- User Since
- Feb 5 2016, 2:19 PM (123 w, 6 d)
Thu, Jun 14
On a 2 sockets, 12 Core Xeon E5 2650 with a Mellanox ConnectX-4:
Wed, Jun 6
Mon, Jun 4
Sat, Jun 2
Tue, May 29
Sat, May 26
Fri, May 25
May 2 2018
May 1 2018
Apr 29 2018
Apr 18 2018
Same improvement on 8-cores ATOM with ixgbe drivers:
Apr 17 2018
Lot's better on 4core AMD, but need to reset my non-IPMI Netgate tomorrow on the lab:
Panic on PC engines APU2 (AMD GX-412TC):
Apr 15 2018
Apr 13 2018
Mar 28 2018
Mar 27 2018
Mar 25 2018
Mar 19 2018
Mar 13 2018
Feb 26 2018
Then, here is my bench results regarding forwarding performance impact with this patch: I'm using a simple 802.1q setup (no LAGG).
Configuration on the Device Under Test (DUT):
Feb 20 2018
Feb 17 2018
Feb 13 2018
Feb 9 2018
OK: This patch improves ixgbe performance with 8core Xeon, but on a 4core Atom with igb, I've got a big degradation (almost half performance):
Feb 7 2018
Feb 2 2018
Any news about pushing this change to head ?
Jan 28 2018
ConcurrencyKit was MFC : https://svnweb.freebsd.org/base?view=revision&revision=328515
Jan 15 2018
Jan 10 2018
And what about updating all ports depending of your renamed ports ? like devel/pear-PHP_CodeCoverage
Dec 19 2017
Yes it's work now, and here are the result: This patch greatly improve D11727 performance!
Dec 7 2017
Nov 30 2017
Same problem on fresh r326378 "panic: Lock (rw) ifnet_rw not locked ".
I can fix this problem by adding kern.smp.disabled="1" into the boot/loader.
Nov 29 2017
Still the same problem: I've svnuped to r326359 and I've still have this panic (only when this patch is applied):
Nov 28 2017
Nov 27 2017
Nov 23 2017
Would it be possible to get the output of the ddb "ps", "show all locks", and "show witness" commands? This is just weird.
Nov 22 2017
I've got a new panic (head with WITNESS and INVARIANTS enabled):
Nov 21 2017
Nov 20 2017
Nov 19 2017
Good catch for the no_dad!
Add no_dad to inet6 setup for avoiding a sleep
Nov 17 2017
How to dump a panic when the kernel crash during boot before loading disk controller drivers ?
Can I compile a kernel with .debug embedded into the kernel ?
New tests output following r325872 that fixed cbc key lenght:
Updating test scripts following kristof's advices
Nov 15 2017
Nov 14 2017
I don't reach to apply the patch, and when I've tried to "manually" merge it, I've broke the compilation :-(
Nov 13 2017
Here are my updated benches "forwarding smallest packet size" results on 2 different hardware.
I'm using a fresh head (r325763) and the latest diff (35190) of this review.
Nov 10 2017
I've tried to update my previous benches, but on a recent head (r325618), and this review need to be updated because it no more apply (a small part was committed into head).
And compilation failed on this recent head too:
Nov 9 2017
Nov 8 2017
Nov 5 2017
Nov 3 2017
Nov 1 2017
Oct 31 2017
Oct 30 2017
I confirm: I'm using static key only on my tests.
Oct 27 2017
I've found the commit that broke AES-GCM: r324037 "aesni(4): Add support for x86 SHA intrinsics".
But how is possible that I'm impacted without loading aesni module ?!?
And now comparing pf vs ipfw:
Wow, results regarding the 5M UDP session bench:
After adding a new port, you need to add it to the category Makefile too (here in devel/Makefile): I didn't see modifications to devel/Makefile here.
And each time I'm touching such category Makefile file, I'm checking index is still building fine with an indexbuild (cd /usr/port; make index).