[B! performance] ori53ã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

ori53 id:ori53

performanceã«é–¢ã™ã‚‹ori53ã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (21)

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

${{author_name}}$
{{author_name}}{{created}}
{{ #comment }}{{ comment }}{{ /comment }}
- {{ label }}

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

MySQL 5.6ã¨5.7ã«ãŠã‘ã‚‹é«˜åº¦ãªã‚¯ã‚¨ãƒªãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã®Q&A(The Percona Performance Blogã‚ˆã‚Š) | Yakst
ç´„9å¹´å‰æŠ•ç¨¿ ä¿®æ£ã‚ã‚ŠMySQL 5.6ã¨5.7ã«ãŠã‘ã‚‹é«˜åº¦ãªã‚¯ã‚¨ãƒªãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã®Q&A(The Percona Performance Blogã‚ˆã‚Š) å‡ºå…¸ã«ã¤ã„ã¦ ã“ã®è¨˜äº‹ã¯The Percona Performance Blogå†…ã®Alexander Rubinæ°ã«ã‚ˆã‚‹ã€ŒAdvanced Query Tuning in MySQL 5.6 and MySQL 5.7 Webinar: Q&Aã€(2015/8/24)ã‚’ç¿»è¨³ã—ãŸã‚‚ã®ã§ã‚ã‚‹ã€‚ 8æœˆ22æ—¥ã®ã‚ªãƒ³ãƒ©ã‚¤ãƒ³ã‚»ãƒŸãƒŠãƒ¼ã€ŒMySQL 5.6ãŠã‚ˆã³5.7ã«ãŠã‘ã‚‹é«˜åº¦ãªã‚¯ã‚¨ãƒªãƒ¼ãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã€ã«å‚åŠ ã—ã¦ã„ãŸã ã„ã¦ã‚ã‚ŠãŒã¨ã†(ç§ã®ã‚¹ãƒ©ã‚¤ãƒ‰ãŠã‚ˆã³å‹•ç”»ã¯ã“ã“ã§ç¢ºèªã§ãã‚‹)ã€‚ã“ã“ã§ã¯è³ªå•ã¨ãã®å›žç”ã®ä¸€è¦§ã‚’ç´¹ä»‹ã™ã‚‹(ã„ã„è³ªå•ã‚’ã‚ã‚ŠãŒã¨ã†) ã€‚ Q: ã“ã“ã«explainã®ä¾‹ãŒã‚ã‚‹ mysql> explain extended select id, s
ori53 2015/09/14
mysql

