0 views collected around this technical thread.
This article explains how to use Flame Graphs to visualize MySQL execution plans, discusses the limitations of traditional EXPLAIN output, introduces the EXPLAIN ANALYZE feature in MySQL 8.0, provides sample SQL and command‑line usage, and shows how the visual tool helps quickly identify performance bottlenecks.
The article examines Java thread states—WAITING and TIMED_WAITING—through monitoring screenshots, explains their definitions, trigger conditions, and recovery mechanisms, analyzes real‑world code involving concurrent tasks, and presents flame‑graph based performance optimizations for backend services.
The article investigates why pure‑read QPS drops significantly after bulk updates in OceanBase, reproduces the issue with a sysbench workload, analyses flame‑graph and SQL audit data, explains the LSM‑Tree read‑amplification mechanism, and proposes practical mitigation steps such as major freeze, plan binding, index creation, and the queuing‑table feature.
The Tencent Docs SmartSheet view’s sluggish 20 FPS performance was resolved by a suite of optimizations—including incremental rendering of only visible widgets, disabling costly canvas hit‑testing, replacing node cloning with direct construction, caching text measurements, and employing offscreen canvas rendering—boosting frame rates to near 60 FPS.
Using lightweight dynamic‑tracing tools that record allocator calls and page‑fault events, the authors diagnose a production MySQL‑proxy memory leak in TDSQL, generate focused flame‑graphs with custom memstacks and pgfaultstacks, and demonstrate a fast, source‑independent alternative to gdb or Valgrind.
The article details how the author used async-profiler to analyze a Java dynamic QPS test case, identified a CPU hotspot in a time‑checking method, replaced it with a timestamp check, and achieved a modest 0.1% reduction in overall CPU usage, illustrated with flame‑graph images and code snippets.
This comprehensive guide explains Linux kernel performance profiling—both on‑CPU and off‑CPU—by stressing the need to target the critical 3 % of code, covering throughput, latency and power metrics, scalability laws, flame‑graph visualizations, perf and eBPF tools, lock‑contention analysis, and further reading recommendations.
The article describes an iOS lag‑monitoring system that detects main‑thread RunLoop blocks, samples stacks every 50 ms into a circular buffer, uses an annealing Fibonacci‑based interval to minimize overhead, visualizes hot paths with flame graphs, and streams data through a Flink‑APM pipeline with only ~2 % CPU and a few megabytes of memory impact.
The article describes an iOS lag‑monitoring system that uses RunLoop state checks to detect main‑thread stalls, captures and caches stack traces, employs a Fibonacci‑based annealing algorithm to limit overhead, symbolises addresses on a server, and visualises results with flame graphs while maintaining low CPU and memory impact.
This article presents a comprehensive guide to Linux performance analysis, covering background, methodology, tools, and step‑by‑step case studies for CPU, memory, disk I/O, network, system load, and flame‑graph techniques to quickly locate and resolve bottlenecks.
This comprehensive guide explains how to diagnose Linux system performance issues using a structured 5W2H approach, covering CPU, memory, disk I/O, network, load, and flame‑graph analysis, with practical command examples and a real‑world nginx case study.
This article introduces three popular Linux performance profiling tools—Perf, gprof, and Valgrind—explaining their installation, basic command‑line usage, and how to visualize results with flame graphs, call graphs, or KCachegrind, while comparing their intrusiveness, startup methods, and output formats.
The article details how to identify and resolve memory leaks and performance bottlenecks in high‑concurrency Nginx workloads using tools such as Valgrind, AddressSanitizer, perf and flame‑graphs, while also sharing practical tips and personal reflections on debugging under pressure.