Performance Analysis (16)

• The SGI XFS Filesystem — The Linux Kernel documentation (docs.kernel.org) reference
  XFS mount options and on-disk behaviour: allocsize, discard, journaling and large-filesystem tuning
  Filesystem Kernel #
• PHP: FastCGI Process Manager (FPM) - Manual (php.net) reference
  PHP FastCGI process manager: per-pool uid/chroot workers, dynamic spawning, slowlog, status output
  Application Server Web Server #
• SQL Indexing and Tuning e-Book for developers: Use The Index, Luke covers Oracle, MySQL, PostgreSQL, SQL Server, ... (use-the-index-luke.com) tutorial
  vendor-agnostic SQL indexing and query tuning; free web edition of SQL Performance Explained
  Relational Database SQL #
• Jaeger: open source, distributed tracing platform (Jaeger) tool
  CNCF platform mapping request flow across microservices to find bottlenecks; ClickHouse storage backend
  Distributed Tracing Observability #
• GitHub - akopytov/sysbench: Scriptable database and system performance benchmark (GitHub) repo
  scriptable LuaJIT benchmark: OLTP database workloads plus CPU, memory, fileio and thread tests
  Database Administration Load Testing #
• Welcome to FIO’s documentation! — fio 3.42-115-gcd29 documentation (fio.readthedocs.io) reference
  job-file reference for the flexible I/O tester: engines, block sizes, latency, terse and JSON output
  Block Storage Load Testing #
• GitHub - wg/wrk: Modern HTTP benchmarking tool (GitHub) repo
  Multithreaded HTTP load generator on epoll/kqueue, with optional LuaJIT request and report scripting
  HTTP Load Testing #
• Grafana k6 | Grafana k6 documentation (Grafana Labs) reference
  scripting load, spike, stress and soak tests in JavaScript; open source, paid Grafana Cloud backend
  Load Testing #
• iPerf - The TCP, UDP and SCTP network bandwidth measurement tool (iperf.fr) tool
  TCP, UDP and SCTP throughput, loss and jitter measurement between two hosts, BSD-licensed
  Load Testing Network Diagnostic #
• GitHub - ColinIanKing/stress-ng: This is the stress-ng upstream project git repository. stress-ng will stress test a computer system in various selectable ways. It was designed to exercise various physical subsystems of a computer as well as the various operating system kernel interfaces. (GitHub) repo
  380+ stress tests loading CPU, memory, filesystem and cache to trip thermal and kernel faults
  Hardware Load Testing #
• Netdata: Monitoring and troubleshooting transformed (netdata.cloud) tool
  Per-second metrics, dashboards and alerts from an open agent; paid managed and on-prem cloud tiers
  Observability Self Hosting #
• Prometheus - Monitoring system & time series database (prometheus.io) tool
  dimensional metrics model queried with PromQL, alerting via Alertmanager; standalone Go binary, local storage
  Observability #
• GitHub - aristocratos/btop: A monitor of resources (GitHub) repo
  C++ rewrite of bashtop/bpytop with mouse support, themes and GPU stats; Linux, macOS and BSD
  Command Line #
• bpftrace: dynamic tracing for Linux | bpftrace (bpftrace.org) tool
  Awk-like language for writing eBPF probes without touching the raw eBPF toolchain, plus a tool collection
  eBPF Kernel #
• Brendan Gregg's Homepage (brendangregg.com) personal-site
  Flame graphs, eBPF tracing methods, talks and slides from a datacenter performance engineer
  eBPF Kernel #
• iperf3 — iperf3 3.21 documentation (software.es.net) reference
  Active TCP/UDP throughput measurement with tunable buffers and JSON output; not compatible with iperf2
  Command Line Network Diagnostic #