"Lesados são aqueles que chega no bagulho sem procurar como é a segurança do ambiente" - (Provérbios do Negão da BL 27:2)

Both VictoriaMetrics and VictoriaLogs are optimized for persistent storage with low IOPS (aka HDD): - Data ingestion path. Both systems buffer recently ingested data in memory before writing it to files. Both systems rely on the OS page cache for minimising the number of write operations to persistent storage when writing the buffered data to files - regular writes to files do not induce physical writes to disk - the operating system stores the written data in memory (page cache) and writes it to disk in the background. Both VictoriaMetrics and VictoriaLogs call rsync() before closing just created immutable data files in order to guarantee that the data is properly stored to disk. This prevents data loss and data corruption on unclean shutdown such as accidental power off in the middle of creating a data file. The frequency of fsync() calls is usually quite low, even for high data ingestion rate (e.g. a few tens of fsync() calls per second for millions of ingested samples per second / hundreds of thousands of ingested logs per second). This allows using HDD disks with 100-200 iops for high data ingestion workloads at VictoriaMetrics and VictoriaLogs. - Querying path. Usually the most frequent queries are executed over the recently ingested data - the majority of alerting and recording rules usually rely on the data ingested during the last few hours. There are very high chances that this data is located in the OS page cache, since the operating system automatically and transparently stores all the recently written and read files' data there (of course if there is enough RAM for storing such a data aka working set). In this case the majority of queries don't induce any read operations from disk - they are satisfied by the OS page cache. Some rare and heavy queries over the historical data may need disk read operations for reading the historical data from disk. Both VictoriaMetrics and VictoriaLogs have data storage format optimized for minimising random disk read operations when reading the data for heavy queries over historical data. This data storage format is optimized for sequential reads of large chunks of data from disk, and these chunks of data are stored in a compressed form with high compression ratio. This allows minimising both random disk read operations and disk read bandwidth needed for executing heavy queries over historical data, which is missing in the OS page cache, so regular HDD disks are enough for the majority of use cases. When to use SSD and NVMe at VictoriaMetrics and VictoriaLogs? There are two cases: - When the working set doesn't fit the OS page cache. Then the operating system needs to read the frequently requested data from disk, so it needs disk with high iops. But I'd recommend increasing the available RAM instead of switching from HDD to SSD in this case - it will give better performance and capacity for both queries and data ingestion. - When heavy queries need higher performance and the bottleneck is in disk read bandwidth or in disk read iops.

The Vulkanised 2026 program has been released! The 2026 program includes keynote presentations & technical talks spanning a wide range of topics that matter to everyone using Vulkan Explore the program and register today! vulkan.org/events/vulkanised… #vulkan #api #programming #gpu

KOJIMA PRODUCTIONS is hiring! If you’re interested in joining the development of our new projects “OD” and “PHYSINT,” check out the link below 👍 kojimaproductions.jp/en/care… #KojimaProductions

How we avoided significant size growth for VictoriaTraces executable (from 20MB to 28MB, +40%) while adding support for receiving traces via gRPC. This also reduced CPU usage and improved performance for traces' ingestion over gRPC.

Conheça alguns membros da equipe organizadora da Elixir Curitiba 2025! #ElixirLang Inscrições em curitiba.elixiremfoco.com/ CUPOM ELIXIREMFOCO

Na Elixir Curitiba 2025 teremos a palestra "A visão de Joe Armstrong: resiliência no mundo real", de Pedro Castilho @coproduto (CTO na Cumbuca) #ElixirLang Ingressos em curitiba.elixiremfoco.com/ Cupom: ELIXIREMFOCO

True. A big share of Kubernetes clusters in production do not resolve any practical issues, while they bring a lot of trouble with the unnecessary complexity, over-engineered abstractions, silly yaml-programming and performance issues.

A Guide to Superhet radio Technology - ebook This book covers all the basic aspects of the superhet radio. The aim was to provide all the essential elements of the superheterodyne radio in one volume, explaining the background, the basic concepts and the function and operation of the different circuit blocks. All the different areas of the superheterodyne radio are explained in an easy to understand style that enables even the more complicated concepts to be understood. All aspects of the operation of the radio are included from the overall block diagram to aspects including selectivity, sensitivity, strong signal performance, demodulation and like. Check out my ebook on my online shop: electronics-notes-shop.fourt…

