MySQL 5.6ããã®æ©è½ã§ããGTIDããFacebookã®ç°å¢ã«é©ç¨ããéã®æµãã¨ä¸»ãªä¸å ·åãããã¦ãããã®ä¿®æ£ç¹ã«ã¤ãã¦ãFacebookã®ã¨ã³ã¸ãã¢ã«ããã¾ã¨ãã by Evan Elias and Santosh Praneeth Banda Global Transaction ID (GTID)ã¯ãMySQL 5.6ã®æ°æ©è½ã®ä¸ã§ãæã使ããã«ã¯ããããªãæ©è½ã®ä¸ã¤ã ããã®ãããã§ããã§ã¤ã«ãªã¼ãããã¤ã³ãã¤ã³ã¿ã¤ã ãªã«ããªãé層ãæã£ãã¬ããªã±ã¼ã·ã§ã³ãªã©ã«é常ã«æçã ããã¯ã©ãã·ã¥ã»ã¼ããªãã«ãã¹ã¬ããã¬ããªã±ã¼ã·ã§ã³ã®å¿ é æ¡ä»¶ã«ããªã£ã¦ããããã®æ°ã¶æã§ãæã ã¯Facebookã®å ¨ã¦ã®æ¬çªç¨MySQLã¤ã³ã¹ã¿ã³ã¹ã§ãGTIDãæå¹ã«ããããã®ä¸ã§ããã®æ©è½ã®é©ç¨æ¹æ³ãæä½ã«ã¤ãã¦ãããããã®ç¥è¦ãå¾ããããããããã®ãµã¼ããµã¤ãã®ä¿®æ£äºé ã«ã¤ãã¦ã¯ãWebScaleS
ç±³Facebookã¯9æ15æ¥ãmemcachedãããã³ã«ç¨ã®ã«ã¼ãã£ã³ã°ã½ããã¦ã§ã¢ãmcrouterãããªã¼ãã³ã½ã¼ã¹ã½ããã¦ã§ã¢ã¨ãã¦å ¬éãããmemcachedãã¯ã©ã¹ã¿åããã½ããã¦ã§ã¢ã§ãå®ãµã¼ãã¼ã ãã§ãªãAmazon Web Servicesï¼AWSï¼ã®ã¯ã©ã¦ãç°å¢ã§ãå©ç¨ã§ããã mcrouterã¯å社ã2013å¹´ã«çºè¡¨ãã¦ããã½ããã¦ã§ã¢ã§ãmemcachedãµã¼ãã¼ã¨ã¯ã©ã¤ã¢ã³ãã®éã«çµã¿è¾¼ããã¨ã§memcachedã使ã£ãåæ£ãã£ãã·ã¥ã·ã¹ãã ãæ§ç¯ã§ãããmemchaced ASCIIãããã³ã«ã«å¯¾å¿ããã¯ã©ã¤ã¢ã³ãããã®ãªã¯ã¨ã¹ãã«å¯¾ãã¦ã¯memcachedãµã¼ãã¼ã®ããã«åå¿ããã¾ãmemcachedãµã¼ãã¼å´ã«å¯¾ãã¦ã¯memchacedã¯ã©ã¤ã¢ã³ãã®ããã«ã¢ã¯ã»ã¹ããããã«ãã¯ã©ã¹ã¿ããµãã¼ãããã³ãã¯ã·ã§ã³ãã¼ãªã³ã°ããã¬ãã£ãã¯ã¹ã«ã¼ãã£ã³ã°ããªã³ã©ã¤
When Instagram joined Facebook in 2012, we quickly found numerous integration points with Facebook's infrastructure that allowed us to accelerate our product development and make our community safer. In the beginning, we built these integrations by effectively bouncing through Facebook web services using ad-hoc endpoints. However, we found that this could be cumbersome and it limited our ability t
Facebookã§æ稿ãåçãªã©ããã§ãã¯ã§ãã¾ãã
