[INET]: Remove per bucket rwlock in tcp/dccp ehash table.
As done two years ago on IP route cache table (commit
22c047ccbc68fa8f3fa57f0e8f906479a062c426) , we can avoid using one
lock per hash bucket for the huge TCP/DCCP hash tables.
On a typical x86_64 platform, this saves about 2MB or 4MB of ram, for
litle performance differences. (we hit a different cache line for the
rwlock, but then the bucket cache line have a better sharing factor
among cpus, since we dirty it less often). For netstat or ss commands
that want a full scan of hash table, we perform fewer memory accesses.
Using a 'small' table of hashed rwlocks should be more than enough to
provide correct SMP concurrency between different buckets, without
using too much memory. Sizing of this table depends on
num_possible_cpus() and various CONFIG settings.
This patch provides some locking abstraction that may ease a future
work using a different model for TCP/DCCP table.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index d849739..7a3bea9 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1072,11 +1072,13 @@
}
for (i = 0; i < dccp_hashinfo.ehash_size; i++) {
- rwlock_init(&dccp_hashinfo.ehash[i].lock);
INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain);
INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain);
}
+ if (inet_ehash_locks_alloc(&dccp_hashinfo))
+ goto out_free_dccp_ehash;
+
bhash_order = ehash_order;
do {
@@ -1091,7 +1093,7 @@
if (!dccp_hashinfo.bhash) {
DCCP_CRIT("Failed to allocate DCCP bind hash table");
- goto out_free_dccp_ehash;
+ goto out_free_dccp_locks;
}
for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
@@ -1121,6 +1123,8 @@
out_free_dccp_bhash:
free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
dccp_hashinfo.bhash = NULL;
+out_free_dccp_locks:
+ inet_ehash_locks_free(&dccp_hashinfo);
out_free_dccp_ehash:
free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
dccp_hashinfo.ehash = NULL;
@@ -1139,6 +1143,7 @@
free_pages((unsigned long)dccp_hashinfo.ehash,
get_order(dccp_hashinfo.ehash_size *
sizeof(struct inet_ehash_bucket)));
+ inet_ehash_locks_free(&dccp_hashinfo);
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
dccp_ackvec_exit();
dccp_sysctl_exit();