performance
ãƒªãƒ³ã‚¯
Linux ã®ãƒ—ãƒã‚»ã‚¹ãŒ Copy on Write ã§å…±æœ‰ã—ã¦ã„ã‚‹ãƒ¡ãƒ¢ãƒªã®ã‚µã‚¤ã‚ºã‚’èª¿ã¹ã‚‹
Linux ã¯ fork ã§åãƒ—ãƒã‚»ã‚¹ã‚’ä½œæˆã—ãŸå ´åˆã€è¦ªã®ä»®æƒ³ãƒ¡ãƒ¢ãƒªç©ºé–“ã®å†…å®¹ã‚’åã¸ã‚³ãƒ”ãƒ¼ã™ã‚‹å¿…è¦ãŒã‚ã‚Šã¾ã™ã€‚ã—ã‹ã—ã¾ã¨ã‚‚ã«å…¨ç©ºé–“ã‚’ã‚³ãƒ”ãƒ¼ã—ã¦ã„ãŸã®ã§ã¯ fork ã®ã‚³ã‚¹ãƒˆãŒé«˜ããªã£ã¦ã—ã¾ã„ã¾ã™ã—ã€åãŒè¦ªã¨åŒã˜ã‚ˆã†ãªãƒ—ãƒã‚»ã‚¹ã¨ã—ã¦å‹•ä½œã—ç¶šã‘ã‚‹å ´åˆã¯ã€å†…å®¹ã®é‡è¤‡ã—ãŸãƒšãƒ¼ã‚¸ãŒå¤šæ•°ã§ãã¦ã—ã¾ã„ã€åŠ¹çŽ‡ãŒã‚ˆãã‚ã‚Šã¾ã›ã‚“ã€‚ ãã“ã§ã€Linux ã®ä»®æƒ³ãƒ¡ãƒ¢ãƒªã¯ã€ãƒ¡ãƒ¢ãƒªç©ºé–“ã‚’èˆã‚ã¦ã‚³ãƒ”ãƒ¼ã™ã‚‹ã®ã§ã¯ãªãã€ã¯ã˜ã‚ã¯è¦ªåã§ãƒ¡ãƒ¢ãƒªé ˜åŸŸã‚’å…±æœ‰ã—ã¦ãŠã„ã¦ã€æ›¸ãè¾¼ã¿ãŒã‚ã£ãŸæ™‚ç‚¹ã§ã€ãã®æ›¸ãè¾¼ã¿ã®ã‚ã£ãŸãƒšãƒ¼ã‚¸ã ã‘ã‚’è¦ªåã§å€‹åˆ¥ã«æŒã¤ã¨ã„ã†ä»•çµ„ã¿ã§ã“ã®å•é¡Œã‚’å›žé¿ã—ã¾ã™ã€‚Copy-On-Write (CoW) ã¨å‘¼ã°ã‚Œã‚‹æˆ¦ç•¥ã§ã™ã€‚å…±æœ‰ãƒ¡ãƒ¢ãƒªãƒšãƒ¼ã‚¸ã¯ã€è¦ªåãã‚Œãžã‚Œã®ä»®æƒ³ãƒ¡ãƒ¢ãƒªç©ºé–“ã‚’åŒä¸€ã®ç‰©ç†ãƒ¡ãƒ¢ãƒªã«ãƒžãƒƒãƒ”ãƒ³ã‚°ã™ã‚‹ã“ã¨ã§å®Ÿç¾ã•ã‚Œã¾ã™ã€‚ã‚ˆã‚Šè©³ã—ãã¯ ã‚³ãƒ”ãƒ¼ã‚ªãƒ³ãƒ©ã‚¤ãƒˆ - Wikipedia ãªã©ã‚’å‚ç…§ã—ã¦ãã ã•ã„ã€‚ ã“ã® CoW ã«
ori53 2015/09/02
linux

kernel

performance

memory
ãƒªãƒ³ã‚¯
Linux Profiling at Netflix
This talk discusses Linux profiling using perf_events (also called "perf") based on Netflix's use of it. It covers how to use perf to get CPU profiling working and overcome common issues. The speaker will give a tour of perf_events features and show how Netflix uses it to analyze performance across their massive Amazon EC2 Linux cloud. They rely on tools like perf for customer satisfaction, cost o
ori53 2015/03/11
linux

