From: "Morten Brørup" <mb@smartsharesystems.com>
To: "Georg Sauthoff" <mail@gms.tf>
Cc: <dev@dpdk.org>, "Ferruh Yigit" <ferruh.yigit@intel.com>,
"Olivier Matz" <olivier.matz@6wind.com>,
"Thomas Monjalon" <thomas@monjalon.net>,
"David Marchand" <david.marchand@redhat.com>
Subject: Re: [dpdk-dev] [PATCH 1/1] net: fix aliasing issue in checksum computation
Date: Sat, 16 Oct 2021 10:21:03 +0200 [thread overview]
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35D86C44@smartserver.smartshare.dk> (raw)
In-Reply-To: <14e68fb1-0c73-8a6f-0032-7adf186ceb0c@intel.com>
Geoff,
I have given this some more thoughts.
Most bytes transferred in real life are transferred in large packets, so faster processing of large packets is a great improvement!
Furthermore, a quick analysis of a recent packet sample from an ISP customer of ours shows that less than 8 % of the packets are odd size. Would you consider adding an unlikely() to the branch handling the odd byte at the end?
-Morten
> -----Original Message-----
> From: Morten Brørup
> Sent: Thursday, 14 October 2021 22.22
>
> > -----Original Message-----
> > From: Ferruh Yigit [mailto:ferruh.yigit@intel.com]
> > Sent: Thursday, 14 October 2021 19.20
> >
> > On 9/18/2021 12:49 PM, Georg Sauthoff wrote:
> > > That means a superfluous cast is removed and aliasing through a
> > uint8_t
> > > pointer is eliminated. Note that uint8_t doesn't have the same
> > > strict-aliasing properties as unsigned char.
> > >
> > > Also simplified the loop since a modern C compiler can speed up
> (i.e.
> > > auto-vectorize) it in a similar way. For example, GCC auto-
> vectorizes
> > it
> > > for Haswell using AVX registers while halving the number of
> > instructions
> > > in the generated code.
> > >
> > > Signed-off-by: Georg Sauthoff <mail@gms.tf>
> >
> > + Morten. (Because of past reviews on cksum code)
>
> Thanks, Ferruh.
>
> I have not verified the claimed benefits of the patch, but I have
> reviewed the code thoroughly, and it looks perfectly good to me.
>
> Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
>
> BTW: It makes me wonder if other parts of DPDK could benefit from the
> same treatment. Especially some of the older DPDK code, where we were
> trying to optimize by hand what a modern compiler can optimize for us
> today.
>
> >
> > > ---
> > > lib/net/rte_ip.h | 27 ++++++++-------------------
> > > 1 file changed, 8 insertions(+), 19 deletions(-)
> > >
> > > diff --git a/lib/net/rte_ip.h b/lib/net/rte_ip.h
> > > index 05948b69b7..386db94c85 100644
> > > --- a/lib/net/rte_ip.h
> > > +++ b/lib/net/rte_ip.h
> > > @@ -141,29 +141,18 @@ rte_ipv4_hdr_len(const struct rte_ipv4_hdr
> > *ipv4_hdr)
> > > static inline uint32_t
> > > __rte_raw_cksum(const void *buf, size_t len, uint32_t sum)
> > > {
> > > - /* workaround gcc strict-aliasing warning */
> > > - uintptr_t ptr = (uintptr_t)buf;
> > > + /* extend strict-aliasing rules */
> > > typedef uint16_t __attribute__((__may_alias__)) u16_p;
> > > - const u16_p *u16_buf = (const u16_p *)ptr;
> > > -
> > > - while (len >= (sizeof(*u16_buf) * 4)) {
> > > - sum += u16_buf[0];
> > > - sum += u16_buf[1];
> > > - sum += u16_buf[2];
> > > - sum += u16_buf[3];
> > > - len -= sizeof(*u16_buf) * 4;
> > > - u16_buf += 4;
> > > - }
> > > - while (len >= sizeof(*u16_buf)) {
> > > + const u16_p *u16_buf = (const u16_p *)buf;
> > > + const u16_p *end = u16_buf + len / sizeof(*u16_buf);
> > > +
> > > + for (; u16_buf != end; ++u16_buf)
>
> Personally I would prefer post-incrementing here. It makes no
> difference, so I don't see any need to revise the patch.
>
> > > sum += *u16_buf;
> > > - len -= sizeof(*u16_buf);
> > > - u16_buf += 1;
> > > - }
> > >
> > > - /* if length is in odd bytes */
> > > - if (len == 1) {
> > > + /* if length is odd, keeping it byte order independent */
> > > + if (len % 2) {
I assume that the compiler already optimizes "% 2" to "& 1".
> > > uint16_t left = 0;
> > > - *(uint8_t *)&left = *(const uint8_t *)u16_buf;
> > > + *(unsigned char*)&left = *(const unsigned char *)end;
> > > sum += left;
> > > }
> > >
next prev parent reply other threads:[~2021-10-16 8:21 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-18 11:49 [dpdk-dev] [PATCH 0/1] " Georg Sauthoff
2021-09-18 11:49 ` [dpdk-dev] [PATCH 1/1] " Georg Sauthoff
2021-10-14 17:20 ` Ferruh Yigit
2021-10-14 20:22 ` Morten Brørup
2021-10-16 8:21 ` Morten Brørup [this message]
2021-10-16 17:17 ` Georg Sauthoff
2021-10-16 8:24 ` Morten Brørup
2021-10-15 14:39 ` Olivier Matz
2021-10-16 17:02 ` Georg Sauthoff
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=98CBD80474FA8B44BF855DF32C47DC35D86C44@smartserver.smartshare.dk \
--to=mb@smartsharesystems.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=mail@gms.tf \
--cc=olivier.matz@6wind.com \
--cc=thomas@monjalon.net \
/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).