High Performance Rails (long edition)Which I talked at Rubykaigi 2013 is: https://speakerdeck.com/mirakui/high-performance-rails
O'Reilly Media - Technology and Business Training
New! O’Reilly announces launch of the AI Academy. Read now Introducing the AI Academy Help your entire org put GenAI to work Every employee today needs to know how to prompt GenAI, use it to enhance critical thinking and productivity, and more. With the AI Academy they can. For less. O’Reilly AI-powered Answers just got even smarter O’Reilly Answers instantly generates information teams can trust,
Cybozu Inside Out: ScaleBench 公開
ã©ãƒ¼ã‚‚ã¿ãªã•ã¾ã€‚ã“ã‚“ã«ã¡ã¯ã€‚ amachang ã¨ç”³ã—ã¾ã™ã€‚ ã•ã¦ã€ã‚ˆã†ã‚„ã ScaleBench ã¨ã„ã†ãƒ—ãƒãƒ€ã‚¯ãƒˆãŒç™ºè¡¨ã•ã‚Œã¾ã—ãŸãï¼ ScaleBench ã®ã”紹介 ã§ã€åƒ•ã‚‚ã“ã‚Œã®é–‹ç™ºã«æºã‚ã£ã¦ã„ãŸã®ã§ã¡ã‚‡ã£ã¨æŠ€è¡“çš„ãªã“ã¨ã«ã¤ã„ã¦æ›¸ã„ã¦ã¿ãŸã„ã¨æ€ã„ã¾ã™ã€‚ ScaleBench ã¨ã¯ ScaleBench ã¨ã¯ã€ã‚µã‚¤ãƒœã‚¦ã‚ºè£½å“å‘ã‘ã®è² è·ãƒ†ã‚¹ãƒˆãƒ„ール㧠Grinder ã¨ã„ã†ã‚ªãƒ¼ãƒ—ンソースã®è² è·ãƒ†ã‚¹ãƒˆãƒ„ールをベースã«ã—ã¦ã„ã¾ã™ã€‚ Grinder ã¨ã¯ Java を使ã£ãŸ Web ã®è² è·ãƒ†ã‚¹ãƒˆãƒ„ールã§ã™ã€‚ Jython ã§ã‚·ãƒŠãƒªã‚ªï¼ˆãƒ¦ãƒ¼ã‚¶ãŒã©ã†è¡Œå‹•ã™ã‚‹ã‹ï¼‰ã‚’書ã„ã¦ãれを実行ã—ã¾ã™ã€‚ ã¾ãŸãƒ–ラウザã®æ“作を記録ã—ã¦ã€ã‚·ãƒŠãƒªã‚ªã‚’自動ã§ç”Ÿæˆã™ã‚‹ã“ã¨ã‚‚ã§ããŸã‚Šã—ã¾ã™ã€‚ ã§ã€åƒ•ãŒã“ã®ãƒ—ãƒã‚¸ã‚§ã‚¯ãƒˆã§æ‹…当ã—ã¦ã„ãŸã®ãŒ Grinder ã®æ”¹è‰¯ã€æ”¹é€ シナリオ（ãƒãƒ¼ãƒãƒ£ãƒ«ãƒ¦ãƒ¼ã‚¶ãŒã©ã®ã‚ˆã†ãªé †ã§è² è·ã‚’ã‹ã‘ã¦ã„ãã‹
ã€ãƒã‚¦ãƒ„ー】Cアプリを高速化ã›ã‚ˆ! - æ£å¼ãƒªãƒªãƒ¼ã‚¹ã•ã‚ŒãŸgoogle-perftoolsを試㙠(1) google-perftoolsã¨ã¯ | エンタープライズ | マイコミジャーナル
google-perftoolsã¯Googleã«ã‚ˆã£ã¦æä¾›ã•ã‚Œã¦ã„ã‚‹ã€C/C++アプリケーションã®ãƒ‘フォーマンスを改善ã™ã‚‹ãŸã‚ã®é–‹ç™ºãƒ„ールã‚ットã§ã‚る。2005å¹´3月ã«åˆã‚ã¦å…¬é–‹ã•ã‚Œã€ãŠã‚ˆã4年を経ã¦7æ—¥ã«æ£å¼ç‰ˆãŒãƒªãƒªãƒ¼ã‚¹ã•ã‚ŒãŸã€‚The BSD Licenseã®ä¸‹ã§æä¾›ã•ã‚Œã¦ãŠã‚Šã€Linuxã‚’ã¯ã˜ã‚ã¨ã—ã¦FreeBSDã€Mac OS Xã€Solaris 10ã€Windows XPãªã©ã€å„種プラットフォームã§ã®å‹•ä½œãŒç¢ºèªã•ã‚Œã¦ã„ã‚‹(ãŸã ã—ã€Linux以外ã«ã¤ã„ã¦ã¯ä¸€éƒ¨æ©Ÿèƒ½ã‚’除ã)。 google-perftoolsã«ã¯æ¬¡ã«æŒ™ã’ã‚‹4ã¤ã®ãƒ„ールãŒå«ã¾ã‚Œã¦ã„る。 高速メモリアãƒã‚±ãƒ¼ã‚¿TCMalloc ヒープãƒã‚§ãƒƒã‚«ãƒ¼ ヒーププãƒãƒ•ã‚¡ã‚¤ãƒ© CPUプãƒãƒ•ã‚¡ã‚¤ãƒ© TCMalloc(Thread-Caching Malloc)ã¯é€šå¸¸ã®mallocよりも高速ãªãƒ¡ãƒ¢ãƒªå‰²ã‚Šå½“ã¦ã‚’実ç¾ã™ã‚‹ãƒ©ã‚¤ãƒ–ラリã§ã‚ã‚Šã€ãƒ†ã‚¹ãƒˆ
masuidrive on rails - Railsアプリをãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã™ã‚‹ãªã‚‰New Relic RPM