performance
ãƒªãƒ³ã‚¯
OpenStack Nova Tuning Guideçš„ãªä½•ã‹ - ã‚ã‚‚ã‚ã‚‚
å¤‰æ›´å±¥æ´ 2014/03/19 ver1.0 ä½œæˆ ã“ã®ãƒ‰ã‚ãƒ¥ãƒ¡ãƒ³ãƒˆã®ç›®çš„ Compute NodeãŒæ•°ç™¾å°ã®è¦æ¨¡ã§Novaã‚’åˆ©ç”¨ã™ã‚‹å ´åˆã€å®Ÿç”¨çš„ãªæ€§èƒ½ã‚’å®Ÿç¾ã™ã‚‹ã«ã¯ã€OS/QPID/Novaãªã©ã®ã•ã¾ã–ã¾ãªãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã‚’èª¿æ•´ã™ã‚‹å¿…è¦ãŒå‡ºã¦ãã¾ã™ã€‚ã“ã®ãƒ‰ã‚ãƒ¥ãƒ¡ãƒ³ãƒˆã§ã¯ã€èª¿æ•´ã™ã‚‹ã¹ããƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã®å€™è£œã‚’ã–ã£ãã‚Šã¨ãƒªã‚¹ãƒˆã‚¢ãƒƒãƒ—ã™ã‚‹ã“ã¨ã‚’ç›®æŒ‡ã—ã¾ã™ã€‚RHEL6 + RDOï¼ˆGrizzly/Havanaï¼‰ã‚ãŸã‚Šã‚’å‰æã«ã—ã¦ã„ã¾ã™ã€‚ ã¾ã ã¾ã æ´å²ã®æµ…ã„OpenStackã§ã™ã®ã§ã€ã„ããªã‚Šã™ã¹ã¦ã®æƒ…å ±ã‚’ç¶²ç¾…ã™ã‚‹ã®ã¯é›£ã—ã„éƒ¨åˆ†ã‚‚ã‚ã‚Šã¾ã™ãŒã€ã¿ãªã•ã¾ã‹ã‚‰ã®æƒ…å ±ã‚’å…ƒã«éšæ™‚ã‚¢ãƒƒãƒ—ãƒ‡ãƒ¼ãƒˆã—ã¦ã„ã‘ã‚Œã°ã„ã„ãªãƒ¼ã€ã¨æ€ã£ã¦ã¾ã™ã€‚è¨å®šã™ã‚‹ã¹ãå…·ä½“çš„ãªå€¤ã«ã¤ã„ã¦ã¯ã€ç’°å¢ƒä¾å˜ã®è¦ç´ ã‚‚å¤šãã€å®Ÿç’°å¢ƒã§ã®çµŒé¨“ã‚’å…ƒã«ã€ŒBest Practiceã€ã‚’è¦‹å‡ºã™å¿…è¦ãŒã‚ã‚Šã¾ã™ã€‚å…·ä½“çš„ãªè¨å®šå€¤ã«ã¤ã„ã¦ã‚‚ã€ä»Šå¾Œã€ã§ãã‚‹ã ã‘æƒ…å ±ã‚’è¿½åŠ ã—ã¦ã„ããŸã„ã¨
ori53 2014/03/29
openstack

performance
ãƒªãƒ³ã‚¯
The PHP echo why so slow - Database - Database Skill
The PHP echo why so slow. Get database skills from databaseskill.com.Tag: FUNCtion, string, the php, server Category: Database Author: aqmei Date: 2012-03-01 As a walking old Chinese rivers and lakes for many years, ordered to solve a case of the front page to show the probl em of slow today. The probl em page is as follows: apache + php Using smarty template output content Page final output, 80k
ori53 2014/03/28
php

