ipvs: wakeup master thread
High rate of sync messages in master can lead to
overflowing the socket buffer and dropping the messages.
Fixed sleep of 1 second without wakeup events is not suitable
for loaded masters,
Use delayed_work to schedule sending for queued messages
and limit the delay to IPVS_SYNC_SEND_DELAY (20ms). This will
reduce the rate of wakeups but to avoid sending long bursts we
wakeup the master thread after IPVS_SYNC_WAKEUP_RATE (8) messages.
Add hard limit for the queued messages before sending
by using "sync_qlen_max" sysctl var. It defaults to 1/32 of
the memory pages but actually represents number of messages.
It will protect us from allocating large parts of memory
when the sending rate is lower than the queuing rate.
As suggested by Pablo, add new sysctl var
"sync_sock_size" to configure the SNDBUF (master) or
RCVBUF (slave) socket limit. Default value is 0 (preserve
system defaults).
Change the master thread to detect and block on
SNDBUF overflow, so that we do not drop messages when
the socket limit is low but the sync_qlen_max limit is
not reached. On ENOBUFS or other errors just drop the
messages.
Change master thread to enter TASK_INTERRUPTIBLE
state early, so that we do not miss wakeups due to messages or
kthread_should_stop event.
Thanks to Pablo Neira Ayuso for his valuable feedback!
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 93b81aa..30e43c8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -869,6 +869,8 @@
#endif
int sysctl_snat_reroute;
int sysctl_sync_ver;
+ int sysctl_sync_qlen_max;
+ int sysctl_sync_sock_size;
int sysctl_cache_bypass;
int sysctl_expire_nodest_conn;
int sysctl_expire_quiescent_template;
@@ -889,6 +891,9 @@
struct timer_list est_timer; /* Estimation timer */
/* ip_vs_sync */
struct list_head sync_queue;
+ int sync_queue_len;
+ unsigned int sync_queue_delay;
+ struct delayed_work master_wakeup_work;
spinlock_t sync_lock;
struct ip_vs_sync_buff *sync_buff;
spinlock_t sync_buff_lock;
@@ -911,6 +916,10 @@
#define DEFAULT_SYNC_THRESHOLD 3
#define DEFAULT_SYNC_PERIOD 50
#define DEFAULT_SYNC_VER 1
+#define IPVS_SYNC_WAKEUP_RATE 8
+#define IPVS_SYNC_QLEN_MAX (IPVS_SYNC_WAKEUP_RATE * 4)
+#define IPVS_SYNC_SEND_DELAY (HZ / 50)
+#define IPVS_SYNC_CHECK_PERIOD HZ
#ifdef CONFIG_SYSCTL
@@ -929,6 +938,16 @@
return ipvs->sysctl_sync_ver;
}
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_qlen_max;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_sock_size;
+}
+
#else
static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -946,6 +965,16 @@
return DEFAULT_SYNC_VER;
}
+static inline int sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
+{
+ return IPVS_SYNC_QLEN_MAX;
+}
+
+static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
+{
+ return 0;
+}
+
#endif
/*