Avi Kivity cdee667170 alternator: destroy streamed json values gently
Large json return values are streamed to avoid memory pressure
and stalls, but are destroyed all at once. This in itself can cause
stalls [1].

Destroy them gently to avoid the stalls.

[1]

++[0#1/1 100%] addr=0x46880df total=514498 count=7004 avg=73:
|              seastar::backtrace<seastar::backtrace_buffer::append_backtrace_oneline()::{lambda(seastar::frame)#1}> at ./build/release/seastar.lto/./seastar/include/seastar/util/backtrace.hh:64
++           - addr=0x4680b35:
|              seastar::backtrace_buffer::append_backtrace_oneline at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:839
|              (inlined by) seastar::print_with_backtrace at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:858
++           - addr=0x46800f7:
|              seastar::internal::cpu_stall_detector::generate_trace at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:1469
++           - addr=0x4680178:
|              seastar::internal::cpu_stall_detector::maybe_report at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:1206
|              (inlined by) seastar::internal::cpu_stall_detector::on_signal at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:1226
++           - addr=0x3dbaf: ?? ??:0
  ++[1#1/812 13%] addr=0x217b774 total=69336 count=990 avg=70:
  |               rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericValue at /usr/include/rapidjson/document.h:721
  | ++[2#1/3 85%] addr=0x217b7db total=58974 count=842 avg=70:
  | |             rapidjson::GenericMember<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericMember at /usr/include/rapidjson/document.h:71
  | |             (inlined by) rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericValue at /usr/include/rapidjson/document.h:733
  | | ++[3#1/4 45%] addr=0x217b7db total=902102 count=12903 avg=70:
  | | |             rapidjson::GenericMember<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericMember at /usr/include/rapidjson/document.h:71
  | | |             (inlined by) rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericValue at /usr/include/rapidjson/document.h:733
  | | -> continued at addr=0x217b7db above
  | | |+[3#2/4 40%] addr=0x217b8b3 total=794219 count=11363 avg=70:
  | | |             rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericValue at /usr/include/rapidjson/document.h:726
  | | | ++[4#1/1 100%] addr=0x217b7db total=909571 count=13012 avg=70:
  | | | |              rapidjson::GenericMember<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericMember at /usr/include/rapidjson/document.h:71
  | | | |              (inlined by) rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>::~GenericValue at /usr/include/rapidjson/document.h:733
  | | | -> continued at addr=0x217b7db above
  | | |+[3#3/4 15%] addr=0x43d35a3 total=296768 count=4246 avg=70:
  | | |             seastar::shared_ptr_count_for<rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator> >::~shared_ptr_count_for at ././seastar/include/seastar/core/shared_ptr.hh:492
  | | |             (inlined by) seastar::shared_ptr_count_for<rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator> >::~shared_ptr_count_for at ././seastar/include/seastar/core/shared_ptr.hh:492
  | | | ++[4#1/2 98%] addr=0x43e7d06 total=289680 count=4144 avg=70:
  | | | |             seastar::shared_ptr<rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator> >::~shared_ptr at ././seastar/include/seastar/core/shared_ptr.hh:570
  | | | |             (inlined by) alternator::make_streamed(rapidjson::GenericValue<rapidjson::UTF8<char>, rjson::internal::throwing_allocator>&&)::$_0::operator() at ./alternator/executor.cc:127
  | | | ++          - addr=0x184e0a6:
  | | | |             std::__n4861::coroutine_handle<seastar::internal::coroutine_traits_base<void>::promise_type>::resume at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/coroutine:240
  | | | |             (inlined by) seastar::internal::coroutine_traits_base<void>::promise_type::run_and_dispose at ./build/release/seastar.lto/./seastar/include/seastar/core/coroutine.hh:125
  | | | |             (inlined by) seastar::reactor::run_tasks at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:2651
  | | | |             (inlined by) seastar::reactor::run_some_tasks at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:3114
  | | | | ++[5#1/1 100%] addr=0x2503b87 total=310677 count=4417 avg=70:
  | | | | |              seastar::reactor::do_run at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:3283
  | | | |   ++[6#1/2 78%] addr=0x46a2898 total=400571 count=5450 avg=73:
  | | | |   |             seastar::smp::configure(seastar::smp_options const&, seastar::reactor_options const&)::$_0::operator() at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:4501
  | | | |   |             (inlined by) std::__invoke_impl<void, seastar::smp::configure(seastar::smp_options const&, seastar::reactor_options const&)::$_0&> at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/bits/invoke.h:61
  | | | |   |             (inlined by) std::__invoke_r<void, seastar::smp::configure(seastar::smp_options const&, seastar::reactor_options const&)::$_0&> at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/bits/invoke.h:111
  | | | |   |             (inlined by) std::_Function_handler<void (), seastar::smp::configure(seastar::smp_options const&, seastar::reactor_options const&)::$_0>::_M_invoke at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/bits/std_function.h:290
  | | | |   ++          - addr=0x4673fda:
  | | | |   |             std::function<void ()>::operator() at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/bits/std_function.h:591
  | | | |   |             (inlined by) seastar::posix_thread::start_routine at ./build/release/seastar.lto/./seastar/src/core/posix.cc:90
  | | | |   ++          - addr=0x8c946: ?? ??:0
  | | | |   ++          - addr=0x11296f: ?? ??:0
  | | | |   ++[6#2/2 22%] addr=0x2502c1e total=113613 count=1549 avg=73:
  | | | |   |             seastar::reactor::run at ./build/release/seastar.lto/./seastar/src/core/reactor.cc:3166
  | | | |   ++          - addr=0x22068e0:
  | | | |   |             seastar::app_template::run_deprecated at ./build/release/seastar.lto/./seastar/src/core/app-template.cc:276
  | | | |   ++          - addr=0x220630b:
  | | | |   |             seastar::app_template::run at ./build/release/seastar.lto/./seastar/src/core/app-template.cc:167
  | | | |   ++          - addr=0x22334bc:
  | | | |   |             scylla_main at ./main.cc:672
  | | | |   ++          - addr=0x20411cc:
  | | | |   |             std::function<int (int, char**)>::operator() at /usr/bin/../lib/gcc/x86_64-redhat-linux/13/../../../../include/c++/13/bits/std_function.h:591
  | | | |   |             (inlined by) main at ./main.cc:2072
  | | | |   ++          - addr=0x27b89: ?? ??:0
  | | | |   ++          - addr=0x27c4a: ?? ??:0
  | | | |   ++          - addr=0x28c8fb4:
  | | | |   |             _start at ??:?

