From: Haiyang Zhang <haiyangz@microsoft.com>
To: Stephen Hemminger <stephen@networkplumber.org>,
Chi Song <Song.Chi@microsoft.com>
Cc: KY Srinivasan <kys@microsoft.com>,
Stephen Hemminger <sthemmin@microsoft.com>,
Wei Liu <wei.liu@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>, Andrii Nakryiko <andriin@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@chromium.org>,
"linux-hyperv@vger.kernel.org" <linux-hyperv@vger.kernel.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Subject: RE: [PATCH net-next] net: hyperv: Add attributes to show RX/TX indirection table
Date: Fri, 17 Jul 2020 16:18:11 +0000 [thread overview]
Message-ID: <DM5PR2101MB09344BA75F08EC926E31E040CA7C0@DM5PR2101MB0934.namprd21.prod.outlook.com> (raw)
In-Reply-To: <20200717082451.00c59b42@hermes.lan>
> -----Original Message-----
> From: Stephen Hemminger <stephen@networkplumber.org>
> Sent: Friday, July 17, 2020 11:25 AM
> To: Chi Song <Song.Chi@microsoft.com>
> Cc: KY Srinivasan <kys@microsoft.com>; Haiyang Zhang
> <haiyangz@microsoft.com>; Stephen Hemminger <sthemmin@microsoft.com>;
> Wei Liu <wei.liu@kernel.org>; David S. Miller <davem@davemloft.net>; Jakub
> Kicinski <kuba@kernel.org>; Alexei Starovoitov <ast@kernel.org>; Daniel
> Borkmann <daniel@iogearbox.net>; Martin KaFai Lau <kafai@fb.com>; Song
> Liu <songliubraving@fb.com>; Yonghong Song <yhs@fb.com>; Andrii Nakryiko
> <andriin@fb.com>; John Fastabend <john.fastabend@gmail.com>; KP Singh
> <kpsingh@chromium.org>; linux-hyperv@vger.kernel.org;
> netdev@vger.kernel.org
> Subject: Re: [PATCH net-next] net: hyperv: Add attributes to show RX/TX
> indirection table
>
> On Fri, 17 Jul 2020 06:04:31 +0000
> Chi Song <Song.Chi@microsoft.com> wrote:
>
> > The network is observed with low performance, if TX indirection table is
> imbalance.
> > But the table is in memory and set in runtime, it's hard to know. Add them to
> attributes can help on troubleshooting.
>
>
> The receive indirection table comes from RSS configuration.
> The RSS configuration is already visible via ethtool so adding sysfs support for
> that is redundant.
>
> The transmit indirection table comes from the host, and is unique to this driver.
> So adding a sysfs file for that makes sense.
>
> The format of sysfs files is that in general there should be one value per file.
>
> One other possibility would be to make these as attributes under each queues.
> But that is harder.
The vmbus has per channel sysfs entries, but the channels are numbered by
Rel_ID globally (not the subchannel index). Also the TX table is a many to one
mapping from table index to channel index, ie. Multiple table entries map to
one channel. So display the TX indirection table entries under each channel
will requires additional steps to figure out the actual table contents.
In sysfs, most files are short. But there are existing examples, such as " uevent"
contains multiple values, even name and value pairs.
We knew the ethtool can output the RX table. But for Azure telemetry tools,
it prefers to access the info from sysfs. Also in some minimal installation,
"ethtool" may not always be installed. It will be more reliable for Azure
telemetry tools to have the data in sysfs as well.
Thanks,
- Haiyang
next prev parent reply other threads:[~2020-07-17 16:18 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-17 6:04 [PATCH net-next] net: hyperv: Add attributes to show RX/TX indirection table Chi Song
2020-07-17 10:43 ` Wei Liu
2020-07-17 15:24 ` Stephen Hemminger
2020-07-17 16:18 ` Haiyang Zhang [this message]
2020-07-17 16:55 ` David Miller
2020-07-17 16:59 ` Haiyang Zhang
2020-07-17 17:15 ` Stephen Hemminger
2020-07-17 17:33 ` Haiyang Zhang
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=DM5PR2101MB09344BA75F08EC926E31E040CA7C0@DM5PR2101MB0934.namprd21.prod.outlook.com \
--to=haiyangz@microsoft.com \
--cc=Song.Chi@microsoft.com \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@chromium.org \
--cc=kuba@kernel.org \
--cc=kys@microsoft.com \
--cc=linux-hyperv@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=stephen@networkplumber.org \
--cc=sthemmin@microsoft.com \
--cc=wei.liu@kernel.org \
--cc=yhs@fb.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).