affect write rate
controllers. This patch changes write_controller.cc and rate_limiter.cc to use
monotonic time points.
Closes https://github.com/facebook/rocksdb/pull/1865

Differential Revision: D4561732

Pulled By: siying

fbshipit-source-id: 95ece62
2017-02-14 18:24:24 -08:00
Yi Wu
c2247dc1c7 Make DBImpl::has_unpersisted_data_ atomic
Summary:
Seems to me `has_unpersisted_data_` is read from read thread and write
from write thread concurrently without synchronization. Making it an
atomic.

I update the logic not because seeing any problem with it, but it just
feel confusing.
Closes https://github.com/facebook/rocksdb/pull/1869

Differential Revision: D4555837

Pulled By: yiwu-arbug

fbshipit-source-id: eff2ab8
2017-02-13 18:54:13 -08:00
Sagar Vemuri
eb912a927e Remove disableDataSync option
Summary:
Remove disableDataSync, and another similarly named disable_data_sync options.
This is being done to simplify options, and also because the performance gains of this feature can be achieved by other methods.
Closes https://github.com/facebook/rocksdb/pull/1859

Differential Revision: D4541292

Pulled By: sagar0

fbshipit-source-id: 5b3a6ca
2017-02-13 11:09:13 -08:00
Dmitri Smirnov
a5adda0642 Fix repair issues
Summary:
Record the first parsed sequence number as the minimum
  so we can find the true minimum otherwise everything is larger than zero.
  Fix the comparator name comparision.
Closes https://github.com/facebook/rocksdb/pull/1858

Differential Revision: D4544365

Pulled By: ajkr

fbshipit-source-id: 439cbc2
2017-02-10 10:54:12 -08:00
Andrew Kryczka
b48e4778be Consolidate file cutting logic in compaction loop
Summary:
It was really annoying to have two places (top and bottom of compaction loop) where we cut output files. I had bugs in both DeleteRange and dictionary compression due to updating only one of the two. This diff consolidates the file-cutting logic to the bottom of the compaction loop.

Keep in mind that my goal with input_status is to be consistent with the past behavior, even though I'm not sure it's ideal.
Closes https://github.com/facebook/rocksdb/pull/1832

Differential Revision: D4503038

Pulled By: ajkr

fbshipit-source-id: 7da5213
2017-02-08 16:24:17 -08:00
Maysam Yabandeh
c4a37dcb44 Print the missed last layer in cfstats
Summary:
Printing compaction stats used to operate on two variable:
number_levels_: for printing the layer
num_levels_to_check: for updating the compaction score

After this commit: 361010d447 these two are mixed up and as a result the last layer might not be printed out: https://fb.facebook.com/groups/rocksdb.internal/permalink/1315716625143616/

number_levels_ was used to decide which layers to print: 672300f47f/db/internal_stats.cc (L753) but after the patch it is based on the return value of DumpCFMapStats 361010d447/db/internal_stats.cc (L929) which returns num_levels_to_check: 361010d447/db/internal_stats.cc (L917)
Closes https://github.com/facebook/rocksdb/pull/1853

Differential Revision: D4529280

Pulled By: maysamyabandeh

fbshipit-source-id: 3fd9448
2017-02-08 10:39:15 -08:00
Maysam Yabandeh
69d5262c81 Two-level Indexes
Summary:
Partition Index blocks and use a Partition-index as a 2nd level index.

The two-level index can be used by setting
BlockBasedTableOptions::kTwoLevelIndexSearch as the index type and
configuring BlockBasedTableOptions::index_per_partition

t15539501
Closes https://github.com/facebook/rocksdb/pull/1814

Differential Revision: D4473535

Pulled By: maysamyabandeh

fbshipit-source-id: bffb87e
2017-02-06 16:39:12 -08:00
Dmitri Smirnov
0a4cdde50a Windows thread
Summary:
introduce new methods into a public threadpool interface,
- allow submission of std::functions as they allow greater flexibility.
- add Joining methods to the implementation to join scheduled and submitted jobs with
  an option to cancel jobs that did not start executing.
- Remove ugly `#ifdefs` between pthread and std implementation, make it uniform.
- introduce pimpl for a drop in replacement of the implementation
- Introduce rocksdb::port::Thread typedef which is a replacement for std::thread.  On Posix Thread defaults as before std::thread.
- Implement WindowsThread that allocates memory in a more controllable manner than windows std::thread with a replaceable implementation.
- should be no functionality changes.
Closes https://github.com/facebook/rocksdb/pull/1823

