Pavel Machek wrote:
Hi!
The current VM can get itself into trouble fairly easily
on systems
with a small ZONE_HIGHMEM, which is common on i686
computers with
1GB of memory.
On one side, page_alloc() will allocate down to
zone->pages_low,
while on the other side, kswapd() and balance_pgdat()
Hi!
> The current VM can get itself into trouble fairly easily
> on systems
> with a small ZONE_HIGHMEM, which is common on i686
> computers with
> 1GB of memory.
>
> On one side, page_alloc() will allocate down to
> zone->pages_low,
> while on the other side, kswapd() and balance_pgdat()
> w
Andrew Morton wrote:
On Thu, 06 Sep 2007 12:38:13 -0400 Rik van Riel <[EMAIL PROTECTED]> wrote:
Andrew Morton wrote:
(What happened to the other stuff I said?)
Mlock can cause the problem too. As for all_unreclaimable,
it is ignored when priority == DEF_PRIORITY, balance_pgdat
always seems t
> On Thu, 06 Sep 2007 12:38:13 -0400 Rik van Riel <[EMAIL PROTECTED]> wrote:
> Andrew Morton wrote:
>
(What happened to the other stuff I said?)
> > I guess for a very small upper zone and a very large lower zone this could
> > still put the scan balancing out of whack, fixable by a smarter vers
Andrew Morton wrote:
I guess for a very small upper zone and a very large lower zone this could
still put the scan balancing out of whack, fixable by a smarter version of
"8*zone->pages_high" but it doesn't seem very likely that this will affect
things much.
Why doesn't direct reclaim need simi
> On Wed, 05 Sep 2007 19:01:25 -0400 Rik van Riel <[EMAIL PROTECTED]> wrote:
> The current VM can get itself into trouble fairly easily on systems
> with a small ZONE_HIGHMEM, which is common on i686 computers with
> 1GB of memory.
>
> On one side, page_alloc() will allocate down to zone->pages_lo
The current VM can get itself into trouble fairly easily on systems
with a small ZONE_HIGHMEM, which is common on i686 computers with
1GB of memory.
On one side, page_alloc() will allocate down to zone->pages_low,
while on the other side, kswapd() and balance_pgdat() will try
to free memory from
7 matches
Mail list logo