🚀 Go behind the scenes with the VictoriaMetrics team! In this special talk, Marc Sherwood is joined by our CTO, @valyala, to explore our powerful, open-source logging solution, VictoriaLogs. Whether you're a DevOps engineer, SRE, or a developer dealing with massive amounts of log data, this video will give you a unique look into a modern, cost-effective log management solution. In this discussion, you'll learn: 🟣 An overview of the latest powerful features in VictoriaLogs. 🟣 The fundamental reasons for creating a clustered, horizontally-scalable version. 🟣 A detailed breakdown of the VictoriaLogs Cluster architecture. 🟣 Key engineering decisions that prioritize performance, storage efficiency, and operational simplicity. 🟣 The ideal use cases for deploying VictoriaLogs at scale. Please find the full clip on our YouTube Channel. hubs.li/Q03MR53x0 #Monitoring #Observability #OpenSource

SQL can be programmatically converted to query language for VictoriaLogs and VictoriaTraces - LogsQL - try github.com/VictoriaMetrics/s…

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 a single cell must run in the same availability zone and must be located close to each other in order to achieve high reliability and high performance. The number of services inside a cell doesn't matter - it is a black box for the outside user. A cell must provide a narrow well defined API for external users. This API must abstract away the internal architecture details of the cell. Every cell must process a subset (shard) of some data. If a cell becomes temporarily unavailable, then the whole system consisting of multiple cells continues working. It only temporarily loses access to the data stored in the unavailable cell. This limits blast radius and simplifies troubleshooting and maintenance of the whole system. It is very easy to build a highly available system on top of a cell-based system - just store the same data to multiple cells (replicas). Then if some of these cells become unavailable, the whole system continues working by querying the needed data from the remaining cell replicas. This scheme is the recommended one for building HA on top of VictoriaLogs cluster - docs.victoriametrics.com/vic…

We’re proud to be hosting a #VictoriaMetrics #Meetup in Paris with @Criteoeng! 🇫🇷✨ 📍 Location: Criteo HQ, Paris. 🗓 Date: October 15th 🕡 Time: 18:00 🎙 @dianavtodea- VictoriaMetrics Developer Advocate will present, “Beyond #Prometheus: pushing the boundaries of scalable monitoring with VictoriaMetrics”. Prometheus has become the go-to standard for metrics-based monitoring, but as environments grow in complexity and scale, teams often find themselves hitting its operational limits, especially around cardinality and long-term storage. This talk explores how VictoriaMetrics builds on Prometheus fundamentals to offer a more scalable and efficient alternative for teams managing high-ingestion workloads and demanding retention needs, without abandoning the familiar Prometheus ecosystem. @valyala, VictoriaMetrics co-founder, will present: “VictoriaLogs cluster architecture and typical use cases”. A single-node version of VictoriaLogs can handle hundreds of terabytes of logs. What if this isn't enough for you? Then the cluster version of VictoriaLogs comes to the rescue! Raphael Bizos - Site Reliability Engineer at Criteo will present "A History of Automatic Aggregations". At Criteo, we’ve relied on automatic aggregations for years. “Automatic aggregation” is the name we give to a system of recording rules that matches most metrics and removes certain dimensions, such as the instance emitting the metric, to reduce the cardinality (i.e., the number of metrics) and thus makes queries faster. Sign up for free today and secure your spot. hubs.li/Q03JPVWr0 #LogManagement #TechEvents #monitoring

This is gonna be great

🔔 A firing alert is like someone ringing your doorbell - it demands immediate attention, interrupting whatever else you’re doing. It requires focus and a quick response. But imagine trying to live in an apartment where the doorbell never stops ringing. You could put in earplugs to block the noise, but that only masks the problem - it doesn’t solve it. On the other hand, disconnecting the doorbell entirely isn’t a solution either. You still want to know when your food or a package arrives. A doorbell that’s always silent or constantly ringing is equally useless. The goal is to find the right balance - distinguishing between what truly matters and what doesn’t. 👉 Check out our latest blog post. hubs.li/Q03HtwTV0 #Observability #Monitoring #alerting

In Brazil, the #ElixirLang community gathers on Telegram: t.me/elixirbr

Estamos planejando organizar eventos relacionados a Elixir e à comunidade de Erlang em 2025+ Ainda não temos datas confirmadas para nossos próximos eventos, mas estamos pensando em: Out/nov 2025 em Curitiba 1o semestre 2026 em Maceió Preencha sua proposta forms.gle/eJRFW6wbisKTz2LEA

A AWS acaba de lançar o AWS Treina Brasil, um programa 100% gratuito com a meta de capacitar 1 milhão de brasileiros em Inteligência Artificial e Computação em Nuvem até 2028. O programa oferece conteúdo em português, que vai do básico ao avançado, e inclui trilhas online

Next Tuesday, 09/02/2025, at 4:00 PM (UTC-3), we’ll have a conversation with Mackenzie Morgan at the SE4FP Warm-up. Mackenzie describes herself like this: “I'm a programmer who writes Elixir and Erlang. Former Ubuntu developer. I enjoy languages, Argentine tango +