Differential Revision: D4492902

Pulled By: siying

fbshipit-source-id: c74cb11
2017-02-06 14:54:18 -08:00
Vitaliy Liptchinsky
1aaa898cf1 Adding GetApproximateMemTableStats method
Summary:
Added method that returns approx num of entries as well as size for memtables.
Closes https://github.com/facebook/rocksdb/pull/1841

Differential Revision: D4511990

Pulled By: VitaliyLi

fbshipit-source-id: 9a4576e
2017-02-06 14:54:16 -08:00
Siying Dong
036d668b19 Fix wrong result in data race case related to Get()
Summary:
In theory, Get() can get a wrong result, if it races in a special with with flush. The bug can be reproduced in DBTest2.GetRaceFlush. Fix this bug by getting snapshot after referencing the super version.
Closes https://github.com/facebook/rocksdb/pull/1816

Differential Revision: D4475958

Pulled By: siying

fbshipit-source-id: bd9e67a
2017-02-03 11:39:15 -08:00
Islam AbdelRahman
574b543f80 Rename merger.h -> merging_iterator.h
Summary:
merger.h was always a confusing name for me, simply give the file a better name
Closes https://github.com/facebook/rocksdb/pull/1836

Differential Revision: D4505357

Pulled By: IslamAbdelRahman

fbshipit-source-id: 07b28d8
2017-02-02 16:54:19 -08:00
oranagra
b96372dead improving the C wrapper
Summary:
- rocksdb_property_int (so that we don't have to parse strings)
- and rocksdb_set_options (to allow controlling options via strings)
- a few other missing options exposed
- a documentation comment fix
Closes https://github.com/facebook/rocksdb/pull/1793

Differential Revision: D4456569

Pulled By: yiwu-arbug

fbshipit-source-id: 9f1fac1
2017-01-27 17:39:16 -08:00
Siying Dong
04c4ec41d1 Change corruption_test to use 4 bits.
Summary:
In the patch which LRU cache was made use dynamic shard bits, I changed to 2 shard bits to make the test happy. Look like it is occasionally still unhappy. Change it to 4 shard bits.
Closes https://github.com/facebook/rocksdb/pull/1815

Differential Revision: D4475849

Pulled By: siying

fbshipit-source-id: 575ff00
2017-01-27 11:24:16 -08:00
Siying Dong
2d75cd40d3 NewLRUCache() to pick number of shard bits based on capacity if not given
Summary:
If the users use the NewLRUCache() without passing in the number of shard bits, instead of using hard-coded 6, we'll determine it based on capacity.
Closes https://github.com/facebook/rocksdb/pull/1584

Differential Revision: D4242517

Pulled By: siying

fbshipit-source-id: 86b0f18
2017-01-27 06:39:12 -08:00
Siying Dong
f25f1ec60b Add test DBTest2.GetRaceFlush which can expose a data race bug
Summary:
A current data race issue in Get() and Flush() can cause a Get() to return wrong results when a flush happened in the middle. Disable the test for now.
Closes https://github.com/facebook/rocksdb/pull/1813

Differential Revision: D4472310

Pulled By: siying

fbshipit-source-id: 5755ebd
2017-01-26 16:39:14 -08:00
sdong
5dad9d6d28 Avoid logs_ operation out of DB mutex
Summary:
logs_.back() is called out of DB mutex, which can cause data race. We move the access into the DB mutex protection area.
Closes https://github.com/facebook/rocksdb/pull/1774

Reviewed By: AsyncDBConnMarkedDownDBException

Differential Revision: D4417472

Pulled By: AsyncDBConnMarkedDownDBException

fbshipit-source-id: 2da1f1e
2017-01-25 15:54:13 -08:00
Islam AbdelRahman
a7b13919bf Fix CompactFiles() bug when used with CompactionFilter using SuperVersion
Summary:
GetAndRefSuperVersion() should not be called again in the same thread before ReturnAndCleanupSuperVersion() is called.

