Re: 5.3-RELEASE: WARNING - WRITE_DMA interrupt timout

Hello,

This was on a kernel running with the small patch you posted earlier in 
this thread, so this is bogus :-( I haven't made clean -CURRENT panic 
in conjunction with these messages yet.

But does it tell us anything, or is this just noise?


Mvh,
Frode Nordahl

On Nov 14, 2004, at 12:51, Frode Nordahl wrote:

> Hello,
>
> Got my -CURRENT panic now, while running bonnie++ -r 4096
>
> ad4: FAILURE - WRITE_DMA timed out
> ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=131246815
> ad4: FAILURE - WRITE_DMA timed out
> g_vfs_done():ad4s1f[WRITE(offset=49750032384, length=131072)]error = 5
> ad4: timeout state=0 unexpected
> ad4: timeout state=0 unexpected
> ad4: timeout state=0 unexpected
> ad4: FAILURE - unknown BIO operation
>
> Fatal trap 12: page fault while in kernel mode
> cpuid = 1; apic id = 06
> fault virtual address   = 0xc
> fault code              = supervisor read, page not present
> instruction pointer     = 0x8:0xc05de440
> stack pointer           = 0x10:0xe9389c18
> frame pointer           = 0x10:0xe9389c24
> code segment            = base 0x0, limit 0xfffff, type 0x1b
>                         = DPL 0, pres 1, def32 1, gran 1
> processor eflags        = interrupt enabled, resume, IOPL = 0
> current process         = 4 (g_down)
> [thread 100073]
> Stopped at      g_disk_done+0xcc:       movl    0xc(%eax),%eax
>
> db> trace
> g_disk_done(c6254420,0,5,c077d824,e9389c6c) at g_disk_done+0xcc
> ad_start(c55644ac,0,c6254420,c580ce80,e9389cd0) at ad_start+0x7c
> ata_start(c5564400,0,0,0,0) at ata_start+0x265
> g_disk_start(c6254420,15740000,13,c580cb00,5b07e00) at 
> g_disk_start+0x88
> g_io_schedule_down(c549c480,c54aa000,e9389d34,c05ff130,0) at 
> g_io_schedule_down+0xac
> g_down_procbody(0,e9389d48,0,c05e0724,0) at g_down_procbody+0x1a
> fork_exit(c05e0724,0,e9389d48) at fork_exit+0x58
> fork_trampoline() at fork_trampoline+0x8
> --- trap 0x1, eip = 0, esp = 0xe9389d7c, ebp = 0 ---
> db>
>
> dmesg:
> <dmesg.txt>
>
>
> Mvh,
> Frode Nordahl