|
From: | Anthony Liguori |
Subject: | Re: [Qemu-devel] [PATCH 2/6] change vectored block I/O API to plain iovecs |
Date: | Sun, 15 Mar 2009 08:20:00 -0500 |
User-agent: | Thunderbird 2.0.0.19 (X11/20090105) |
Avi Kivity wrote:
Christoph Hellwig wrote:QEMUIOVector is a useful helper for the dma-helper.c internals but for a generic block API it's more of hindrance. Some top-level consumers like virtio-blk already have the plain iovec and segment number at hand and can pass it down directly, and for those that just have a single element and need to fake upa vector the plain iovec also is a lot easier.virtio gets its iovecs through a hacky (and incorrect, try >=4G) method. IMO virtio should be fixed to use the dma api, at which point it will start to use QEMUIOVector anyway,
>= 4GB should work fine in virtio. It basically replicates the DMA API today. It doesn't handle MMIO memory though.
Last but not leas we want to push down vectored I/O to the lowest level, and if posix-aio-compat.c wants to stay somewhat true to it's goal of beeing like an ehanced posix AIO API it should stick to posix types.Internally yes, but why should bdrv_* not use QEMUIOVector? That API isn't very interested in posix.
Agreed. Regards, Anthony Liguori
[Prev in Thread] | Current Thread | [Next in Thread] |