If we have a compaction filter that is using DB::Get, This will happen
```
CompactFiles() {
  GetAndRefSuperVersion() // -- first call
    ..
    CompactionFilter() {
      GetAndRefSuperVersion() // -- second call
      ReturnAndCleanupSuperVersion()
    }
    ..
  ReturnAndCleanupSuperVersion()
}
```

We solve this issue in the same way Iterator is solving it, but using GetReferencedSuperVersion()

This was discovered in https://github.com/facebook/mysql-5.6/issues/427 by alxyang
Closes https://github.com/facebook/rocksdb/pull/1803

Differential Revision: D4460155

Pulled By: IslamAbdelRahman

fbshipit-source-id: 5e54322
2017-01-25 14:09:13 -08:00
Andrew Kryczka
616a1464ea Fix DeleteRange including sentinels in output files
Summary:
when writing RangeDelAggregator::AddToBuilder, I forgot that there are sentinel tombstones in the middle of the interval map since gaps between real tombstones are represented with sentinels.

blame: #1614
Closes https://github.com/facebook/rocksdb/pull/1804

Differential Revision: D4460426

Pulled By: ajkr

fbshipit-source-id: 69444b5
2017-01-25 11:09:12 -08:00
Islam AbdelRahman
03ca2ac8a9 Remove function from DBImpl that are not used anywhere
Summary:
GetAndRefSuperVersionUnlocked
ReturnAndCleanupSuperVersionUnlocked
GetColumnFamilyHandleUnlocked

Are dead code that are not used any where
Closes https://github.com/facebook/rocksdb/pull/1802

Differential Revision: D4459948

Pulled By: IslamAbdelRahman

fbshipit-source-id: 30fa89d
2017-01-24 19:24:13 -08:00
Andrew Kryczka
b0029bc7fa Test merge op covered by range deletion in memtable
Summary:
It's a test case for #1797. Also got rid of kTypeDeletion in the conditional since we treat it the same as kTypeRangeDeletion.
Closes https://github.com/facebook/rocksdb/pull/1800

Differential Revision: D4451300

Pulled By: ajkr

fbshipit-source-id: b39dda1
2017-01-24 13:39:11 -08:00
Andrew Kryczka
d438e1ec17 Test range deletion block outlives table reader
Summary:
This test ensures RangeDelAggregator can still access blocks even if it outlives the table readers that created them (detailed description in comments).

I plan to optimize away the extra cache lookup we currently do in BlockBasedTable::NewRangeTombstoneIterator(), as it is ~5% CPU in my random read benchmark in a database with 1k tombstones. This test will help make sure nothing breaks in the process.
Closes https://github.com/facebook/rocksdb/pull/1739

Differential Revision: D4375954

Pulled By: ajkr

fbshipit-source-id: aef9357
2017-01-24 13:24:14 -08:00
Andrew Kryczka
9da4d542fe Range deletions unsupported in tailing iterator
Summary:
change the iterator status to NotSupported as soon as a range tombstone
is encountered by a ForwardIterator.
Closes https://github.com/facebook/rocksdb/pull/1593

Differential Revision: D4246294

Pulled By: ajkr

fbshipit-source-id: aef9f49
2017-01-23 13:39:12 -08:00
Hyeonseok Oh
f2b4939da4 fixed typo
Summary:
I fixed exisit -> exist
Closes https://github.com/facebook/rocksdb/pull/1799

Differential Revision: D4451466

Pulled By: yiwu-arbug

fbshipit-source-id: b447c3a
2017-01-23 12:54:13 -08:00
yinqiwen
973f1b78fd memtable: delete merge value for range deleteion
Summary: Closes https://github.com/facebook/rocksdb/pull/1797

Differential Revision: D4448004

Pulled By: ajkr

fbshipit-source-id: 3ffc27c
2017-01-23 12:24:14 -08:00
Vitaliy Liptchinsky
753ff84a3d Fix get approx size
Summary:
Fixing GetApproximateSize bug for the case of computing stats for mem tables only.
Closes https://github.com/facebook/rocksdb/pull/1795

Differential Revision: D4445507

Pulled By: IslamAbdelRahman

fbshipit-source-id: 3905846
2017-01-20 15:54:12 -08:00
Jay Lee
537da370da c: allow set savepoint to writebatch
Summary:
Allow set SavePoint to WriteBatch in C ABI.
Closes https://github.com/facebook/rocksdb/pull/1698

Differential Revision: D4378556

Pulled By: yiwu-arbug

fbshipit-source-id: afca746
2017-01-20 13:24:13 -08:00
Changli Gao
5ac97314e7 Fix std::out_of_range when DBOptions::keep_log_file_num is zero
Summary:
We should validate this option, otherwise we may see
std::out_of_range thrown at: db/db_impl.cc:1124

1123     for (unsigned int i = 0; i <= end; i++) {
1124       std::string& to_delete = old_info_log_files.at(i);
1125       std::string full_path_to_delete =
1126           (immutable_db_options_.db_log_dir.empty()
Closes https://github.com/facebook/rocksdb/pull/1722

Differential Revision: D4379495

Pulled By: yiwu-arbug

fbshipit-source-id: e136552
2017-01-20 13:24:12 -08:00
Shu Zhang
3c0852d1da Make ingest external file backward compatible
Summary: Closes https://github.com/facebook/rocksdb/pull/1783

Differential Revision: D4443463

Pulled By: IslamAbdelRahman

fbshipit-source-id: 39d21d6
2017-01-20 12:09:19 -08:00
Siying Dong
0e8dfd6062 Fix OptimizeForPointLookup()
Summary:
If users directly call OptimizeForPointLookup(), it is broken as the option isn't compatible with parallel memtable insert. Fix it by using memtable bloomo filter instead.
Closes https://github.com/facebook/rocksdb/pull/1791

Differential Revision: D4442836

Pulled By: siying

fbshipit-source-id: bf6c9cd
2017-01-20 10:54:12 -08:00
Vitaliy Liptchinsky
e840213d6e Change DB::GetApproximateSizes for more flexibility needed for MyRocks
Summary:
Added an option to GetApproximateSizes to exclude file stats, as MyRocks has those counted exactly and we need only stats from memtables.
Closes https://github.com/facebook/rocksdb/pull/1787

Differential Revision: D4441111

Pulled By: IslamAbdelRahman

fbshipit-source-id: c11f4c3
2017-01-20 09:39:11 -08:00
Yi Wu
9239103cd4 Flush job should release reference current version if sync log failed
Summary:
Fix the bug when sync log fail, FlushJob::Run() will not be execute and
reference to cfd->current() will not be release.
Closes https://github.com/facebook/rocksdb/pull/1792

Differential Revision: D4441316

Pulled By: yiwu-arbug

fbshipit-source-id: 5523e28
2017-01-19 23:09:15 -08:00
Islam AbdelRahman
da54d36a96 Disable IngestExternalFile in ReadOnly mode
Summary:
Disable IngestExternalFile() in read only mode
Closes https://github.com/facebook/rocksdb/pull/1781

Differential Revision: D4439179

Pulled By: IslamAbdelRahman

fbshipit-source-id: b7e46e7
2017-01-19 15:54:19 -08:00
Reid Horuff
5cf176ca15 Fix for 2PC causing WAL to grow too large
Summary:
Consider the following single column family scenario:
prepare in log A
commit in log B
*WAL is too large, flush all CFs to releast log A*
*CFA is on log B so we do not see CFA is depending on log A so no flush is requested*

To fix this we must also consider the log containing the prepare section when determining what log a CF is dependent on.
Closes https://github.com/facebook/rocksdb/pull/1768

Differential Revision: D4403265

Pulled By: reidHoruff

fbshipit-source-id: ce800ff
2017-01-19 15:39:12 -08:00
Andrew Kryczka
f9d18e22d2 Fix DeleteRange file boundary correctness issue with max_compaction_bytes
Summary:
Cockroachdb exposed this bug in #1778. The bug happens when a compaction's output files are ended due to exceeding max_compaction_bytes. In that case we weren't taking into account the next file's start key when deciding how far to extend the current file's max_key. This caused the non-overlapping key-range invariant to be violated.

Note this was correctly handled for the usual case of cutting compaction output, which is file size exceeding max_output_file_size. I am not sure why these are two separate code paths, but we can consider refactoring it to prevent such errors in the future.
Closes https://github.com/facebook/rocksdb/pull/1784

Differential Revision: D4430235

Pulled By: ajkr

fbshipit-source-id: 80af748
2017-01-18 11:54:22 -08:00
Islam AbdelRahman
3ce091fd73 Add KEEP_DB env var option
Summary:
When debugging tests, it's useful to preserve the DB to investigate it and check the logs
This will allow us to set KEEP_DB=1 to preserve the DB
Closes https://github.com/facebook/rocksdb/pull/1759

Differential Revision: D4393826

Pulled By: IslamAbdelRahman

fbshipit-source-id: 1bff689
2017-01-17 13:54:20 -08:00
Siying Dong
77b4806625 Fix 2PC with concurrent memtable insert
Summary:
If concurrent memtable insert is enabled, and one prepare command and a normal command are grouped into a commit group, the sequence ID will be calculated incorrectly.
Closes https://github.com/facebook/rocksdb/pull/1730

Differential Revision: D4371081

Pulled By: siying

fbshipit-source-id: cd40c6d
2017-01-17 11:24:28 -08:00
Mike Kolupaev
d18dd2c41f Abort compactions more reliably when closing DB
Summary:
DB shutdown aborts running compactions by setting an atomic shutting_down=true that CompactionJob periodically checks. Without this PR it checks it before processing every _output_ value. If compaction filter filters everything out, the compaction is uninterruptible. This PR adds checks for shutting_down on every _input_ value (in CompactionIterator and MergeHelper).

There's also some minor code cleanup along the way.
Closes https://github.com/facebook/rocksdb/pull/1639

Differential Revision: D4306571

Pulled By: yiwu-arbug

fbshipit-source-id: f050890
2017-01-11 15:09:21 -08:00
Changli Gao
9f246298e2 Performance: Iterate vector by reference
Summary: Closes https://github.com/facebook/rocksdb/pull/1763

Differential Revision: D4398796

Pulled By: yiwu-arbug

fbshipit-source-id: b82636d
2017-01-11 10:54:37 -08:00
Dmitri Smirnov
3c233ca4ea Fix Windows environment issues
Summary:
Enable directIO on WritableFileImpl::Append
     with offset being current length of the file.
     Enable UniqueID tests on Windows, disable others but
     leeting them to compile. Unique tests are valuable to
     detect failures on different filesystems and upcoming
     ReFS.
     Clear output in WinEnv Getchildren.This is different from
     previous strategy, do not touch output on failure.
     Make sure DBTest.OpenWhenOpen works with windows error message
Closes https://github.com/facebook/rocksdb/pull/1746

Differential Revision: D4385681

Pulled By: IslamAbdelRahman

fbshipit-source-id: c07b702
2017-01-09 15:54:12 -08:00
Maysam Yabandeh
d0ba8ec8f9 Revert "PinnableSlice"
Summary:
This reverts commit 54d94e9c2c.

The pull request was landed by mistake.
Closes https://github.com/facebook/rocksdb/pull/1755

Differential Revision: D4391678

Pulled By: maysamyabandeh

fbshipit-source-id: 36d5149
2017-01-08 14:24:12 -08:00
Maysam Yabandeh
54d94e9c2c PinnableSlice
Summary:
Currently the point lookup values are copied to a string provided by the user.
This incures an extra memcpy cost. This patch allows doing point lookup
via a PinnableSlice which pins the source memory location (instead of
copying their content) and releases them after the content is consumed
by the user. The old API of Get(string) is translated to the new API
underneath.

