On 05/29/2012 12:07 PM, Christian Lamparter wrote: > On Tuesday, May 29, 2012 08:23:20 PM Ben Greear wrote: >> On 05/27/2012 08:08 AM, Ben Greear wrote: >>> On 05/26/2012 09:39 AM, Sujith Manoharan wrote: >> We started testing with two AR9380 NICs today (one AP, the other STA). >> I applied Felix's skb optimization patch, and the ath9k memleak fix patch >> on top of 3.3.7+. >> >> The system has 2GB RAM, but it is 32-bit kernel, so not all >> is available to the networking code... That said, the OOM >> killer kills VNC and such. >> >> Anyway, I'll try some memleak debugging to see if >> I can find any leaks. It seems to me that we should >> not actually OOM just by trying to transmit too fast >> on a station interface :P > well, there's that: > http://comments.gmane.org/gmane.linux.drivers.ath9k.devel/8233 > > It might not fix the bug, but it can save you time to confirm > that is not related to this particular skb leak.
I ported this to 3.3.7+ and applied it to my kernel trees. It has tested out fine so far, though it did not actually fix the problem I was having. That was not a real leak, just always-growing pending queue length, probably due to some issue with our version of pktgen. It is mostly a port-by-hand type of thing since there are lots of conflicts. Let me know if you'd like me to post my version (and plz confirm your signed-off-by). Thanks, Ben -- Ben Greear <[email protected]> Candela Technologies Inc http://www.candelatech.com _______________________________________________ ath9k-devel mailing list [email protected] https://lists.ath9k.org/mailman/listinfo/ath9k-devel
