* [PATCH] block: virtio_blk: don't hold spin lock during world switch
@ 2014-05-30 2:49 Ming Lei
2014-05-30 3:19 ` Jens Axboe
` (2 more replies)
0 siblings, 3 replies; 13+ messages in thread
From: Ming Lei @ 2014-05-30 2:49 UTC (permalink / raw)
To: Jens Axboe, linux-kernel
Cc: Ming Lei, Rusty Russell, Michael S. Tsirkin, virtualization
Firstly, it isn't necessary to hold lock of vblk->vq_lock
when notifying hypervisor about queued I/O.
Secondly, virtqueue_notify() will cause world switch and
it may take long time on some hypervisors(such as, qemu-arm),
so it isn't good to hold the lock and block other vCPUs.
On arm64 quad core VM(qemu-kvm), the patch can increase I/O
performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
- without the patch: 14K IOPS
- with the patch: 34K IOPS
fio script:
[global]
direct=1
bsrange=4k-4k
timeout=10
numjobs=4
ioengine=libaio
iodepth=64
filename=/dev/vdc
group_reporting=1
[f1]
rw=randread
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
drivers/block/virtio_blk.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 9f340fa..a6f5424 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -162,6 +162,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
unsigned int num;
const bool last = (req->cmd_flags & REQ_END) != 0;
int err;
+ bool notify = false;
BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
@@ -214,10 +215,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
return BLK_MQ_RQ_QUEUE_ERROR;
}
- if (last)
- virtqueue_kick(vblk->vq);
-
+ if (last && virtqueue_kick_prepare(vblk->vq))
+ notify = true;
spin_unlock_irqrestore(&vblk->vq_lock, flags);
+
+ if (notify)
+ virtqueue_notify(vblk->vq);
return BLK_MQ_RQ_QUEUE_OK;
}
--
1.7.9.5
^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 2:49 [PATCH] block: virtio_blk: don't hold spin lock during world switch Ming Lei
@ 2014-05-30 3:19 ` Jens Axboe
2014-05-30 3:34 ` Ming Lei
2014-05-30 6:05 ` Rusty Russell
2014-05-30 15:27 ` Michael S. Tsirkin
2 siblings, 1 reply; 13+ messages in thread
From: Jens Axboe @ 2014-05-30 3:19 UTC (permalink / raw)
To: Ming Lei, linux-kernel; +Cc: Rusty Russell, Michael S. Tsirkin, virtualization
On 2014-05-29 20:49, Ming Lei wrote:
> Firstly, it isn't necessary to hold lock of vblk->vq_lock
> when notifying hypervisor about queued I/O.
>
> Secondly, virtqueue_notify() will cause world switch and
> it may take long time on some hypervisors(such as, qemu-arm),
> so it isn't good to hold the lock and block other vCPUs.
>
> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
> - without the patch: 14K IOPS
> - with the patch: 34K IOPS
Patch looks good to me. I don't see a hit on my qemu-kvm testing, but it
definitely makes sense and I can see it hurting in other places.
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 3:19 ` Jens Axboe
@ 2014-05-30 3:34 ` Ming Lei
2014-05-30 3:35 ` Jens Axboe
0 siblings, 1 reply; 13+ messages in thread
From: Ming Lei @ 2014-05-30 3:34 UTC (permalink / raw)
To: Jens Axboe
Cc: Linux Kernel Mailing List, Rusty Russell, Michael S. Tsirkin,
virtualization
On Fri, May 30, 2014 at 11:19 AM, Jens Axboe <axboe@kernel.dk> wrote:
> On 2014-05-29 20:49, Ming Lei wrote:
>>
>> Firstly, it isn't necessary to hold lock of vblk->vq_lock
>> when notifying hypervisor about queued I/O.
>>
>> Secondly, virtqueue_notify() will cause world switch and
>> it may take long time on some hypervisors(such as, qemu-arm),
>> so it isn't good to hold the lock and block other vCPUs.
>>
>> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
>> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
>> - without the patch: 14K IOPS
>> - with the patch: 34K IOPS
>
>
> Patch looks good to me. I don't see a hit on my qemu-kvm testing, but it
> definitely makes sense and I can see it hurting in other places.
It isn't easy to observe the improvement on x86 VM, especially
with few vCPUs, because qemu-system-x86_64 only takes
several microseconds to handle the notification, but on arm64, it
may take hundreds of microseconds, so the improvement is
obvious on arm VM.
I hope this patch can be merged, at least arm VM can benefit
from it.
Thanks,
--
Ming Lei
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 3:34 ` Ming Lei
@ 2014-05-30 3:35 ` Jens Axboe
2014-05-30 5:58 ` Ming Lei
2014-05-30 6:10 ` Rusty Russell
0 siblings, 2 replies; 13+ messages in thread
From: Jens Axboe @ 2014-05-30 3:35 UTC (permalink / raw)
To: Ming Lei
Cc: Linux Kernel Mailing List, Rusty Russell, Michael S. Tsirkin,
virtualization
On 2014-05-29 21:34, Ming Lei wrote:
> On Fri, May 30, 2014 at 11:19 AM, Jens Axboe <axboe@kernel.dk> wrote:
>> On 2014-05-29 20:49, Ming Lei wrote:
>>>
>>> Firstly, it isn't necessary to hold lock of vblk->vq_lock
>>> when notifying hypervisor about queued I/O.
>>>
>>> Secondly, virtqueue_notify() will cause world switch and
>>> it may take long time on some hypervisors(such as, qemu-arm),
>>> so it isn't good to hold the lock and block other vCPUs.
>>>
>>> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
>>> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
>>> - without the patch: 14K IOPS
>>> - with the patch: 34K IOPS
>>
>>
>> Patch looks good to me. I don't see a hit on my qemu-kvm testing, but it
>> definitely makes sense and I can see it hurting in other places.
>
> It isn't easy to observe the improvement on x86 VM, especially
> with few vCPUs, because qemu-system-x86_64 only takes
> several microseconds to handle the notification, but on arm64, it
> may take hundreds of microseconds, so the improvement is
> obvious on arm VM.
>
> I hope this patch can be merged, at least arm VM can benefit
> from it.
If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 3:35 ` Jens Axboe
@ 2014-05-30 5:58 ` Ming Lei
2014-05-30 6:10 ` Rusty Russell
1 sibling, 0 replies; 13+ messages in thread
From: Ming Lei @ 2014-05-30 5:58 UTC (permalink / raw)
To: Jens Axboe
Cc: Linux Kernel Mailing List, Rusty Russell, Michael S. Tsirkin,
virtualization
On Fri, May 30, 2014 at 11:35 AM, Jens Axboe <axboe@kernel.dk> wrote:
> On 2014-05-29 21:34, Ming Lei wrote:
>>
>> On Fri, May 30, 2014 at 11:19 AM, Jens Axboe <axboe@kernel.dk> wrote:
>>>
>>> On 2014-05-29 20:49, Ming Lei wrote:
>>>>
>>>>
>>>> Firstly, it isn't necessary to hold lock of vblk->vq_lock
>>>> when notifying hypervisor about queued I/O.
>>>>
>>>> Secondly, virtqueue_notify() will cause world switch and
>>>> it may take long time on some hypervisors(such as, qemu-arm),
>>>> so it isn't good to hold the lock and block other vCPUs.
>>>>
>>>> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
>>>> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
>>>> - without the patch: 14K IOPS
>>>> - with the patch: 34K IOPS
>>>
>>>
>>>
>>> Patch looks good to me. I don't see a hit on my qemu-kvm testing, but it
>>> definitely makes sense and I can see it hurting in other places.
>>
>>
>> It isn't easy to observe the improvement on x86 VM, especially
>> with few vCPUs, because qemu-system-x86_64 only takes
>> several microseconds to handle the notification, but on arm64, it
>> may take hundreds of microseconds, so the improvement is
>> obvious on arm VM.
>>
>> I hope this patch can be merged, at least arm VM can benefit
>> from it.
>
>
> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
Interesting, even on x86, I still can observe the improvement
when the numjobs is set as 2 in the fio script(see commit log), but
when numjobs is set as 4, 8, 12, the difference isn't obvious between
patched kernel and non-patched kernel.
1, environment
- host: 2sockets, each CPU(4cores, 2 threads), total 16 logical cores
- guest: 16cores, 8GB ram
- guest kernel: 3.15-rc7-next with patch[1]
- fio: the script in commit log with numjobs set as 2
2, result
- without the patch: ~104K IOPS
- with the patch: ~140K IOPS
Rusty, considered the same trick has been applied in virt-scsi,
do you agree to take the same approach in virt-blk too?
[1], http://marc.info/?l=linux-kernel&m=140135041423441&w=2
Thanks,
--
Ming Lei
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 2:49 [PATCH] block: virtio_blk: don't hold spin lock during world switch Ming Lei
2014-05-30 3:19 ` Jens Axboe
@ 2014-05-30 6:05 ` Rusty Russell
2014-05-30 15:27 ` Michael S. Tsirkin
2 siblings, 0 replies; 13+ messages in thread
From: Rusty Russell @ 2014-05-30 6:05 UTC (permalink / raw)
To: Ming Lei, Jens Axboe, linux-kernel
Cc: Ming Lei, Michael S. Tsirkin, virtualization
Ming Lei <ming.lei@canonical.com> writes:
> Firstly, it isn't necessary to hold lock of vblk->vq_lock
> when notifying hypervisor about queued I/O.
>
> Secondly, virtqueue_notify() will cause world switch and
> it may take long time on some hypervisors(such as, qemu-arm),
> so it isn't good to hold the lock and block other vCPUs.
>
> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
> - without the patch: 14K IOPS
> - with the patch: 34K IOPS
>
> fio script:
> [global]
> direct=1
> bsrange=4k-4k
> timeout=10
> numjobs=4
> ioengine=libaio
> iodepth=64
>
> filename=/dev/vdc
> group_reporting=1
>
> [f1]
> rw=randread
>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: virtualization@lists.linux-foundation.org
> Signed-off-by: Ming Lei <ming.lei@canonical.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Thanks!
Rusty.
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 3:35 ` Jens Axboe
2014-05-30 5:58 ` Ming Lei
@ 2014-05-30 6:10 ` Rusty Russell
2014-05-30 13:52 ` Jens Axboe
1 sibling, 1 reply; 13+ messages in thread
From: Rusty Russell @ 2014-05-30 6:10 UTC (permalink / raw)
To: Jens Axboe, Ming Lei
Cc: Linux Kernel Mailing List, Michael S. Tsirkin, virtualization
Jens Axboe <axboe@kernel.dk> writes:
> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
Really stable? It improves performance, which is nice. But every patch
which goes into the kernel fixes a bug, improves clarity, improves
performance or adds a feature. I've now seen all four cases get CC'd
into stable.
Including some of mine explicitly not marked stable which get swept up
by enthusiastic stable maintainers :(
Is now there *any* patch short of a major rewrite which shouldn't get
cc: stable?
Cheers,
Rusty.
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 6:10 ` Rusty Russell
@ 2014-05-30 13:52 ` Jens Axboe
2014-06-02 1:23 ` Rusty Russell
0 siblings, 1 reply; 13+ messages in thread
From: Jens Axboe @ 2014-05-30 13:52 UTC (permalink / raw)
To: Rusty Russell, Ming Lei
Cc: Linux Kernel Mailing List, Michael S. Tsirkin, virtualization
On 2014-05-30 00:10, Rusty Russell wrote:
> Jens Axboe <axboe@kernel.dk> writes:
>> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
>
> Really stable? It improves performance, which is nice. But every patch
> which goes into the kernel fixes a bug, improves clarity, improves
> performance or adds a feature. I've now seen all four cases get CC'd
> into stable.
>
> Including some of mine explicitly not marked stable which get swept up
> by enthusiastic stable maintainers :(
>
> Is now there *any* patch short of a major rewrite which shouldn't get
> cc: stable?
I agree that there's sometimes an unfortunate trend there. I didn't
check, but my assumption was that this is a regression after the blk-mq
conversion, in which case I do think it belongs in stable.
