[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path i
From: |
Paul Brook |
Subject: |
Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed |
Date: |
Sat, 4 Oct 2008 01:00:27 +0100 |
User-agent: |
KMail/1.9.9 |
On Saturday 04 October 2008, Anthony Liguori wrote:
> Paul Brook wrote:
> > On Friday 03 October 2008, Ryan Harper wrote:
> >> The default buffer size breaks up larger read/write requests
> >> unnecessarily. When we encounter requests larger than the default dma
> >> buffer, reallocate the buffer to support the request.
> >
> > Allocating unboundedly large host buffers based on guest input seems like
> > a bad idea.
>
> Perhaps they could be at least bound to phys_ram_size.
That's still way too large. It means that the maximum host footprint of qemu
is many times the size of the guest RAM. There's a good chance that the host
machine doesn't even have enough virtual address space to satisfy this
request.
I expect that the only situation where you can only avoid breaking up large
transfers when you have zero-copy IO. Previous zero-copy/vectored IO patches
suffered from a similar problem: It is not acceptable to allocate huge chunks
of host ram when you fallback to normal IO.
> In general, I don't think there's a correct size to bound them that's
> less than phys_ram_size. The guest may be issuing really big IO requests.
Qemu is perfectly capable of handling large IO requests by splitting them into
multiple smaller requests. Enlarging the size of this buffer is just a
secondary performance optimisation.
Admittedly we don't currently limit the number of simultaneous commands a
guest can submit, but that's relatively easy to fix.
Paul
- [Qemu-devel] [PATCH 0/4] Improve emulated scsi write performance, Ryan Harper, 2008/10/03
- [Qemu-devel] [PATCH 1/4] lsi_queue_command: add dma direction parameter, Ryan Harper, 2008/10/03
- [Qemu-devel] [PATCH 2/4] Refactor lsi_do_command to queue read and write ops, Ryan Harper, 2008/10/03
- [Qemu-devel] [PATCH 3/4] Refactor scsi-disk layer for queue'ing writes, Ryan Harper, 2008/10/03
- [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Ryan Harper, 2008/10/03
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Paul Brook, 2008/10/03
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Anthony Liguori, 2008/10/03
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed,
Paul Brook <=
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Avi Kivity, 2008/10/04
- Message not available
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Ryan Harper, 2008/10/04
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Anthony Liguori, 2008/10/04
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Avi Kivity, 2008/10/05
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Ryan Harper, 2008/10/05
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Avi Kivity, 2008/10/06
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Paul Brook, 2008/10/04
- Re: [Qemu-devel] [PATCH 4/4] Reallocate dma buffers in read/write path if needed, Avi Kivity, 2008/10/05
Re: [Qemu-devel] [PATCH 0/4] Improve emulated scsi write performance, Ryan Harper, 2008/10/05