> On Oct. 30, 2015, 10:17 p.m., Andreas Hansson wrote:
> > src/mem/packet_queue.cc, line 117
> > <http://reviews.gem5.org/r/3183/diff/1/?file=50969#file50969line117>
> >
> > That is 64 kB of implicit storage! As I've already mentioned many
> > times, this check has been instrumental in finding lots of problems in the
> > memory system, and I am against changing it.
> >
> > I think the best option here is a compile-time switch for disabling
> > this sanity check. Perhaps we can call it "ludicrous mode" :-)
> >
> > If you want to set that from Ruby and remove the safety net that's fine.
First off, thank you for suggesting a solution this time around rather than
just stating you are against the patch!
Can you further elaborate on what sort of compile-time switch you will approve?
Would you be ok with the src/mem/SConscript doing something like this?
if env['PROTOCOL'] == 'None':
#define MAX_PKT_Q_SIZE = 100
else:
#define MAX_PKT_Q_SIZE = 10000
Also don't worry about increasing the packet queue size for Ruby. Ruby already
includes a deadlock safety net that identifies when things have gone off the
rails.
- Brad
-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3183/#review7426
-----------------------------------------------------------
On Oct. 30, 2015, 9:52 p.m., Tony Gutierrez wrote:
>
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3183/
> -----------------------------------------------------------
>
> (Updated Oct. 30, 2015, 9:52 p.m.)
>
>
> Review request for Default.
>
>
> Repository: gem5
>
>
> Description
> -------
>
> Changeset 11189:d89321a4dac4
> ---------------------------
> mem: increase arbitrary limit on the packet queue
>
>
> Diffs
> -----
>
> src/mem/packet_queue.cc 4daf60db14d794e2344a6c86a93bdd8273bc5bb6
>
> Diff: http://reviews.gem5.org/r/3183/diff/
>
>
> Testing
> -------
>
>
> Thanks,
>
> Tony Gutierrez
>
>
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev