Look at everything on interrupt queue 10.
pciide1: using irq 10 for native-PCI interrupt
bge1 at pci3 dev 0 function 0 "Broadcom BCM5721" rev 0x11, BCM5750 B1
(0x4101): irq 10, address 00:17:08:2c:2a:76
em2 at pci7 dev 6 function 0 "Intel PRO/1000MT QP (82546GB)" rev 0x03:
irq 10,
address 00:13:21:78:0f:2e
ohci0 at pci0 dev 2 function 0 "NVIDIA nForce4 USB" rev 0xa2: irq 10,
version
Move bge1 and em2 to different interrupts. And follow Johan's directions...
Pierre
[EMAIL PROTECTED] wrote:
dmesg
OpenBSD 4.2-stable (fw) #0: Wed Dec 12 13:37:05 CET 2007
[EMAIL PROTECTED]:/usr/src/sys/arch/amd64/compile/fw
real mem = 2146136064 (2046MB)
avail mem = 2075025408 (1978MB)
mainbus0 at root
bios0 at mainbus0: SMBIOS rev. 2.34 @ 0xf10c0 (45 entries)
bios0: vendor HP version "2.17 " date 09/26/2006
bios0: HP ProLiant DL145 G2
acpi0 at mainbus0: rev 0
acpi0: tables DSDT FACP SSDT SRAT SPCR APIC MCFG BOOT
acpitimer0 at acpi0: 3579545 Hz, 24 bits
acpi device at acpi0 from table DSDT not configured
acpi device at acpi0 from table FACP not configured
acpi device at acpi0 from table SSDT not configured
acpi device at acpi0 from table SRAT not configured
acpi device at acpi0 from table SPCR not configured
acpi device at acpi0 from table APIC not configured
acpi device at acpi0 from table MCFG not configured
acpi device at acpi0 from table BOOT not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpiprt at acpi0 not configured
acpicpu0 at acpi0 PSS
acpicpu1 at acpi0
acpicpu2 at acpi0
acpicpu3 at acpi0
acpibtn0 at acpi0: PWRB
ipmi0 at mainbus0: version 2.0 interface KCS iobase 0xca2/2 spacing 1
cpu0 at mainbus0: (uniprocessor)
cpu0: AMD Opteron(tm) Processor 246, 2000.23 MHz
cpu0:
FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUS
H,MMX,FXSR,SSE,SSE2,SSE3,NXE,MMXX,FFXSR,LONG,3DNOW2,3DNOW
cpu0: 64KB 64b/line 2-way I-cache, 64KB 64b/line 2-way D-cache, 1MB 64b/line
16-way L2 cache
cpu0: ITLB 32 4KB entries fully associative, 8 4MB entries fully associative
cpu0: DTLB 32 4KB entries fully associative, 8 4MB entries fully associative
cpu0: AMD erratum 89 present, BIOS upgrade may be required
cpu0: Cool'n'Quiet K8 2000 MHz: speeds: 2000 1800 1000 MHz
pci0 at mainbus0 bus 0: configuration mode 1
"NVIDIA nForce4 DDR" rev 0xa3 at pci0 dev 0 function 0 not configured
pcib0 at pci0 dev 1 function 0 "NVIDIA nForce4 ISA" rev 0xa3
nviic0 at pci0 dev 1 function 1 "NVIDIA nForce4 SMBus" rev 0xa2
iic0 at nviic0: disabled to avoid ipmi0 interactions
iic1 at nviic0: disabled to avoid ipmi0 interactions
ohci0 at pci0 dev 2 function 0 "NVIDIA nForce4 USB" rev 0xa2: irq 10, version
1.0, legacy support
ehci0 at pci0 dev 2 function 1 "NVIDIA nForce4 USB" rev 0xa3: irq 11
usb0 at ehci0: USB revision 2.0
uhub0 at usb0: NVIDIA EHCI root hub, rev 2.00/1.00, addr 1
pciide0 at pci0 dev 6 function 0 "NVIDIA nForce4 IDE" rev 0xa2: DMA, channel 0
configured to compatibility, channel 1 configured to compatibility
pciide0: channel 0 disabled (no drives)
pciide0: channel 1 disabled (no drives)
pciide1 at pci0 dev 8 function 0 "NVIDIA nForce4 SATA" rev 0xa3: DMA
pciide1: using irq 10 for native-PCI interrupt
wd0 at pciide1 channel 0 drive 0: <Maxtor 6L080M0>
wd0: 16-sector PIO, LBA48, 76319MB, 156301488 sectors
wd0(pciide1:0:0): using PIO mode 4, Ultra-DMA mode 5
ppb0 at pci0 dev 9 function 0 "NVIDIA nForce4 PCI-PCI" rev 0xa2
pci1 at ppb0 bus 1
vga1 at pci1 dev 5 function 0 "NVIDIA GeForce2 MX" rev 0xb2
wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation)
wsdisplay0: screen 1-5 added (80x25, vt100 emulation)
ppb1 at pci0 dev 12 function 0 "NVIDIA nForce4 PCIE" rev 0xa3
pci2 at ppb1 bus 2
bge0 at pci2 dev 0 function 0 "Broadcom BCM5721" rev 0x11, BCM5750 B1
(0x4101): irq 11, address 00:17:08:2c:2a:77
