[HACKERS] 答复:[HACKERS] 答复:[HACKERS] 答复:[HACKERS] about fsync in CLOG buffer write

2015-09-09 Thread ()
 the selected page is clean, we're set.    */   if (!shared->page_dirty[bestvalidslot])    return bestvalidslot; --发件人:Andres Freund 发送时间:2015年9月9日(星期三) 02:28收件人:周正中(德歌) 抄 送:Amit Kapila ,张广舟(明虚) ,pgsql-hackers ,范孝剑(康贤) ,曾文旌(义从) ,窦贤明(执白) ,萧少聪(铁庵) ,陈新坚(惧留孙) 主 题:Re:

[HACKERS] 答复:[HACKERS] 答复:[HACKERS] about fsync in CLOG buffer write

2015-09-08 Thread ()
rc/backend/storage/file/fd.c:1710").return,  par:14 2088013 postgres(2924): -> time:1441503929819,  pp:process("/opt/pgsql9.4.4/bin/postgres").function("pg_fsync@/opt/soft_bak/postgresql-9.4.4/src/backend/storage/file/fd.c:315").call,  par:fd=14 2089250 postgres(2924): <

[HACKERS] 答复:[HACKERS] about fsync in CLOG buffer write

2015-09-07 Thread ()
>On 2015-09-10 19:39:59 +0800, 张广舟(明虚) wrote: >> We found there is a fsync call when CLOG buffer >> is written out in SlruPhysicalWritePage(). It is often called when a backend >> needs to check transaction status with SimpleLruReadPage(). >That's when there's not enough buffers available some ot