Hi Andrea!
I tested vm20 against bare 2.2.0-pre7 and it doesn't do the job 8*(
The system is a little bit more responsive while doing a 12G mke2fs
now only taking about 10-20 seconds ;-( to bring up another kvt
compared to end of mke2fs without vm20.
But compared to < 2.2.0 VM this is about at least 10-20!!! times slower.
The system (2*PII/350, 256M RAM) swaps out 30MB (kvts etc.) for _no_
obvious reason with paging rates up to > 100/s ?!
I don't like 1 process eating up main memory for buffer/page cache
_and_ thereby causing swaping out inactive others.
Other testers reported the same effect, if the system runs
for some days under medium load.
/proc,sys/vm/{buffermemm, pagecache} are gone now because they haven't been
used any longer, but at least i liked them.
Why not keep that interface and the thereby implied limits in the kernel
VM to allow the admin to set them to 100% if he likes to?
Sorry if this sounds too bad, but to my opinion this behaviour is an absolute
_must_ change before the final 2.2 release!
Keep up the good work,
Heinz
--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Systemmanagement Entwicklungsbereich 2 Deutsche Telekom AG Entwicklungszentrum Darmstadt Heinz Mauelshagen Otto-Roehm-Strasse 71c Postfach 10 05 41 mge@ez-darmstadt.telekom.de 64205 Darmstadt Germany +49 6151 886-425 FAX-386 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
- 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/