sun x4500 and smp

Remy Nonnenmacher remy.nonnenmacher at activnetworks.com
Fri Mar 20 17:15:13 UTC 2015



On 03/20/15 18:00, rondzierwa at comcast.net wrote:
> Thank you Remy!   Your recommendation solved the problem.  Its been
> running for over a day now without a single hiccup.
>
> thanks also to everyone else who took time to respond with help and
> suggestions.
>
>

I also noticed after some experiencing that you may try to restrict the 
stickiness only to the 8 marvell chips and let the other relocate 
dynamically but I haven't completed all the tests so I keep bounding to 
cpu0.

BTW, the solution was engraved on an old parchmail in the list and, as 
for you, it took me weeks to unearth it....

>
> At the risk of being a bother, were you able to get all four ethernet
> devices working?  on mine, only the first two are working.  the other
> two get errors on ioport allocation.
>

I confirm only two over the four interfaces are usable. Have not looked 
farther.

> em2: <Intel(R) PRO/1000 Legacy Network Connection 1.0.6> mem
> 0xfdbe0000-0xfdbfffff irq 61 at device 1.0 on pci8
> em2: 0x40 bytes of rid 0x20 res 4 failed (0, 0xffffffffffffffff).
> em2: Unable to allocate bus resource: ioport
> em2: Allocation of PCI resources failed
> device_attach: em2 attach returned 6
> em2: <Intel(R) PRO/1000 Legacy Network Connection 1.0.6> mem
> 0xfdbc0000-0xfdbdffff irq 62 at device 1.1 on pci8
> em2: 0x40 bytes of rid 0x20 res 4 failed (0, 0xffffffffffffffff).
> em2: Unable to allocate bus resource: ioport
> em2: Allocation of PCI resources failed
> device_attach: em2 attach returned 6
>
>
> ron.
>
>
> ------------------------------------------------------------------------
> *From: *"Remy Nonnenmacher" <remy.nonnenmacher at activnetworks.com>
> *To: *rondzierwa at comcast.net, freebsd-amd64 at freebsd.org
> *Sent: *Tuesday, March 17, 2015 4:39:33 AM
> *Subject: *Re: sun x4500 and smp
>
> Hi Ron,
>
> Fighted the same problem on mine. It seems to be a problem of interrupts
> dynamic routing on those old good opterons.
>
> I fixed it by sticking all interrupts to processor 0 (cpuset -l 0 -x
> ..). Since then, it works without any trouble.
>
>
> On 03/16/15 21:11, rondzierwa at comcast.net wrote:
>  > I am using a sunfire x4500 (thumper) with a pair of dual-core opteron
> 290 processors, running 10.1-RELEASE to serve up zfs filesystems via nfs
> and samba.
>  >
>  > The system reboots periodically when under load. I cannot find
> anything in any of the system logs that would account for why it
> rebooted, it just goes away for a while and comes back in a few minutes.
>  >
>  > Out of desperation, I tried disabling all but one of the processors.
> (hint.lapic.x.disabled=1 where x == 1, 2 and 3). Oddly enough the system
> doesn't reboot anymore.
>  >
>  > Is there any known issues about SMP not working on a sunfire x4500? I
> have searched the mail archives and haven't found anything useful.
>  >
>  > thanks in advance for any help or suggestions.
>  > ron.
>  >
>  > _______________________________________________
>  > freebsd-amd64 at freebsd.org mailing list
>  > http://lists.freebsd.org/mailman/listinfo/freebsd-amd64
>  > To unsubscribe, send any mail to "freebsd-amd64-unsubscribe at freebsd.org"
>  >
>


More information about the freebsd-amd64 mailing list