Download as PDF, PPTX
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-28-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-29-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-30-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-31-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-32-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-33-320.jpg)
![Unless...
future<> f = seastar::async([&] {
future<> f = …;
f.get();
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-35-320.jpg)
![Unless...
future<> f = seastar::async([&] {
future<> f = …;
f.get();
});](https://image.slidesharecdn.com/duartenunes-170608091341/85/ScyllaDB-NoSQL-at-Ludicrous-Speed-36-320.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-28-2048.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-29-2048.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-30-2048.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-31-2048.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-32-2048.jpg)
![Futures
future<> f = _conn->read_exactly(4).then([] (temporary_buffer<char> buf) {
int id = buf_to_id(buf);
unsigned core = id % smp::count;
return smp::submit_to(core, [id] {
return lookup(id);
}).then([this] (sstring result) {
return _conn->write(result);
});
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-33-2048.jpg)
![Unless...
future<> f = seastar::async([&] {
future<> f = …;
f.get();
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-35-2048.jpg)
![Unless...
future<> f = seastar::async([&] {
future<> f = …;
f.get();
});](https://image.slidesharecdn.com/duartenunes-170608091341/75/ScyllaDB-NoSQL-at-Ludicrous-Speed-36-2048.jpg)
Uploaded byJ On The Beach
ScyllaDB: NoSQL at Ludicrous Speed
ScyllaDB is a high-performance, clustered NoSQL database compatible with Apache Cassandra, offering significant improvements in latency and resource management due to its unique architecture and use of Seastar for asynchronous processing. It demonstrates proficiency in handling workloads with mechanisms like efficient memory allocation and workload conditioning while maximizing throughput without requiring extensive tuning from the user. The document outlines its advantages, technical design, and how it contrasts with traditional systems like Cassandra.
More Related Content
Similar to ScyllaDB: NoSQL at Ludicrous Speed
ScyllaDB: NoSQL at Ludicrous Speed
- 1. SCYLLA: NoSQL atLudicrous Speed Duarte Nunes @duarte_nunes
- 2. ❏ Introducing ScyllaDB ❏Seastar ❏ Resource Management ❏ Workload Conditioning ❏ Closing AGENDA
- 3. ScyllaDB ● Clustered NoSQLdatabase compatible with Apache Cassandra ● ~10X performance on same hardware ● Low latency, esp. higher percentiles ● Self tuning ● Mechanically sympathetic C++14
- 4. YCSB Benchmark: 3 nodeScylla cluster vs 3, 9, 15, 30 Cassandra machines 3 Scylla 30 Cassandra 3 Cassandra 3 Scylla 30 Cassandra 3 Cassandra
- 5. Scylla vs Cassandra- CL:LOCAL_QUORUM, Outbrain Case Study Scylla and Cassandra handling the full load (peak of ~12M RPM) 200ms 10ms 20x Lower Latency 5
- 6. Scylla benchmark bySamsung op/s Full report: http://tinyurl.com/msl-scylladb
- 7.
- 8. Data model Partition Key1 ClusteringKey1 Clustering Key1 Clustering Key2 Clustering Key2 ... ... ... ... ... CREATE TABLE playlists (id int, song_id int, title text, PRIMARY KEY (id, song_id )); INSERT INTO playlists (id, song_id, title) VALUES (62, 209466, 'Ænima’'); SortedbyPrimaryKey
- 9.
- 10. Log-Structured Merge Tree SStable1 SStable 2 Time
- 11. Log-Structured Merge Tree SStable1 SStable 2 SStable 3 Time
- 12. Log-Structured Merge Tree SStable1 SStable 2 SStable 3 Time SStable 4
- 13. Log-Structured Merge Tree SStable1 SStable 2 SStable 3 Time SStable 4 SStable 1+2+3
- 14. Log-Structured Merge Tree SStable1 SStable 2 SStable 3 Time SStable 4 SStable 5 SStable 1+2+3
- 15. Log-Structured Merge Tree SStable1 SStable 2 SStable 3 Time SStable 4 SStable 5 SStable 1+2+3 Foreground Job Background Job
- 16.
- 17.
- 18.
- 19. Implementation Goals ● Efficiency: ○Make the most out of every cycle ● Utilization: ○ Squeeze every cycle from the machine ● Control ○ Spend the cycles on what we want, when we want
- 20. ❏ Introducing ScyllaDB ❏System Architecture ❏ Node Architecture ❏ Seastar ❏ Resource Management ❏ Workload Conditioning ❏ Closing AGENDA
- 21. ● Thread-per-core design(shard) ○ No blocking. Ever. Enter Seastar www.seastar-project.org
- 22. Enter Seastar www.seastar-project.org ● Thread-per-coredesign (shard) ○ No blocking. Ever. ● Asynchronous networking, file I/O, multicore
- 23. Enter Seastar www.seastar-project.org ● Thread-per-coredesign (shard) ○ No blocking. Ever. ● Asynchronous networking, file I/O, multicore ● Future/promise based APIs
- 24. Enter Seastar www.seastar-project.org ● Thread-per-coredesign (shard) ○ No blocking. Ever. ● Asynchronous networking, file I/O, multicore ● Future/promise based APIs ● Usermode TCP/IP stack included in the box
- 25. Seastar task scheduler Traditionalstack Seastar stack Promise Task Promise Task Promise Task Promise Task CPU Promise Task Promise Task Promise Task Promise Task CPU Promise Task Promise Task Promise Task Promise Task CPU Promise Task Promise Task Promise Task Promise Task CPU Promise Task Promise Task Promise Task Promise Task CPU Promise is a pointer to eventually computed value Task is a pointer to a lambda function Scheduler CPU Scheduler CPU Scheduler CPU Scheduler CPU Scheduler CPU Thread Stack Thread Stack Thread Stack Thread Stack Thread Stack Thread Stack Thread Stack Thread Stack Thread is a function pointer Stack is a byte array from 64k to megabytes Context switch cost is high. Large stacks pollutes the caches No sharing, millions of parallel events
- 26.
