Re: Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-07 Thread Nicole Harrington

--- Mike Tancsa <[EMAIL PROTECTED]> wrote:

> At 10:18 PM 2/6/2007, Nicole Harrington wrote:
> >
> > > I use RELENG_6 in i386 mode on this MB (two
> > > integrated em nics) and it
> > > works quite well
> >
> >  Have you tried it with the tune for Diskd
> mentioned.
> 
> No,
>  But I have a box scheduled to be put
> together tomorrow and 
> will give it a try.  How much RAM do you have on
> them ?
> 
> 
>  ---Mike 

 Ok - I have done more tests and it gets more odd.
  I was running actually 6.2-PreRelease. To see if 
something was fixed, I setup a new disk with a fresh
install of 6.2-RELEASE amd64. Now even without the
sysctl modifications I can reboot the server with:
 bonnie++ -d /home -u root -s1g

 Tyan S3992 Mb with a 2210 CPU and 4Gigs Ram.
 Western Digital Raptor WD740ADFD

 Error on console: Tons of ones like these zoom by.

 g_vfs_done():ad4s1a[READ(offset=172627162,
Length=626729(] error=6


 This is true under P-ATA or S-ATA.

 
 Nicole

 

___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Re: Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-07 Thread Mike Tancsa

At 10:18 PM 2/6/2007, Nicole Harrington wrote:


> I use RELENG_6 in i386 mode on this MB (two
> integrated em nics) and it
> works quite well

 Have you tried it with the tune for Diskd mentioned.


No,
But I have a box scheduled to be put together tomorrow and 
will give it a try.  How much RAM do you have on them ?



---Mike 


___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Re: Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-06 Thread Nicole Harrington
--- Mike Tancsa <[EMAIL PROTECTED]> wrote:
> On Tue, 6 Feb 2007 15:26:27 -0800 (PST), in
> sentex.lists.freebsd.questions you wrote:

> > If I run: bonnie++ -d /home -u root s1g
> >  The system reboots.
> >
> > I have tried this is both S-ATA and P-ATA
> emulation.
> >atapci0: 
> port
> >0xb080-0xb087,0xb000-0xb003,0xac00-0xac07
> >,0xa880-0xa883,0xa800-0xa81f mem
> 0xff4fe000-0xff4f
> >irq 11 at device 14.0 on pci1
> >
> >S-ATA:
> >ad4: 70911MB  at
> >ata2-master SATA150
> >
> > OR
> >P-ATA:
> >ad4: DMA limited to UDMA33, device found non-ATA66
> >cable
> >ad4: 70911MB  at
> >ata2-master UDMA33

 
> I use RELENG_6 in i386 mode on this MB (two
> integrated em nics) and it
> works quite well

 Have you tried it with the tune for Diskd mentioned.
 
> atapci0: 
> port
>
0xc080-0xc087,0xc000-0xc003,0xbc00-0xbc07,0xb880-0xb883,0xb800-0xb81f
> mem 0xff
> 3fe000-0xff3f irq 11 at device 14.0 on pci1
> ata2:  on atapci0
> ata3:  on atapci0
> ata4:  on atapci0
> ata5:  on atapci0
> atapci1: 
> port
> 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xffa0-0xffaf at
> device 2.1 on
> pci0
> ata0:  on atapci1
> ata1:  on atapci1
> 
> ad4: 76319MB  at
> ata2-master SATA150
> 
> # atacontrol list
> ATA channel 0:
> Master:  no device present
> Slave:   no device present
> ATA channel 1:
> Master:  no device present
> Slave:   no device present
> ATA channel 2:
> Master:  ad4  Serial ATA II
> Slave:   no device present
> ATA channel 3:
> Master:  no device present
> Slave:   no device present
> ATA channel 4:
> Master:  no device present
> Slave:   no device present
> ATA channel 5:
> Master:  no device present
> Slave:   no device present
> 
> 
> However, update the BIOS and make sure you dont use
> PATA emulation on
> the SATA controller as that doesnt really work. 
> 
>   ---Mike
>

> Mike Tancsa, Sentex communications
> http://www.sentex.net
> Providing Internet Access since 1994
> [EMAIL PROTECTED], (http://www.tancsa.com)

Hi Mike
 Yes, it does work quite well. But not if I use the
same tuning parameters used on systems running on Non
Serverworks chipsets. (Tyan S2881 or S2882 Board)

 I use these for supporting many heavy loaded Squid
servers. 

 The normal tweaks suggested for Squid, and work well
on Non Serverworks chipsets are:

/boot/loader.conf
kern.ipc.maxsockets=16424
kern.ipc.msgmnb=16384
kern.ipc.msgmni=41
kern.ipc.msgseg=2049
kern.ipc.msgssz=64
kern.ipc.msgtql=2048
 OR
kern.ipc.msgmnb=8192
kern.ipc.msgmni=40
kern.ipc.msgseg=512
kern.ipc.msgssz=64
kern.ipc.msgtql=1024

 However, with any setting of kern.ipc.msgtql (What
does it do anyway?) above 64 the server crashes with
the Bonnie test.

