From: David Miller <davem@davemloft.net>
To: edumazet@google.com
Cc: netdev@vger.kernel.org, michael.chan@broadcom.com,
aviad.krawczyk@huawei.com, songliubraving@fb.com,
dougmill@linux.vnet.ibm.com, yisen.zhuang@huawei.com,
mst@redhat.com, jasowang@redhat.com, harish.patil@cavium.com,
manish.chopra@cavium.com, netanel@amazon.com,
linux-net-drivers@solarflare.com, tlfalcon@linux.vnet.ibm.com
Subject: Re: [PATCH net 00/11] netpoll: second round of fixes.
Date: Fri, 28 Sep 2018 11:14:18 -0700 (PDT) [thread overview]
Message-ID: <20180928.111418.1921695439745155316.davem@davemloft.net> (raw)
In-Reply-To: <20180927163201.56609-1-edumazet@google.com>
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Sep 2018 09:31:50 -0700
> As diagnosed by Song Liu, ndo_poll_controller() can
> be very dangerous on loaded hosts, since the cpu
> calling ndo_poll_controller() might steal all NAPI
> contexts (for all RX/TX queues of the NIC).
>
> This capture, showing one ksoftirqd eating all cycles
> can last for unlimited amount of time, since one
> cpu is generally not able to drain all the queues under load.
>
> It seems that all networking drivers that do use NAPI
> for their TX completions, should not provide a ndo_poll_controller() :
>
> Most NAPI drivers have netpoll support already handled
> in core networking stack, since netpoll_poll_dev()
> uses poll_napi(dev) to iterate through registered
> NAPI contexts for a device.
>
> First patch is a fix in poll_one_napi().
>
> Then following patches take care of ten drivers.
Series applied, thanks Eric.
prev parent reply other threads:[~2018-09-29 0:39 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-27 16:31 [PATCH net 00/11] netpoll: second round of fixes Eric Dumazet
2018-09-27 16:31 ` [PATCH net 01/11] netpoll: do not test NAPI_STATE_SCHED in poll_one_napi() Eric Dumazet
2018-09-27 18:25 ` Michael Chan
2018-09-27 18:33 ` Song Liu
2018-09-27 16:31 ` [PATCH net 02/11] hinic: remove ndo_poll_controller Eric Dumazet
2018-09-27 16:31 ` [PATCH net 03/11] ehea: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 04/11] net: hns: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 05/11] virtio_net: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 06/11] qlcnic: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 07/11] qlogic: netxen: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 08/11] net: ena: " Eric Dumazet
2018-09-27 16:31 ` [PATCH net 09/11] sfc: " Eric Dumazet
2018-09-28 7:30 ` Bert Kenward
2018-09-27 16:32 ` [PATCH net 10/11] sfc-falcon: " Eric Dumazet
2018-09-28 7:30 ` Bert Kenward
2018-09-27 16:32 ` [PATCH net 11/11] ibmvnic: " Eric Dumazet
2018-09-28 18:14 ` David Miller [this message]
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=20180928.111418.1921695439745155316.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=aviad.krawczyk@huawei.com \
--cc=dougmill@linux.vnet.ibm.com \
--cc=edumazet@google.com \
--cc=harish.patil@cavium.com \
--cc=jasowang@redhat.com \
--cc=linux-net-drivers@solarflare.com \
--cc=manish.chopra@cavium.com \
--cc=michael.chan@broadcom.com \
--cc=mst@redhat.com \
--cc=netanel@amazon.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=tlfalcon@linux.vnet.ibm.com \
--cc=yisen.zhuang@huawei.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