brgphy0 at bge0 phy 1: BCM5750 10/100/1000baseT PHY, rev. 0
ppb2 at pci0 dev 13 function 0 "NVIDIA nForce4 PCIE" rev 0xa3
pci3 at ppb2 bus 3
bge1 at pci3 dev 0 function 0 "Broadcom BCM5721" rev 0x11, BCM5750 B1
(0x4101): irq 10, address 00:17:08:2c:2a:76
brgphy1 at bge1 phy 1: BCM5750 10/100/1000baseT PHY, rev. 0
ppb3 at pci0 dev 14 function 0 "NVIDIA nForce4 PCIE" rev 0xa3
pci4 at ppb3 bus 4
pchb0 at pci0 dev 24 function 0 "AMD AMD64 HyperTransport" rev 0x00pci5 at
pchb0 bus 128
ppb4 at pci5 dev 1 function 0 "AMD 8132 PCIX" rev 0x12
pci6 at ppb4 bus 129
ppb5 at pci6 dev 1 function 0 "Pericom PI7C21P100 PCIX-PCIX" rev 0x01
pci7 at ppb5 bus 130
em0 at pci7 dev 4 function 0 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 7,
address 00:13:21:78:0f:2c
em1 at pci7 dev 4 function 1 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 5,
address 00:13:21:78:0f:2d
em2 at pci7 dev 6 function 0 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 10,
address 00:13:21:78:0f:2e
em3 at pci7 dev 6 function 1 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 11,
address 00:13:21:78:0f:2f
"AMD 8132 PCIX IOAPIC" rev 0x12 at pci5 dev 1 function 1 not configured
ppb6 at pci5 dev 2 function 0 "AMD 8132 PCIX" rev 0x12
pci8 at ppb6 bus 135
"AMD 8132 PCIX IOAPIC" rev 0x12 at pci5 dev 2 function 1 not configured
pchb1 at pci0 dev 24 function 1 "AMD AMD64 Address Map" rev 0x00
pchb2 at pci0 dev 24 function 2 "AMD AMD64 DRAM Cfg" rev 0x00
pchb3 at pci0 dev 24 function 3 "AMD AMD64 Misc Cfg" rev 0x00
isa0 at pcib0
isadma0 at isa0
pckbc0 at isa0 port 0x60/5
pckbd0 at pckbc0 (kbd slot)
pckbc0: using irq 1 for kbd slot
wskbd0 at pckbd0: console keyboard, using wsdisplay0
pcppi0 at isa0 port 0x61
spkr0 at pcppi0
usb1 at ohci0: USB revision 1.0
uhub1 at usb1: NVIDIA OHCI root hub, rev 1.00/1.00, addr 1
Kernelized RAIDframe activated
dkcsum: wd0 matches BIOS drive 0x80
root on wd0a swap on wd0b dump on wd0b
ok i try to update the kernel to current
holger
-----Urspr|ngliche Nachricht-----
Von: "Johan Mson Lindman" <[EMAIL PROTECTED]>
Gesendet: 06.02.08 17:22:45
An: holger glaess <[EMAIL PROTECTED]>
CC: misc@openbsd.org
Betreff: Re: high load irq trouble
1. Supply dmesg, we're not playing guessing games
2. This HW is known to have interrupt issues similar to what is described in
PR 5707, so if you are runing -current snapshot on the box, try disabling all
the acpi bells and whistles and things should improve substantially.
Regards
Johan M:son
On Wednesday 06 February 2008 14:59:25 holger glaess wrote:
hi
my hardeware are 2 pices of
hp dl 145 g2 2gb ram and a intel based 1gb quad interfaces card 1 sata hd.
this work as firewall system with 5 carp interfaces with up to 15 ip.
per box are 5 ethernet interfaces active. ( the system have 6 , the quad
card and 2 on board )
is is possible the the hp box is not possible to do more than 2000
interupts per irq ? i have in my environment a trougthput per interface
from 10 to 50Mbit.
if interupts going over 1800 on one interface i get massiv slow downs and
packet lost.
the rise the net.inet.ip.ifq.maxlen to 1024 ( i saw before drops ) .
to solve the problem as hot fix i did a trunk of 2 interfaces for this
interfaces with highes interrupts load.
top shows me close to 100% interrupts load but less then 1 overall load.
vmstat -i
interrupt total rate
irq12/pciide1 62702 0
irq11/bge0 84232199 986
irq10/bge1 11944226 139
irq7/em0 129003925 1510
irq5/em1 59507109 696
irq11/em2 134192386 1571
irq11/em3 5185828 60
irq1/pckbc0 6 0
irq0/clock 8539373 99
irq8/rtc 10930625 128
Total 443598379 5194
it is possible that this hardware to small for this traffic or it is a
problem from the design of the hp dl145 g2 ?
holger
