Subject: Re: Strange VM behaviour
To: None <firstname.lastname@example.org>
From: Lennart Augustsson <email@example.com>
Date: 02/04/2001 14:54:33
> When my machine is heavily loaded memory-wise (which happens a lot
> with UBC) I've observed a strange behaviour. Perhaps it's normal, but I
> doubt it.
> All of a sudden the machine freezes. I can't move the mouse, there is no
> sound from my speakers anymore, and there is no disk activity. This lasts
> 1 - 5 seconds and then everything is back to normal again (i.e. paging like
> Can anyone shed any light? (No, I've not been able to switch console
> to get into the debugger, so no stack traces.)
> Haven't been paying very much attention to tech-kern lately,
> have we?
> What you're seeing is typical UBC behavior:
> 1) the buffer cache useage is unlimited,
> so any/all pages are eventually swallowed
> by the buffer cache, displacing everything
> else including the X server.
> 2) there is no limit on dirty buffer cache
> pages and nothing to force immediate writing
> so when the sync-er runs a huge number of pages
> are scheduled to be written, which swamps the
> I/O subsystem.
> 3) The page scanner was broken so it degraded
> to FIFO page replacement rather than LRU. Jason
> has fixed that a couple of weeks ago.
> For #3, upgrade.
> For #1, you can use a patch that Jason sent
> out a few weeks ago.
> For #1 and #2, you can try the following patch
> (which potentially causes TLB issues, but those
> are much less expensive than UBC issues):
First of all, I'm running -current (about a day old), so #3 is not an issue.
I doubt your analysis of my problem is correct. Note that when the system
freezes there is no disk activity. If the syncer was flushing pages I would expect
heavy disk activity.
The only normal condition I can imagine this to happen is if the scheduler
decide to run processes that all happen to be totally in core and that don't
need any disk I/O. This is not impossible, but very improbable. Especially
for a time period of 5 seconds.