[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: [dm-devel] Latest dm-userspace kernel code

FT> I think that it would be better for the kerne module to provide
FT> only generic mechanisms.

I definitely see the value in removing the copy functionality from the
kernel pieces, I just want to make sure that performance will not

>> In order for this to perform well, we will need to use AIO, right?
FT> I'm not sure about this. Can you elaborate?

Well, assuming that a copy operation (and an fsync() to make sure it
is on-disk) is a non-trivial operation, it would be good to allow the
copy to happen in the background while still being able to service
other requests from the kernel.

In cowd, I need to write metadata when blocks are mapped, and fsync()
them to make sure they are on disk before I allow the IO to complete.
If I do this with a normal write()/fsync() (or open the file O_SYNC),
then cowd is blocked until the write is complete.  This means that
other requests that are in the queue, which may not require a copy,
are also blocked unnecessarily.  I assume that unless copy operations
are performed asynchronously (as they are now by letting the kernel do
it), the problem will get even worse.

Dan Smith
IBM Linux Technology Center
Open Hypervisor Team
email: danms us ibm com

Attachment: pgpYlJrRb3DNR.pgp
Description: PGP signature

[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]