performance
ãƒªãƒ³ã‚¯
IDCF ãƒ†ãƒƒã‚¯ãƒ–ãƒã‚°
IDCãƒ•ãƒãƒ³ãƒ†ã‚£ã‚¢ã®UIãƒ»UXãƒãƒ¼ãƒ ã§ã™ã€‚ å‰å›žã¯ãƒ•ãƒãƒ³ãƒˆã‚¨ãƒ³ãƒ‰é ˜åŸŸã®é–‹ç™ºã«é–¢ã™ã‚‹æ¥å‹™ãƒ•ãƒãƒ¼ã‚’ä¸å¿ƒã«ã”ç´¹ä»‹ã—ã¾ã—ãŸã€‚ä»Šå›žã¯åˆ©ç”¨æŠ€è¡“ã ã‘ã§ãªãã€åŠ¹çŽ‡çš„ã«é–‹ç™ºã‚’é€²ã‚ã‚‹ãŸã‚ã®å·¥å¤«ã‚„æ™®æ®µæ°—ã‚’ä»˜ã‘ã¦ã„ã‚‹ç‚¹ãªã©ã‚’ã”ç´¹ä»‹ã—ã¾ã™ã€‚ å‰å›žã®ãƒ–ãƒã‚°å†…å®¹ã¨åˆã‚ã›ã¦èªã‚“ã§ã„ãŸã ãã¨ã€å®Ÿéš›ã®æ¥å‹™ã‚¤ãƒ¡ãƒ¼ã‚¸ãŒæƒ³åƒã—ã‚„ã™ã„ã‹ã‚‚ã—ã‚Œã¾ã›ã‚“ã€‚ åˆ©ç”¨æŠ€è¡“ JavaScriptãƒ©ã‚¤ãƒ–ãƒ©ãƒª ãƒ©ã‚¤ãƒ–ãƒ©ãƒªã®å–ã‚Šæ‰±ã„ é™çš„è§£æžãƒ„ãƒ¼ãƒ« CI CD ç”Ÿç”£æ€§ã‚’ä¸Šã’ã‚‹ãŸã‚ã®å·¥å¤« ãƒ‡ã‚¶ã‚¤ãƒ³ã‚·ã‚¹ãƒ†ãƒ ã‚’ç”¨ã„ãŸUIä»•æ§˜ã®æ±ºå®š ãƒ†ã‚¹ãƒˆé§†å‹•é–‹ç™ºã‚’ç”¨ã„ãŸæ‰‹æˆ»ã‚Šãƒ»æŠœã‘æ¼ã‚Œã®é˜²æ¢ Autifyã‚’ç”¨ã„ãŸE2Eãƒ†ã‚¹ãƒˆã®å®Ÿæ–½ æ™®æ®µé–‹ç™ºã‚„ã‚³ãƒ¼ãƒ‰ãƒ¬ãƒ“ãƒ¥ãƒ¼ã§æ„è˜ã—ã¦ã„ã‚‹ã“ã¨ é•·æœŸãƒ¡ãƒ³ãƒ†ã‚’è€ƒæ…®ã—ãŸè¨è¨ˆãƒ»å®Ÿè£…ã«ã™ã‚‹ åˆå¿ƒè€…ã§ã‚‚èªã‚ã‚‹å®Ÿè£…ã‚’å¿ƒãŒã‘ã‚‹ ã©ã‚“ãªæ–¹ãŒå‘ã„ã¦ã„ã‚‹ã‹ ãŠå®¢ã•ã¾ã®åˆ†ã‹ã‚Šã‚„ã™ã•ã‚’è¿½åŠã™ã‚‹ãŸã‚ã«ã©ã‚“ãªUIãŒã„ã„ã‹è€ƒãˆã‚‰ã‚Œã‚‹æ–¹ ã‚ˆã‚Šèªã¿ã‚„ã™ãä¿å®ˆã—ã‚„ã™ã„ã‚³ãƒ¼ãƒ‰ã‚’æ›¸ã
ori53 2013/12/01
benchmark

performance
ãƒªãƒ³ã‚¯
High Performance Web Frontend
â˜…è¿½è¨˜ï¼š https://speakerdeck.com/ahomu/high-performance-web-frontend-2013-qiu ã®ã»ã†ãŒãƒ–ãƒ©ãƒƒã‚·ãƒ¥ã‚¢ãƒƒãƒ—ç‰ˆã§ã™ WCAN 2013 Summer (7/6) ã§è¡Œã‚ã‚ŒãŸã€"High Performance Web Frontendâ€¦
ori53 2013/11/21
performance

web

frontend
ãƒªãƒ³ã‚¯
Navigation Timing (W3C Working Draft 26 October 2010)
W3C Recommendation 17 December 2012 This version: http://www.w3.org/TR/2012/REC-navigation-timing-20121217/ Latest version: http://www.w3.org/TR/navigation-timing/ Previous version: http://www.w3.org/TR/2012/PR-navigation-timing-20120726/ Editor: Zhiheng Wang (Google Inc.) <zhihengw@google.com> Please refer to the errata for this document, which may include some normative corrections. See also tra
ori53 2013/11/13
performance

