Re: unexpected paging during large file reads in 2.1.127

["Stephen C. Tweedie" <sct@redhat.com>]

Hi,

On 17 Nov 1998 02:21:14 +0100, Zlatko Calusic <Zlatko.Calusic@CARNet.hr>
said:

> "Stephen C. Tweedie" <sct@redhat.com> writes:

>> No, we don't.  We don't evict just-read-in data, because we mark such
>> pages as PG_Referenced.  It takes two complete shrink_mmap() passes
>> before we can evict such pages.

> I didn't find this in the source (in fact, add_to_page_cache clears
> PG_referenced bit, if I understood source correctly). But, see below.

You didn't understand the source correctly. :)  There is an extra
bracket you missed:

	page->flags = (page->flags & ~((1 << PG_uptodate) | (1 << PG_error))) | (1 << PG_referenced);

We clear PG_uptodate and PG_error, but we _set_ PG_referenced.

> I must agree entirely, because with small patch you can find below,
> performance is very very good. Thanks to marking readahead pages as
> referenced, I've been able to see exact behaviour that I wanted for a
> long time. 

Excellent.  

--Stephen
--
This is a majordomo managed list.  To unsubscribe, send a message with
the body 'unsubscribe linux-mm me@address' to: majordomo@kvack.org