Re: [ Mind testing experimental one-liner? ]

Benjamin LaHaise (kernel@kvack.org)
Mon, 18 Jan 1999 14:06:36 -0500 (EST)


On Mon, 18 Jan 1999, Simon Kirby wrote:

> Everything on the machine has either got fsync()/sync() options disabled
> or is using an LD_PRELOAD wrapper so that it doesn't. Trust me, I even
> patched the kernel to report processes that call fsync()/sync() to track
> everything down...It should be only up the OS to flush buffers IMHO.

Hmmm, puzzling.

> Hmm...What would this do? Allow flushing to be done asynchronously?
> Is there anything that could be unsafe with this change?

It should be as safe as anything else (it's the fallback for filesystems
that don't implement fsync). file_fsync does a sync on the device the
filesystem is mounted on, which covers everything except dirty shared
mmap()ings of the file (which ext2_file_sync doesn't deal with anyways);
it just generates more disk writes than nescessary, but no reads.

-ben

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