api

web
ãƒªãƒ³ã‚¯
Navigation Timing
ori53 2013/11/13
performance

api

web
ãƒªãƒ³ã‚¯
Navigation timing - Web APIs | MDN
DOM construction has finished and interaction with the DOM is possible. Only the current document is included, so usually there is only one PerformanceNavigationTiming object to observe. It extends the PerformanceEntry interface with the entryType of "navigation" and also inherits from PerformanceResourceTiming, so all of the timestamps from the process of fetching the document are available as we
ori53 2013/11/13
performance

api

web
ãƒªãƒ³ã‚¯
collectd
collectd-6.0.0.rc3 collectd-5.12.0 Start | Download | Documentation | Contact collectd is a daemon collecting system and application performance metrics periodically and provides mechanisms to store the values in a variety of ways, for example in RRD files. What does collectd do? collectd gathers metrics from various sources, e.g. the operating system, applications, logfiles and external devices,
ori53 2013/06/11
performance

ç›£è¦–
ãƒªãƒ³ã‚¯
Brendan Gregg's Talk on Linux at SCaLE 11x | Triton DataCenter
Brendan Gregg will be keynoting at SCaLE 12x - February 21-23, 2014. Register Now. Linux Performance Analysis and Tools from brendangregg Our friends at SCaLE invited our lead performance engineer, Brendan Gregg, to speak (again) this year,and he was happy to return. The talk is about Linux Performance Analysis and Tools: specifically, observability tools and the methodologies to use them. Brendan
ori53 2013/03/05
linux

performance
ãƒªãƒ³ã‚¯
kernel: TCP: time wait bucket table overflow ã®è§£æ¶ˆã¨TIME_WAITã‚’æ¸›ã‚‰ã™ãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚° - æ°—ã¾ã¾ã«ã‚¤ãƒ³ãƒ•ãƒ©ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢
æ•´ç†ãŒã¦ã‚‰ã€‚ httpdãŒå‹•ã„ã¦ã„ã‚‹ã‚ã‚‹ãƒ›ã‚¹ãƒˆä¸Šã§ã€ /var/log/messages ã«ä»¥ä¸‹ã®ã‚ˆã†ãªãƒ¡ãƒƒã‚»ãƒ¼ã‚¸ãŒå‡ºã¦ã„ãŸã€‚ kernel: TCP: time wait bucket table overflow kernel: printk: 50078 messages suppressed. "netstat -tna |grep TIME_WAIT"ã™ã‚‹ã¨ã€10ä¸‡ä»¥ä¸Šã®æ•°ã§TIME_WAITãŒå‡ºã¦ã„ã‚‹ã€‚ã“ã‚Œã‚’è§£æ¶ˆã™ã‚‹ã¾ã§ã®æµã‚Œã€‚ ãã‚‚ãã‚‚ã“ã®å€¤ã¯ã€ã‚«ãƒ¼ãƒãƒ«ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã® net.ipv4.tcp_max_tw_buckets ã§è¨å®šã•ã‚Œã¦ã„ã‚‹ã€‚ãƒ‡ãƒ•ã‚©ãƒ«ãƒˆã¯16384ã€‚ ï¼ˆâ†‘ã®é€šã‚Šã€ã‚¨ãƒ©ãƒ¼ãŒå‡ºãŸç’°å¢ƒã§ã¯æ—¢ã«ã‹ãªã‚Šå¤§ããªå€¤ãŒè¨å®šã•ã‚Œã¦ã„ãŸã®ã ãŒã€‚ï¼‰ /proc/sys/net/ipv4/tcp_max_tw_buckets ã‚·ã‚¹ãƒ†ãƒ ãŒåŒæ™‚ã«ä¿æŒã™ã‚‹ time-wait ã‚½ã‚±ãƒƒãƒˆã®æœ€å¤§
ori53 2013/02/06
TIME_WAIT

