>> >The patch, against 2.1.106, is a bit long for the list:
>> >
>> > ftp://mozart.stat.wisc.edu/pub/misc/patch-2.1.106-freeinodes
>>
>> I have tried it and the kernel started to make mess. No fs corruption
>> though. After a lot of IO the HD continued to run. I couldn' t reboot,
>> and I had to press reset. I could have applyed the patch badly since I had
>> to apply it partly by hand due lots of patch reject...
Now I applyed the right patch and it perform in the same way. I have not
the /proc sysctl and I had to reset again after cp /tmp/zero /dev/null.
>Also, I've noticed that the default sysctl settings for my inode
>freeing code are *way* too agressive for the default kernel swap
>settings. This is because I've been using:
>
> echo 10 80 90 > /proc/sys/vm/pagecache
> echo 3 25 50 > /proc/sys/vm/buffermem
I set these settings and it continue to perform worse than the stock
kernel _during_ cp file /dev/null where file is very long.
Did you tried cp file /dev/null?
Andrea[s] Arcangeli
-
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.altern.org/andrebalsa/doc/lkml-faq.html