Yes! I think your rpm installation is correct! Thanks!
It looks like the v3.6 driver did not affect the issue. However I think I can not just test driver only, maybe we should test by changing the whole kernel due to it may has another fixes in neworking or other related subsystem.
Yes! I think your rpm installation is correct! Thanks!
It looks like the v3.6 driver did not affect the issue. However I think I can not just test driver only, maybe we should test by changing the whole kernel due to it may has another fixes in neworking or other related subsystem.
Actually there already had a bisected result, it may related to the issue (from: https:/ /bugzilla. kernel. org/show_ bug.cgi? id=54021# c14)
commit 69b08f62e17439e e3d436faf0b9a7c a6fffb78db
Author: Eric Dumazet <email address hidden>
Date: Wed Sep 26 06:46:57 2012 +0000
net: use bigger pages in __netdev_alloc_frag
We currently use percpu order-0 pages in __netdev_alloc_frag alloc_skb( )
to deliver fragments used by __netdev_
Depending on NIC driver and arch being 32 or 64 bit, it allows a page to
be split in several fragments (between 1 and 8), assuming PAGE_SIZE=4096
Switching to bigger pages (32768 bytes for PAGE_SIZE=4096 case) allows :
- Better filling of space (the ending hole overhead is less an issue)
- Less calls to page allocator or accesses to page->_count
- Could allow struct skb_shared_info futures changes without major
performance impact.
This patch implements a transparent fallback to smaller
pages in case of memory pressure.
It also uses a standard "struct page_frag" instead of a custom one.