>From linux-3.7, (commit 5640f7685831 "net: use a per task frag
allocator") TCP sendmsg() has preferred using order-3 allocations.
While it gives good results for most cases, we had reports
that heavy uses of TCP over loopback were hitting a spinlock
contention in page allocations/freeing.
This commits adds a sysctl so that admins can opt-in
for order-0 allocations. Hopefully mm layer might optimize
order-3 allocations in the future since it could give us
a nice boost (see 8 lines of following benchmark)
The following benchmark shows a win when more than 8 TCP_STREAM
threads are running (56 x86 cores server in my tests)
for thr in {1..30}
do
sysctl -wq net.core.high_order_alloc_disable=0
T0=`./super_netperf $thr -H 127.0.0.1 -l 15`
sysctl -wq net.core.high_order_alloc_disable=1
T1=`./super_netperf $thr -H 127.0.0.1 -l 15`
echo $thr:$T0:$T1
done
1: 49979: 37267
2: 98745: 76286
3: 141088: 110051
4: 177414: 144772
5: 197587: 173563
6: 215377: 208448
7: 241061: 234087
8: 267155: 263373
9: 295069: 297402
10: 312393: 335213
11: 340462: 368778
12: 371366: 403954
13: 412344: 443713
14: 426617: 473580
15: 474418: 507861
16: 503261: 538539
17: 522331: 563096
18: 532409: 567084
19: 550824: 605240
20: 525493: 641988
21: 564574: 665843
22: 567349: 690868
23: 583846: 710917
24: 588715: 736306
25: 603212: 763494
26: 604083: 792654
27: 602241: 796450
28: 604291: 797993
29: 611610: 833249
30: 577356: 841062
Signed-off-by: Eric Dumazet <eduma...@google.com>
---
include/net/sock.h | 2 ++
net/core/sock.c | 4 +++-
net/core/sysctl_net_core.c | 7 +++++++
3 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index
7d7f4ce63bb2aae7c87a9445d11339b6e6b19724..6cbc16136357d158cf1e84b98ecb7e06898269a6
100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2534,6 +2534,8 @@ extern int sysctl_optmem_max;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
+DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
+
static inline int sk_get_wmem0(const struct sock *sk, const struct proto
*proto)
{
/* Does this proto have per netns sysctl_wmem ? */
diff --git a/net/core/sock.c b/net/core/sock.c
index
2b3701958486219a26385c8fca1498c4e294dc1d..7f49392579a5826b0a8446bb88428396422cc0b6
100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2320,6 +2320,7 @@ static void sk_leave_memory_pressure(struct sock *sk)
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
+DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
/**
* skb_page_frag_refill - check that a page_frag contains enough room
@@ -2344,7 +2345,8 @@ bool skb_page_frag_refill(unsigned int sz, struct
page_frag *pfrag, gfp_t gfp)
}
pfrag->offset = 0;
- if (SKB_FRAG_PAGE_ORDER) {
+ if (SKB_FRAG_PAGE_ORDER &&
+ !static_branch_unlikely(&net_high_order_alloc_disable_key)) {
/* Avoid direct reclaim but allow kswapd to wake */
pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP | __GFP_NOWARN |
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index
1a2685694abd537d7ae304754b84b237928fd298..f9204719aeeeb4700582d03fda244f2f8961f8a7
100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -562,6 +562,13 @@ static struct ctl_table net_core_table[] = {
.extra1 = &zero,
.extra2 = &two,
},
+ {
+ .procname = "high_order_alloc_disable",
+ .data = &net_high_order_alloc_disable_key.key,
+ .maxlen = sizeof(net_high_order_alloc_disable_key),
+ .mode = 0644,
+ .proc_handler = proc_do_static_key,
+ },
{ }
};
--
2.22.0.410.gd8fdbe21b5-goog
