The improvement (over 2.0.35) in high-load situations is truly amazing.
Been bangin' on it hard, and it hasn't rolled over yet.
I just want to reiterate Paul's thanks, guys.
BTW, I do have some archived benchmarks from 2.0.35 from lmbench, nbench,
and bm. Some of these are with different hardware configurations, etc, but
I will try to sort through them and see if I can come up with some
meaningful apples to compare and summarize within a couple of days...
gl
- the revolution will *not* be televised.
Gene Lege'
Manager - Configuration Management, Landmark Graphics Corporation
-----Original Message-----
From: Paul Barton-Davis [mailto:pbd@Op.Net]
Sent: Monday, January 04, 1999 11:09 PM
To: linux-kernel@vger.rutgers.edu
Subject: 2.2.0-pre4 success report
just a quick success report. I just jumped from 2.1.131 tonight all
the way to 2.2.0-pre4. It has seen 4 complete kernel compiles, 4 full
reboots, a bunch of MIDI I/O, RT FIFO processes, and lots of other
development work tonight. No problems of any kind noted. This is all
on a dual PII-450 on an SuperMicro P6DBU (Award BIOS, Adaptec 7890 U2W
SCSI).
Subjective speed is way up. X performance has visibly improved
(probably the mtrr stuff ?) A kernel compile with my usual config
takes 1m 48s (elapsed, on 2 processors (899.48 BogoMIPS) using make
-j4 MAKE="make -j4").
i've wanted to say thanks before, but this time i really should say
it: Thanks to Linus and every Linux kernel contributor who has made
this possible. And thanks also to every user-land contributor who has
enabled me to sit in front of a lightning fast machine and have easy
access to the source code for every aspect of this ultra-stable,
ultra-usable system.
Hell, this is so fast, I might even bother to get GNOME :)
--p
-
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/
-
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/