Re: TSO panic

On 02.09.2010 00:11, ben wilber wrote:
> On Sep 1, 2010, at 8:57 AM, Andre Oppermann wrote:
>
>> On 01.09.2010 01:13, ben wilber wrote:
>>> Hi,
>>>
>>> I just upgraded from r210042 to r212073 and keep getting the panic
>>> introduced in r211317:
>>>
>>> panic: tcp_output: len<= tso_segsz
>>
>> Please try the attached patch and report back whether it
>> fixes the issue.
>
> The system ran for 8 hours or so before I received the same panic.  Previously, it would panic within 20 minutes.
>
> db:0:kdb.enter.default>   bt
> Tracing pid 17131 tid 100601 td 0xffffff0236603440
> kdb_enter() at kdb_enter+0x3d
> panic() at panic+0x1c8
> tcp_output() at tcp_output+0x1495
> tcp_usr_send() at tcp_usr_send+0x267
> sosend_generic() at sosend_generic+0x49e
> sosend() at sosend+0x1f
> soo_write() at soo_write+0x51
> dofilewrite() at dofilewrite+0x87
> kern_writev() at kern_writev+0x46
> write() at write+0x4e
> syscallenter() at syscallenter+0x251
> syscall() at syscall+0x39
> Xfast_syscall() at Xfast_syscall+0xe2
> --- syscall (4, FreeBSD ELF64, write), rip = 0x800f5d1ac, rsp = 0x7fffffffc3b8, rbp = 0x8007a1340 ---

Can you send me the core.txt.X file and the output of "p len" from
DDB or kgdb on a crash dump in private email?

-- 
Andre