But in any case, I think the patch is obviously correct and the wins are
sufficiently large to warrant a stable inclusion even if it isn't a
regression.
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 2:49 [PATCH] block: virtio_blk: don't hold spin lock during world switch Ming Lei
2014-05-30 3:19 ` Jens Axboe
2014-05-30 6:05 ` Rusty Russell
@ 2014-05-30 15:27 ` Michael S. Tsirkin
2 siblings, 0 replies; 13+ messages in thread
From: Michael S. Tsirkin @ 2014-05-30 15:27 UTC (permalink / raw)
To: Ming Lei; +Cc: Jens Axboe, linux-kernel, Rusty Russell, virtualization
On Fri, May 30, 2014 at 10:49:29AM +0800, Ming Lei wrote:
> Firstly, it isn't necessary to hold lock of vblk->vq_lock
> when notifying hypervisor about queued I/O.
>
> Secondly, virtqueue_notify() will cause world switch and
> it may take long time on some hypervisors(such as, qemu-arm),
> so it isn't good to hold the lock and block other vCPUs.
>
> On arm64 quad core VM(qemu-kvm), the patch can increase I/O
> performance a lot with VIRTIO_RING_F_EVENT_IDX enabled:
> - without the patch: 14K IOPS
> - with the patch: 34K IOPS
>
> fio script:
> [global]
> direct=1
> bsrange=4k-4k
> timeout=10
> numjobs=4
> ioengine=libaio
> iodepth=64
>
> filename=/dev/vdc
> group_reporting=1
>
> [f1]
> rw=randread
>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Cc: virtualization@lists.linux-foundation.org
> Signed-off-by: Ming Lei <ming.lei@canonical.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
> ---
> drivers/block/virtio_blk.c | 9 ++++++---
> 1 file changed, 6 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> index 9f340fa..a6f5424 100644
> --- a/drivers/block/virtio_blk.c
> +++ b/drivers/block/virtio_blk.c
> @@ -162,6 +162,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
> unsigned int num;
> const bool last = (req->cmd_flags & REQ_END) != 0;
> int err;
> + bool notify = false;
>
> BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
>
> @@ -214,10 +215,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
> return BLK_MQ_RQ_QUEUE_ERROR;
> }
>
> - if (last)
> - virtqueue_kick(vblk->vq);
> -
> + if (last && virtqueue_kick_prepare(vblk->vq))
> + notify = true;
> spin_unlock_irqrestore(&vblk->vq_lock, flags);
> +
> + if (notify)
> + virtqueue_notify(vblk->vq);
> return BLK_MQ_RQ_QUEUE_OK;
> }
>
> --
> 1.7.9.5
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-05-30 13:52 ` Jens Axboe
@ 2014-06-02 1:23 ` Rusty Russell
2014-06-02 13:06 ` Ming Lei
2014-06-02 14:15 ` Jens Axboe
0 siblings, 2 replies; 13+ messages in thread
From: Rusty Russell @ 2014-06-02 1:23 UTC (permalink / raw)
To: Jens Axboe, Ming Lei
Cc: Linux Kernel Mailing List, Michael S. Tsirkin, virtualization
Jens Axboe <axboe@kernel.dk> writes:
> On 2014-05-30 00:10, Rusty Russell wrote:
>> Jens Axboe <axboe@kernel.dk> writes:
>>> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
>>
>> Really stable? It improves performance, which is nice. But every patch
>> which goes into the kernel fixes a bug, improves clarity, improves
>> performance or adds a feature. I've now seen all four cases get CC'd
>> into stable.
>>
>> Including some of mine explicitly not marked stable which get swept up
>> by enthusiastic stable maintainers :(
>>
>> Is now there *any* patch short of a major rewrite which shouldn't get
>> cc: stable?
>
> I agree that there's sometimes an unfortunate trend there. I didn't
> check, but my assumption was that this is a regression after the blk-mq
> conversion, in which case I do think it belongs in stable.
No, it's always been that way. In the original driver the entire "issue
requests" function was under the lock.
It was your mq conversion which made this optimization possible, and
also made it an optimization: now other the queues can continue while
this one is going.
> But in any case, I think the patch is obviously correct and the wins are
> sufficiently large to warrant a stable inclusion even if it isn't a
> regression.
