From: Jakub Kicinski <kuba@kernel.org>
To: Justin Iurman <justin.iurman@uliege.be>
Cc: netdev@vger.kernel.org, davem@davemloft.net, dsahern@kernel.org,
yoshfuji@linux-ipv6.org, linux-mm@kvack.org, cl@linux.com,
penberg@kernel.org, rientjes@google.com,
iamjoonsoo kim <iamjoonsoo.kim@lge.com>,
akpm@linux-foundation.org, vbabka@suse.cz,
Roopa Prabhu <roopa@nvidia.com>,
Nikolay Aleksandrov <nikolay@nvidia.com>,
Andrew Lunn <andrew@lunn.ch>,
Stephen Hemminger <sthemmin@microsoft.com>,
Vladimir Oltean <olteanv@gmail.com>,
Florian Fainelli <f.fainelli@gmail.com>,
Florian Westphal <fw@strlen.de>, Paolo Abeni <pabeni@redhat.com>
Subject: Re: [RFC net-next 2/2] ipv6: ioam: Support for Buffer occupancy data field
Date: Thu, 9 Dec 2021 16:38:28 -0800 [thread overview]
Message-ID: <20211209163828.223815bd@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> (raw)
In-Reply-To: <1067680364.223350225.1639059024535.JavaMail.zimbra@uliege.be>
On Thu, 9 Dec 2021 15:10:24 +0100 (CET) Justin Iurman wrote:
> > because Linux routers can run a full telemetry stack and all sort
> > of advanced SW instrumentation. The use case for reporting kernel
> > memory use via IOAM's constrained interface does not seem particularly
> > practical since it's not providing a very strong signal on what's
> > going on.
>
> I agree and disagree. I disagree because this value definitely tells you
> that something (potentially bad) is going on, when it increases
> significantly enough to reach a critical threshold. Basically, we need
> more skb's, but oh, the pool is exhausted. OK, not a problem, expand the
> pool. Oh wait, no memory left. Why? Is it only due to too much
> (temporary?) load? Should I put the blame on the NIC? Is it a memory
> issue? Is it something else? Or maybe several issues combined? Well, you
> might not know exactly why (though you know there is a problem), which is
> also why I agree with you. But, this is also why you have other data
> fields available (i.e., detecting a problem might require 2+ symptoms
> instead of just one).
>
> > For switches running Linux the switch ASIC buffer occupancy can be read
> > via devlink-sb that'd seem like a better fit for me, but unfortunately
> > the devlink calls can sleep so we can't read such device info from the
> > datapath.
>
> Indeed, would be a better fit. I didn't know about this one, thanks for
> that. It's a shame it can't be used in this context, though. But, at the
> end of the day, we're left with nothing regarding buffer occupancy. So
> I'm wondering if "something" is not better than "nothing" in this case.
> And, for that, we're back to my previous answer on why I agree and
> disagree with what you said about its utility.
I think we're on the same page, the main problem is I've not seen
anyone use the skbuff_head_cache occupancy as a signal in practice.
I'm adding a bunch of people to the CC list, hopefully someone has
an opinion one way or the other.
Lore link to the full thread, FWIW:
https://lore.kernel.org/all/20211206211758.19057-1-justin.iurman@uliege.be/
next prev parent reply other threads:[~2021-12-10 0:38 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-06 21:17 [RFC net-next 0/2] IOAM queue depth and buffer occupancy Justin Iurman
2021-12-06 21:17 ` [RFC net-next 1/2] ipv6: ioam: Support for Queue depth data field Justin Iurman
2021-12-06 21:17 ` [RFC net-next 2/2] ipv6: ioam: Support for Buffer occupancy " Justin Iurman
2021-12-07 0:16 ` Jakub Kicinski
2021-12-07 11:54 ` Justin Iurman
2021-12-07 15:50 ` Jakub Kicinski
2021-12-07 16:35 ` Justin Iurman
2021-12-07 17:07 ` Jakub Kicinski
2021-12-07 18:05 ` Justin Iurman
2021-12-08 22:18 ` Jakub Kicinski
2021-12-09 14:10 ` Justin Iurman
2021-12-10 0:38 ` Jakub Kicinski [this message]
2021-12-10 12:57 ` Justin Iurman
2021-12-21 17:06 ` Justin Iurman
2021-12-21 17:23 ` Vladimir Oltean
2021-12-21 20:13 ` Jakub Kicinski
2021-12-22 16:13 ` Justin Iurman
2021-12-22 15:49 ` Justin Iurman
2021-12-07 16:37 ` David Ahern
2021-12-07 16:54 ` Justin Iurman
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=20211209163828.223815bd@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com \
--to=kuba@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=andrew@lunn.ch \
--cc=cl@linux.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=f.fainelli@gmail.com \
--cc=fw@strlen.de \
--cc=iamjoonsoo.kim@lge.com \
--cc=justin.iurman@uliege.be \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=nikolay@nvidia.com \
--cc=olteanv@gmail.com \
--cc=pabeni@redhat.com \
--cc=penberg@kernel.org \
--cc=rientjes@google.com \
--cc=roopa@nvidia.com \
--cc=sthemmin@microsoft.com \
--cc=vbabka@suse.cz \
--cc=yoshfuji@linux-ipv6.org \
/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