summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
Diffstat (limited to 'include/net')
-rw-r--r--include/net/ip_vs.h88
1 files changed, 83 insertions, 5 deletions
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a4d44138c2a8..04960dc6228f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -42,6 +42,8 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
/* Connections' size value needed by ip_vs_ctl.c */
extern int ip_vs_conn_tab_size;
+extern struct mutex __ip_vs_mutex;
+
struct ip_vs_iphdr {
int hdr_flags; /* ipvs flags */
__u32 off; /* Where IP or IPv4 header starts */
@@ -365,7 +367,7 @@ struct ip_vs_cpu_stats {
/* IPVS statistics objects */
struct ip_vs_estimator {
- struct list_head list;
+ struct hlist_node list;
u64 last_inbytes;
u64 last_outbytes;
@@ -378,6 +380,10 @@ struct ip_vs_estimator {
u64 outpps;
u64 inbps;
u64 outbps;
+
+ s32 ktid:16, /* kthread ID, -1=temp list */
+ ktrow:8, /* row/tick ID for kthread */
+ ktcid:8; /* chain ID for kthread tick */
};
/*
@@ -415,6 +421,66 @@ struct ip_vs_stats *ip_vs_stats_alloc(void);
void ip_vs_stats_release(struct ip_vs_stats *stats);
void ip_vs_stats_free(struct ip_vs_stats *stats);
+/* Process estimators in multiple timer ticks (20/50/100, see ktrow) */
+#define IPVS_EST_NTICKS 50
+/* Estimation uses a 2-second period containing ticks (in jiffies) */
+#define IPVS_EST_TICK ((2 * HZ) / IPVS_EST_NTICKS)
+
+/* Limit of CPU load per kthread (8 for 12.5%), ratio of CPU capacity (1/C).
+ * Value of 4 and above ensures kthreads will take work without exceeding
+ * the CPU capacity under different circumstances.
+ */
+#define IPVS_EST_LOAD_DIVISOR 8
+
+/* Kthreads should not have work that exceeds the CPU load above 50% */
+#define IPVS_EST_CPU_KTHREADS (IPVS_EST_LOAD_DIVISOR / 2)
+
+/* Desired number of chains per timer tick (chain load factor in 100us units),
+ * 48=4.8ms of 40ms tick (12% CPU usage):
+ * 2 sec * 1000 ms in sec * 10 (100us in ms) / 8 (12.5%) / 50
+ */
+#define IPVS_EST_CHAIN_FACTOR \
+ ALIGN_DOWN(2 * 1000 * 10 / IPVS_EST_LOAD_DIVISOR / IPVS_EST_NTICKS, 8)
+
+/* Compiled number of chains per tick
+ * The defines should match cond_resched_rcu
+ */
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
+#define IPVS_EST_TICK_CHAINS IPVS_EST_CHAIN_FACTOR
+#else
+#define IPVS_EST_TICK_CHAINS 1
+#endif
+
+#if IPVS_EST_NTICKS > 127
+#error Too many timer ticks for ktrow
+#endif
+
+/* Multiple chains processed in same tick */
+struct ip_vs_est_tick_data {
+ struct hlist_head chains[IPVS_EST_TICK_CHAINS];
+ DECLARE_BITMAP(present, IPVS_EST_TICK_CHAINS);
+ DECLARE_BITMAP(full, IPVS_EST_TICK_CHAINS);
+ int chain_len[IPVS_EST_TICK_CHAINS];
+};
+
+/* Context for estimation kthread */
+struct ip_vs_est_kt_data {
+ struct netns_ipvs *ipvs;
+ struct task_struct *task; /* task if running */
+ struct ip_vs_est_tick_data __rcu *ticks[IPVS_EST_NTICKS];
+ DECLARE_BITMAP(avail, IPVS_EST_NTICKS); /* tick has space for ests */
+ unsigned long est_timer; /* estimation timer (jiffies) */
+ struct ip_vs_stats *calc_stats; /* Used for calculation */
+ int tick_len[IPVS_EST_NTICKS]; /* est count */
+ int id; /* ktid per netns */
+ int chain_max; /* max ests per tick chain */
+ int tick_max; /* max ests per tick */
+ int est_count; /* attached ests to kthread */
+ int est_max_count; /* max ests per kthread */
+ int add_row; /* row for new ests */
+ int est_row; /* estimated row */
+};
+
struct dst_entry;
struct iphdr;
struct ip_vs_conn;
@@ -953,9 +1019,17 @@ struct netns_ipvs {
struct ctl_table_header *lblcr_ctl_header;
struct ctl_table *lblcr_ctl_table;
/* ip_vs_est */
- struct list_head est_list; /* estimator list */
- spinlock_t est_lock;
- struct timer_list est_timer; /* Estimation timer */
+ struct delayed_work est_reload_work;/* Reload kthread tasks */
+ struct mutex est_mutex; /* protect kthread tasks */
+ struct hlist_head est_temp_list; /* Ests during calc phase */
+ struct ip_vs_est_kt_data **est_kt_arr; /* Array of kthread data ptrs */
+ unsigned long est_max_threads;/* Hard limit of kthreads */
+ int est_calc_phase; /* Calculation phase */
+ int est_chain_max; /* Calculated chain_max */
+ int est_kt_count; /* Allocated ptrs */
+ int est_add_ktid; /* ktid where to add ests */
+ atomic_t est_genid; /* kthreads reload genid */
+ atomic_t est_genid_done; /* applied genid */
/* ip_vs_sync */
spinlock_t sync_lock;
struct ipvs_master_sync_state *ms;
@@ -1486,10 +1560,14 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state);
void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts);
/* IPVS rate estimator prototypes (from ip_vs_est.c) */
-void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
+int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_zero_estimator(struct ip_vs_stats *stats);
void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats);
+void ip_vs_est_reload_start(struct netns_ipvs *ipvs);
+int ip_vs_est_kthread_start(struct netns_ipvs *ipvs,
+ struct ip_vs_est_kt_data *kd);
+void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd);
/* Various IPVS packet transmitters (from ip_vs_xmit.c) */
int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,