Re: test1-ac22-classzone performance

From: Juan J. Quintela (quintela@fi.udc.es)
Date: Tue Jun 20 2000 - 07:15:33 EST

>>>>> "hpa" == H Peter Anvin <hpa@transmeta.com> writes:

hpa> I can confirm that test1-ac22-classzone has very bad performance on a
hpa> machine with very large memory (1 GB, compiled with bigmem=4 GB). When
hpa> copying a large set of files from one drive (Symbios SCSI) to another
hpa> (UDMA-66, which for some reason gets detected as UDMA-33) it spends a
hpa> lot of time in kswapd/kflushd and the machine feels actively sluggish.
hpa> This is the kind of stuff it should be able to do completely in the
hpa> background.

Do you have the time to check my two patches against ac22-riel????

You can get them from the lists or from my webpage:

http://carpanta.dc.fi.udc.es/~quintela/kernel/2.4.0-test1-ac22-riel/{alloc_pages_01.patch,kswapd_03.patch}

It should improve things in machines with a lot of memory (where a lot
means more that 128MB or something like that...).

Later, Juan. 

-- 
In theory, practice and theory are the same, but in practice they 
are different -- Larry McVoy

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

This archive was generated by hypermail 2b29 : Fri Jun 23 2000 - 21:00:19 EST