IPv6: Avoid taking write lock for /proc/net/ipv6_route
During some debugging I needed to look into how /proc/net/ipv6_route operated and in my digging I found its calling fib6_clean_all() which uses "write_lock_bh(&table->tb6_lock)" before doing the walk of the table. I found this on 2.6.32, but reading the code I believe the same basic idea exists currently. Looking at the rtnetlink code they are only calling "read_lock_bh(&table->tb6_lock);" via fib6_dump_table(). While I realize reading from proc isn't the recommended way of fetching the ipv6 route table; taking a write lock seems unnecessary and would probably cause network performance issues. To verify this I loaded up the ipv6 route table and then ran iperf in 3 cases: * doing nothing * reading ipv6 route table via proc (while :; do cat /proc/net/ipv6_route > /dev/null; done) * reading ipv6 route table via rtnetlink (while :; do ip -6 route show table all > /dev/null; done) * Load the ipv6 route table up with: * for ((i = 0;i < 4000;i++)); do ip route add unreachable 2000::$i; done * iperf commands: * client: iperf -i 1 -V -c <ipv6 addr> * server: iperf -V -s * iperf results - 3 runs each (in Mbits/sec) * nothing: client: 927,927,927 server: 927,927,927 * proc: client: 179,97,96,113 server: 142,112,133 * iproute: client: 928,927,928 server: 927,927,927 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. Signed-off-by: Josh Hunt <joshhunt00@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
parent
c9da99e647
commit
32b293a53d
|
@ -199,6 +199,10 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
|
|||
const struct in6_addr *daddr, int dst_len,
|
||||
const struct in6_addr *saddr, int src_len);
|
||||
|
||||
extern void fib6_clean_all_ro(struct net *net,
|
||||
int (*func)(struct rt6_info *, void *arg),
|
||||
int prune, void *arg);
|
||||
|
||||
extern void fib6_clean_all(struct net *net,
|
||||
int (*func)(struct rt6_info *, void *arg),
|
||||
int prune, void *arg);
|
||||
|
|
|
@ -1462,6 +1462,26 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
|
|||
fib6_walk(&c.w);
|
||||
}
|
||||
|
||||
void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
|
||||
int prune, void *arg)
|
||||
{
|
||||
struct fib6_table *table;
|
||||
struct hlist_node *node;
|
||||
struct hlist_head *head;
|
||||
unsigned int h;
|
||||
|
||||
rcu_read_lock();
|
||||
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
|
||||
head = &net->ipv6.fib_table_hash[h];
|
||||
hlist_for_each_entry_rcu(table, node, head, tb6_hlist) {
|
||||
read_lock_bh(&table->tb6_lock);
|
||||
fib6_clean_tree(net, &table->tb6_root,
|
||||
func, prune, arg);
|
||||
read_unlock_bh(&table->tb6_lock);
|
||||
}
|
||||
}
|
||||
rcu_read_unlock();
|
||||
}
|
||||
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
|
||||
int prune, void *arg)
|
||||
{
|
||||
|
|
|
@ -2680,7 +2680,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
|
|||
static int ipv6_route_show(struct seq_file *m, void *v)
|
||||
{
|
||||
struct net *net = (struct net *)m->private;
|
||||
fib6_clean_all(net, rt6_info_route, 0, m);
|
||||
fib6_clean_all_ro(net, rt6_info_route, 0, m);
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue