Date: Thu, 4 May 2000 12:05:38 +0100 From: Nik Clayton <nik@freebsd.org> To: mobile@freebsd.org Subject: Heavy activity bogs down system Message-ID: <20000504120537.A5958@kilt.nothing-going-on.org>
next in thread | raw e-mail | index | archive | help
Hi folks,
Joe Karthauser and I were chatting last weekend, and we both commented
on how lots of disk activity would bog down our laptops. I've got a
VAIO F270, his is a F290 (I think). Mine runs 3.2+PAO, his runs a
very up to date -current, so we don't think it's release specific.
On my desktop system (P200 w/ 64MB RAM, bunch of Netscapes and Xemacs
open, SCSI disks, 3.4-stable) I can
cd doc/en_US.ISO_8859-1/books/handbook
make book.html
and things remain relatively snappy. By that I mean the focus follows to
other windows promptly, simple shell commands run fine, I can open up new
xterms running Mutt with only a little bit of lag.
Conversely, doing the same thing on the laptop (P333 w/ 64MB RAM, 1 xemacs,
1 Netscape, IDE disks, 3.2+PAO) I can do the same thing and the system
effectively becomes unusable. The mouse cursor is sluggish, if I shift
the pointer to another xterm it takes seconds (five or more) for the hollow
cursor to fill in, indicating the focus has shifted. Also (and this is
my favourite benchmark) keystrokes get lost. You can see this in vi by
opening a document and using the cursor keys to scroll through it. You get
spurious 'B' characters inserted when the keyboard driver misses one of the
extended characters returned by the cursor keys.
I don't have a desktop system with IDE disks to compare this too (in fact,
I've never run another FreeBSD system without SCSI disks). Should I expect
IDE to have such an impact on system performance?
I can run 'proper' benchmarks if people have specific recommendations for
ones to use.
FWIW, "/usr/bin/time -l make book.html" for one of the documents when this
happens prints
47.83 real 0.00 user 45.11 sys
0 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
6368 page reclaims
2 page faults
0 swaps
0 block input operations
10 block output operations
0 messages sent
0 messages received
0 signals received
24 voluntary context switches
830 involuntary context switches
which doesn't look like the sort of load that should freeze a machine. The
boot probes for the IDE devices look like:
[...]
ide_pci0: <Intel PIIX4 Bus-master IDE controller> rev 0x01 on pci0.7.1
[...]
wdc0 at 0x1f0-0x1f7 irq 14 on isa
wdc0: unit 0 (wd0): <IBM-DBCA-206480>
wd0: 6194MB (12685680 sectors), 13424 cyls, 15 heads, 63 S/T, 512 B/S
wdc1 at 0x170-0x177 irq 15 on isa
wdc1: unit 0 (atapi): <CD-224E/1.5A>, removable, accel, ovlap, dma, iordis
[...]
Any thoughts?
N
--
Internet connection, $19.95 a month. Computer, $799.95. Modem, $149.95.
Telephone line, $24.95 a month. Software, free. USENET transmission,
hundreds if not thousands of dollars. Thinking before posting, priceless.
Somethings in life you can't buy. For everything else, there's MasterCard.
-- Graham Reed, in the Scary Devil Monastery
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-mobile" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000504120537.A5958>