On 07/04/2012 10:40 AM, Rusty Russell wrote:
On Tue, 03 Jul 2012 08:39:39 +0800, Asias He wrote:
On 07/02/2012 02:41 PM, Rusty Russell wrote:
Sure, our guest merging might save us 100x as many exits as no merging.
But since we're not doing many requests, does it matter?
We can still have man
Il 03/07/2012 16:28, Dor Laor ha scritto:
Users using a spinning disk still get IO scheduling in the host though.
What benefit is there in doing it in the guest as well?
>>>
>>> The io scheduler waits for requests to merge and thus batch IOs
>>> together. It's not important w.r.t spinning
On Tue, 03 Jul 2012 08:39:39 +0800, Asias He wrote:
> On 07/02/2012 02:41 PM, Rusty Russell wrote:
> > Sure, our guest merging might save us 100x as many exits as no merging.
> > But since we're not doing many requests, does it matter?
>
> We can still have many requests with slow devices. The nu
On 07/03/2012 05:22 PM, Ronen Hod wrote:
On 06/18/2012 02:14 PM, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch intr
On 06/18/2012 02:14 PM, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch introduces bio-based IO path for virtio-blk.
On 07/03/2012 09:31 PM, Paolo Bonzini wrote:
Il 02/07/2012 08:41, Rusty Russell ha scritto:
With the same workload in guest, the guest fires 200K requests to host
with merges enabled in guest (echo 0 > /sys/block/vdb/queue/nomerges),
while the guest fires 4K requests to host with merges disa
Il 02/07/2012 08:41, Rusty Russell ha scritto:
>> With the same workload in guest, the guest fires 200K requests to host
>> with merges enabled in guest (echo 0 > /sys/block/vdb/queue/nomerges),
>> while the guest fires 4K requests to host with merges disabled in
>> guest (echo 2 > /sys/bloc
On 07/02/2012 02:41 PM, Rusty Russell wrote:
On Mon, 02 Jul 2012 10:45:05 +0800, Asias He wrote:
On 07/02/2012 07:54 AM, Rusty Russell wrote:
Confused. So, without merging we get 6k exits (per second?) How many
do we get when we use the request-based IO path?
Sorry for the confusion. The n
On Mon, 02 Jul 2012 10:45:05 +0800, Asias He wrote:
> On 07/02/2012 07:54 AM, Rusty Russell wrote:
> > Confused. So, without merging we get 6k exits (per second?) How many
> > do we get when we use the request-based IO path?
>
> Sorry for the confusion. The numbers were collected from request-b
On 07/02/2012 07:54 AM, Rusty Russell wrote:
On Tue, 19 Jun 2012 10:51:18 +0800, Asias He wrote:
On 06/18/2012 07:39 PM, Sasha Levin wrote:
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On
On Tue, 19 Jun 2012 10:51:18 +0800, Asias He wrote:
> On 06/18/2012 07:39 PM, Sasha Levin wrote:
> > On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
> >> On 06/18/2012 01:05 PM, Rusty Russell wrote:
> >>> On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
> On 06/18/2012 03:46 PM, Rusty
On 06/20/2012 07:46 AM, Asias He wrote:
On 06/19/2012 02:21 PM, Dor Laor wrote:
On 06/19/2012 05:51 AM, Asias He wrote:
On 06/18/2012 07:39 PM, Sasha Levin wrote:
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +080
On 06/19/2012 02:21 PM, Dor Laor wrote:
On 06/19/2012 05:51 AM, Asias He wrote:
On 06/18/2012 07:39 PM, Sasha Levin wrote:
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 P
On 06/19/2012 05:51 AM, Asias He wrote:
On 06/18/2012 07:39 PM, Sasha Levin wrote:
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2
On 06/18/2012 07:39 PM, Sasha Levin wrote:
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
Th
On 06/18/2012 06:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch introduces bio-based IO path for virtio-blk.
Why make it optional?
request-based IO
On 06/18/2012 06:21 PM, Michael S. Tsirkin wrote:
On Mon, Jun 18, 2012 at 02:53:10PM +0800, Asias He wrote:
+static void virtblk_make_request(struct request_queue *q, struct bio *bio)
+{
+ struct virtio_blk *vblk = q->queuedata;
+ unsigned int num, out = 0, in = 0;
+ struct vir
On 06/18/2012 06:13 PM, Michael S. Tsirkin wrote:
On Mon, Jun 18, 2012 at 04:03:23PM +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch introduces bio-based IO path for virtio-blk.
Why make it optional?
reques
Hello, guys.
On Mon, Jun 18, 2012 at 07:35:22PM +0930, Rusty Russell wrote:
> On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
> > On 06/18/2012 03:46 PM, Rusty Russell wrote:
> > > On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
> > >> This patch introduces bio-based IO path for virtio-b
On Mon, 2012-06-18 at 14:14 +0300, Dor Laor wrote:
> On 06/18/2012 01:05 PM, Rusty Russell wrote:
> > On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
> >> On 06/18/2012 03:46 PM, Rusty Russell wrote:
> >>> On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
> This patch introduces bio-ba
On 06/18/2012 01:05 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch introduces bio-based IO path for virtio-blk.
Why make it optional?
request-based IO
On Mon, Jun 18, 2012 at 11:21 AM, Michael S. Tsirkin wrote:
> On Mon, Jun 18, 2012 at 02:53:10PM +0800, Asias He wrote:
>> +static void virtblk_make_request(struct request_queue *q, struct bio *bio)
>> +{
>> + struct virtio_blk *vblk = q->queuedata;
>> + unsigned int num, out = 0, in = 0;
On Mon, Jun 18, 2012 at 02:53:10PM +0800, Asias He wrote:
> +static void virtblk_make_request(struct request_queue *q, struct bio *bio)
> +{
> + struct virtio_blk *vblk = q->queuedata;
> + unsigned int num, out = 0, in = 0;
> + struct virtblk_req *vbr;
> +
> + BUG_ON(bio->bi_phys_se
On Mon, 18 Jun 2012 16:03:23 +0800, Asias He wrote:
> On 06/18/2012 03:46 PM, Rusty Russell wrote:
> > On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
> >> This patch introduces bio-based IO path for virtio-blk.
> >
> > Why make it optional?
>
> request-based IO path is useful for users who
On Mon, Jun 18, 2012 at 04:03:23PM +0800, Asias He wrote:
> On 06/18/2012 03:46 PM, Rusty Russell wrote:
> >On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
> >>This patch introduces bio-based IO path for virtio-blk.
> >
> >Why make it optional?
>
> request-based IO path is useful for users wh
On Mon, Jun 18, 2012 at 7:53 AM, Asias He wrote:
> +static void virtblk_add_buf_wait(struct virtio_blk *vblk,
> + struct virtblk_req *vbr,
> + unsigned long out,
> + unsigned long in)
> +{
> + DEFINE
On 06/18/2012 03:46 PM, Rusty Russell wrote:
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
This patch introduces bio-based IO path for virtio-blk.
Why make it optional?
request-based IO path is useful for users who do not want to bypass the
IO scheduler in guest kernel, e.g. users us
On Mon, 18 Jun 2012 14:53:10 +0800, Asias He wrote:
> This patch introduces bio-based IO path for virtio-blk.
Why make it optional?
Thanks,
Rusty.
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.o
This patch introduces bio-based IO path for virtio-blk.
Compared to request-based IO path, bio-based IO path uses driver
provided ->make_request_fn() method to bypasses the IO scheduler. It
handles the bio to device directly without allocating a request in block
layer. This reduces the IO path in
29 matches
Mail list logo