- 27.
- 28. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 29. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 30. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 31. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 32. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 33. Futures future<> f =_conn->read_exactly(4).then([] (temporary_buffer<char> buf) { int id = buf_to_id(buf); unsigned core = id % smp::count; return smp::submit_to(core, [id] { return lookup(id); }).then([this] (sstring result) { return _conn->write(result); }); });
- 34. No escaping themonad future<> f = …; f.get(); // not allowed
- 35. Unless... future<> f =seastar::async([&] { future<> f = …; f.get(); });
- 36. Unless... future<> f =seastar::async([&] { future<> f = …; f.get(); });
- 37. Seastar memory allocator ●Non-Thread safe! ○ Each core gets a private memory pool
- 38. Seastar memory allocator ●Non-Thread safe! ○ Each core gets a private memory pool ● Allocation back pressure ○ Allocator calls a callback when low on memory ○ Scylla evicts cache in response
- 39. Seastar memory allocator ●Non-Thread safe! ○ Each core gets a private memory pool ● Allocation back pressure ○ Allocator calls a callback when low on memory ○ Scylla evicts cache in response ● Inter-core free() through message passing
- 40. ❏ Introducing ScyllaDB ❏System Architecture ❏ Node Architecture ❏ Seastar ❏ Resource Management ❏ Workload Conditioning ❏ Closing AGENDA
- 41. Usermode I/O scheduler Storage BlockLayer Filesystem
- 42. Usermode I/O scheduler Storage BlockLayer Filesystem Disk I/O Scheduler Class A Class B
- 43.
- 44. Figuring out optimaldisk concurrency Max useful disk concurrency
- 45. Cassandra cache Linux pagecache SSTables ● 4k granularity ● Thread-safe ● Synchronous APIs ● General-purpose ● Lack of control2 ● ...on the other hand ○ Exists ○ Hundreds of man-years ○ Handling lots of edge cases
- 46. Cassandra cache Linux pagecache SSTables ● Parasitic rows SSTable page (4k) Your data (300b)
- 47. Cassandra cache Linux pagecache SSTables ● Page faults Page fault Suspend thread Initiate I/O Context switch I/O completes Context switch Interrupt Map page Resume thread App thread Kernel SSD
- 48. Cassandra cache Key cache Rowcache On-heap / Off-heap Linux page cache SSTables ● Complex tuning
- 49.
- 50. Probabilistic Cache Warmup ●A replica with a cold cache should be sent less requests ●
- 51. Yet another allocator (Problemswith malloc/free) ● Memory gets fragmented over time ○ If the workload changes sizes of allocated objects ○ Allocating a large contiguous block requires evicting most of cache
- 52.
- 53.
- 54.
- 55.
- 56.
- 57.
- 58.
- 59.
- 60.
- 61.
- 62.
- 63.
- 64.
- 65.
- 66.
- 67.
- 68.
- 69.
- 70.
- 71.
- 72.
- 73.
- 74.
- 75.
- 76. Log-structured memory allocation ●Bump-pointer allocation to current segment ● Frees leave holes in segments ● Compaction will try to solve this
- 77. Compacting LSA ● Teachallocator how to move objects around ○ Updating references ● Garbage collect Compact! ○ Starting with the most sparse segments ○ Lock to pin objects ● Used mostly for the cache ○ Large majority of memory allocated ○ Small subset of allocation sites
- 78. ❏ Introducing ScyllaDB ❏System Architecture ❏ Node Architecture ❏ Seastar ❏ Resource Management ❏ Workload Conditioning ❏ Closing AGENDA
- 79. ● Internal feedbackloops to balance competing loads ○ Consume what you export Workload Conditioning
- 80.
- 81.
- 82.
- 83.
- 84.
- 85. ❏ Introducing ScyllaDB ❏System Architecture ❏ Node Architecture ❏ Seastar ❏ Workload Conditioning ❏ Closing AGENDA
- 86. ● Careful systemdesign and control of the software stack can maximize throughput ● Without sacrificing latency ● Without requiring complex end-user tuning ● While having a lot of fun Conclusions
- 87. ● Download: http://www.scylladb.com ●Twitter: @ScyllaDB ● Source: http://github.com/scylladb/scylla ● Mailing lists: scylladb-user @ groups.google.com ● Slack: ScyllaDB-Users ● Blog: http://www.scylladb.com/blog ● Join: http://www.scylladb.com/company/careers ● Me: duarte@scylladb.com How to interact
- 88. SCYLLA, NoSQL atLudicrous Speed Thank you. @duarte_nunes