At MySQL Connect 2013, I talked about how we used MySQL 5.6 at Facebook, and explained some of new features we added to our Facebook MySQL 5.6 source tree. In this post, I'm going to talk about how we made full table scan faster in InnoDB. Faster full table scan in InnoDB In general, almost all queries from applications are using indexes, and reading very few rows (0..1 on primary key lookups and
ç±³ãªã©ã¯ã«ã主å¬ããMySQLã®ã¤ãã³ããMySQL Connectãã9æ21æ¥ãã23æ¥ã¾ã§ããµã³ãã©ã³ã·ã¹ã³ã§éå¬ããã¾ãããOracle OpenWorldãJavaOneã¨ã®åæéå¬ã§ããã åºèª¿è¬æ¼ã®1ã¤ã«ã¯ãMySQLã®ããã¼ã¦ã¼ã¶ã¼ã§ããFacebookã®Harrison Fiskæ°ãç»å£ãFacebookã«ãããMySQLã®å½¹å²ã大è¦æ¨¡éç¨ã®èæ¯ãªã©ãç´¹ä»ãã¦ãã¾ãããã®å 容ããã¤ã¸ã§ã¹ãã§ç´¹ä»ãã¾ãããã MySQL@Facebook Lots and lots of small data Harrison Fiskæ°ã Facebookã§ãã¼ã¿ããã©ã¼ãã³ã¹ãã¼ã ã®ããã¼ã¸ã£ããã¦ããã社å ã§ã¯MySQLã¯ãã¡ãããHBase Hadoopãªã©ã«ãé¢ãã£ã¦ããã ã¾ãã¯ãã©ããªç¨®é¡ã®ãã¼ã¿ãMySQLã§æ±ã£ã¦ããã®ãã«ã¤ãã¦ã Facebookã¨ã¯åºæ¬çã«ã°ã©ãã ãã°
Facebookã§æ稿ãåçãªã©ããã§ãã¯ã§ãã¾ãã
by Michael Piatek Responsiveness is essential for web services. Speed drives user engagement, which drives revenue. To reduce response latency, modern web services are architected to serve as much as possible from in-memory caches. The structure is familiar: a database is split among servers with caches for scaling reads. Over time, caches tends to accumulate more responsibility in the storage sta
