From: Thomas Monjalon <thomas.monjalon@6wind.com>
To: Avi Kivity <avi@cloudius-systems.com>,
Vladislav Zolotarov <vladz@cloudius-systems.com>,
"didier.pallard" <didier.pallard@6wind.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v1] ixgbe_pmd: forbid tx_rs_thresh above 1 for all NICs but 82598
Date: Fri, 11 Sep 2015 18:08:17 +0200 [thread overview]
Message-ID: <3734976.j9Azrvq6io@xps13> (raw)
In-Reply-To: <55F2F6A9.6080405@cloudius-systems.com>
2015-09-11 18:43, Avi Kivity:
> On 09/11/2015 06:12 PM, Vladislav Zolotarov wrote:
> > On Sep 11, 2015 5:55 PM, "Thomas Monjalon" <thomas.monjalon@6wind.com
> > <mailto:thomas.monjalon@6wind.com>> wrote:
> > > 2015-09-11 17:47, Avi Kivity:
> > > > On 09/11/2015 05:25 PM, didier.pallard wrote:
> > > > > Hi vlad,
> > > > >
> > > > > Documentation states that a packet (or multiple packets in transmit
> > > > > segmentation) can span any number of
> > > > > buffers (and their descriptors) up to a limit of 40 minus WTHRESH
> > > > > minus 2.
> > > > >
> > > > > Shouldn't there be a test in transmit function that drops
> > properly the
> > > > > mbufs with a too large number of
> > > > > segments, while incrementing a statistic; otherwise transmit
> > function
> > > > > may be locked by the faulty packet without
> > > > > notification.
> > > > >
> > > >
> > > > What we proposed is that the pmd expose to dpdk, and dpdk expose
> > to the
> > > > application, an mbuf check function. This way applications that can
> > > > generate complex packets can verify that the device will be able to
> > > > process them, and applications that only generate simple mbufs can
> > avoid
> > > > the overhead by not calling the function.
> > >
> > > More than a check, it should be exposed as a capability of the port.
> > > Anyway, if the application sends too much segments, the driver must
> > > drop it to avoid hang, and maintain a dedicated statistic counter to
> > > allow easy debugging.
> >
> > I agree with Thomas - this should not be optional. Malformed packets
> > should be dropped. In the icgbe case it's a very simple test - it's a
> > single branch per packet so i doubt that it could impose any
> > measurable performance degradation.
>
> A drop allows the application no chance to recover. The driver must
> either provide the ability for the application to know that it cannot
> accept the packet, or it must fix it up itself.
I have the feeling that everybody agrees on the same thing:
the application must be able to make a well formed packet by checking
limitations of the port. What about a field rte_eth_dev_info.max_tx_segs?
In case the application fails in its checks, the driver must drop it and
notify the user via a stat counter.
The driver can also remove the hardware limitation by gathering the segments
but it may be hard to implement and would be a slow operation.
next prev parent reply other threads:[~2015-09-11 16:09 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-13 18:06 Vlad Zolotarov
2015-08-13 20:28 ` Zhang, Helin
2015-08-14 5:37 ` Vlad Zolotarov
2015-08-19 0:42 ` Lu, Wenzhuo
2015-08-19 4:55 ` Vladislav Zolotarov
2015-08-19 7:43 ` Ananyev, Konstantin
2015-08-19 10:02 ` Vlad Zolotarov
2015-08-20 8:41 ` Ananyev, Konstantin
2015-08-20 8:56 ` Vlad Zolotarov
2015-08-20 9:05 ` Vlad Zolotarov
2015-08-20 9:06 ` Vlad Zolotarov
2015-08-25 17:33 ` Ananyev, Konstantin
2015-08-25 17:39 ` Avi Kivity
2015-08-19 17:29 ` Zhang, Helin
2015-08-25 18:13 ` Zhang, Helin
2015-08-25 18:33 ` Vladislav Zolotarov
2015-08-25 18:43 ` Zhang, Helin
2015-08-25 18:52 ` Vlad Zolotarov
2015-08-25 19:16 ` Zhang, Helin
2015-08-25 19:23 ` Avi Kivity
2015-08-25 19:30 ` Vladislav Zolotarov
2015-08-25 20:07 ` Vlad Zolotarov
2015-08-25 20:13 ` Zhang, Helin
2015-09-09 12:18 ` Thomas Monjalon
2015-09-09 13:19 ` Ananyev, Konstantin
2015-09-11 15:17 ` Vladislav Zolotarov
2015-09-11 14:25 ` didier.pallard
2015-09-11 14:47 ` Avi Kivity
2015-09-11 14:55 ` Thomas Monjalon
2015-09-11 15:12 ` Vladislav Zolotarov
2015-09-11 15:43 ` Avi Kivity
2015-09-11 16:04 ` Vladislav Zolotarov
2015-09-11 16:07 ` Richardson, Bruce
2015-09-11 16:14 ` Vladislav Zolotarov
2015-09-11 17:44 ` Avi Kivity
2015-09-11 16:08 ` Thomas Monjalon [this message]
2015-09-11 16:18 ` Vladislav Zolotarov
2015-09-11 17:17 ` Matthew Hall
2015-09-11 17:42 ` Ananyev, Konstantin
2015-09-11 17:58 ` Matthew Hall
2015-09-11 17:48 ` Avi Kivity
2015-09-13 11:47 ` Ananyev, Konstantin
2015-09-13 12:24 ` Vlad Zolotarov
2015-09-13 12:32 ` Avi Kivity
2015-09-13 15:54 ` Ananyev, Konstantin
2015-09-13 16:01 ` Avi Kivity
2015-09-11 16:00 ` Richardson, Bruce
2015-09-11 16:13 ` Vladislav Zolotarov
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=3734976.j9Azrvq6io@xps13 \
--to=thomas.monjalon@6wind.com \
--cc=avi@cloudius-systems.com \
--cc=dev@dpdk.org \
--cc=didier.pallard@6wind.com \
--cc=vladz@cloudius-systems.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).