[
https://issues.apache.org/jira/browse/CASSGO-89?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18019351#comment-18019351
]
Bohdan Siryk commented on CASSGO-89:
------------------------------------
The benchmarks results:
cd ./pre-proto5; go test -bench . -memprofile mem.profile
goos: linux
goarch: amd64
pkg: github.com/worryg0d/test/benchmarks/pre-proto5
cpu: 13th Gen Intel(R) Core(TM) i7-13700H
Benchmark_Proto4_QuerySelect-20 70 21438042 ns/op 110491 B/op 50 allocs/op
PASS
ok github.com/worryg0d/test/benchmarks/pre-proto5 1.533s
cd ./proto5-commit; go test -bench . -memprofile mem.profile
goos: linux
goarch: amd64
pkg: github.com/worryg0d/test/benchmarks/proto5-commit
cpu: 13th Gen Intel(R) Core(TM) i7-13700H
Benchmark_Proto4_QuerySelect-20 55 20893064 ns/op 110847 B/op 53 allocs/op
PASS
ok github.com/worryg0d/test/benchmarks/proto5-commit 2.020s
cd ./v1.7.0; go test -bench . -memprofile mem.profile
goos: linux
goarch: amd64
pkg: github.com/worryg0d/test/benchmarks/v1-7-0
cpu: 13th Gen Intel(R) Core(TM) i7-13700H
Benchmark_Proto4_QuerySelect-20 55 21501161 ns/op 110967 B/op 54 allocs/op
PASS
ok github.com/worryg0d/test/benchmarks/v1-7-0 1.220s
> Performance regression due to CASSGO-1 changes
> ----------------------------------------------
>
> Key: CASSGO-89
> URL: https://issues.apache.org/jira/browse/CASSGO-89
> Project: Apache Cassandra Go driver
> Issue Type: Task
> Components: Core
> Reporter: Bohdan Siryk
> Priority: Normal
>
> > Hey all. Trying to track down an issue, which is appearing when switching
> > the version of the Go driver. The team I'm working with has narrowed it
> > down to this
> > [commit|https://github.com/apache/cassandra-gocql-driver/commit/63b6d7830710a0c6c5411c08bf16d38cb88d2a8a#diff-4f427d2b022907c552328e63f137561f6de92396d7a6e8f6c2ea1bcf0db52654].
> > They bumped the driver version to that commit & pinned the protocol to
> > v4. They're seeing a massive increase in allocation and increased latency.
> > The memory allocation isn't actually coming from the driver, but rather
> > later in the stack where it creates a protobuf object. Based on the
> > network traffic, there's a lot more data coming back to the client than
> > there was before.
> Originally raised in
> [https://the-asf.slack.com/archives/C05LPRVNZV1/p1756169350344849]
> Potential regression due to changes brought by CASSGO-1
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