Closes scylladb/scylladb#19968
2024-08-05 00:35:52 +03:00
2024-07-20 21:21:42 +03:00
2024-07-28 21:04:45 +03:00
2024-07-31 13:58:09 +03:00
2024-07-22 17:12:09 +03:00
2024-06-26 12:07:21 +03:00
2024-05-05 23:31:09 +03:00
2024-06-25 12:11:28 +03:00
2024-06-25 12:11:28 +03:00
2024-03-20 09:16:46 +02:00
2024-06-07 06:44:59 +08:00
2024-06-23 19:24:40 +03:00
2024-05-08 09:41:17 -04:00
2024-05-08 09:41:17 -04:00
2024-03-20 09:16:46 +02:00
2024-06-07 06:44:59 +08:00
2024-06-07 06:44:59 +08:00
2024-06-07 06:44:59 +08:00

Scylla

Slack Twitter

What is Scylla?

Scylla is the real-time big data database that is API-compatible with Apache Cassandra and Amazon DynamoDB. Scylla embraces a shared-nothing approach that increases throughput and storage capacity to realize order-of-magnitude performance improvements and reduce hardware costs.

For more information, please see the ScyllaDB web site.

Build Prerequisites

Scylla is fairly fussy about its build environment, requiring very recent versions of the C++20 compiler and of many libraries to build. The document HACKING.md includes detailed information on building and developing Scylla, but to get Scylla building quickly on (almost) any build machine, Scylla offers a frozen toolchain, This is a pre-configured Docker image which includes recent versions of all the required compilers, libraries and build tools. Using the frozen toolchain allows you to avoid changing anything in your build machine to meet Scylla's requirements - you just need to meet the frozen toolchain's prerequisites (mostly, Docker or Podman being available).

Building Scylla

Building Scylla with the frozen toolchain dbuild is as easy as:

$ git submodule update --init --force --recursive
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla

For further information, please see:

Running Scylla

To start Scylla server, run:

$ ./tools/toolchain/dbuild ./build/release/scylla --workdir tmp --smp 1 --developer-mode 1

This will start a Scylla node with one CPU core allocated to it and data files stored in the tmp directory. The --developer-mode is needed to disable the various checks Scylla performs at startup to ensure the machine is configured for maximum performance (not relevant on development workstations). Please note that you need to run Scylla with dbuild if you built it with the frozen toolchain.

For more run options, run:

$ ./tools/toolchain/dbuild ./build/release/scylla --help

Testing

Build with the latest Seastar Check Reproducible Build clang-nightly

See test.py manual.

Scylla APIs and compatibility

By default, Scylla is compatible with Apache Cassandra and its API - CQL. There is also support for the API of Amazon DynamoDB™, which needs to be enabled and configured in order to be used. For more information on how to enable the DynamoDB™ API in Scylla, and the current compatibility of this feature as well as Scylla-specific extensions, see Alternator and Getting started with Alternator.

Documentation

Documentation can be found here. Seastar documentation can be found here. User documentation can be found here.

Training

Training material and online courses can be found at Scylla University. The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling, administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions, multi-datacenters and how Scylla integrates with third-party applications.

Contributing to Scylla

If you want to report a bug or submit a pull request or a patch, please read the contribution guidelines.

If you are a developer working on Scylla, please read the developer guidelines.

Contact

  • The community forum and Slack channel are for users to discuss configuration, management, and operations of the ScyllaDB open source.
  • The developers mailing list is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
Description
No description provided
Readme 458 MiB
Languages
C++ 72.3%
Python 26.5%
CMake 0.3%
GAP 0.3%
Shell 0.3%