ipvs: add conn_lfactor and svc_lfactor sysctl vars

Allow the default load factor for the connection and service tables
to be configured.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Florian Westphal <fw@strlen.de>

diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
index 3fb5fa142eef1d0346906927ded31bcc5ccf1da1..a556439f8be7b8c12eb4fad2a448407e14686643 100644 (file)
--- a/Documentation/networking/ipvs-sysctl.rst
+++ b/Documentation/networking/ipvs-sysctl.rst
@@ -29,6 +29,33 @@ backup_only - BOOLEAN
        If set, disable the director function while the server is
        in backup mode to avoid packet loops for DR/TUN methods.
 
+conn_lfactor - INTEGER
+       Possible values: -8 (larger table) .. 8 (smaller table)
+
+       Default: -4
+
+       Controls the sizing of the connection hash table based on the
+       load factor (number of connections per table buckets):
+
+               2^conn_lfactor = nodes / buckets
+
+       As result, the table grows if load increases and shrinks when
+       load decreases in the range of 2^8 - 2^conn_tab_bits (module
+       parameter).
+       The value is a shift count where negative values select
+       buckets = (connection hash nodes << -value) while positive
+       values select buckets = (connection hash nodes >> value). The
+       negative values reduce the collisions and reduce the time for
+       lookups but increase the table size. Positive values will
+       tolerate load above 100% when using smaller table is
+       preferred with the cost of more collisions. If using NAT
+       connections consider decreasing the value with one because
+       they add two nodes in the hash table.
+
+       Example:
+       -4: grow if load goes above 6% (buckets = nodes * 16)
+       2: grow if load goes above 400% (buckets = nodes / 4)
+
 conn_reuse_mode - INTEGER
        1 - default
 
@@ -219,6 +246,16 @@ secure_tcp - INTEGER
        The value definition is the same as that of drop_entry and
        drop_packet.
 
+svc_lfactor - INTEGER
+       Possible values: -8 (larger table) .. 8 (smaller table)
+
+       Default: -3
+
+       Controls the sizing of the service hash table based on the
+       load factor (number of services per table buckets). The table
+       will grow and shrink in the range of 2^4 - 2^20.
+       See conn_lfactor for explanation.
+
 sync_threshold - vector of 2 INTEGERs: sync_threshold, sync_period
        default 3 50
 

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index fb1df61edfdd5f67bd83cb08600754920f90396d..6632daa87ded1c448a47bb79d9fa190bd4937553 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2445,6 +2445,60 @@ static int ipvs_proc_run_estimation(const struct ctl_table *table, int write,
        return ret;
 }
 
+static int ipvs_proc_conn_lfactor(const struct ctl_table *table, int write,
+                                 void *buffer, size_t *lenp, loff_t *ppos)
+{
+       struct netns_ipvs *ipvs = table->extra2;
+       int *valp = table->data;
+       int val = *valp;
+       int ret;
+
+       struct ctl_table tmp_table = {
+               .data = &val,
+               .maxlen = sizeof(int),
+       };
+
+       ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+       if (write && ret >= 0) {
+               if (val < -8 || val > 8) {
+                       ret = -EINVAL;
+               } else {
+                       *valp = val;
+                       if (rcu_access_pointer(ipvs->conn_tab))
+                               mod_delayed_work(system_unbound_wq,
+                                                &ipvs->conn_resize_work, 0);
+               }
+       }
+       return ret;
+}
+
+static int ipvs_proc_svc_lfactor(const struct ctl_table *table, int write,
+                                void *buffer, size_t *lenp, loff_t *ppos)
+{
+       struct netns_ipvs *ipvs = table->extra2;
+       int *valp = table->data;
+       int val = *valp;
+       int ret;
+
+       struct ctl_table tmp_table = {
+               .data = &val,
+               .maxlen = sizeof(int),
+       };
+
+       ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
+       if (write && ret >= 0) {
+               if (val < -8 || val > 8) {
+                       ret = -EINVAL;
+               } else {
+                       *valp = val;
+                       if (rcu_access_pointer(ipvs->svc_table))
+                               mod_delayed_work(system_unbound_wq,
+                                                &ipvs->svc_resize_work, 0);
+               }
+       }
+       return ret;
+}
+
 /*
  *     IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
  *     Do not change order or insert new entries without
@@ -2633,6 +2687,18 @@ static struct ctl_table vs_vars[] = {
                .mode           = 0644,
                .proc_handler   = ipvs_proc_est_nice,
        },
+       {
+               .procname       = "conn_lfactor",
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = ipvs_proc_conn_lfactor,
+       },
+       {
+               .procname       = "svc_lfactor",
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = ipvs_proc_svc_lfactor,
+       },
 #ifdef CONFIG_IP_VS_DEBUG
        {
                .procname       = "debug_level",
@@ -4853,6 +4919,16 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
        tbl[idx].extra2 = ipvs;
        tbl[idx++].data = &ipvs->sysctl_est_nice;
 
+       if (unpriv)
+               tbl[idx].mode = 0444;
+       tbl[idx].extra2 = ipvs;
+       tbl[idx++].data = &ipvs->sysctl_conn_lfactor;
+
+       if (unpriv)
+               tbl[idx].mode = 0444;
+       tbl[idx].extra2 = ipvs;
+       tbl[idx++].data = &ipvs->sysctl_svc_lfactor;
+
 #ifdef CONFIG_IP_VS_DEBUG
        /* Global sysctls must be ro in non-init netns */
        if (!net_eq(net, &init_net))