Feng Tang reported a performance regression after introduction
of per TCP socket tx/rx caches, for TCP over loopback (netperf)
There is high chance the regression is caused by a change on
how well the 32 KB per-thread page (current->task_frag) can
be recycled, and lack of pcp caches for order-3 pages.
I could not reproduce the regression myself, cpus all being
spinning on the mm spinlocks for page allocs/freeing, regardless
of enabling or disabling the per tcp socket caches.
It seems best to disable the feature by default, and let
admins enabling it.
MM layer either needs to provide scalable order-3 pages
allocations, or could attempt a trylock on zone->lock if
the caller only attempts to get a high-order page and is
able to fallback to order-0 ones in case of pressure.
Tests run on a 56 cores host (112 hyper threads)
- 35.49% netperf [kernel.vmlinux] [k]
queued_spin_lock_slowpath
- 35.49% queued_spin_lock_slowpath
- 18.18% get_page_from_freelist
- __alloc_pages_nodemask
- 18.18% alloc_pages_current
skb_page_frag_refill
sk_page_frag_refill
tcp_sendmsg_locked
tcp_sendmsg
inet_sendmsg
sock_sendmsg
__sys_sendto
__x64_sys_sendto
do_syscall_64
entry_SYSCALL_64_after_hwframe
__libc_send
+ 17.31% __free_pages_ok
+ 31.43% swapper [kernel.vmlinux] [k] intel_idle
+ 9.12% netperf [kernel.vmlinux] [k]
copy_user_enhanced_fast_string
+ 6.53% netserver [kernel.vmlinux] [k]
copy_user_enhanced_fast_string
+ 0.69% netserver [kernel.vmlinux] [k]
queued_spin_lock_slowpath
+ 0.68% netperf [kernel.vmlinux] [k]
skb_release_data
+ 0.52% netperf [kernel.vmlinux] [k]
tcp_sendmsg_locked
0.46% netperf [kernel.vmlinux] [k]
_raw_spin_lock_irqsave
Fixes: 472c2e07eef0 ("tcp: add one skb cache for tx")
Signed-off-by: Eric Dumazet <eduma...@google.com>
Reported-by: Feng Tang <feng.t...@intel.com>
---
include/net/sock.h | 4 +++-
net/ipv4/sysctl_net_ipv4.c | 8 ++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index
b02645e2dfad722769c1455bcde76e46da9fc5ac..7d7f4ce63bb2aae7c87a9445d11339b6e6b19724
100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1463,12 +1463,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int
size)
__sk_mem_reclaim(sk, 1 << 20);
}
+DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
sk->sk_wmem_queued -= skb->truesize;
sk_mem_uncharge(sk, skb->truesize);
- if (!sk->sk_tx_skb_cache && !skb_cloned(skb)) {
+ if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
+ !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
skb_zcopy_clear(skb, true);
sk->sk_tx_skb_cache = skb;
return;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index
886b58d31351df44725bdc34081e798bcb89ecf0..08a428a7b2749c4f2a03aa6352e44c053596ef75
100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -54,6 +54,8 @@ static int one_day_secs = 24 * 3600;
DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
EXPORT_SYMBOL(tcp_rx_skb_cache_key);
+DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
+
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -568,6 +570,12 @@ static struct ctl_table ipv4_table[] = {
.mode = 0644,
.proc_handler = proc_do_static_key,
},
+ {
+ .procname = "tcp_tx_skb_cache",
+ .data = &tcp_tx_skb_cache_key.key,
+ .mode = 0644,
+ .proc_handler = proc_do_static_key,
+ },
{ }
};
--
2.22.0.410.gd8fdbe21b5-goog
