Summary:
This diff adds support for concurrent adds to the skiplist memtable
implementations. Memory allocation is made thread-safe by the addition of
a spinlock, with small per-core buffers to avoid contention. Concurrent
memtable writes are made via an additional method and don't impose a
performance overhead on the non-concurrent case, so parallelism can be
selected on a per-batch basis.
Write thread synchronization is an increasing bottleneck for higher levels
of concurrency, so this diff adds --enable_write_thread_adaptive_yield
(default off). This feature causes threads joining a write batch
group to spin for a short time (default 100 usec) using sched_yield,
rather than going to sleep on a mutex. If the timing of the yield calls
indicates that another thread has actually run during the yield then
spinning is avoided. This option improves performance for concurrent
situations even without parallel adds, although it has the potential to
increase CPU usage (and the heuristic adaptation is not yet mature).
Parallel writes are not currently compatible with
inplace updates, update callbacks, or delete filtering.
Enable it with --allow_concurrent_memtable_write (and
--enable_write_thread_adaptive_yield). Parallel memtable writes
are performance neutral when there is no actual parallelism, and in
my experiments (SSD server-class Linux and varying contention and key
sizes for fillrandom) they are always a performance win when there is
more than one thread.
Statistics are updated earlier in the write path, dropping the number
of DB mutex acquisitions from 2 to 1 for almost all cases.
This diff was motivated and inspired by Yahoo's cLSM work. It is more
conservative than cLSM: RocksDB's write batch group leader role is
preserved (along with all of the existing flush and write throttling
logic) and concurrent writers are blocked until all memtable insertions
have completed and the sequence number has been advanced, to preserve
linearizability.
My test config is "db_bench -benchmarks=fillrandom -threads=$T
-batch_size=1 -memtablerep=skip_list -value_size=100 --num=1000000/$T
-level0_slowdown_writes_trigger=9999 -level0_stop_writes_trigger=9999
-disable_auto_compactions --max_write_buffer_number=8
-max_background_flushes=8 --disable_wal --write_buffer_size=160000000
--block_size=16384 --allow_concurrent_memtable_write" on a two-socket
Xeon E5-2660 @ 2.2Ghz with lots of memory and an SSD hard drive. With 1
thread I get ~440Kops/sec. Peak performance for 1 socket (numactl
-N1) is slightly more than 1Mops/sec, at 16 threads. Peak performance
across both sockets happens at 30 threads, and is ~900Kops/sec, although
with fewer threads there is less performance loss when the system has
background work.
Test Plan:
1. concurrent stress tests for InlineSkipList and DynamicBloom
2. make clean; make check
3. make clean; DISABLE_JEMALLOC=1 make valgrind_check; valgrind db_bench
4. make clean; COMPILE_WITH_TSAN=1 make all check; db_bench
5. make clean; COMPILE_WITH_ASAN=1 make all check; db_bench
6. make clean; OPT=-DROCKSDB_LITE make check
7. verify no perf regressions when disabled
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: MarkCallaghan, IslamAbdelRahman, anthony, yhchiang, rven, sdong, guyg8, kradhakrishnan, dhruba
Differential Revision: https://reviews.facebook.net/D50589
Summary:
Fixed the compile error in util/arena.h caused by not
including TLB related header.
Test Plan: make db_stress
Reviewers: igor, sdong, anthony, IslamAbdelRahman
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D47697
Summary:
Fixed the following compile warning when hugetlb is not supported.
./util/arena.h:102:10: error: private field 'hugetlb_size_' is not used [-Werror,-Wunused-private-field]
size_t hugetlb_size_ = 0;
^
1 error generated.
Test Plan: make db_stress
Reviewers: igor, sdong, anthony, IslamAbdelRahman
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D47691
Summary: Remove unnecessary rocksdb::kInlineSize, since it's not used and there is rocksdb::Arena::kInlineSize.
Test Plan: make all check
Reviewers: igor
Reviewed By: igor
Subscribers: dhruba
Differential Revision: https://reviews.facebook.net/D34905
Summary:
Introduces a new class for managing write buffer memory across column
families. We supplement ColumnFamilyOptions::write_buffer_size with
ColumnFamilyOptions::write_buffer, a shared pointer to a WriteBuffer
instance that enforces memory limits before flushing out to disk.
Test Plan: Added SharedWriteBuffer unit test to db_test.cc
Reviewers: sdong, rven, ljin, igor
Reviewed By: igor
Subscribers: tnovak, yhchiang, dhruba, xjin, MarkCallaghan, yoshinorim
Differential Revision: https://reviews.facebook.net/D22581
Summary:
arena doesn't use huge page by default. This change will make it happen
if possible. A new paramerter is added for Arena(). If it's set, Arena
will use huge page always. If huge page allocation fails, Arena
allocation will fallback to malloc().
Test Plan:
Change util/arena_test to support huge page allocation.
