During Pinterest’s migration of its custom search platform Manas to the PinCompute Kubernetes environment, a rare latency spike—one request per million taking 100 times longer—was traced to cAdvisor’s memory‑intensive smaps scans, revealing hidden resource contention and prompting a targeted fix.
During Pinterest’s migration of its high‑traffic Manas search platform to the PinCompute Kubernetes environment, engineers observed an extremely rare latency outlier—one in a million requests took 100 times longer—prompting a deep investigation that traced the root cause to cAdvisor’s memory‑intensive smaps scans interfering with leaf node processing.
This tutorial explains Prometheus' core components, shows how to deploy Prometheus Server, Node Exporter, cAdvisor, and Grafana as Docker containers on two hosts, configures scraping and alerting, and demonstrates visualizing metrics with ready‑made Grafana dashboards.
This guide walks through building a complete Kubernetes monitoring stack, covering metric exposure, collection, visualization, alerting, Prometheus configuration for cAdvisor and custom Java apps, dynamic pod discovery, and integrating OpenTelemetry Collector for push‑based observability.
This article explains how Alibaba Cloud Container Service for Kubernetes (ACK) has upgraded its storage monitoring dashboards to provide detailed visibility into local, PVC, and cloud‑based volumes, enabling users to detect IO bottlenecks, track real‑time read/write performance, and improve overall container reliability.
This guide explains how to use cAdvisor‑provided container network traffic counters as custom metrics for Kubernetes HPA, covering metric collection, Prometheus‑adapter configuration, verification, and a complete HPA testing workflow for elastic scaling of non‑CPU‑intensive workloads.
This guide shows how to enable Horizontal Pod Autoscaling for traffic‑driven workloads by leveraging cAdvisor's container network receive and transmit byte counters, converting them to per‑second rates with Prometheus‑adapter, and validating the custom metric through Kubernetes commands and console views.
This guide walks through a full Kubernetes monitoring solution using cAdvisor, node_exporter, Prometheus, and Grafana, covering architecture, data collection, service discovery, deployment steps with DaemonSets, and detailed YAML configurations for a production‑ready observability stack.
This article details how Vivo's container platform faced exploding metric volumes, component overload, data gaps, and storage spikes, and explains the step‑by‑step architectural redesign, metric governance, performance tuning, cAdvisor redeployment, and VictoriaMetrics upgrade that restored high‑availability, low‑latency monitoring across a large Kubernetes fleet.
This article explains the mechanics of Kubernetes CPU resource limits, how to interpret limits as time slices, the Linux accounting system behind them, and which Prometheus metrics can be used to set proper limits and diagnose CPU throttling issues.
This article explains how Kubernetes resource limits function, how to interpret CPU limits as time slices, the Linux accounting system behind them, relevant Prometheus metrics for detecting throttling, practical examples with multithreaded containers, and guidance on setting alerts and avoiding performance pitfalls.
This guide explains how to monitor Docker containers using the open‑source cAdvisor tool, integrate its metrics with Prometheus, and visualize the data in Grafana, providing step‑by‑step commands and configuration examples for a complete container‑monitoring solution.
This article explains why Kubernetes pods encounter out‑of‑memory errors and CPU throttling, how limits and requests influence resource allocation, and provides practical monitoring techniques using Prometheus and cAdvisor to proactively identify and mitigate these issues before they impact performance or cause pod eviction.
This article explains how the kubectl top command retrieves real‑time CPU and memory metrics for Kubernetes nodes and pods, details the underlying data flow, metric‑server and cAdvisor architecture, and addresses common issues and calculation differences compared to traditional system tools.
This article explains how the kubectl top command gathers real‑time CPU and memory usage for nodes and pods, details the underlying data flow and metric API implementation in Kubernetes, compares heapster and metrics‑server, and addresses common troubleshooting scenarios.
This article explains how the kubectl top command retrieves real‑time CPU and memory usage for nodes and pods, details the underlying data flow from cAdvisor through heapster or metrics‑server, clarifies metric calculations, compares results with native top and docker stats, and addresses common errors and troubleshooting steps.
This article explains how kubectl top retrieves real‑time CPU and memory usage for nodes and pods, details the underlying data flow and metric‑server architecture, and addresses frequent errors such as missing components, pause‑container accounting, and differences from host top or docker stats.
After moving IoT services to Kubernetes, containers were OOM‑killed despite RSS staying below limits because Kubernetes bases OOM decisions on the Working Set Size (WSS) metric, which includes file cache, and the article explains its calculation, reproduces the issue, and offers practical mitigation strategies.
Learn how to set up a comprehensive container monitoring solution using CAdvisor for metrics collection, InfluxDB for time‑series storage, and Grafana for visualization, including deployment steps, integration details, common issues, and best‑practice configurations for reliable Docker‑based environments.
Monitoring ensures Kubernetes applications run smoothly, and while Prometheus is a popular open‑source solution, this article examines six viable alternatives—Grafana, cAdvisor, Fluentd, Jaeger, Telepresence, and Zabbix—detailing their key features, strengths, and use‑cases for effective cluster observability.
This guide introduces Prometheus, explains its advantages over traditional monitoring tools, walks through installation, configuration, and Docker deployment, and demonstrates practical monitoring of Docker containers, Linux hosts, and visualization with Grafana, providing complete code snippets and screenshots.
This article explains how to design and implement a Docker container monitoring system using CAdvisor for metric collection, InfluxDB for time‑series storage, and Grafana for visualization, covering deployment, integration, common issues, and practical configuration details.
To effectively monitor Dockerized services, this guide walks through selecting a monitoring solution, deploying CAdvisor, integrating it with InfluxDB for persistent storage, visualizing metrics via Grafana, and addressing common issues such as missing utilities, memory stats, and network traffic inaccuracies.
This tutorial walks through deploying InfluxDB, cAdvisor, and Grafana containers, configuring them to collect and visualize time‑series metrics such as CPU, memory, network, and disk usage from Docker workloads, and shows how to create dashboards and queries for effective container monitoring.
This article explains why monitoring is essential for system reliability, outlines the key components of a comprehensive monitoring framework, compares data collection methods, and presents practical container monitoring solutions—from Docker stats to cAdvisor with InfluxDB and Grafana, as well as Kubernetes and Mesos integrations.