If you're running SMP under an emulator where exits are expensive, then
this wins. Under KVM it's marginal at best.
Locking changes which are "obviously correct" make me nervous, too :)
But IIRC last KS the argument is that not *enough* is going into stable,
not that stable isn't stable enough. So maybe it's a non-problem?
Cheers,
Rusty.
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-06-02 1:23 ` Rusty Russell
@ 2014-06-02 13:06 ` Ming Lei
2014-06-11 14:44 ` Paolo Bonzini
2014-06-02 14:15 ` Jens Axboe
1 sibling, 1 reply; 13+ messages in thread
From: Ming Lei @ 2014-06-02 13:06 UTC (permalink / raw)
To: Rusty Russell
Cc: Jens Axboe, Linux Kernel Mailing List, Michael S. Tsirkin,
virtualization
On Mon, Jun 2, 2014 at 9:23 AM, Rusty Russell <rusty@rustcorp.com.au> wrote:
> Jens Axboe <axboe@kernel.dk> writes:
>> On 2014-05-30 00:10, Rusty Russell wrote:
>>> Jens Axboe <axboe@kernel.dk> writes:
>>>> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
>>>
>>> Really stable? It improves performance, which is nice. But every patch
>>> which goes into the kernel fixes a bug, improves clarity, improves
>>> performance or adds a feature. I've now seen all four cases get CC'd
>>> into stable.
>>>
>>> Including some of mine explicitly not marked stable which get swept up
>>> by enthusiastic stable maintainers :(
>>>
>>> Is now there *any* patch short of a major rewrite which shouldn't get
>>> cc: stable?
>>
>> I agree that there's sometimes an unfortunate trend there. I didn't
>> check, but my assumption was that this is a regression after the blk-mq
>> conversion, in which case I do think it belongs in stable.
>
> No, it's always been that way. In the original driver the entire "issue
> requests" function was under the lock.
>
> It was your mq conversion which made this optimization possible, and
> also made it an optimization: now other the queues can continue while
> this one is going.
>
>> But in any case, I think the patch is obviously correct and the wins are
>> sufficiently large to warrant a stable inclusion even if it isn't a
>> regression.
>
> If you're running SMP under an emulator where exits are expensive, then
> this wins. Under KVM it's marginal at best.
Both my tests on arm64 and x86 are under KVM, and looks the
patch can improve performance a lot. IMO, even though under
KVM, virtio-blk performance still depends how well hypervisor(
qemu, ...) emulates the device, and basically speaking, it is
expensive to switch from guest to host and let host handle the
notification.
Thanks,
--
Ming Lei
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-06-02 1:23 ` Rusty Russell
2014-06-02 13:06 ` Ming Lei
@ 2014-06-02 14:15 ` Jens Axboe
1 sibling, 0 replies; 13+ messages in thread
From: Jens Axboe @ 2014-06-02 14:15 UTC (permalink / raw)
To: Rusty Russell, Ming Lei
Cc: Linux Kernel Mailing List, Michael S. Tsirkin, virtualization
On 2014-06-01 19:23, Rusty Russell wrote:
> Jens Axboe <axboe@kernel.dk> writes:
>> On 2014-05-30 00:10, Rusty Russell wrote:
>>> Jens Axboe <axboe@kernel.dk> writes:
>>>> If Rusty agrees, I'd like to add it for 3.16 with a stable marker.
>>>
>>> Really stable? It improves performance, which is nice. But every patch
>>> which goes into the kernel fixes a bug, improves clarity, improves
>>> performance or adds a feature. I've now seen all four cases get CC'd
>>> into stable.
>>>
>>> Including some of mine explicitly not marked stable which get swept up
>>> by enthusiastic stable maintainers :(
>>>
>>> Is now there *any* patch short of a major rewrite which shouldn't get
>>> cc: stable?
>>
>> I agree that there's sometimes an unfortunate trend there. I didn't
>> check, but my assumption was that this is a regression after the blk-mq
>> conversion, in which case I do think it belongs in stable.
>
> No, it's always been that way. In the original driver the entire "issue
> requests" function was under the lock.
