Maybe it's unrelated to this problem, but it is interesting observation,
at least for me.
All boxes running for two weeks now and spitting these assert messages
have about 1,5GB of slab size allocated, with skbuff_head_cache entry
being the largest entry. After rebooting, it is all nice and small, but
it is noticable, that this entry is again constantly growing. This is
happening on all my boxes, which print these asserts.
Could this be simply a result of a data corruption happening somwhere in
e1000 driver in relevance with this problem?
After seting TSO to off on all boxes affected with this slab leak, it
suddenly works perfectly. No slab leaking occurs and no errors in dmesg
regarding TCP asserts.
--
Michal Feix
[EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
