Re: select on 22 GB table causes "An I/O error occured while sending to the backend." exception
От | Craig James |
---|---|
Тема | Re: select on 22 GB table causes "An I/O error occured while sending to the backend." exception |
Дата | |
Msg-id | 48B814FF.3000600@emolecules.com обсуждение исходный текст |
Ответ на | Re: select on 22 GB table causes "An I/O error occured while sending to the backend." exception (James Mansion <james@mansionfamily.plus.com>) |
Ответы |
Re: select on 22 GB table causes "An I/O error occured
while sending to the backend." exception
|
Список | pgsql-performance |
James Mansion wrote: > I can't see how an OS can lie to processes about memory being allocated > to them and not be ridiculed as a toy, but there you go. I don't think > Linux is the only perpetrator - doesn't AIX do this too? This is a leftover from the days of massive physical modeling (chemistry, physics, astronomy, ...) programs written in FORTRAN.Since FORTRAN didn't have pointers, scientists would allocate massive three-dimensional arrays, and their code mightonly access a tiny fraction of the memory. The operating-system vendors, particularly SGI, added features to the variousflavors of UNIX, including the ability to overcommit memory, to support these FORTRAN programs, which at the timewere some of the most important applications driving computer science and computer architectures of workstation-classcomputers. When these workstation-class computers evolved enough to rival mainframes, companies started shifting apps like Oracle ontothe cheaper workstation-class computers. Unfortunately, the legacy of the days of these FORTRAN programs is still withus, and every few years we have to go through this discussion again. Disable overcommitted memory. There is NO REASON to use it on any modern server-class computer, and MANY REASONS WHY ITIS A BAD IDEA. Craig
В списке pgsql-performance по дате отправления: