From: Oliver Neukum <oneukum@suse.com>
To: David Miller <davem@davemloft.net>, bjorn@mork.no
Cc: jim_baxter@mentor.com, linux-kernel@vger.kernel.org,
linux-usb@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [RFC V1 1/1] net: cdc_ncm: Reduce memory use when kernel memory low
Date: Thu, 18 May 2017 12:01:52 +0200 [thread overview]
Message-ID: <1495101712.6672.4.camel@suse.com> (raw)
In-Reply-To: <20170517.141819.1307166900606639947.davem@davemloft.net>
Am Mittwoch, den 17.05.2017, 14:18 -0400 schrieb David Miller:
> From: Bjørn Mork <bjorn@mork.no>
> Date: Tue, 16 May 2017 20:24:10 +0200
>
> > Jim Baxter <jim_baxter@mentor.com> writes:
> >
> >> The CDC-NCM driver can require large amounts of memory to create
> >> skb's and this can be a problem when the memory becomes fragmented.
> >>
> >> This especially affects embedded systems that have constrained
> >> resources but wish to maximise the throughput of CDC-NCM with 16KiB
> >> NTB's.
> >>
> >> The issue is after running for a while the kernel memory can become
> >> fragmented and it needs compacting.
> >> If the NTB allocation is needed before the memory has been compacted
> >> the atomic allocation can fail which can cause increased latency,
> >> large re-transmissions or disconnections depending upon the data
> >> being transmitted at the time.
> >> This situation occurs for less than a second until the kernel has
> >> compacted the memory but the failed devices can take a lot longer to
> >> recover from the failed TX packets.
> >>
> >> To ease this temporary situation I modified the CDC-NCM TX path to
> >> temporarily switch into a reduced memory mode which allocates an NTB
> >> that will fit into a USB_CDC_NCM_NTB_MIN_OUT_SIZE (default 2048 Bytes)
> >> sized memory block and only transmit NTB's with a single network frame
> >> until the memory situation is resolved.
> >> Once the memory is compacted the CDC-NCM data can resume transmitting
> >> at the normal tx_max rate once again.
> >
> > I must say that I don't like the additional complexity added here. If
> > there are memory issues and you can reduce the buffer size to
> > USB_CDC_NCM_NTB_MIN_OUT_SIZE, then why don't you just set a lower tx_max
> > buffer size in the first place?
> >
> > echo 2048 > /sys/class/net/wwan0/cdc_ncm/tx_max
>
> When there isn't memory pressure this will hurt performance of
> course.
>
> It is a quite common paradigm to back down to 0 order memory requests
> when higher order ones fail, so this isn't such a bad change from the
> perspective.
>
> However, one negative about it is that when the system is under memory
> stress it doesn't help at all to keep attemping high order allocations
> when the system hasn't recovered yet. In fact, this can make it
> worse.
This makes me wonder why there is no notifier chain for this.
Or am I just too stupid to find it?
Regards
Oliver
next prev parent reply other threads:[~2017-05-18 10:03 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-16 17:41 [RFC V1 0/1] Reduce cdc_ncm memory use when kernel memory low Jim Baxter
2017-05-16 17:41 ` [RFC V1 1/1] net: cdc_ncm: Reduce " Jim Baxter
2017-05-16 18:24 ` Bjørn Mork
2017-05-17 7:44 ` Oliver Neukum
2017-05-17 10:56 ` Baxter, Jim
2017-05-17 18:18 ` David Miller
2017-05-18 10:01 ` Oliver Neukum [this message]
2017-05-22 15:45 ` Baxter, Jim
2017-05-22 15:54 ` David Miller
2017-05-23 8:42 ` Oliver Neukum
2017-05-23 15:26 ` David Miller
2017-05-23 19:06 ` Baxter, Jim
[not found] ` <1497263047.15677.13.camel@suse.com>
2017-06-12 12:32 ` Baxter, Jim
2017-05-19 11:10 ` David Laight
2017-05-19 13:55 ` Bjørn Mork
2017-05-19 14:46 ` David Laight
2017-05-22 13:27 ` Oliver Neukum
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=1495101712.6672.4.camel@suse.com \
--to=oneukum@suse.com \
--cc=bjorn@mork.no \
--cc=davem@davemloft.net \
--cc=jim_baxter@mentor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-usb@vger.kernel.org \
--cc=netdev@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).