cvs commit: src/sys/dev/bce if_bce.c src/sys/dev/bge if_bge.c src/sys/dev/em if_em.c src/sys/dev/ixgb if_ixgb.c src/sys/dev/nfe if_nfe.c src/sys/dev/nge if_nge.c src/sys/dev/re if_re.c src/sys/dev/stge if_stge.c src/sys/dev/ti if_ti.c src/sys/dev/txp ...

[Gleb Smirnoff]

On Mon, Sep 18, 2006 at 01:54:18PM -0400, John Baldwin wrote:
J> Did you ever get a chance to benchmark this?  I know in principle it should be 
J> faster, but as I had mentioned to you earlier, sometimes things that seem 
J> like they should be faster end up being slower, so it's generally helpful to 
J> verify one's assumptions with actual benchmarks or testing, etc.  Also, it 
J> would have been helpful to have Robert's review on this as he has been 
J> talking about moving the vlan stuff into the ether input/output routines for 
J> quite a while now.

/me seconds. When introducing the mtag UMA zone I've done benchmarking,
that proved that this change should go into CVS. I'd appreciate if the
removal would be confirmed with a benchmark result.

-- 
Totus tuus, Glebius.
GLEBIUS-RIPN GLEB-RIPE