Photo by Riverman72 ã‚ã¨ã§è‡ªåˆ†ãƒ¡ãƒ¢ã‚’書ã“ã†ã¨æ€ã†ã‘ã©ã€å…ˆã«ä¸€è¨€ã€‚ 37signalsも使ã£ã¦ã„ã‚‹ã¨ã„ã†ã†ãŸã„æ–‡å¥ã«æƒ¹ã‹ã‚Œã¦è©¦ã—ã¦ã¿ãŸã€Railsã®ãƒ‘フォーマンス記録ツール/サービスNew Relic RPM(Rails Performance Management)ãŒã€ã™ã°ã‚‰ã—ã„。 RPMã¯é–‹ç™ºæ™‚用ã®Developerã¨ã€å®Ÿæ©Ÿç”¨ã®Productionã®ãŒäºŒã¤ã‚ã‚Šã€ã¾ã 開発時用ã®Developerモードã—ã‹è©¦ã—ã¦ã¯ã„ãªã„ã‚“ã ã‘ã©ã€å°‚用ã®ç®¡ç†ç”»é¢ã§ã€ã‚¢ã‚¯ã‚·ãƒ§ãƒ³ã‚’実行時ã®ãƒ¡ã‚½ãƒƒãƒ‰å˜ä½ã®å®Ÿè¡Œæ™‚é–“ã€ç”Ÿæˆã•ã‚Œã‚‹SQLã€SQLã®å®Ÿè¡Œæ™‚間やインデックスã®åˆ©ç”¨çŠ¶æ³ãªã©ãŒéžå¸¸ã«ç°¡å˜ã«æŠŠæ¡ã§ãã¾ã™ã€‚ Railsã§é–‹ç™ºã—ã¦ã„る人ãªã‚‰ã€ä¸‹ã®ãƒ ービーを見れã°ã€ãã®ã™ã”ã•ãŒåˆ†ã‹ã‚‹ã¯ãšã€‚ RPM developerã®ãƒ‡ãƒ¢å‹•ç”» | RPM production ã®ãƒ‡ãƒ¢å‹•ç”» ã„ã¾ã“れを使ã£ã¦ã€PhotoS
Scaling Twitter: Making Twitter 10000 Percent Faster - High Scalability -
Update 6: Some interesting changes from Twitter's Evan Weaver: everything in RAM now, database is a backup; peaks at 300 tweets/second; every tweet followed by average 126 people; vector cache of tweet IDs; row cache; fragment cache; page cache; keep separate caches; GC makes Ruby optimization resistant so went with Scala; Thrift and HTTP are used internally; 100s internal requests for every exter
Google-perftoolsを使ã£ã¦CPUプãƒãƒ•ã‚¡ã‚¤ãƒªãƒ³ã‚°ã‚’ã¨ã‚‹ - PS3 Linux Information Site / Cell/B.E.ã®ãƒ‘ワーを体験ã—よã†
google-perftoolsã¨ã¯ ã‚°ãƒ¼ã‚°ãƒ«æ ªå¼ä¼šç¤¾ã§é–‹ç™ºã€å…¬é–‹ã•ã‚Œã¦ã„る高速mallocã‚„CPUプãƒãƒ•ã‚¡ã‚¤ãƒªãƒ³ã‚°ã¨è§£æžãªã©ã‚’è¡Œã†ã‚ªãƒ¼ãƒ—ンソースã®ãƒ„ール群ã§ã™ã€‚ ã“ã“ã“ã§ã¯ã‚µãƒ³ãƒ—リングベースã®CPUプãƒãƒ•ã‚¡ã‚¤ãƒ©ãƒ¼ã§ã‚ã‚‹ cpu profiler を紹介ã—ã¾ã™ã€‚ cpu profilerã¯ã‚¢ãƒ¼ã‚テクãƒãƒ£ãƒ¼ã«ä¾å˜ã—ãªã„Linux用ソフトウェアãªã®ã§å½“然Cellã§ã‚‚使用ã™ã‚‹ã“ã¨ãŒå¯èƒ½ã§ã™ã€‚ ã“ã“ã§ãƒ—ãƒãƒ•ã‚¡ã‚¤ãƒ«ã®æ¸¬å®šå¯¾è±¡ã¨ã—ãŸã‚½ãƒ¼ã‚¹ã‚³ãƒ¼ãƒ‰ã¯ã“ã‚Œã§ã™ã€‚ Media:Google-perftools-cpuprofile.tar.gz google-perftoolsã®ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ« google-perftoolsã¯ã“ã¡ã‚‰ã‹ã‚‰ãƒ€ã‚¦ãƒ³ãƒãƒ¼ãƒ‰ã§ãã¾ã™ã€‚http://goog-perftools.sourceforge.net/ ãƒã‚¤ãƒŠãƒªãƒ‘ッケージ(*.rpm)ã¯ãªã„ã®ã§ã‚½ãƒ¼ã‚¹ã‚’ダウンãƒãƒ¼ãƒ‰ã—ã¦ã‚³ãƒ³ãƒ‘
NLANR/DAST : Iperf The TCP/UDP Bandwidth Measurement Tool
The National Laboratory for Applied Network Research (NLANR) has as its primary goal to provide technical, engineering, and traffic analysis support of NSF High Performance Connections sites and HPNSP (high-performance network service providers) such as the NSF/MCI very high performance Backbone Network Service (vBNS). Funded by the National Science Foundation Computer and Information Science and
1
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
http://www.designwalker.com/2009/01/speedup.html
{{#tags}}- {{label}}
{{/tags}}