Re: Sync Rep v17
От | Daniel Farina |
---|---|
Тема | Re: Sync Rep v17 |
Дата | |
Msg-id | AANLkTimnYtVHuzw48FXV=rDDd1bPdNcJ-2-ScxXj3GwT@mail.gmail.com обсуждение исходный текст |
Ответ на | Re: Sync Rep v17 (Jeff Davis <pgsql@j-davis.com>) |
Список | pgsql-hackers |
On Fri, Feb 25, 2011 at 4:52 PM, Jeff Davis <pgsql@j-davis.com> wrote: > On Wed, 2011-02-23 at 22:42 -0800, Daniel Farina wrote: >> Oh, yes, this reproduces past shutdowns/startups, and there's quite a >> few txids before I catch up. I'm also comfortable poking around with >> gdb (I have already recompiled with debugging symbols and >> optimizations off and was poking around, especially at >> MemoryContextStats(TopMemoryContext), but was not rewarded. > > Where is all of that memory going during recovery? Recovery shouldn't > use much memory at all, as far as I can tell. > > What's even allocating memory at all? I noticed this is RSS fooling with me. As pages get touched in shared memory, for some reason RSS was constantly getting increased, along with SHR at the same time. Still, the long recovery time was mystifying to me, considering the lack of unclean shutdowns. -- fdr
В списке pgsql-hackers по дате отправления: