java_dnk's profile picture. Interested in Java performance tuning, distributed systems and high availability

Dmitry Konstantinov

@java_dnk

Interested in Java performance tuning, distributed systems and high availability

Dmitry Konstantinov reposted

It still has to be reviewed, but finally the cursor based C* compaction patch is in the open: issues.apache.org/jira/browse/CA… "3-5x faster [compaction] in most scenarios and allocates ~20mb vs. multiple GB[per compaction]" :-)


Dmitry Konstantinov reposted

🚀 Call for Contributors If you're interested in contributing to the #JVM #Performance #Benchmarks project - an initiative that gained significant traction in the #Java community through our recent #JDK17 and #JDK11 analyses - check out the repo: 🔗 github.com/ionutbalosin/j…


Dmitry Konstantinov reposted

A fantastic blog series on memory subsystem optimizations!!! johnnysswlab.com/memory-subsyst…

vivekgalatage's tweet image. A fantastic blog series on memory subsystem optimizations!!!

johnnysswlab.com/memory-subsyst…

Dmitry Konstantinov reposted

JEP 509 ("JFR CPU-Time Profiling (Experimental)") added. See openjdk.org/jeps/509


Dmitry Konstantinov reposted

Profiling: you are doing it all WRONG! The SHOCKING truth about CPU vs. real time Now that I get your attention :) My perf latency profiling changes merged: web.git.kernel.org/pub/scm/linux/… First profiler ever that samples realtime (not CPU time) and suitable for latency optimization


Dmitry Konstantinov reposted

Async-Profiler v4.0 Heatmaps and Native memory profiling and VMStructs-based stack walker github.com/async-profiler…


Dmitry Konstantinov reposted

I am excited to finally announce the release of #netty 4.2.0.Final which is in the making for quite some time! This release comes with a lot of new exciting features, including the highly anticipated #io_uring support. See netty.io/news/2025/04/0…


Dmitry Konstantinov reposted

Interesting issue in OpenJDK's UUID.compareTo(): It uses signed comparisons, which leads to unexpected sorting when the highest bit in either word is set. It can't be fixed since altering a sort order between versions is a big no-no. bugs.openjdk.org/browse/JDK-702…


Dmitry Konstantinov reposted

🚨 There has been a breakthrough in the world of hash tables 🚨 A paper that disproves the longstanding conjecture that uniform hashing is optimal. "Optimal Bounds for Open Addressing Without Reordering" by Martín Farach-Colton, Andrew Krapivin, William Kuszmaul…

royvanrijn's tweet image. 🚨 There has been a breakthrough in the world of hash tables 🚨

A paper that disproves the longstanding conjecture that uniform hashing is optimal.

"Optimal Bounds for Open Addressing Without Reordering" by Martín Farach-Colton, Andrew Krapivin, William Kuszmaul…

Dmitry Konstantinov reposted

a university undergrad made hash tables faster and broke 40-year-old belief 🤯 for 40 years, it was believed that we cannot have better than O(n) operation for hash table worst case inserts and searches if it uses open addressing - for the hash index, look linearly until you…


Dmitry Konstantinov reposted

Lilliput 2 (aka 4-byte-object-headers) is now in the Lilliput project repo (based on JDK25-dev). For testing, grab nightlies from here (thanks, @shipilev): builds.shipilev.net/openjdk-jdk-li…


Dmitry Konstantinov reposted

New @CMUDB Course: Database Query Optimization! A survey of how to build a SQL optimizer from scratch covering foundational and state-of-the-art implementations. All lectures available on Youtube: 15799.courses.cs.cmu.edu/spring2025/


Dmitry Konstantinov reposted

github.com/davidtos/JUring io_uring for Java. "Doing Random reads JUring achieves 33% better performance than Java NIO FileChannel operations for local files and 78% better performance for remote files."


Dmitry Konstantinov reposted

Parts of Leyden and other CDS improvements are now in JDK mainline, in time for JDK 24 fork. The improvements are visible even on simple HelloWorld-style examples. There are even more things to squeeze!

shipilev's tweet image. Parts of Leyden and other CDS improvements are now in JDK mainline, in time for JDK 24 fork. The improvements are visible even on simple HelloWorld-style examples. There are even more things to squeeze!

Завтра, 12 ноября в 19:00 МСК, в преддверии нового сезона Podlodka Java Crew, посвященного асинхронной архитектуре, Никита Коваль раскроет внутренние механизмы каналов в Kotlin coroutines, которые делают их такими эффективными. youtube.com/live/qCCuSsR0i…

java_dnk's tweet card. Доклад: Устройство каналов в Kotlin Coroutines

youtube.com

YouTube

Доклад: Устройство каналов в Kotlin Coroutines


Dmitry Konstantinov reposted

Let's say you commit a change that makes an application 0.05% slower. No big deal, right? Well, at the scale of Meta, it is a big deal--a small slowdown for a large application can waste thousands of servers. It's such a big deal that Meta needs a way to catch these performance…

petereliaskraft's tweet image. Let's say you commit a change that makes an application 0.05% slower. No big deal, right?

Well, at the scale of Meta, it is a big deal--a small slowdown for a large application can waste thousands of servers. It's such a big deal that Meta needs a way to catch these performance…

Dmitry Konstantinov reposted

Hello Apache Kafka 3.9.0! - last release using ZooKeeper - tiered storage is production-ready Plus many more KIPs, improvements, and bug-fixes. For details, check out the release blog post: kafka.apache.org/blog#apache_ka… Thanks to 133 contributors and our RM @cmccabe314!


Dmitry Konstantinov reposted

Upgrade time! We just released Apache Kafka 3.8.1! Thanks to all 24 contributors and our RM @jlprat! For more details checkout out the release blog post: kafka.apache.org/blog#apache_ka…


Dmitry Konstantinov reposted

Leyden is going to be a breakthrough technology for startup and time-to-performance improvements. There are many other things that could be improved, squeezing even more perf. Just a taste:

shipilev's tweet image. Leyden is going to be a breakthrough technology for startup and time-to-performance improvements. There are many other things that could be improved, squeezing even more perf. Just a taste:

Loading...

Something went wrong.


Something went wrong.