I fixed ann-benchmarks and got ~20× higher QPS — without touching the database.
Here’s why many published DBMS results are unreliable 👇
https://t.co/jL42qQ5czC
We would like to share amazing news: YDB toolkit now includes an adapter for DBT!
Check official DBT docs for more https://t.co/6xkCxS0NSj
Consider reading YDB docs for quick how-tos https://t.co/HdaGIfno6e
Thanks @getdbt !
#distributedsql#bigdata
It doesn’t matter if your database is lightning-fast—if your gRPC client is the bottleneck, everything slows down. In this post, we share a real case from YDB: how gRPC turned out to be surprisingly slow even in low-latency networks. Fortunately, there’s a fix.
https://t.co/9zn9AfJf81
Good news everyone!
We have released 🚀 YDB Server 25.1.2.7-rc – https://t.co/jjDJFYoAfL
Complete changelog is available in the docs section – https://t.co/yAjlQqAqru
Which feature would you like to try first?
#ydb#distributedsql
@_trish_xD Wonderful and simple explanation! Thank you! But why limit yourself to sql / nosql dichotomies? There are numerous #distributedsql systems like @YDBPlatform or @Yugabyte which serve the best of both worlds!
YDB core team contributor @eivanov89 has published new post in our blog about advantages one can gain from using YDB instead of sharding relational databases.
@ElonClipsX Elon’s insight resonates with TRIZ’s focus on eliminating contradictions and achieving the “Ideal Final Result.”
Let’s innovate and strip unnecessary down! #TRIZ#Innovation
«Каждый раз, когда основные задачи решены, я сажусь разрабатывать оптимизатор запросов. Расскажу о том, что такое оптимизаторы запросов в базах данных и почему их непросто делать»
Стоимостной оптимизатор. Сердце гибридной базы данных YDB: https://t.co/XZzcd8BVli
That's a very well-written paper from 2020 focusing on decoupling storage and compute in a distributed database. In their approach, they are very close to YDB. In YDB, the "Database layer" is built on top of distributed storage, which is somewhat similar to Hailstorm, because YDB fully disaggregates compute and storage - the main goal of Hailstorm. I would like to highlight some key differences between Hailstorm and YDB ⬇️