From f86dcc5aa8c7908f2c287e7a211228df599e3e71 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Oct 2009 00:37:59 +0000 Subject: udp: dynamically size hash tables at boot time UDP_HTABLE_SIZE was initialy defined to 128, which is a bit small for several setups. 4000 active UDP sockets -> 32 sockets per chain in average. An incoming frame has to lookup all sockets to find best match, so long chains hurt latency. Instead of a fixed size hash table that cant be perfect for every needs, let UDP stack choose its table size at boot time like tcp/ip route, using alloc_large_system_hash() helper Add an optional boot parameter, uhash_entries=x so that an admin can force a size between 256 and 65536 if needed, like thash_entries and rhash_entries. dmesg logs two new lines : [ 0.647039] UDP hash table entries: 512 (order: 0, 4096 bytes) [ 0.647099] UDP Lite hash table entries: 512 (order: 0, 4096 bytes) Maximal size on 64bit arches would be 65536 slots, ie 1 MBytes for non debugging spinlocks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/udp.c | 91 ++++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 66 insertions(+), 25 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6ec6a8a4a224..194bcdc6d9fc 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -106,7 +106,7 @@ #include #include "udp_impl.h" -struct udp_table udp_table; +struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); int sysctl_udp_mem[3] __read_mostly; @@ -121,14 +121,16 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); -#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE) +#define MAX_UDP_PORTS 65536 +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2), + unsigned int log) { struct sock *sk2; struct hlist_nulls_node *node; @@ -142,8 +144,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (*saddr_comp)(sk, sk2)) { if (bitmap) - __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE, - bitmap); + __set_bit(sk2->sk_hash >> log, bitmap); else return 1; } @@ -180,13 +181,15 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ - rand = (rand | 1) * UDP_HTABLE_SIZE; - for (last = first + UDP_HTABLE_SIZE; first != last; first++) { - hslot = &udptable->hash[udp_hashfn(net, first)]; + rand = (rand | 1) * (udptable->mask + 1); + for (last = first + udptable->mask + 1; + first != last; + first++) { + hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, - saddr_comp); + saddr_comp, udptable->log); snum = first; /* @@ -196,7 +199,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, */ do { if (low <= snum && snum <= high && - !test_bit(snum / UDP_HTABLE_SIZE, bitmap)) + !test_bit(snum >> udptable->log, bitmap)) goto found; snum += rand; } while (snum != first); @@ -204,9 +207,10 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, } goto fail; } else { - hslot = &udptable->hash[udp_hashfn(net, snum)]; + hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); - if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp)) + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, + saddr_comp, 0)) goto fail_unlock; } found: @@ -283,7 +287,7 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); + unsigned int hash = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; @@ -1013,8 +1017,8 @@ void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; - unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash); - struct udp_hslot *hslot = &udptable->hash[hash]; + struct udp_hslot *hslot = udp_hashslot(udptable, sock_net(sk), + sk->sk_hash); spin_lock_bh(&hslot->lock); if (sk_nulls_del_node_init_rcu(sk)) { @@ -1169,7 +1173,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_table *udptable) { struct sock *sk; - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; spin_lock(&hslot->lock); @@ -1609,9 +1613,14 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { + for (state->bucket = start; state->bucket <= state->udp_table->mask; + ++state->bucket) { struct hlist_nulls_node *node; struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + + if (hlist_nulls_empty(&hslot->head)) + continue; + spin_lock_bh(&hslot->lock); sk_nulls_for_each(sk, node, &hslot->head) { if (!net_eq(sock_net(sk), net)) @@ -1636,7 +1645,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); if (!sk) { - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } @@ -1656,7 +1665,7 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) static void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; - state->bucket = UDP_HTABLE_SIZE; + state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1678,7 +1687,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } @@ -1738,7 +1747,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, __u16 destp = ntohs(inet->dport); __u16 srcp = ntohs(inet->sport); - seq_printf(f, "%4d: %08X:%04X %08X:%04X" + seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), @@ -1804,11 +1813,43 @@ void udp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ -void __init udp_table_init(struct udp_table *table) +static __initdata unsigned long uhash_entries; +static int __init set_uhash_entries(char *str) { - int i; + if (!str) + return 0; + uhash_entries = simple_strtoul(str, &str, 0); + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) + uhash_entries = UDP_HTABLE_SIZE_MIN; + return 1; +} +__setup("uhash_entries=", set_uhash_entries); - for (i = 0; i < UDP_HTABLE_SIZE; i++) { +void __init udp_table_init(struct udp_table *table, const char *name) +{ + unsigned int i; + + if (!CONFIG_BASE_SMALL) + table->hash = alloc_large_system_hash(name, + sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + 64 * 1024); + /* + * Make sure hash table has the minimum size + */ + if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { + table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * + sizeof(struct udp_hslot), GFP_KERNEL); + if (!table->hash) + panic(name); + table->log = ilog2(UDP_HTABLE_SIZE_MIN); + table->mask = UDP_HTABLE_SIZE_MIN - 1; + } + for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); spin_lock_init(&table->hash[i].lock); } @@ -1818,7 +1859,7 @@ void __init udp_init(void) { unsigned long nr_pages, limit; - udp_table_init(&udp_table); + udp_table_init(&udp_table, "UDP"); /* Set the pressure threshold up by the same strategy of TCP. It is a * fraction of global memory that is up to 1/2 at 256 MB, decreasing * toward zero with the amount of memory, with a floor of 128 pages. -- cgit v1.2.2