bf3d0b3543
Observed 3% throughput improvement in sstable-heavy workload bounded by CPU.
SStable parsing involves lots of buffer operations which obtain and
destroy resource_units. Before the patch, reosurce_unit destruction
invoked maybe_admit_waiters(), which performs some computations on
waiting permits. We don't really need to admit on each change of
resources, since the CPU is used by other things anyway. We can batch
the computation. There is already a fiber which does this for
processing the _ready_list. We can reuse it for processing _wait_list
as well.
The changes violate an assumption made by tests that releasing
resources immediately triggers an admission check. Therefore, some of
the BOOST_REQUIRE_EQUAL needs to be replaced with REQUIRE_EVENTUALLY_EQUAL
as the admision check is now done in the fiber processing the _ready_list.
`perf-simple-query` --tablets --smp 1 -m 1G results obtained for
fixed 400MHz frequency:
Before:
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=read, frontend=cql, query_single_key=no, counters=no}
Disabling auto compaction
Creating 10000 partitions...
112590.60 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41353 insns/op, 17992 cycles/op, 0 errors)
122620.68 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41310 insns/op, 17713 cycles/op, 0 errors)
118169.48 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41353 insns/op, 17857 cycles/op, 0 errors)
120634.65 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41328 insns/op, 17733 cycles/op, 0 errors)
117317.18 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41347 insns/op, 17822 cycles/op, 0 errors)
throughput: mean=118266.52 standard-deviation=3797.81 median=118169.48 median-absolute-deviation=2368.13 maximum=122620.68 minimum=112590.60
instructions_per_op: mean=41337.86 standard-deviation=18.73 median=41346.89 median-absolute-deviation=14.64 maximum=41352.53 minimum=41309.83
cpu_cycles_per_op: mean=17823.50 standard-deviation=111.75 median=17821.97 median-absolute-deviation=90.45 maximum=17992.04 minimum=17713.00
```
After
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=read, frontend=cql, query_single_key=no, counters=no}
Disabling auto compaction
Creating 10000 partitions...
123689.63 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 40997 insns/op, 17384 cycles/op, 0 errors)
129643.24 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 40997 insns/op, 17325 cycles/op, 0 errors)
128907.27 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 41009 insns/op, 17325 cycles/op, 0 errors)
130342.56 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 40993 insns/op, 17286 cycles/op, 0 errors)
130294.09 tps ( 63.1 allocs/op, 0.0 logallocs/op, 14.1 tasks/op, 40972 insns/op, 17336 cycles/op, 0 errors)
throughput: mean=128575.36 standard-deviation=2792.75 median=129643.24 median-absolute-deviation=1718.73 maximum=130342.56 minimum=123689.63
instructions_per_op: mean=40993.51 standard-deviation=13.23 median=40996.73 median-absolute-deviation=3.30 maximum=41008.86 minimum=40972.48
cpu_cycles_per_op: mean=17331.16 standard-deviation=35.02 median=17324.84 median-absolute-deviation=6.49 maximum=17383.97 minimum=17286.33
```
Closes scylladb/scylladb#21918
[avi: patch was co-authored by Łukasz Paszkowski <lukasz.paszkowski@scylladb.com>]
Scylla
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++23 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:
- Developer documentation for more information on building Scylla.
- Build documentation on how to build Scylla binaries, tests, and packages.
- Docker image build documentation for information on how to build Docker images.
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
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.