Messages in this thread | | | Date | Fri, 30 Dec 2011 17:09:05 -0500 (EST) | Subject | Re: [PATCH RFC] IPv6: Avoid taking write lock for /proc/net/ipv6_route | From | David Miller <> |
| |
From: Josh Hunt <joshhunt00@gmail.com> Date: Wed, 28 Dec 2011 17:23:07 -0600
> lock_stat shows taking the write lock is causing the slowdown. Using > this info I decided to write a version of fib6_clean_all() which > replaces write_lock_bh(&table->tb6_lock) with > read_lock_bh(&table->tb6_lock). With this new function I see the same > results as with my rtnetlink iperf test. I guess my question is what > am I missing? Is there a reason you need to take the write lock when > reading the route table to display to proc?
You're not missing anything, it's just an oversight or laziness. :-)
I've applied your patch thanks.
Longer term we should make the ipv6 tree traversals RCU safe just like net/ipv4/fib_trie.c is. Then we can do away with even the read locks for read-only traversals.
| |