Re: can't handle large number of INSERT/UPDATEs

Поиск
Список
Период
Сортировка
От Matt Clark
Тема Re: can't handle large number of INSERT/UPDATEs
Дата
Msg-id 417F3B91.9080002@ymogen.net
обсуждение исходный текст
Ответ на Re: can't handle large number of INSERT/UPDATEs  (John Meinel <john@johnmeinel.com>)
Ответы Re: can't handle large number of INSERT/UPDATEs  (Markus Bertheau <twanger@bluetwanger.de>)
Список pgsql-performance
>> and certainly anyone who's been around a computer more than a week or
>> two knows which direction "in" and "out" are customarily seen from.
>>
>>             regards, tom lane
>>
>
Apparently not whoever wrote the man page that everyone copied ;-)

> Interesting. I checked this on several machines. They actually say
> different things.
>
> Redhat 9- bi: Blocks sent to a block device (blocks/s).
> Latest Cygwin- bi: Blocks sent to a block device (blocks/s).
> Redhat 7.x- bi: Blocks sent to a block device (blocks/s).
> Redhat AS3- bi: blocks sent out to a block device (in blocks/s)
>
> I would say that I probably agree, things should be relative to the
> cpu. However, it doesn't seem to be something that was universally
> agreed upon. Or maybe the man-pages were all wrong, and only got
> updated recently.
>
Looks like the man pages are wrong, for RH7.3 at least.  It says bi is
'blocks written', but an actual test like 'dd if=/dev/zero of=/tmp/test
bs=1024 count=16384' on an otherwise nearly idle RH7.3 box gives:
   procs                      memory    swap          io
system         cpu
 r  b  w   swpd   free   buff  cache  si  so    bi    bo   in    cs  us
sy  id
0  0  0  75936 474704 230452 953580   0   0     0     0  106  2527   0
0  99
 0  0  0  75936 474704 230452 953580   0   0     0 16512  376  2572
0   2  98
 0  0  0  75936 474704 230452 953580   0   0     0     0  105  2537
0   0 100

Which is in line with bo being 'blocks written'.

M

В списке pgsql-performance по дате отправления:

Предыдущее
От: "Iain"
Дата:
Сообщение: Re: can't handle large number of INSERT/UPDATEs
Следующее
От: "D'Arcy J.M. Cain"
Дата:
Сообщение: Re: Free PostgreSQL Training, Philadelphia, Oct 30