Date: Wed, 3 Sep 1997 10:21:41 +0300 From: Antti-Pekka Liedes <apl@mail.cs.hut.fi> To: Steve Passe <smp@csn.net> Cc: freebsd-smp@FreeBSD.ORG Subject: Re: SMP performance on P5 systems? Message-ID: <19970903102141.63694@hutcs.cs.hut.fi> In-Reply-To: <199709022238.QAA01594@Ilsa.StevesCafe.com>; from Steve Passe on Tue, Sep 02, 1997 at 04:38:31PM -0600 References: <19970903005101.00664@hutcs.cs.hut.fi> <199709022238.QAA01594@Ilsa.StevesCafe.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--8nViIGeoXxdpn2Pv
Content-Type: text/plain; charset=us-ascii
On Tue, Sep 02, 1997 at 04:38:31PM -0600, Steve Passe wrote:
> Hi,
> >
> > The current SMP performance on my Tyan Tomcat IIID dual pentium 200MMX
> > system is not quite what I had expected, as a simple benchmark, this is
> > what it takes for me to compile kernel, with UP kernel:
> > make -j3 283.19s user 32.56s system 94% cpu 5:32.83 total
> > and with SMP:
> > make -j3 341.23s user 134.72s system 183% cpu 4:18.80 total
>
> try -j16, using just 3 processes are leaving you diskbound.
>
-j12 or -j16 didn't give any practical differences:
text data bss dec hex
1142784 98304 347076 1588164 183bc4
make -j16 349.22s user 129.98s system 189% cpu 4:12.77 total
I guess it's just so heavily disk bound operation that SMP doesn't give
much edge compared to UP.
> ---
> > I was expecting the wall clock time to be less for the SMP kernel, also,
> > there seems to be quite a lot of system overhead :-/. Of course this
> > might be because of my relatively slow disks (I use striping on two
> > Quantum Fireballs, both on different channel of my AHA-3940U). The
> > benchmarks at www.freebsd.org SMP pages show a lot better performance. Is
> > it just that ppro beats pentium so much on SMP or what?
>
> I need to see the output from "mptable -dmesg > outfile" run shortly
> after boot. the 3940 is a bridged PCI card and many MP BIOS's fail to
> probe it properly. you might be missing INTs from one channel.
Tomcat BIOS used to fail on this too, but the latest 4.01, which I am
running, has fixed this problem.
> --
> Steve Passe | powered by
> smp@csn.net | Symmetric MultiProcessor FreeBSD
>
--
Antti-Pekka Liedes * apl@IRC * In two hells there's
JMT 6 B 406 * apl@iki.fi * one hell too many
02150 ESPOO * apl@apocalypse.tky.hut.fi * - Lucifer
+358 - 9 - 468 3121 * +358 - 40 - 5873 593 * (in God's Army)
--8nViIGeoXxdpn2Pv
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment; filename="mptable.out"
===============================================================================
MPTable, version 2.0.14
-------------------------------------------------------------------------------
MP Floating Pointer Structure:
location: BIOS
physical address: 0x000f5a60
signature: '_MP_'
length: 16 bytes
version: 1.4
checksum: 0xc3
mode: Virtual Wire
-------------------------------------------------------------------------------
MP Config Table Header:
physical address: 0x000f5a74
signature: 'PCMP'
base table length: 308
version: 1.1
checksum: 0x68
OEM ID: 'OEM00000'
Product ID: 'PROD00000000'
OEM table pointer: 0x00000000
OEM table size: 0
entry count: 30
local APIC address: 0xfee00000
extended table length: 0
extended table checksum: 0
-------------------------------------------------------------------------------
MP Config Base Table Entries:
--
Processors: APIC ID Version State Family Model Step Flags
0 0x11 BSP, usable 5 2 1 0x07bf
1 0x11 AP, usable 5 2 1 0x07bf
--
Bus: Bus ID Type
0 PCI
1 PCI
2 ISA
--
I/O APICs: APIC ID Version State Address
2 0x11 usable 0xfec00000
--
I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT#
ExtINT conforms conforms 2 0 2 0
INT conforms conforms 2 1 2 1
INT conforms conforms 2 0 2 2
INT conforms conforms 2 3 2 3
INT conforms conforms 2 4 2 4
INT conforms conforms 2 5 2 5
INT conforms conforms 2 6 2 6
INT conforms conforms 2 7 2 7
INT conforms conforms 2 8 2 8
INT conforms conforms 2 9 2 9
INT conforms conforms 2 10 2 10
INT conforms conforms 2 11 2 11
INT conforms conforms 2 12 2 12
INT conforms conforms 2 13 2 13
INT conforms conforms 2 14 2 14
INT conforms conforms 2 15 2 15
INT active-lo level 0 7:B 2 19
INT active-lo level 0 20:A 2 16
INT active-lo level 0 17:A 2 19
INT active-lo level 1 4:A 2 18
INT active-lo level 1 5:A 2 19
SMI conforms conforms 2 0 2 23
--
Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID INT#
ExtINT conforms conforms 0 0:A 255 0
NMI conforms conforms 0 0:A 255 1
-------------------------------------------------------------------------------
# SMP kernel config file options:
# Required:
options SMP # Symmetric MultiProcessor Kernel
options APIC_IO # Symmetric (APIC) I/O
# Optional (built-in defaults will work in most cases):
#options NCPU=2 # number of CPUs
#options NBUS=3 # number of busses
#options NAPIC=1 # number of IO APICs
#options NINTR=24 # number of INTs
-------------------------------------------------------------------------------
dmesg output:
Copyright (c) 1992-1997 FreeBSD Inc.
