Eric W. Biederman a écrit :
Eric Dumazet <[EMAIL PROTECTED]> writes:
Eric W. Biederman a écrit :
Eric Dumazet <[EMAIL PROTECTED]> writes:
Definitly wanted here. Thank you.
One more refcounting on each socket creation/deletion was expensive.
Really? Have you actually measured that? If the overhead is
measurable and expensive we may want to look at per cpu counters or
something like that. So far I don't have any numbers that say any
of the network namespace work inherently has any overhead.
It seems that on some old opterons (two 246 for example),
"if (atomic_dec_and_test(&net->count))" is rather expensive yes :(
I won't argue that atomic_dec_and_test is costly. My gut feel is that
socket creation/destruction is sufficiently rare that such a test
would be lost in the noise. Doing anything more sophisticated is
likely to be less readable, and unless we can measure some overhead
my preference right now is to keep the code stupid and simple. Which
usually has a good icache footprint.
I agree with you that with current state, this atomic_inc/atomic_dec_and_test
wont come in profiles unless a trivial bench is writen
for(;;){close(socket(....));}
If David or another dev can eliminate the atomic inc/dec on device refcount
cost for each packet traveling, the socket creation/destruction would
certainly raise.
Other contention points is the mnt_count (yet another refcount) in "struct
vfsmount", a truly useless refcount as I never had (and nobody had) to
un-mount sock_mnt :)
-
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