ã©ãã¯ãã¨ã«ç©ççã«ã³ã³ãã¥ã¼ã¿ãªã½ã¼ã¹ãæé©åããFacebookã®æè¡ãDisaggregated Rackãã¨ã¯ä½ãï¼ Facebookã¯ããã¼ã¿ã»ã³ã¿ã¼ã®ãµã¼ãæ§æãããæè»ã«ããããã®æ°ããææ³ãDisaggregated Rackããã1æã«ç±³ãµã³ã¿ã¯ã©ã©ã§éå¬ãããOpen Compute Summit Winter 2013ã§æããã«ãã¦ãã¾ãï¼ãã¾ã«ãªã£ã¦å ¬éãããåç»ãè¦ã¦ãããè¦ã¤ãã¾ããï¼ã ãã¼ã¿ã»ã³ã¿ã¼ã®ãµã¼ããã¹ãã¬ã¼ã¸ãå¹ççã«å©ç¨ããããã«ã¯ãä»®æ³åã«ãã£ã¦ãªã½ã¼ã¹ãã¼ã«ãä½ããã¢ããªã±ã¼ã·ã§ã³ã«å¿ãã¦ãããåãåºãã¦ä½¿ãæ¹æ³ãä¸è¬ã«èãããã¦ãã¾ãã ãããFacebookãæ¡ç¨ããæ¹æ³ã¯ãCPUãã¡ã¢ãªãã¹ãã¬ã¼ã¸ãç©ççãªã³ã³ãã¼ãã³ãã«ãã¦ããããã©ãã¯ã«è¿½å ãããå¼ãæããããããã¨ã§ã©ãã¯ãã¨ã®ã·ã¹ãã æ§æãç©ççã«å¤ãã¦ãã¾ããã¨ããææ³ã§ã
å ¬éãããã®ã¯ããå»å¹´ã®ã¯ãªãã ãã©ãFacebook ã® ãªãªã¼ã¹ã¨ã³ã¸ãã¢ãªã³ã°ã® Tech Talk (äºåç·¨) ã¯é¢ç½ãã話ãã¦ãã Chuck Rossi ãã㯠Facebook ã®ãªãªã¼ã¹ã¨ã³ã¸ãã¢ãªã³ã°ãã¼ã ã®ãªã¼ãã¼ã ã 彼㯠âThe business requires change, but change is the root cause of most outages!â ã¨è©±ãã¯ããããFacebook ã®è¦æ¨¡ã§æ¯æ¥å¤æ´ããªãªã¼ã¹ããããã«ããªãªã¼ã¹ã®ãªã¹ã¯ãã§ãããããæ¸ãããªãã¦ã¯ãããªãããã®ããã«åºã¦ããã®ããæåãã¨ãéå ·ãã ã ç¾å¨ã®ã½ããã¦ã§ã¢éçºã§ã¯éçºè ã¨é¡§å®¢ (your mom) ã®éã«èãã¬ã¤ã¤ã¼ãããªã: æ㯠QA ã¨ããããã¯ãããã¸ã£ã¼ã¨ããããããããã©ããã¾ã¯éãã ãã©ã³ãã¨ãªãªã¼ã¹: éçºè 㯠trunk ã«ã³ããããããæ¥
ã¯ã©ã¦ãã®ããã«å¤§è¦æ¨¡ãªã·ã¹ãã ã§ã¯ãã½ããã¦ã§ã¢ã®éçºã¨åç以ä¸ã«ã大è¦æ¨¡éç¨ã®å·§æããã·ã¹ãã å ¨ä½ã®æåã大ããå·¦å³ãã¾ãã 6æ22æ¥ãããç±³ãµã³ã¿ã¯ã©ã©ã§è¡ããã¦ããWebãµã¤ãã®ããã©ã¼ãã³ã¹ã¨éç¨ã«é¢ãããªã©ã¤ãªã¼ã®ã¤ãã³ããVelocity 2010ãã§ãFacebookã®Technical Operations teamãæ å½ããTom Cookæ°ããA Day in the Life of Facebook Operationsãï¼Facebookéç¨ã®ãã1æ¥ï¼ã¨é¡ããã»ãã·ã§ã³ã§ãFacebookããµã ãã©ã®ãããªéç¨ãè¡ã£ã¦ããããç´¹ä»ãã¦ãã¾ãã ä¸çã§ãããã¯ã©ã¹ã®å¤§è¦æ¨¡ãµã¤ãããæ®æ®µã©ã®ãããªãã¼ã«ãç¨ããã©ã®ãããªæ¹æ³ã§éç¨ãã¦ããã®ããã»ãã·ã§ã³ã®å 容ãç´¹ä»ãã¾ãããã 6å¹´ã§4åã¢ã¯ãã£ãã¦ã¼ã¶ã¼ã3ã«æã®ãã¼ã¿ã»ã³ã¿ã¼ Tom Cookæ°ãFacebo