Copyright (c) 1982, 1986, 1989, 1991, 1993
The Regents of the University of California. All rights reserved.
FreeBSD 3.0-CURRENT #1: Wed Sep 3 00:06:49 EEST 1997
apl@apocalypse.tky.hut.fi:/var/src/sys/compile/APOCALYPSE-SMP
CPU: Pentium (586-class CPU)
Origin = "GenuineIntel" Id = 0x544 Stepping=4
Features=0x8003bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,APIC,MMX>
real memory = 67108864 (65536K bytes)
Physical memory hole(s):
avail memory = 62668800 (61200K bytes)
FreeBSD/SMP: Multiprocessor motherboard
cpu0 (BSP): apic id: 0, version: 0x00030010, at 0xfee00000
cpu1 (AP): apic id: 1, version: 0x00030010, at 0xfee00000
io0 (APIC): apic id: 2, version: 0x00170011, at 0xfec00000
DEVFS: ready for devices
Probing for devices on PCI bus 0:
chip0: <Intel 82439> rev 0x03 on pci0.0.0
chip1: <Intel 82371SB PCI to ISA bridge> rev 0x01 on pci0.7.0
de0: <Digital 21140A Fast Ethernet> rev 0x20 int a irq 19 on pci0.17.0
de0: SMC 9332BDT 21140A [10-100Mb/s] pass 2.0
de0: address 00:00:c0:30:46:f9
chip2: <DEC 21050 PCI-PCI bridge> rev 0x02 on pci0.18.0
vga0: <VGA-compatible display device> rev 0x01 int a irq 16 on pci0.20.0
Probing for devices on PCI bus 1:
ahc0: <Adaptec 3940 Ultra SCSI host adapter> rev 0x00 int a irq 18 on pci1.4.0
ahc0: aic7880 Channel A, SCSI Id=7, 16/255 SCBs
ahc0: waiting for scsi devices to settle
scbus0 at ahc0 bus 0
ahc0: target 0 Tagged Queuing Device
sd0 at scbus0 target 0 lun 0
sd0: <IBM DSAS-3540 S47W> type 0 fixed SCSI 2
sd0: Direct-Access 522MB (1070496 512 byte sectors)
ahc0: target 2 Tagged Queuing Device
sd1 at scbus0 target 2 lun 0
sd1: <QUANTUM FIREBALL_TM3200S 300X> type 0 fixed SCSI 2
sd1: Direct-Access 3067MB (6281856 512 byte sectors)
ahc1: <Adaptec 3940 Ultra SCSI host adapter> rev 0x00 int a irq 19 on pci1.5.0
ahc1: aic7880 Channel B, SCSI Id=7, 16/255 SCBs
ahc1: waiting for scsi devices to settle
scbus1 at ahc1 bus 0
ahc1: target 3 Tagged Queuing Device
sd2 at scbus1 target 3 lun 0
sd2: <QUANTUM FIREBALL_TM3200S 300X> type 0 fixed SCSI 2
sd2: Direct-Access 3067MB (6281856 512 byte sectors)
ahc1: target 4 Tagged Queuing Device
sd3 at scbus1 target 4 lun 0
sd3: <QUANTUM EMPIRE_2100S 1022> type 0 fixed SCSI 2
sd3: Direct-Access 2006MB (4108600 512 byte sectors)
Probing for devices on the ISA bus:
sc0 at 0x60-0x6f irq 1 on motherboard
sc0: VGA color <16 virtual consoles, flags=0x0>
sio0 at 0x3f8-0x3ff irq 4 on isa
sio0: type 16550A
sio1 at 0x2f8-0x2ff irq 3 on isa
sio1: type 16550A
lpt0 at 0x378-0x37f irq 7 on isa
lpt0: Interrupt-driven port
lp0: TCP/IP capable interface
psm0 at 0x60-0x64 irq 12 on motherboard
psm0: device ID 0
fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa
fdc0: NEC 72065B
fd0: 1.44MB 3.5in
wdc0 at 0x1f0-0x1f7 irq 14 on isa
wdc0: unit 0 (atapi): <ALPS ELECTRIC CO.,LTD. DC544C/SW03B>, removable, iordy
atapi0.0: unknown phase
wdc1 not found at 0x170
sb0 at 0x220-0x22f irq 5 drq 1 on isa
sb0: <SoundBlaster 16 4.13>
sbxvi0 drq 5 on isa
sbxvi0: <SoundBlaster 16 4.13>
sbmidi0 at 0x330-0x331 on isa
sbmidi0: <SoundBlaster 16 MPU-401>
npx0 on motherboard
npx0: INT 16 interface
apm0 on isa
apm: found APM BIOS version 1.2
DEVFS: ready to run
APIC_IO: routing 8254 via 8259 on pin 0
ccd0-15: Concatenated disk drivers
SMP: AP CPU #1 Launched!
de0: enabling Full Duplex 100baseTX port
mountmsdosfs(): Warning: root directory is not a multiple of the clustersize in length
===============================================================================
--8nViIGeoXxdpn2Pv--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19970903102141.63694>