From: "Sanford, Robert" <rsanford@akamai.com>
To: Bruce Richardson <bruce.richardson@intel.com>,
Stephen Hemminger <stephen@networkplumber.org>,
"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] IXGBE RX packet loss with 5+ cores
Date: Tue, 13 Oct 2015 14:47:36 +0000 [thread overview]
Message-ID: <D2428901.CE78%rsanford@akamai.com> (raw)
In-Reply-To: <20151013135955.GA31844@bricha3-MOBL3>
>>> [Robert:]
>>> 1. The 82599 device supports up to 128 queues. Why do we see trouble
>>> with as few as 5 queues? What could limit the system (and one port
>>> controlled by 5+ cores) from receiving at line-rate without loss?
>>>
>>> 2. As far as we can tell, the RX path only touches the device
>>> registers when it updates a Receive Descriptor Tail register (RDT[n]),
>>> roughly every rx_free_thresh packets. Is there a big difference
>>> between one core doing this and N cores doing it 1/N as often?
>>[Stephen:]
>>As you add cores, there is more traffic on the PCI bus from each core
>>polling. There is a fix number of PCI bus transactions per second
>>possible.
>>Each core is increasing the number of useless (empty) transactions.
>[Bruce:]
>The polling for packets by the core should not be using PCI bandwidth
>directly,
>as the ixgbe driver (and other drivers) check for the DD bit being set on
>the
>descriptor in memory/cache.
I was preparing to reply with the same point.
>>[Stephen:] Why do you think adding more cores will help?
We're using run-to-completion and sometimes spend too many cycles per pkt.
We realize that we need to move to io+workers model, but wanted a better
understanding of the dynamics involved here.
>[Bruce:] However, using an increased number of queues can
>use PCI bandwidth in other ways, for instance, with more queues you
>reduce the
>amount of descriptor coalescing that can be done by the NICs, so that
>instead of
>having a single transaction of 4 descriptors to one queue, the NIC may
>instead
>have to do 4 transactions each writing 1 descriptor to 4 different
>queues. This
>is possibly why sending all traffic to a single queue works ok - the
>polling on
>the other queues is still being done, but has little effect.
Brilliant! This idea did not occur to me.
--
Thanks guys,
Robert
next prev parent reply other threads:[~2015-10-13 14:47 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-13 2:57 Sanford, Robert
2015-10-13 5:18 ` Stephen Hemminger
2015-10-13 13:59 ` Bruce Richardson
2015-10-13 14:47 ` Sanford, Robert [this message]
2015-10-13 15:34 ` Venkatesan, Venky
2018-11-01 6:42 ` Saber Rezvani
2015-10-13 20:24 ` Alexander Duyck
2015-10-14 9:29 ` Bruce Richardson
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=D2428901.CE78%rsanford@akamai.com \
--to=rsanford@akamai.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=stephen@networkplumber.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).