Re: 2.5.66: slow to friggin slow journal recover

Andrew Morton (akpm@digeo.com)
Fri, 11 Apr 2003 19:24:13 -0700


CaT <cat@zip.com.au> wrote:
>
> On Tue, Apr 01, 2003 at 02:28:44AM -0800, Andrew Morton wrote:
> > If the journal recovery is still slow then try capturing the state when it is
> > stuck with sysrq-T.
>
> It finally didn't kill it. This is what it's like when it's not doing
> anything (ie no disk access).
> ...
> fsck.ext3 R CF971E28 4293902656 40 37 (NOTLB)
> Call Trace:
> [<c0118a2e>] io_schedule+0xe/0x18
> [<c012cde8>] wait_on_page_bit+0x9c/0xb8
> [<c0119088>] autoremove_wake_function+0x0/0x3c
> [<c0119088>] autoremove_wake_function+0x0/0x3c
> [<c012d3a2>] do_generic_mapping_read+0x1be/0x328
> [<c012d7a0>] __generic_file_aio_read+0x184/0x1a0
> [<c012d50c>] file_read_actor+0x0/0x110
> [<c012d887>] generic_file_read+0x7f/0x9c
> [<c0138618>] handle_mm_fault+0x68/0xfc
> [<c0116960>] do_page_fault+0x0/0x3fe
> [<c01494ee>] blkdev_file_write+0x26/0x30
> [<c0142f4e>] vfs_read+0xa2/0xd4
> [<c014312a>] sys_read+0x2a/0x40
> [<c0108cf3>] syscall_call+0x7/0xb

OK, you may be thrashing the VM. fsck can use a lot of memory.

How large is the filesystem?

How many files are on the filesystem?

How much physical memory does the machine have?

Run ALT-sysrq-M during the fsck to get some stats.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/