From: Klaus Jensen <its@irrelevant.dk>
To: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Cc: qemu-devel@nongnu.org, kbusch@kernel.org
Subject: Re: [RFC] hw/nvme: Use irqfd to send interrupts
Date: Tue, 12 Jul 2022 14:26:11 +0200 [thread overview]
Message-ID: <Ys1oY9LmeDCGT9FT@apples> (raw)
In-Reply-To: <20220709043503.2228736-1-fanjinhao21s@ict.ac.cn>
[-- Attachment #1: Type: text/plain, Size: 1136 bytes --]
On Jul 9 12:35, Jinhao Fan wrote:
> Use irqfd to directly notify KVM to inject interrupts. This is done by
> registering a virtual IRQ(virq) in KVM and associate the virq with an
> irqfd, so that KVM can directly inject the interrupt when it receives
> notification from the irqfd. This approach is supposed to improve
> performance because it bypasses QEMU's MSI interrupt emulation logic.
>
> However, I did not see an obvious improvement of the emulation KIOPS:
>
> QD 1 4 16 64
> QEMU 38 123 210 329
> irqfd 40 129 219 328
>
> I found this problem quite hard to diagnose since irqfd's workflow
> involves both QEMU and the in-kernel KVM.
>
> Could you help me figure out the following questions:
>
> 1. How much performance improvement can I expect from using irqfd?
This is a level of QEMU/KVM that I am by no means an expert on and I
would have to let the broader QEMU community comment on this.
> 2. How can I debug this kind of cross QEMU-KVM problems?
Not sure how to directly "debug" it, but there is `perf kvm` to get
information about what is happing in the kvm subsystem.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
next prev parent reply other threads:[~2022-07-12 12:30 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-09 4:35 [RFC] hw/nvme: Use irqfd to send interrupts Jinhao Fan
2022-07-12 12:26 ` Klaus Jensen [this message]
2022-07-14 4:18 ` Klaus Jensen
2022-07-14 14:31 ` Jinhao Fan
2022-07-20 9:19 ` Jinhao Fan
2022-07-20 10:21 ` Stefan Hajnoczi
2022-07-21 2:36 ` Jinhao Fan
2022-07-21 13:29 ` Stefan Hajnoczi
2022-07-24 15:20 ` Jinhao Fan
2022-07-24 19:36 ` Stefan Hajnoczi
2022-07-25 2:48 ` Jinhao Fan
2022-07-27 7:18 ` Klaus Jensen
2022-07-27 15:18 ` Stefan Hajnoczi
2022-07-28 15:34 ` Jinhao Fan
2022-07-28 15:38 ` Stefan Hajnoczi
2022-08-02 4:03 ` Jinhao Fan
2022-08-02 5:29 ` Klaus Jensen
2022-08-08 2:23 ` Jinhao Fan
2022-08-09 15:31 ` 樊金昊
2022-08-09 16:21 ` Keith Busch
2022-08-09 16:40 ` 樊金昊
2022-08-09 16:48 ` 樊金昊
2022-08-09 17:01 ` Keith Busch
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Ys1oY9LmeDCGT9FT@apples \
--to=its@irrelevant.dk \
--cc=fanjinhao21s@ict.ac.cn \
--cc=kbusch@kernel.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).