hi
i did first disable the whole acpi part at the kernel and restart the box.
after reboot the irq rise ..... and the box feels more performant .
here some statistics
/var/log >vmstat -i
interrupt total rate
irq10/pciide1 6938 0
irq11/bge0 11713535 789
irq10/bge1 3384537 228
irq7/em0 39496778 2661
irq5/em1 33568487 2261
irq10/em2 51607108 3477
irq11/em3 903541 60
irq0/clock 1484363 100
irq8/rtc 1899973 128
Total 144065260 9706
demesg wo /acpi
OpenBSD 4.2-stable (fw) #18: Thu Feb 7 11:27:23 CET 2008
[EMAIL PROTECTED]:/usr/src/sys/arch/amd64/compile/fw
real mem = 2146136064 (2046MB)
avail mem = 2075103232 (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
ipmi0 at mainbus0: version 2.0 interface KCS iobase 0xca2/2 spacing 1
cpu0 at mainbus0: (uniprocessor)
cpu0: AMD Opteron(tm) Processor 246, 2000.26 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
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
ehci0: timed out waiting for BIOS
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 12 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 00:17:08:92:3a:c5
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 00:17:08:92:3a:c4
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 00:0e:0c:b4:c4:84
em1 at pci7 dev 4 function 1 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 5,
address 00:0e:0c:b4:c4:85
em2 at pci7 dev 6 function 0 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 11,
address 00:0e:0c:b4:c4:86
em3 at pci7 dev 6 function 1 "Intel PRO/1000MT QP (82546GB)" rev 0x03: irq 11,
address 00:0e:0c:b4:c4:87
"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
com2 at isa0 port 0x3e8/8 irq 4: ns16550a, 16 byte fifo
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
kernel w/ acpi:
/usr/src/sys/arch/amd64/compile/fw >md5 -t
MD5 time trial. Processing 10000 10000-byte blocks...
Digest = 52e5f9c9e6f656f3e1800dfa5579d089
Time = 0.418380 seconds
Speed = 239017161.432191 bytes/second
make in /usr/src/sys/arch/amd64/compile/fw
2m58.18s real 2m26.99s user 0m19.43s system
kernel wo/ acpi:
MD5 time trial. Processing 10000 10000-byte blocks...
Digest = 52e5f9c9e6f656f3e1800dfa5579d089
Time = 0.419656 seconds
Speed = 238290409.287607 bytes/second
make in /usr/src/sys/arch/amd64/compile/fw
2m56.15s real 2m26.46s user 0m18.24s system
and it is not possible to setup the irqs by bios.
holger
-----Urspr|ngliche Nachricht-----
Von: "Pierre Lamy" <[EMAIL PROTECTED]>
Gesendet: 07.02.08 14:53:03
An: [EMAIL PROTECTED]
CC: OpenBSD Misc <misc@openbsd.org>
Betreff: Re: high load irq trouble
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
