panic: sbdrop

Robert Watson rwatson at FreeBSD.org
Wed Feb 28 21:41:13 UTC 2007


On Wed, 28 Feb 2007, Paulius Bulotas wrote:

> we have two Sun Fire X4100 running quite recent current: FreeBSD 7.0-CURRENT 
> #0: Fri Feb 23 21:12:46 EET 2007 root at anti:/usr/obj/usr/src/sys/GENERIC 
> amd64
>
> and they both panic once a day or two with:

If this is the panic I think it is, I have a patch that may help at:

   http://www.watson.org/~robert/freebsd/netperf/20070223-udp-sbdrop.diff

I've handed this patch off to Kris to test but as you've no doubt seen from 
the lists, he's being kept well out of trouble with all the scalability work, 
so I've not had a definitive answer as to whether it resolves the issues for 
him.

Thanks,

Robert N M Watson
Computer Laboratory
University of Cambridge

>
> panic: sbdrop
> cpuid = 1
> KDB: enter: panic
> [thread pid 68163 tid 100266 ]
> Stopped at      kdb_enter+0x2f: nop
> db> bt
> Tracing pid 68163 tid 100266 td 0xffffff00abdb47b0
> kdb_enter() at kdb_enter+0x2f
> panic() at panic+0x225
> sbdrop_internal() at sbdrop_internal+0x1bd
> sbflush_internal() at sbflush_internal+0x3c
> sbrelease_internal() at sbrelease_internal+0x1c
> sofree() at sofree+0x1ea
> soclose() at soclose+0x249
> soo_close() at soo_close+0x3f
> fdrop_locked() at fdrop_locked+0xc8
> closef() at closef+0x324
> kern_close() at kern_close+0x15d
> syscall() at syscall+0x1ef
> Xfast_syscall() at Xfast_syscall+0xab
> --- syscall (6, FreeBSD ELF64, close), rip = 0x800c7a3cc, rsp = 0x7fffffffec48, rbp = 0 ---
>
> it seems, there is open PR with similar panic, but difference backtrace:
> http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/96042
>
> any ideas?
>
> TIA
> Paulius
> _______________________________________________
> freebsd-current at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-current
> To unsubscribe, send any mail to "freebsd-current-unsubscribe at freebsd.org"
>


More information about the freebsd-current mailing list