Run below tests:
1. normal regression test:
make check
2. Check if huge page allocation works
echo 50 > /proc/sys/vm/nr_hugepages
make check
Reviewers: sdong
Reviewed By: sdong
Subscribers: dhruba
Differential Revision: https://reviews.facebook.net/D28647
Summary:
In this patch, try to allocate the whole iterator tree starting from DBIter from an arena
1. ArenaWrappedDBIter is created when serves as the entry point of an iterator tree, with an arena in it.
2. Add an option to create iterator from arena for following iterators: DBIter, MergingIterator, MemtableIterator, all mem table's iterators, all table reader's iterators and two level iterator.
3. MergeIteratorBuilder is created to incrementally build the tree of internal iterators. It is passed to mem table list and version set and add iterators to it.
Limitations:
(1) Only DB::NewIterator() without tailing uses the arena. Other cases, including readonly DB and compactions are still from malloc
(2) Two level iterator itself is allocated in arena, but not iterators inside it.
Test Plan: make all check
Reviewers: ljin, haobo
Reviewed By: haobo
Subscribers: leveldb, dhruba, yhchiang, igor
Differential Revision: https://reviews.facebook.net/D18513
Summary:
In order to use arena to a use case that the total allocation size might be small (LogBuffer is already such a case), inline 1KB of data in it, so that it can be mostly in stack or inline in another class.
If always inlining 2KB is a concern, I could make it a template to determine what to inline. However, dependents need to changes. Doesn't go with it for now
Test Plan: make all check.
Reviewers: haobo, igor, yhchiang, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18609
Summary:
TLB page allocation errors are now logged to info logs, instead of stderr.
In order to do that, mem table rep's factory functions take a info logger now.
Test Plan: make all check
Reviewers: haobo, igor, yhchiang
Reviewed By: yhchiang
CC: leveldb, yhchiang, dhruba
Differential Revision: https://reviews.facebook.net/D18471
Summary: Add an option to allocate a piece of memory from huge page TLB. Add options to trigger it in dynamic bloom, plain table indexes andhash linked list hash table.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: nkg-, dhruba, leveldb, igor, yhchiang
Differential Revision: https://reviews.facebook.net/D18357
Summary:
Original Summary:
Yesterday, @ljin and I were debugging various db_stress issues. We suspected one of them happens when we concurrently call NewIterator without prefix_seek on HashSkipList. This test demonstrates it.
Update:
Arena is not thread-safe!! When creating a new full iterator, we *have* to create a new arena, otherwise we're doomed.
Test Plan: SIGSEGV and assertion-throwing test now works!
Reviewers: ljin, haobo, sdong
Reviewed By: sdong
CC: leveldb, ljin
Differential Revision: https://reviews.facebook.net/D16857
Summary:
This is is based on https://reviews.facebook.net/D15027. It's not finished but I would like to give a prototype to avoid arena over-allocation while making better use of the already allocated memory blocks.
Instead of check approximate memtable size, we will take a deeper look at the arena, which incorporate essential idea that @sdong suggests: flush when arena has allocated its last and the last is "almost full"
Test Plan: N/A
Reviewers: haobo, sdong
Reviewed By: sdong
CC: leveldb, sdong
Differential Revision: https://reviews.facebook.net/D15051
Summary:
this is the key component extracted from diff: https://reviews.facebook.net/D14271
I separate it to a dedicated patch to make the review easier.
Test Plan: added a unit test and passed it.
Reviewers: haobo, sdong, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16245
Summary:
Easy thing goes first. This patch moves arena to internal dir; based
on which, the coming patch will deal with memtable_rep.
Test Plan: make check
Reviewers: haobo, sdong, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15615
Summary:
Add an option for arena block size, default value 4096 bytes. Arena will allocate blocks with such size.
I am not sure about passing parameter to skiplist in the new virtualized framework, though I talked to Jim a bit. So add Jim as reviewer.
Test Plan:
new unit test, I am running db_test.
For passing paramter from configured option to Arena, I tried tests like:
TEST(DBTest, Arena_Option) {
std::string dbname = test::TmpDir() + "/db_arena_option_test";
DestroyDB(dbname, Options());
DB* db = nullptr;
Options opts;
opts.create_if_missing = true;
opts.arena_block_size = 1000000; // tested 99, 999999
Status s = DB::Open(opts, dbname, &db);
db->Put(WriteOptions(), "a", "123");
}
and printed some debug info. The results look good. Any suggestion for such a unit-test?
Reviewers: haobo, dhruba, emayanke, jpaton
Reviewed By: dhruba
CC: leveldb, zshao
Differential Revision: https://reviews.facebook.net/D11799
- Replace raw slice comparison with a call to user comparator.
Added test for custom comparators.
- Fix end of namespace comments.
- Fixed bug in picking inputs for a level-0 compaction.
When finding overlapping files, the covered range may expand
as files are added to the input set. We now correctly expand
the range when this happens instead of continuing to use the
old range. For example, suppose L0 contains files with the
following ranges:
F1: a .. d
F2: c .. g
F3: f .. j
and the initial compaction target is F3. We used to search
for range f..j which yielded {F2,F3}. However we now expand
the range as soon as another file is added. In this case,
when F2 is added, we expand the range to c..j and restart the
search. That picks up file F1 as well.
This change fixes a bug related to deleted keys showing up
incorrectly after a compaction as described in Issue 44.
(Sync with upstream @25072954)
