> I don't see this as a big problem. For most skbs we waste a lot of
> memory anyways because they they have to fit into the power-of-2 blocks
> of the slab allocator. BTW did you have any luck with the slab skb
> patch?
It works, but it is not clear how it affects performance.
We got an obsure problem after CVS was merged to >2.1.72,
and with all of Linus' kernels. (No matter, with your patch or without it)
It is still not clear what did occur, but the things looks like
slab became weirdly slow: at least thrice...
In 2.1.72+CVS we jumped to 100Kpps area and returning back to 40Kpps
is not very interesting adventure :), so that the solution is backlogged.
Alexey
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu