[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240816085241.326978a6@kernel.org>
Date: Fri, 16 Aug 2024 08:52:41 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Haiyang Zhang <haiyangz@...rosoft.com>
Cc: Erni Sri Satya Vennela <ernis@...ux.microsoft.com>, Erni Sri Satya
Vennela <ernis@...rosoft.com>, KY Srinivasan <kys@...rosoft.com>,
"wei.liu@...nel.org" <wei.liu@...nel.org>, Dexuan Cui
<decui@...rosoft.com>, "davem@...emloft.net" <davem@...emloft.net>,
"edumazet@...gle.com" <edumazet@...gle.com>, "pabeni@...hat.com"
<pabeni@...hat.com>, "linux-hyperv@...r.kernel.org"
<linux-hyperv@...r.kernel.org>, "netdev@...r.kernel.org"
<netdev@...r.kernel.org>, "linux-kernel@...r.kernel.org"
<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2] net: netvsc: Update default VMBus channels
On Thu, 15 Aug 2024 19:23:50 +0000 Haiyang Zhang wrote:
> Your suggestion on netif_get_num_default_rss_queues() is not ignored.
> We discussed internally on the formula we used for the num_chn, and
> chose a similar formula for higher number of vCPUs as in
> netif_get_num_default_rss_queues().
> For lower number of vCPUs, we use the same default as Windows guests,
> because we don't want any potential regression.
Ideally you'd just use netif_get_num_default_rss_queues()
but the code is close enough to that, and I don't have enough
experience with the question of online CPUs vs physical CPUs.
I would definitely advise you to try this on real workloads.
While "iperf" looks great with a lot of rings, real workloads
suffer measurably from having more channels eating up memory
and generating interrupts.
But if you're confident with the online_cpus() / 2, that's fine.
You may be better off coding it up using max:
dev_info->num_chn = max(DIV_ROUND_UP(num_online_cpus(), 2),
VRSS_CHANNEL_DEFAULT);
Powered by blists - more mailing lists