> On May 24, 2016, 10 p.m., Andreas Hansson wrote:
> > src/dev/net/etherswitch.cc, line 182
> > <http://reviews.gem5.org/r/3465/diff/7/?file=55548#file55548line182>
> >
> >     all reschedule instead?

good point. Fixed.


> On May 24, 2016, 10 p.m., Andreas Hansson wrote:
> > src/dev/net/etherswitch.cc, line 347
> > <http://reviews.gem5.org/r/3465/diff/7/?file=55548#file55548line347>
> >
> >     Does this break checkpoint compatibility?
> >     
> >     If so that needs to be addressed.

It probably does. How should I address that?


> On May 24, 2016, 10 p.m., Andreas Hansson wrote:
> > src/dev/net/etherswitch.cc, line 93
> > <http://reviews.gem5.org/r/3465/diff/7/?file=55548#file55548line93>
> >
> >     should this perhaps even be a warn (or do we ever expect this to happen 
> > in a correct setup?

I would say It can happen in a correct setup. If someone set the fifo size of 
the ethernet switch smaller than MTU of ethernet packets then it would happen. 
But I can change it to warn if you think it's better.


> On May 24, 2016, 10 p.m., Andreas Hansson wrote:
> > src/dev/net/etherswitch.hh, line 147
> > <http://reviews.gem5.org/r/3465/diff/7/?file=55547#file55547line147>
> >
> >     unsigned? if not it really needs a comment

I added a comment. I used "int" intentionally.


> On May 24, 2016, 10 p.m., Andreas Hansson wrote:
> > src/dev/net/etherswitch.hh, line 108
> > <http://reviews.gem5.org/r/3465/diff/7/?file=55547#file55547line108>
> >
> >     all these members could be const?

I don't think so. We set them inside 
"EtherSwitch::Interface::PortFifoEntry::unserialize"


- Mohammad


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3465/#review8336
-----------------------------------------------------------


On May 25, 2016, 3:50 a.m., Mohammad Alian wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3465/
> -----------------------------------------------------------
> 
> (Updated May 25, 2016, 3:50 a.m.)
> 
> 
> Review request for Default.
> 
> 
> Repository: gem5
> 
> 
> Description
> -------
> 
> Changeset 11472:24da17267b22
> ---------------------------
> dist, dev: Fixed the packet ordering in etherswitch
> This patch fixes the order that packets gets pushed into the output fifo
> of etherswitch. If two packets arrive at the same tick to the etherswitch,
> we sort and push them based on their source port id.
> In dist-gem5 simulations, if there is no ordering inforced while two
> packets arrive at the same tick, it can lead to non-deterministic simulations
> 
> 
> Diffs
> -----
> 
>   src/dev/net/etherswitch.hh 954d3014f7f0 
>   src/dev/net/etherswitch.cc 954d3014f7f0 
> 
> Diff: http://reviews.gem5.org/r/3465/diff/
> 
> 
> Testing
> -------
> 
> 
> Thanks,
> 
> Mohammad Alian
> 
>

_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to