 Here is the summary for improvements:
 1. value 100 byte: 1.8%  regular, 1.2% merge values
 2. value 1k   byte: 11.5% regular, 7.5% merge values
 3. value 10k byte: 26% regular,    29.9% merge values

 The improvement for merge could be more if we extend this approach to
 pin the merge output and delay the full merge operation until the user
 actually needs it. We have put that for future work.

PS:
Sometimes we observe a small decrease in performance when switching from
t5452014 to this patch but with the old Get(string) API. The difference
is a little and could be noise. More importantly it is safely
cancelled
Closes https://github.com/facebook/rocksdb/pull/1732

Differential Revision: D4374613

Pulled By: maysamyabandeh

fbshipit-source-id: a077f1a
2017-01-08 13:54:13 -08:00
Andrew Kryczka
b104b87814 Maintain position in range deletions map
Summary:
When deletion-collapsing mode is enabled (i.e., for DBIter/CompactionIterator), we maintain position in the tombstone maps across calls to ShouldDelete(). Since iterators often access keys sequentially (or reverse-sequentially), scanning forward/backward from the last position can be faster than binary-searching the map for every key.

- When Next() is invoked on an iterator, we use kForwardTraversal to scan forwards, if needed, until arriving at the range deletion containing the next key.
- Similarly for Prev(), we use kBackwardTraversal to scan backwards in the range deletion map.
- When the iterator seeks, we use kBinarySearch for repositioning
- After tombstones are added or before the first ShouldDelete() invocation, the current position is set to invalid, which forces kBinarySearch to be used.
- Non-iterator users (i.e., Get()) use kFullScan, which has the same behavior as before---scan the whole map for every key passed to ShouldDelete().
Closes https://github.com/facebook/rocksdb/pull/1701

Differential Revision: D4350318

Pulled By: ajkr

fbshipit-source-id: 5129b76
2017-01-05 10:39:12 -08:00
siddontang
653ac1f9c6 C API: support total_order_mode
Summary: Closes https://github.com/facebook/rocksdb/pull/1687

Differential Revision: D4349210

Pulled By: IslamAbdelRahman

fbshipit-source-id: 32d0fbd
2017-01-03 18:39:14 -08:00
Adam Retter
85ac1a320a Fix rocksdb::Status::getState
Summary:
This fixes the Java API for Status#getState use in Native code and also simplifies the implementation of rocksdb::Status::getState.
Closes https://github.com/facebook/rocksdb/issues/1688
Closes https://github.com/facebook/rocksdb/pull/1714

Differential Revision: D4364181

Pulled By: yiwu-arbug

fbshipit-source-id: 8e073b4
2017-01-03 18:39:14 -08:00
Islam AbdelRahman
76711b6e77 Make ExternalSSTFileTest::CompactionDeadlock more deterministic
Summary:
It's not always true that `ASSERT_EQ(running_threads.load(), 2);`
Closes https://github.com/facebook/rocksdb/pull/1736

Differential Revision: D4374091

Pulled By: IslamAbdelRahman

fbshipit-source-id: 4f70bbd
2017-01-03 18:09:20 -08:00
Islam AbdelRahman
c963460dbc Fix tests under GCC_481
Summary:
This fix the issue with tests failing under GCC 481, I am not sure what is the exact reason
Closes https://github.com/facebook/rocksdb/pull/1735

Differential Revision: D4374094

Pulled By: IslamAbdelRahman

fbshipit-source-id: b3625bc
2017-01-03 17:54:12 -08:00
Vincent Lee
e425ec1162 utilities/backupable: backup should limit the copy size of wal.
Summary:
Since the backup work as snapshot, we should only copy
 the bytes of the wal while we get the alive files.
Closes https://github.com/facebook/rocksdb/pull/1733

Differential Revision: D4373457

Pulled By: ajkr

fbshipit-source-id: 389318f
2016-12-31 10:54:20 -08:00