This video was recorded a few months ago, but it remains actual for those who is interested in architecture details and design decisions behind VictoriaLogs cluster

See also the playground at https://t.co/iBFxWoOH4A and the SQL to LogsQL conversion guide at

SQL can be programmatically converted to query language for VictoriaLogs and VictoriaTraces - LogsQL - try

Cell-based architecture is the best for achieving linear scalability and decent reliability in distributed systems. A cell is a self-contained isolated system, which doesn't know about other systems and doesn't initiate communications with other systems. All the services inside

There'll always be more emails in need of reply, more meetings to attend, and more updates to read. A person can fill the entire workweek with these tasks over and over again. But to stay sane and sharp, you must pay yourself first by doing the work that actually means something

It your application cannot be built and tested on a local computer without access to the Internet, you are doomed - developers will always have a "good" reason why they couldn't work - the missing Internet or random issues with the dedicated CI/CD server. If your application

In over 15 years of open source, I can't remember ever saying "your example doesn't compile" (I probably did, but it's so rare I can't remember). Now, I literally say this everyday. Please, can people using AI be less fucking stupid about it.

I'll be at Open Source Summit Japan with Tang Yudong from #Bilibili to talk about the metrics monitoring architecture in practice. With #VictoriaMetrics, they've unlocked faster query speed by 10x. Join us on December 9 in Tokyo

An important insight about software is that there's literally no limit to the amount of work you can generate. Part of the job of a product designer is to *limit* the amount of work people can do. If you don't, people will generate infinite amount of work. Meetings about how

VictoriaLogs is a great database for SIEM events and logs: - It is optimized for storing, querying and analyzing billions of SIEM events and structured logs with big number of fields (hundreds per log entry). - It automatically parses CEF messages received over Syslog protocol

You are a software engineer. Don't become a prompt refiner. https://t.co/ZcVELmu1em

Cluster version of VictoriaLogs prefers consistent query results over the availability during querying. That's why it returns an error when some of the configured storage nodes are temporarily unavailable. There are practical cases when partial responses are OK when some of

PromCon is one month away! 🤗 We wrote all your need to know on our blog:

VictoriaLogs v1.34.0 supports the ability to set the number of parallel data readers during query execution. This can help improving query performance over the data stored on a persistent storage with high read latency such as Ceph, NFS (and S3 in the near future).

Join Mathias and Marc, for the first episode of our new series on building a robust, scalable, and user-friendly #VictoriaMetrics Platform as a Service! 📆 Don't miss it on September 25th at 10 am PT | 6 pm GMT | 7 pm CET, As organizations grow, so does the complexity of their

St. Louis, Here we go! Mathias Palmersheim, VictoriaMetrics Solutions #Engineer, will present “Better Together: Leveraging Your #Observability Tools as a SIEM” at #DevOps Midwest 2025 - @sketchdevelops on September 18th at 3:30 PM CDT. 🌐 Don't miss out—save the date! 📅

Some time ago we received a report from VictoriaLogs user, which said that single-node VictoriaLogs couldn't scale to more than 300K of ingested logs per second on a machine with hundreds of CPU cores. This was unexpected. Initially we thought that the issue is related to high