From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: "Xia, Chenbo" <chenbo.xia@intel.com>,
"Eugenio Pérez" <eperezma@redhat.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, Pei Zhang <pezhang@redhat.com>,
Jason Wang <jasowang@redhat.com>
Subject: Re: [dpdk-dev] [PATCH] vhost: Clean iotlb cache on vring stop
Date: Thu, 23 Sep 2021 10:50:02 +0200 [thread overview]
Message-ID: <f1b95093-0144-a95b-da46-9f118506a6b5@redhat.com> (raw)
In-Reply-To: <MN2PR11MB4063CA19BF7C6C8B57814A0E9CA39@MN2PR11MB4063.namprd11.prod.outlook.com>
On 9/23/21 10:48, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -----Original Message-----
>> From: Maxime Coquelin <maxime.coquelin@redhat.com>
>> Sent: Thursday, September 23, 2021 4:34 PM
>> To: Eugenio Pérez <eperezma@redhat.com>; Xia, Chenbo <chenbo.xia@intel.com>
>> Cc: dev@dpdk.org; Pei Zhang <pezhang@redhat.com>; Jason Wang
>> <jasowang@redhat.com>
>> Subject: Re: [PATCH] vhost: Clean iotlb cache on vring stop
>>
>>
>>
>> On 8/27/21 18:12, Eugenio Pérez wrote:
>>> Old IOVA cache entries are left when there is a change on virtio driver
>>> in VM. In case that all these old entries have iova addresses lesser
>>> than new iova entries, vhost code will need to iterate all the cache to
>>> find the new ones. In case of just a new iova entry needed for the new
>>> translations, this condition will last forever.
>>>
>>> This has been observed in virtio-net to testpmd's vfio-pci driver
>>> transition, reducing the performance from more than 10Mpps to less than
>>> 0.07Mpps if the hugepage address was higher than the networking
>>> buffers. Since all new buffers are contained in this new gigantic page,
>>> vhost needs to scan IOTLB_CACHE_SIZE - 1 for each translation at worst.
>>>
>>> Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
>>> Reported-by: Pei Zhang <pezhang@redhat.com>
>>> ---
>>> lib/vhost/vhost_user.c | 2 ++
>>> 1 file changed, 2 insertions(+)
>>>
>>> diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
>>> index 29a4c9af60..7de48f5333 100644
>>> --- a/lib/vhost/vhost_user.c
>>> +++ b/lib/vhost/vhost_user.c
>>> @@ -2113,6 +2113,8 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
>>> msg->size = sizeof(msg->payload.state);
>>> msg->fd_num = 0;
>>>
>>> + vhost_user_iotlb_flush_all(vq);
>>> +
>>> vring_invalidate(dev, vq);
>>>
>>> return RTE_VHOST_MSG_RESULT_REPLY;
>>>
>>
>> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>
> So you will fix title and add fix tag when applying, right?
Yes, I will. Thanks for the heads-up!
Maxime
> /Chenbo
>
>>
>> Thanks,
>> Maxime
>
next prev parent reply other threads:[~2021-09-23 8:50 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-27 16:12 Eugenio Pérez
2021-08-30 11:57 ` Xia, Chenbo
2021-08-30 18:10 ` Eugenio Perez Martin
2021-08-31 2:02 ` Xia, Chenbo
2021-08-31 7:10 ` Eugenio Perez Martin
2021-09-23 8:34 ` Maxime Coquelin
2021-09-23 8:48 ` Xia, Chenbo
2021-09-23 8:50 ` Maxime Coquelin [this message]
2021-09-23 8:54 ` Xia, Chenbo
2021-09-28 15:29 ` Maxime Coquelin
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=f1b95093-0144-a95b-da46-9f118506a6b5@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=chenbo.xia@intel.com \
--cc=dev@dpdk.org \
--cc=eperezma@redhat.com \
--cc=jasowang@redhat.com \
--cc=pezhang@redhat.com \
/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).