(off-list ancestor, not in this archive)
[LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Kanchan Joshi <hidden> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Bart Van Assche <bvanassche@acm.org> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Kanchan Joshi <hidden> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Bart Van Assche <bvanassche@acm.org> · 2023-02-13
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Jens Axboe <axboe@kernel.dk> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · John Garry <john.g.garry@oracle.com> · 2023-02-14
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Jens Axboe <axboe@kernel.dk> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Sagi Grimberg <sagi@grimberg.me> · 2023-02-13
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Kanchan Joshi <hidden> · 2023-04-11
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Jens Axboe <axboe@kernel.dk> · 2023-04-11
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Kanchan Joshi <hidden> · 2023-04-11
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Jens Axboe <axboe@kernel.dk> · 2023-04-12
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Ming Lei <hidden> · 2023-04-12
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Kanchan Joshi <hidden> · 2023-04-12
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Ming Lei <hidden> · 2023-04-12
RE: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Clay Mayers <hidden> · 2023-02-10
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Ming Lei <hidden> · 2023-02-11
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · Hannes Reinecke <hare@suse.de> · 2023-02-11
Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO · John Meneghini <hidden> · 2023-02-28

Re: [LSF/MM/BPF ATTEND][LSF/MM/BPF Topic] Non-block IO

From: Bart Van Assche <bvanassche@acm.org>
Date: 2023-02-10 18:18:23
Also in: io-uring, linux-nvme

On 2/10/23 10:00, Kanchan Joshi wrote:

3. DMA cost: is high in presence of IOMMU. Keith posted the work[1],
with block IO path, last year. I imagine plumbing to get a bit simpler
with passthrough-only support. But what are the other things that must
be sorted out to have progress on moving DMA cost out of the fast path?

Are performance numbers available?

Isn't IOMMU cost something that has already been solved? From 
https://www.usenix.org/system/files/conference/atc15/atc15-paper-peleg.pdf: 
"Evaluation of our designs under Linux shows that (1)
they achieve 88.5%–100% of the performance obtained
without an IOMMU".

Thanks,

Bart.

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help