 The higher the setting the faster the crash.

 

 Nicole



___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Re: Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-06 Thread Mike Tancsa
On Tue, 6 Feb 2007 15:26:27 -0800 (PST), in
sentex.lists.freebsd.questions you wrote:

>
> If I run: bonnie++ -d /home -u root s1g
>  The system reboots.
>
> I have tried this is both S-ATA and P-ATA emulation.


>atapci0:  port
>0xb080-0xb087,0xb000-0xb003,0xac00-0xac07
>,0xa880-0xa883,0xa800-0xa81f mem 0xff4fe000-0xff4f
>irq 11 at device 14.0 on pci1
>
>S-ATA:
>ad4: 70911MB  at
>ata2-master SATA150
>
> OR
>P-ATA:
>ad4: DMA limited to UDMA33, device found non-ATA66
>cable
>ad4: 70911MB  at
>ata2-master UDMA33

I use RELENG_6 in i386 mode on this MB (two integrated em nics) and it
works quite well

atapci0:  port
0xc080-0xc087,0xc000-0xc003,0xbc00-0xbc07,0xb880-0xb883,0xb800-0xb81f
mem 0xff
3fe000-0xff3f irq 11 at device 14.0 on pci1
ata2:  on atapci0
ata3:  on atapci0
ata4:  on atapci0
ata5:  on atapci0
atapci1:  port
0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xffa0-0xffaf at device 2.1 on
pci0
ata0:  on atapci1
ata1:  on atapci1

ad4: 76319MB  at ata2-master SATA150

# atacontrol list
ATA channel 0:
Master:  no device present
Slave:   no device present
ATA channel 1:
Master:  no device present
Slave:   no device present
ATA channel 2:
Master:  ad4  Serial ATA II
Slave:   no device present
ATA channel 3:
Master:  no device present
Slave:   no device present
ATA channel 4:
Master:  no device present
Slave:   no device present
ATA channel 5:
Master:  no device present
Slave:   no device present


However, update the BIOS and make sure you dont use PATA emulation on
the SATA controller as that doesnt really work. 

---Mike

Mike Tancsa, Sentex communications http://www.sentex.net
Providing Internet Access since 1994
[EMAIL PROTECTED], (http://www.tancsa.com)
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-06 Thread N. Harrington
 Hello.
 I am testing out a new tyan motherboard that uses the
next generation of AMD chips and the Serverworks
Chipset. It seems that I can reliably crash it with a
simple bonnie++ test if I set:

/boot/loader.conf  - Used for DiskD for Squid
  kern.ipc.msgtql=2048 

 I am using FreeBSD 6.1-STABLE amd64. This all works
just fine on a non Serverworks Chipset Tyan Board.
(literaly I unplug the drive and move it to another
system and it works and works in production)


 If I run: bonnie++ -d /home -u root s1g
  The system reboots.

 I have tried this is both S-ATA and P-ATA emulation.

 Any ideas on why this setting, which works on non
Serverworks boards, would make the Serverworks so
twitchy?


  Thanks

  Nicole


atapci0:  port
0xb080-0xb087,0xb000-0xb003,0xac00-0xac07
,0xa880-0xa883,0xa800-0xa81f mem 0xff4fe000-0xff4f
irq 11 at device 14.0 on pci1

S-ATA:
ad4: 70911MB  at
ata2-master SATA150

 OR
P-ATA:
ad4: DMA limited to UDMA33, device found non-ATA66
cable
ad4: 70911MB  at
ata2-master UDMA33

/boot/loader.conf
kern.ipc.msgtql=2048

___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Problem with Serverworks HT1000 serial ATA support - Tyan S3992 Motherboard

2007-02-06 Thread N. Harrington
 Hello
 I am testing out a new tyan motherboard that uses the
next generation of AMD chips and the Serverworks
Chipset. It seems that I can reliably crash it with a
simple bonnie++ test if I set:

/boot/loader.conf  - Used for DiskD for Squid
  kern.ipc.msgtql=2048 

 I am using FreeBSD 6.1-STABLE amd64. This all works
just fine on a non Serverworks Chipset Tyan Board.
(literaly I unplug the drive and move it to another
system and it works and works in production)


 If I run: bonnie++ -d /home -u root s1g
  The system reboots.

 I have tried this is both S-ATA and P-ATA emulation.

 Any ideas on why this setting, which works on non
Serverworks boards, would make the Serverworks so
twitchy?


  Thanks

  Nicole


atapci0:  port
0xb080-0xb087,0xb000-0xb003,0xac00-0xac07
,0xa880-0xa883,0xa800-0xa81f mem 0xff4fe000-0xff4f
irq 11 at device 14.0 on pci1

S-ATA:
ad4: 70911MB  at
ata2-master SATA150

 OR
P-ATA:
ad4: DMA limited to UDMA33, device found non-ATA66
cable
ad4: 70911MB  at
ata2-master UDMA33

/boot/loader.conf
kern.ipc.msgtql=2048


___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"