I'm now able to get reliable clean starts (no more startup warnings) by
ramping up my cycle time in increments; like 1, 2, 4, 8, 10 kHz over a
short period.
Is anyone using similar "warm-up" technique?
The work around seems to work fine, I was thinking I might be able to
get rid of it, maybe something non-optimal in my kernel config?
Regards,
Matthieu
On 6/11/12 2:45 PM, Matthieu Bec wrote:
Hello all,
I'm experimenting with different NIC to better understand the pros, cons
and tradeoff of different solution. My system has on-board e1000e, and a
PCIe r8169, my test application runs in kernel cycled by hr-timer. I'm
cranking up the frame rate looking how far it will reliably go and
checking dmesg logs.
In all cases, there seems to be an intermediate frame rate where I get
skipped/unmatched datagrams right after inserting my app. module, but
quickly; once the master has found all the slaves (?) no more warnings
show in the logs
I was wondering if it was safe to ignore those skipped/unmatched
warnings? Should I plan some checks in my application to verify the pdo
mapping, sdo config, etc have all been properly applied?
Regards,
_______________________________________________
etherlab-users mailing list
[email protected]
http://lists.etherlab.org/mailman/listinfo/etherlab-users
