Achieving maximum write speed with QuasarDB

Posted by Edouard on 22 Oct 2020

QuasarDB is the fastest timeseries database in the world by ingestion speed (and probably by querying speed, but it's very hard to establish objectively), by a significant margin. In the 3.9 branch, we furthered our advance further, and we are working to deliver another major performance boost in the following releases.

Read More

Tags: time series, performance, tuning

Using C++ containers efficiently

Posted by Edouard on 23 Mar 2020

Hello, dear reader! I think you have many assumptions about the performance and usage of data structures in C++. This blog post is me, destroying your world.

Read More

Tags: c++, performance, containers

Ingesting 10 billion rows of timeseries data in 95 seconds

Posted by Edouard on 12 Dec 2019

Timeseries data = ingestion challenges

If there’s one thing that’s hard when managing timeseries data is just the sheer amount of it. Timeseries data has volume built-in because it’s cumulative. You don’t want a single picture: you want the whole movie!

Read More

Tags: quasardb, time series, performance

Introducing Delta4C: a high speed, adaptive, lossless compressor for timeseries

Posted by Edouard on 08 May 2019

This post is part of a series about the challenges behind database performance and how to accurately assess it.

Why compression matters so much for timeseries data

Whatever database engine you are using, efficient disk storage is always welcomed. When your 10 GiB become 100 GiB once in the database, that’s never a nice thing!

Read More

Tags: quasardb, time series, performance, compression, managed

Should you care about performance?

Posted by Edouard on 29 Apr 2019
This post is part of a series about the challenges behind database performance and how to accurately assess it.

You don’t care about performance

When we started selling QuasarDB, we focused on its performance advantages and touted how great they were. The logic behind that was obvious: we were very strong in this area; thus we should bring the battle to where we are strong!

Read More

Tags: quasardb, software, time series, performance

Benchmarking timeseries ingress

Posted by Edouard on 16 Apr 2019
This post is part of a series about the challenges behind database performance and how to accurately assess it.

Purpose of an ingress benchmark

When evaluating a timeseries database management system (later referred as TSDBMS or TSDB), one important dimension is the ingress speed (a.k.a. insertion or ingestion), that is, how fast the database can store new data points.

Read More

Tags: quasardb, time series, performance

Database performance

Posted by Edouard on 12 Mar 2019

This port is the first in a series about the challenges behind database performance and how to accurately assess it. In future posts, we will dig more into the specifics of benchmarks and design choices.

The Penrose stairs of performance

If you are following database innovation you can see that nearly every database vendor out there has at least one benchmark putting them in the first place. With every vendor selling the fastest database there is, you end up in a Penrose stairs situation where everyone is faster than everyone.

Read More

Tags: memory, optimization, process, software, performance