Facebookã®æ°ãããªã¢ã«ã¿ã¤ã 解æã®ã·ã¹ãã ã§ã¯ãHBaseã§1æ¥200å件ã®ã¤ãã³ããå¦çãã¦ããããã§ãã以ä¸ã®è¨äºã®ç¿»è¨³ã§ããHigh Scalability - High Scalability - Facebookâs New Realtime Analytics System: HBase to Process 20 Billion Events Per DayFacebookãã¾ããã£ã¦ããããå½¼ãã¯å·¨å¤§ãªãªã¢ã«ã¿ã¤ã ãã¼ã¿ã®ã¹ããªã¼ã ãå¦çãããã1ã¤ã®ã·ã¹ãã ãæ§ç¯ããã®ã ã以åã«ãFacebookã¯ãªã¢ã«ã¿ã¤ã ãªã¡ãã»ã¼ã¸ã·ã¹ãã ãHBaseã§æ§ç¯ãã¦ãã(http://highscalability.com/blog/2010/11/16/facebooks-new-real-time-messaging-system-hbase-to-store-135.ht
以åããæ¥æ¬ã®ã½ã¼ã·ã£ã«ã²ã¼ã ã¯ãFacebookãã§åãã¦ããã®ãï¼ãã¨é¡ããè¨äºãæ¸ããããããã¯ããã®å¾ã®çµéã追跡ããè¨äºã¨ãªãã ä»åãããã¹ã¯ã¦ã§ã¢ã»ã¨ããã¯ã¹ã®2ã¿ã¤ãã«ã追å ãããä¸éãè¦ãå°è±¡ã§ã¯ã1ã¿ã¤ãã«ãé¤ãã¦ãåãä¸ããã¢ããªã®MAUãç·ãã¦ä¸ãã£ã¦ãããã¨ã確èªãããã ãã ãæ¥æ¬è£½ã¢ããªã ãã§ãªããä»ã®ãããã¢ããªãä½ä¸ãã¦ãããä¾ãã°ãMAUä¸ä½30ã¢ããªã®ãã¡ãFarmvilleãCityVilleãå«ã15ã¢ããªãä½ä¸å¾åã«ãã£ãã å æ¥ããFacebookãã§ã¢ã«ã¦ã³ãåé¤é¨åããã£ãããè¤æ°ã¢ã«ã¦ã³ããé§ä½¿ããã¦ã¼ã¶ã¼ãåé¤ãããå½±é¿ã ããããããèããã¨ãæ¥æ¬è£½ã¢ããªã®åé¡ã¨ããããããFacebookå ¨ä½ã®åããªã®ãããããªãã ãã ã®æãã¤ããæ¸ãã¦ãä»æ¹ãªãã®ã§ãå¥éèãããã以ä¸ãåã¢ããªã®ååãè¨è¿°ãã¦ããããååã¨åãããAppData
Facebookã大è¦æ¨¡ã¹ã±ã¼ã©ããªãã£ã¸ã®ææ¦ã§å¦ãã ãã¨ï¼åç·¨ï¼ï½800åæã®åçãã¼ã¿ã¨PHPã®ã¹ã±ã¼ã©ããªãã£åé¡ å ¨ä¸çã§3å人ãè¶ ããä¼å¡ãæ±ããä¸çæ大ã®SNSã¨ãªã£ãFacebookãå社ã®å·¨å¤§ãªã·ã¹ãã ã¯ã3ã¤ã®ãã¼ã¿ã»ã³ã¿ã¼ã«ããç´3ä¸å°ã®ãµã¼ãã¨ãPHPãC++ãMemcacheãMySQLãªã©ã®ã½ããã¦ã§ã¢ç¾¤ã«ãã£ã¦æ¯ãããã¦ãã¾ãï¼å社ã®ãã¼ã¿ã»ã³ã¿ã¼ã®å·¨å¤§ãã¯ãè¨äºã3åã®ã¦ã¼ã¶ã¼ãæ±ããFacebookã®ãã¼ã¿ã»ã³ã¿ã¼ã移åã¯èªè»¢è»ãå¸æã¯100Gbã¤ã¼ãµããã ããåç §ï¼ã å社ã®æè¡æ å½ãã¤ã¹ãã¬ã¸ãã³ã Jeff Rothschildæ°ã¯ãFacebookãå®ç¾ãã¦ãã大è¦æ¨¡ãªã¹ã±ã¼ã©ããªãã£ããããã«ãã¦ãããã®ã½ããã¦ã§ã¢ã§å®ç¾ãã¦ããã®ãã10æ8æ¥ã«ç±³ã«ãªãã©ã«ãã¢å¤§å¦ãµã³ãã£ã¨ã´æ ¡ã§è¡ã£ãã»ããã¼ãHigh Performance at Mas
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}