- Queries
- All Stories
- Search
- Advanced Search
- Transactions
- Transaction Logs
Advanced Search
Jul 4 2016
Jun 29 2016
Jun 26 2016
Jun 25 2016
Jun 22 2016
Jun 21 2016
Jun 17 2016
Jun 15 2016
Jun 14 2016
Jun 13 2016
Jun 10 2016
I'm still OK with this.
Jun 6 2016
Jun 3 2016
Jun 2 2016
I've tested this in a two host test using iperf. https://github.com/gvnn3/netperf/tree/master/VANILLA/Tests/iperf-twohost-nooffload
Jun 1 2016
May 31 2016
Why are we implementing new sorts in the TCP stack? The stack should depend on generic sorting functions placed in a library.
May 27 2016
May 23 2016
May 20 2016
May 19 2016
Push it out to 64 bits please.
May 18 2016
May 17 2016
May 14 2016
May 5 2016
May 1 2016
Apr 27 2016
Apr 23 2016
I have confirmed this fixes the problem I initially saw.
Apr 21 2016
Not my comment "once everyone agrees" :-)
Let's keep this moving along. Mike isn't (yet) a committer but if someone can commit this once everyone agrees that would be great.
Apr 20 2016
I'm in private conversation with hps@ about this proposal.
Apr 13 2016
Apr 11 2016
Apr 10 2016
Apr 2 2016
Mar 31 2016
Mar 30 2016
Only one requested change from me. I have not tested this directly, only read the code.
Mar 29 2016
Carry on then!
Why does it need to be called kmod? I'd just name it intel-ixl
Mar 28 2016
Mar 25 2016
That delay is kind of hackish. But it's a start.