On Oct 20 13:35, Klaus Jensen wrote:
> From: Klaus Jensen
>
> Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
> updates") had the unintended effect of disabling batching of CQEs.
>
> This patch changes the sq/cq timers to bottom halfs and instead of
> calling nvme_post_cqes() imm
at 1:37 PM, Klaus Jensen wrote:
> On Okt 21 10:37, Jinhao Fan wrote:
>> at 7:35 PM, Klaus Jensen wrote:
>>
>>> Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
>>> updates") had the unintended effect of disabling batching of CQEs.
>>>
>>> This patch changes the sq/cq timers to b
On Okt 21 10:37, Jinhao Fan wrote:
> at 7:35 PM, Klaus Jensen wrote:
>
> > Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
> > updates") had the unintended effect of disabling batching of CQEs.
> >
> > This patch changes the sq/cq timers to bottom halfs and instead of
> > calling
at 7:35 PM, Klaus Jensen wrote:
> Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
> updates") had the unintended effect of disabling batching of CQEs.
>
> This patch changes the sq/cq timers to bottom halfs and instead of
> calling nvme_post_cqes() immediately (causing an interru
On Thu, Oct 20, 2022 at 01:35:38PM +0200, Klaus Jensen wrote:
> From: Klaus Jensen
>
> Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
> updates") had the unintended effect of disabling batching of CQEs.
>
> This patch changes the sq/cq timers to bottom halfs and instead of
> cal
From: Klaus Jensen
Commit 2e53b0b45024 ("hw/nvme: Use ioeventfd to handle doorbell
updates") had the unintended effect of disabling batching of CQEs.
This patch changes the sq/cq timers to bottom halfs and instead of
calling nvme_post_cqes() immediately (causing an interrupt per cqe), we
defer t