Whatโs going on in your OpenSearch cluster right now? ๐
Live queries in OpenSearch 3.0 let you monitor searches in real time, troubleshoot faster, and stay ahead of performance issues.
Learn more โ https://opensearch.org/blog/real-time-query-monitoring-with-live-queries-in-opensearch-3-0/
๐ฆซ ๐ Overhead for distributed tracing can be costly, but #eBPF can help reduce resource strain on CPUs, memory, and network traffic: https://t.ly/QBRYt
#Golang #Go #observability #kubernetes #tech #IT #Linux #Datadog #SigNoz #Valkey #Redis #opentelemetry #OTEL
#AmazonEKSDashboard is now Generally Available!
Get unified visibility across your #Kubernetes clusters deployed in multiple AWS regions and accounts.
Learn more: https://bit.ly/45nExJU
Log management in large Kubernetes environments poses challenges with thousands of pods generating vast data volumes, increasing CPU, RAM, and disk costs. Aliaksandr will discuss strategies using #Elasticsearch, #Grafana #loki and #VictoriaLogs to cut infrastructure costs by 10x or more.
This talk is essential for anyone building or running large-scale #Kubernetes clusters.
Large Kubernetes clusters can generate significant volumes of logs, especially when housing thousands of running pods. This may demand substantial CPU, RAM, disk IO, and disk space for storing and querying large log volumes. In this talk, we will look into different strategies of storing those logs in ElasticSearch, Grafana Loki and VictoriaLogs and examine how we can save 10x or more on infrastructure costs. This talk presents real-world examples of efficient log management in large-scale Kubernetes clusters. It includes setup demonstrations, numerical data, and graphical representations from reproducible benchmarks.
My obsession with #MCP servers continues. And like many of my obsessions, I love finding ways in which they intersect with other obsessions (hello, #Observability). I decided to leverage the #Dynatrace MCP server to use natural language to query #OpenTelemetry data in Dynatrace. End result? Well, youโll need to read the blog post!
Speaking of #Datadog, I recently sat down with the company's new chief scientist, Ameet Talwalkar, to discuss its latest venture into #AIresearch. Talwalkar joined the company in February to lead its new #AI research lab, and its first project, Toto, a time-series foundational model for #observability, was just unveiled last month.
Talwalkar highlighted how specialized foundational models like Toto could enhance AI responses for #o11y tools such as Watchdog and potentially lead to cost reductions compared with general-purpose frontier models.
Our dialogue also delved into future-oriented topics, including #agenticAI, observability for AI, AI for observability, the evolution of human-computer interaction, and the persistent challenge of AI explainability.
Check out our discussion on the #ITOps Query podcast: https://www.podbean.com/ew/pb-hqa2e-18d36d7 #DASH2025
Ameet Talwalkar joined observability vendor Datadog in February to lead a new AI research lab at the company. He is also an Associate Professor at Carnegie Mellon University. One of the first projects from the lab was released to open source in May โ Toto, a foundation model trained on real-world observability data. Talwalkar discusses how Toto could improve observability forecasting tools such as Datadog's Watchdog, and does some forecasting of his own about how AI agents will alter observability and human-computer interactions.
OpenSearch Project
Eric D. Schabell
Coroot
Nicole van der Hoeven
InfoQ
VictoriaMetrics
Beth Pariseau
Holistic Mathematics Agency
Adriana Villela ๐ง๐ท๐จ๐ฆ