Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1236578
| From | Santosh Shilimkar <santosh.shilimkar@oracle.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH v2 02/14] RDS: make socket bind/release locking scheme simple and more efficient |
| Date | 2015-09-30 19:40 +0200 |
| Message-ID | <qetwe-3ox-17@gated-at.bofh.it> (permalink) |
| References | <qetmx-3dp-5@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
RDS bind and release locking scheme is very inefficient. It
uses RCU for maintaining the bind hash-table which is great but
it also needs to hold spinlock for [add/remove]_bound(). So
overall usecase, the hash-table concurrent speedup doesn't pay off.
In fact blocking nature of synchronize_rcu() makes the RDS
socket shutdown too slow which hurts RDS performance since
connection shutdown and re-connect happens quite often to
maintain the RC part of the protocol.
So we make the locking scheme simpler and more efficient by
replacing spin_locks with reader/writer locks and getting rid
off rcu for bind hash-table.
In subsequent patch, we also covert the global lock with per-bucket
lock to reduce the global lock contention.
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
net/rds/af_rds.c | 6 ------
net/rds/bind.c | 35 +++++++++++++++--------------------
2 files changed, 15 insertions(+), 26 deletions(-)
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index a2f28a6..dc08766 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -72,13 +72,7 @@ static int rds_release(struct socket *sock)
rds_clear_recv_queue(rs);
rds_cong_remove_socket(rs);
- /*
- * the binding lookup hash uses rcu, we need to
- * make sure we synchronize_rcu before we free our
- * entry
- */
rds_remove_bound(rs);
- synchronize_rcu();
rds_send_drop_to(rs, NULL);
rds_rdma_drop_keys(rs);
diff --git a/net/rds/bind.c b/net/rds/bind.c
index dd666fb..01989e2 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -40,7 +40,7 @@
#define BIND_HASH_SIZE 1024
static struct hlist_head bind_hash_table[BIND_HASH_SIZE];
-static DEFINE_SPINLOCK(rds_bind_lock);
+static DEFINE_RWLOCK(rds_bind_lock);
static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
{
@@ -48,6 +48,7 @@ static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
(BIND_HASH_SIZE - 1));
}
+/* must hold either read or write lock (write lock for insert != NULL) */
static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
struct rds_sock *insert)
{
@@ -56,30 +57,24 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
u64 cmp;
u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port);
- rcu_read_lock();
- hlist_for_each_entry_rcu(rs, head, rs_bound_node) {
+ hlist_for_each_entry(rs, head, rs_bound_node) {
cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) |
be16_to_cpu(rs->rs_bound_port);
- if (cmp == needle) {
- rcu_read_unlock();
+ if (cmp == needle)
return rs;
- }
}
- rcu_read_unlock();
if (insert) {
/*
* make sure our addr and port are set before
- * we are added to the list, other people
- * in rcu will find us as soon as the
- * hlist_add_head_rcu is done
+ * we are added to the list.
*/
insert->rs_bound_addr = addr;
insert->rs_bound_port = port;
rds_sock_addref(insert);
- hlist_add_head_rcu(&insert->rs_bound_node, head);
+ hlist_add_head(&insert->rs_bound_node, head);
}
return NULL;
}
@@ -93,8 +88,11 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
{
struct rds_sock *rs;
+ unsigned long flags;
+ read_lock_irqsave(&rds_bind_lock, flags);
rs = rds_bind_lookup(addr, port, NULL);
+ read_unlock_irqrestore(&rds_bind_lock, flags);
if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
rds_sock_addref(rs);
@@ -103,6 +101,7 @@ struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
ntohs(port));
+
return rs;
}
@@ -121,7 +120,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
last = rover - 1;
}
- spin_lock_irqsave(&rds_bind_lock, flags);
+ write_lock_irqsave(&rds_bind_lock, flags);
do {
if (rover == 0)
@@ -135,7 +134,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
}
} while (rover++ != last);
- spin_unlock_irqrestore(&rds_bind_lock, flags);
+ write_unlock_irqrestore(&rds_bind_lock, flags);
return ret;
}
@@ -144,19 +143,19 @@ void rds_remove_bound(struct rds_sock *rs)
{
unsigned long flags;
- spin_lock_irqsave(&rds_bind_lock, flags);
+ write_lock_irqsave(&rds_bind_lock, flags);
if (rs->rs_bound_addr) {
rdsdebug("rs %p unbinding from %pI4:%d\n",
rs, &rs->rs_bound_addr,
ntohs(rs->rs_bound_port));
- hlist_del_init_rcu(&rs->rs_bound_node);
+ hlist_del_init(&rs->rs_bound_node);
rds_sock_put(rs);
rs->rs_bound_addr = 0;
}
- spin_unlock_irqrestore(&rds_bind_lock, flags);
+ write_unlock_irqrestore(&rds_bind_lock, flags);
}
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -200,9 +199,5 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
out:
release_sock(sk);
-
- /* we might have called rds_remove_bound on error */
- if (ret)
- synchronize_rcu();
return ret;
}
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH v2 00/14] RDS: connection scalability and performance improvements Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:30 +0200
[PATCH v2 13/14] RDS: IB: use max_mr from HCA caps than max_fmr Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:30 +0200
[PATCH v2 07/14] RDS: IB: ack more receive completions to improve performance Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:30 +0200
[PATCH v2 08/14] RDS: IB: split send completion handling and do batch ack Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:30 +0200
[PATCH v2 05/14] RDS: defer the over_batch work to send worker Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:40 +0200
Re: [PATCH v2 05/14] RDS: defer the over_batch work to send worker David Miller <davem@davemloft.net> - 2015-10-05 12:20 +0200
Re: [PATCH v2 05/14] RDS: defer the over_batch work to send worker santosh shilimkar <santosh.shilimkar@oracle.com> - 2015-10-05 17:40 +0200
[PATCH v2 03/14] RDS: fix rds_sock reference bug while doing bind Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:40 +0200
[PATCH v2 02/14] RDS: make socket bind/release locking scheme simple and more efficient Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:40 +0200
[PATCH v2 06/14] RDS: use rds_send_xmit() state instead of RDS_LL_SEND_FULL Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:40 +0200
[PATCH v2 04/14] RDS: Use per-bucket rw lock for bind hash-table Santosh Shilimkar <santosh.shilimkar@oracle.com> - 2015-09-30 19:40 +0200
RE: [PATCH v2 00/14] RDS: connection scalability and performance improvements David Laight <David.Laight@ACULAB.COM> - 2015-10-01 18:30 +0200
Re: [PATCH v2 00/14] RDS: connection scalability and performance improvements "santosh.shilimkar@oracle.com" <santosh.shilimkar@oracle.com> - 2015-10-01 21:10 +0200
csiph-web