performance

network

linux

kernel
ãƒªãƒ³ã‚¯
ARCãƒŸã‚¹ã‚’åˆ†æžã—ã¦ã¿ãŸ
æ—¥æœ¬æœ€å¼·ã®çœ‹æ¿ã‚’ä¸‹ã‚ã—ãŸãƒŸãƒ©ãƒ¼ã‚µãƒ¼ãƒftp.jaist.ac.jpã®ç®¡ç†è€…ã®ä¸€äººãŒã€ ã“ã®ã‚µãƒ¼ãƒã«ã¾ã¤ã‚ã‚‹ã‚ˆã—ãªã—ã”ã¨ã‚’èªžã‚Šã¾ã™ã€‚ English versions of some posts on another blog. å…ˆæ—¥ã®éšœå®³ã§ã€ARCãƒŸã‚¹ã—ãŸI/OãŒHDDã§å‡¦ç†ã§ãã‚‹IOPSã‚’è¶…ãˆã¦ã„ã‚‹ã“ã¨ãŒã‚ã‹ã‚Šã¾ã—ãŸã€‚ãã“ã§ZFSã¸ã®ã‚¢ã‚¯ã‚»ã‚¹ã®ã†ã¡ã€ã©ã‚“ãªARCãƒŸã‚¹ãŒã©ã‚Œãã‚‰ã„ç™ºç”Ÿã—ã¦ã„ã‚‹ã‹ã‚’èª¿ã¹ã¦ã¿ã¾ã—ãŸã€‚ä½¿ã£ãŸã®ã¯ã“ã®DTraceã‚¹ã‚¯ãƒªãƒ—ãƒˆã§ã™ã€‚ãƒ—ãƒã‚»ã‚¹ã¨ãƒ•ã‚¡ã‚¤ãƒ«ã‚·ã‚¹ãƒ†ãƒ ã®ã‚ªãƒšãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³(vnode operation)ã”ã¨ã«ã€ARCãƒŸã‚¹ã¨L2ARCãƒŸã‚¹ã®ç™ºç”Ÿå›žæ•°ã‚’100ç§’é–“è¨ˆæ¸¬ã—ã¾ã™ã€‚12æœˆ12æ—¥ã®16:30ã«HDDã®è² è·ã®å¹³å‡ãŒ81.7%ã®ã¨ãã«ãƒ‡ãƒ¼ã‚¿ã‚’å–ã‚Šã¾ã—ãŸã€‚ ARCã®ãƒ’ãƒƒãƒˆçŽ‡ã¯å¹³å‡ã§93%ã§ã™ãŒã€ARCãƒŸã‚¹ã¯1ç§’å½“ãŸã‚Š1,709å›žç™ºç”Ÿã—ã¦ã„ã¾ã—ãŸã€‚ãã—ã¦L2ARCãƒŸã‚¹ã¯1
ori53 2012/12/30
zfs

L2ARC

storage

performance
ãƒªãƒ³ã‚¯
Gartner
Understand, plan, pilot, implement and maintain GenAI. Learn More
ori53 2012/08/06
cloud

performance

benchmark
ãƒªãƒ³ã‚¯
GCViewer
GCViewer (download) is a free open source tool to visualize data produced by the Java VM options -verbose:gc and -Xloggc:<file>. It also calculates garbage collection related performance metrics (throughput, accumulated pauses, longest pause, etc.). This can be very useful when tuning the garbage collection of a particular application by changing generation sizes or setting the initial heap size.
ori53 2012/07/27
java

