Commit Graph

11 Commits

Author SHA1 Message Date
Matt Macy
d7c5a620e2 ifnet: Replace if_addr_lock rwlock with epoch + mutex
Run on LLNW canaries and tested by pho@

gallatin:
Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5
based ConnectX 4-LX NIC, I see an almost 12% improvement in received
packet rate, and a larger improvement in bytes delivered all the way
to userspace.

When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1,
I see, using nstat -I mce0 1 before the patch:

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
4.98   0.00   4.42   0.00 4235592     33   83.80 4720653 2149771   1235 247.32
4.73   0.00   4.20   0.00 4025260     33   82.99 4724900 2139833   1204 247.32
4.72   0.00   4.20   0.00 4035252     33   82.14 4719162 2132023   1264 247.32
4.71   0.00   4.21   0.00 4073206     33   83.68 4744973 2123317   1347 247.32
4.72   0.00   4.21   0.00 4061118     33   80.82 4713615 2188091   1490 247.32
4.72   0.00   4.21   0.00 4051675     33   85.29 4727399 2109011   1205 247.32
4.73   0.00   4.21   0.00 4039056     33   84.65 4724735 2102603   1053 247.32

After the patch

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
5.43   0.00   4.20   0.00 3313143     33   84.96 5434214 1900162   2656 245.51
5.43   0.00   4.20   0.00 3308527     33   85.24 5439695 1809382   2521 245.51
5.42   0.00   4.19   0.00 3316778     33   87.54 5416028 1805835   2256 245.51
5.42   0.00   4.19   0.00 3317673     33   90.44 5426044 1763056   2332 245.51
5.42   0.00   4.19   0.00 3314839     33   88.11 5435732 1792218   2499 245.52
5.44   0.00   4.19   0.00 3293228     33   91.84 5426301 1668597   2121 245.52

Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch

Reviewed by:	gallatin
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15366
2018-05-18 20:13:34 +00:00
Ed Maste
3e85b721d6 Remove register keyword from sys/ and ANSIfy prototypes
A long long time ago the register keyword told the compiler to store
the corresponding variable in a CPU register, but it is not relevant
for any compiler used in the FreeBSD world today.

ANSIfy related prototypes while here.

Reviewed by:	cem, jhb
Sponsored by:	The FreeBSD Foundation
Differential Revision:	https://reviews.freebsd.org/D10193
2017-05-17 00:34:34 +00:00
Kevin Lo
938e9a89c4 Add support for the TP-Link TG-3468 v2.
This is an RTL8168 chip, which we already support so all we have to do is add
the vendor ID.

PR:	212876
Submitted by:	Tobias Kortkamp <t@tobik.me>
MFC after:	3 days
2016-09-21 14:15:15 +00:00
Pedro F. Giffuni
453130d9bf sys/dev: minor spelling fixes.
Most affect comments, very few have user-visible effects.
2016-05-03 03:41:25 +00:00
Pedro F. Giffuni
73a1170a8c sys/dev: use our nitems() macro when it is avaliable through param.h.
No functional change, only trivial cases are done in this sweep,
Drivers that can get further enhancements will be done independently.

Discussed in:	freebsd-current
2016-04-19 23:37:24 +00:00
Pyun YongHyeon
4a1ff07b39 Fix a bug introduced in r295736
TX descriptor address should be updated for valid chain.

Pointed out by:	jmallett
2016-02-18 03:05:08 +00:00
Pyun YongHyeon
90cf5d3043 Remove duplicated check.
Found by:	PVS-Studio
2016-02-18 01:30:49 +00:00
Marius Strobl
14013280b2 - Although it doesn't make a whole lot of sense to enable RX and TX
before their initial configuration is done, it turns out that r281337
  has the inverse effect on some older chips. Moreover, as with newer
  chips before, two chips seemingly identical according to their MAC
  revisions may behave differently in this regard, with most working
  but a few not, making changes extremely hard to test.
  Closer inspection of the corresponding Linux code suggests that RX
  and TX should only be enabled after their initial configuration with
  RTL8168G and later chips, i. e. RTL8106E{,US}, RTL8107E, as well as
  RTL8168{EP,G,GU,H}, so limit the new code path to these. [1]
- Distinguish between RTL8168H and RTL8107E, with the latter being the
  10/100-Mbit/s-only variant of the former.
- For MAC variants that can only do Fast Ethernet at a maximum, ensure
  that we don't advertise Gigabit Ethernet speed.
- In re_stop(), do the inverse of re_init_locked() and enable RXDV
  gate on RTL8168G and later chips again, matching what Linux does.

PR:		203422 [1]
MFC after:	1 week
2015-11-09 00:19:04 +00:00
Marius Strobl
96b2c26ae1 Add preliminary support for RTL8168H, tested by Sreenath Battalahalli.
MFC after:	1 week
2015-09-13 22:22:30 +00:00
Gleb Smirnoff
e3393daf63 Mechanically convert to if_inc_counter(). 2014-09-19 10:33:23 +00:00
Gleb Smirnoff
b2d3d26fa0 Move rl(4) to dev/rl. 2014-09-19 10:32:20 +00:00