>
> It was your mq conversion which made this optimization possible, and
> also made it an optimization: now other the queues can continue while
> this one is going.
Ah, I stand corrected, you are right. I had this recollection that the
prepare and kick where separate before as well, but apparently just bad
memory.
>> But in any case, I think the patch is obviously correct and the wins are
>> sufficiently large to warrant a stable inclusion even if it isn't a
>> regression.
>
> If you're running SMP under an emulator where exits are expensive, then
> this wins. Under KVM it's marginal at best.
>
> Locking changes which are "obviously correct" make me nervous, too :)
I tend to agree. But I think this one is simple enough to warrant doing
it, when the performance increase is as large as it is.
> But IIRC last KS the argument is that not *enough* is going into stable,
> not that stable isn't stable enough. So maybe it's a non-problem?
In principle, pushing the patch to stable definitely isn't an issue with
the stable crew. And yes, they apparently do want more stuff. If you
look at it from the distro side, having a stable(r) repository is a no
brainer. And they'd want to pick this patch anyway, so...
--
Jens Axboe
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [PATCH] block: virtio_blk: don't hold spin lock during world switch
2014-06-02 13:06 ` Ming Lei
@ 2014-06-11 14:44 ` Paolo Bonzini
0 siblings, 0 replies; 13+ messages in thread
From: Paolo Bonzini @ 2014-06-11 14:44 UTC (permalink / raw)
To: Ming Lei, Rusty Russell
Cc: Jens Axboe, virtualization, Linux Kernel Mailing List,
Michael S. Tsirkin
Il 02/06/2014 15:06, Ming Lei ha scritto:
>> >
>> > If you're running SMP under an emulator where exits are expensive, then
>> > this wins. Under KVM it's marginal at best.
> Both my tests on arm64 and x86 are under KVM, and looks the
> patch can improve performance a lot. IMO, even though under
> KVM, virtio-blk performance still depends how well hypervisor(
> qemu, ...) emulates the device, and basically speaking, it is
> expensive to switch from guest to host and let host handle the
> notification.
The difference is that virtio-pci supports ioeventfd and virtio-mmio
doesn't.
With ioeventfd you can tell KVM "I don't care about the value that is
written to a memory location, only that it is accessed". Then when the
write happens, KVM doesn't do an expensive userspace exit; it just
writes 1 to an eventfd.
It then returns to the guest, userspace picks up the eventfd via its
poll() loop and services the device.
This is already useful for throughput on UP, and the small latency cost
(because of the cost of the event loop in the I/O thread, and possibly
the cost of waking up the thread) is usually offset by the benefit.
But on SMP you get double benefit. Obviously, the kernel doesn't have
to spin while userspace does its stuff. On top of this, there is also a
latency improvement from ioeventfd, because QEMU processes
virtqueue_notify under its "big QEMU lock". With ioeventfd, serialized
virtqueue processing can be a bottleneck, but it doesn't affect latency.
Without ioeventfd it affects the VCPUs' latency and negates a lot of
the benefit of Ming Lei's patch.
You can try disabling ioeventfd with "-global
virtio-blk-pci.ioeventfd=off" on the QEMU command line. Performance
will plummet. :)
Paolo
^ permalink raw reply [flat|nested] 13+ messages in thread
end of thread, other threads:[~2014-06-11 14:44 UTC | newest]
Thread overview: 13+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-05-30 2:49 [PATCH] block: virtio_blk: don't hold spin lock during world switch Ming Lei
2014-05-30 3:19 ` Jens Axboe
2014-05-30 3:34 ` Ming Lei
2014-05-30 3:35 ` Jens Axboe
2014-05-30 5:58 ` Ming Lei
2014-05-30 6:10 ` Rusty Russell
2014-05-30 13:52 ` Jens Axboe
2014-06-02 1:23 ` Rusty Russell
2014-06-02 13:06 ` Ming Lei
2014-06-11 14:44 ` Paolo Bonzini
2014-06-02 14:15 ` Jens Axboe
2014-05-30 6:05 ` Rusty Russell
2014-05-30 15:27 ` Michael S. Tsirkin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).