benchmark

performance

metrics
ãƒªãƒ³ã‚¯
MySQLã®DRBDæ§‹æˆã«ãŠã‘ã‚‹ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯é…å»¶ã®å½±éŸ¿ã«ã¤ã„ã¦ - SH2ã®æ—¥è¨˜
ä»Šã•ã‚‰ã§ã™ãŒã€Amazon RDSã®ãƒžãƒ«ãƒAZãƒ‡ãƒ—ãƒã‚¤ãƒ¡ãƒ³ãƒˆã«ã¤ã„ã¦èª¿ã¹ã¦ã„ã¾ã—ãŸã€‚ãƒžãƒ«ãƒAZãƒ‡ãƒ—ãƒã‚¤ãƒ¡ãƒ³ãƒˆã¨ã¯ã€ç‹¬ç«‹ã—ãŸé›»æºã€ç©ºèª¿ã€ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã€ã‚»ã‚ãƒ¥ãƒªãƒ†ã‚£ã‚’å‚™ãˆãŸç‰©ç†çš„ã«ç•°ãªã‚‹ãƒã‚±ãƒ¼ã‚·ãƒ§ãƒ³ã«å¯¾ã—ã¦åŒæœŸãƒ¬ãƒ—ãƒªã‚±ãƒ¼ã‚·ãƒ§ãƒ³ã‚’è¡Œã†ã“ã¨ã§ã€ãƒ‡ãƒ¼ã‚¿ãƒ™ãƒ¼ã‚¹ã®è€éšœå®³æ€§ã‚’é«˜ã‚ã‚‹æ©Ÿèƒ½ã§ã™ã€‚AZã¯Availability Zoneã®ç•¥ã§ã™ã€‚ ç•°ãªã‚‹ãƒã‚±ãƒ¼ã‚·ãƒ§ãƒ³ã«å¯¾ã™ã‚‹åŒæœŸãƒ¬ãƒ—ãƒªã‚±ãƒ¼ã‚·ãƒ§ãƒ³ã¨èžãã¨ã€æ€§èƒ½ãŒå‡ºãªã„ã®ã§ã¯ãªã„ã‹ã¨ã„ã†æ‡¸å¿µãŒã©ã†ã—ã¦ã‚‚å‡ºã¦ãã¾ã™ã€‚ãã“ã§ã€ã©ã®ç¨‹åº¦æ€§èƒ½ãŒè½ã¡ã‚‹ã‚‚ã®ãªã®ã‹æ¤œè¨¼ã‚’è¡Œã„ã¾ã—ãŸã€‚ãªãŠã€ã™ã§ã«å®Ÿéš›ã®Amazon RDSã‚’åˆ©ç”¨ã—ã¦æ¤œè¨¼ã‚’è¡Œã£ãŸæ–¹ãŒã„ã‚‰ã£ã—ã‚ƒã„ã¾ã—ãŸã®ã§ã€ä»Šå›žã¯æ‰‹å…ƒã®ç’°å¢ƒã‚’åˆ©ç”¨ã—ã¦ã€ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯é…å»¶ã‚„MySQLãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã¨æ€§èƒ½ã¨ã®é–¢é€£æ€§ã‚’ç¢ºèªã—ã¦ã„ããŸã„ã¨æ€ã„ã¾ã™ã€‚ Amazon RDS MYSQL Performance Benchmarking - Cloud
ori53 2012/06/25
mysql

DRBD

performance

benchmark
ãƒªãƒ³ã‚¯
High Performance Web Sites
14 Rules for Faster-Loading Web Sites These rules are the key to speeding up your web pages. They've been tested on some of the most popular sites on the Internet and have successfully reduced the response times of those pages by 25-50%. The key insight behind these best practices is the realization that only 10-20% of the total end-user response time is spent getting the HTML document to the brow
ori53 2012/06/17
performance

benchmark
ãƒªãƒ³ã‚¯
Home
There are many new serving databases available, including: HBase Hyperta ble Cassandra Couchbase Voldemort Mongo DB OrientDB Infinispan Redis GemFire DynamoDB Tarantool Memcached â€¦and many others It is difficult to decide which system is right for your application, partially because the features differ between systems, and partially because there is not an easy way to compare the performance of one
ori53 2012/05/20
benchmark

performance

cloud
ãƒªãƒ³ã‚¯
DBå‡¦ç†ã§æ€§èƒ½ãŒ40ï½ž60ï¼…ä½Žä¸‹
ä»®æƒ³åŒ–ã‚½ãƒ•ãƒˆã€ŒKVMï¼ˆKernel-based Virtual Machineï¼‰ã€ã¯ã€å‡¦ç†æ€§èƒ½ãŒé«˜ã„ã€ã¤ã¾ã‚Šä»®æƒ³åŒ–ã«ä¼´ã†ã‚ªãƒ¼ãƒãƒ¼ãƒ˜ãƒƒãƒ‰ãŒå°ã•ã„ã¨ã„ã‚ã‚Œã¦ã„ã‚‹ã€‚Linuxã‚«ãƒ¼ãƒãƒ«ã«çµ„ã¿è¾¼ã¾ã‚Œã¦ã„ã‚‹ã“ã¨ã«åŠ ãˆã€Intel VT-xãŠã‚ˆã³AMD-Vãªã©æœ€è¿‘ã®CPUãŒæŒã¤ãƒãƒ¼ãƒ‰ã‚¦ã‚¨ã‚¢ã«ã‚ˆã‚‹ä»®æƒ³åŒ–æ”¯æ´æ©Ÿæ§‹ã‚’æ´»ç”¨ã—ã¦ã„ã‚‹ã‹ã‚‰ã ã€‚ãã“ã§ã€KVMã®å®ŸåŠ›ã‚’è¦‹ã‚‹ãŸã‚ã«ã€å…ã¤ã®æ¤œè¨¼ã‚’å®Ÿæ–½ã—ãŸã€‚ æ¤œè¨¼(1)ã§ã¯ã€ãƒ‡ãƒ¼ã‚¿ãƒ™ãƒ¼ã‚¹ã‚µãƒ¼ãƒãƒ¼ã¨ã—ã¦ä½¿ã£ãŸå ´åˆã®å‡¦ç†æ€§èƒ½ã‚’æ¸¬å®šã—ã€KVMã®ã‚ªãƒ¼ãƒãƒ¼ãƒ˜ãƒƒãƒ‰ã‚’èª¿ã¹ãŸï¼ˆå›³1ï¼‰ã€‚ãã®çµæžœã€ã‚ªãƒ¼ãƒãƒ¼ãƒ˜ãƒƒãƒ‰ã¯æœ€å¤§60ï¼…è¿‘ãã‚ã‚‹ã“ã¨ãŒåˆ†ã‹ã£ãŸã€‚ã“ã®å€¤ã¯ä¸€è¦‹ã€å¤§ããæ€ãˆã‚‹ãŒã€ä»®æƒ³åŒ–ã‚½ãƒ•ãƒˆã®ä¸ã§ã©ã®ãã‚‰ã„ã®ãƒ¬ãƒ™ãƒ«ãªã®ã‹ã‚’åˆ¤åˆ¥ã™ã‚‹ãŸã‚ã€æ¤œè¨¼(2)ã§ã¯KVMã¨åŒã˜ãã‚ªãƒ¼ãƒ—ãƒ³ã‚½ãƒ¼ã‚¹ã®ä»®æƒ³åŒ–ã‚½ãƒ•ãƒˆã§ã‚ã‚‹Xenã¨æ¯”è¼ƒã—ãŸã€‚ä»¥é™ã®æ¤œè¨¼(3)ï½ž(6)ã§ã¯ã€KVMã®ã‚ªãƒ¼ãƒãƒ¼ãƒ˜ãƒƒãƒ‰ãŒã©ã®ã‚ˆã†ãªå‡¦ç†ã§ç”Ÿã˜ã‚‹ã®ã‹æŽ¢ã‚‹
ori53 2012/04/10
KVM

performance

ãƒ™ãƒ³ãƒãƒžãƒ¼ã‚¯

benchmark
ãƒªãƒ³ã‚¯
1 2 æ¬¡ã®ãƒšãƒ¼ã‚¸