diff options
author | Eric Dumazet <dada1@cosmosbay.com> | 2006-11-16 02:30:37 -0800 |
---|---|---|
committer | David S. Miller <davem@sunset.davemloft.net> | 2006-12-02 21:21:44 -0800 |
commit | 72a3effaf633bcae9034b7e176bdbd78d64a71db (patch) | |
tree | b7a331527f1b15335a358f97809134f35587e57a /net/core | |
parent | 3c62f75aac7348ee262b1295cfcfeb3473f76815 (diff) | |
download | linux-3.10-72a3effaf633bcae9034b7e176bdbd78d64a71db.tar.gz linux-3.10-72a3effaf633bcae9034b7e176bdbd78d64a71db.tar.bz2 linux-3.10-72a3effaf633bcae9034b7e176bdbd78d64a71db.zip |
[NET]: Size listen hash tables using backlog hint
We currently allocate a fixed size (TCP_SYNQ_HSIZE=512) slots hash table for
each LISTEN socket, regardless of various parameters (listen backlog for
example)
On x86_64, this means order-1 allocations (might fail), even for 'small'
sockets, expecting few connections. On the contrary, a huge server wanting a
backlog of 50000 is slowed down a bit because of this fixed limit.
This patch makes the sizing of listen hash table a dynamic parameter,
depending of :
- net.core.somaxconn tunable (default is 128)
- net.ipv4.tcp_max_syn_backlog tunable (default : 256, 1024 or 128)
- backlog value given by user application (2nd parameter of listen())
For large allocations (bigger than PAGE_SIZE), we use vmalloc() instead of
kmalloc().
We still limit memory allocation with the two existing tunables (somaxconn &
tcp_max_syn_backlog). So for standard setups, this patch actually reduce RAM
usage.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/request_sock.c | 35 |
1 files changed, 25 insertions, 10 deletions
diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 79ebd75fbe4..5f0818d815e 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -15,6 +15,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/vmalloc.h> #include <net/request_sock.h> @@ -29,22 +30,31 @@ * it is absolutely not enough even at 100conn/sec. 256 cures most * of problems. This value is adjusted to 128 for very small machines * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). - * Further increasing requires to change hash table size. + * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; int reqsk_queue_alloc(struct request_sock_queue *queue, - const int nr_table_entries) + unsigned int nr_table_entries) { - const int lopt_size = sizeof(struct listen_sock) + - nr_table_entries * sizeof(struct request_sock *); - struct listen_sock *lopt = kzalloc(lopt_size, GFP_KERNEL); - + size_t lopt_size = sizeof(struct listen_sock); + struct listen_sock *lopt; + + nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); + nr_table_entries = max_t(u32, nr_table_entries, 8); + nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); + lopt_size += nr_table_entries * sizeof(struct request_sock *); + if (lopt_size > PAGE_SIZE) + lopt = __vmalloc(lopt_size, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + PAGE_KERNEL); + else + lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) return -ENOMEM; - for (lopt->max_qlen_log = 6; - (1 << lopt->max_qlen_log) < sysctl_max_syn_backlog; + for (lopt->max_qlen_log = 3; + (1 << lopt->max_qlen_log) < nr_table_entries; lopt->max_qlen_log++); get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); @@ -65,9 +75,11 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) { /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); + size_t lopt_size = sizeof(struct listen_sock) + + lopt->nr_table_entries * sizeof(struct request_sock *); if (lopt->qlen != 0) { - int i; + unsigned int i; for (i = 0; i < lopt->nr_table_entries; i++) { struct request_sock *req; @@ -81,7 +93,10 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) } BUG_TRAP(lopt->qlen == 0); - kfree(lopt); + if (lopt_size > PAGE_SIZE) + vfree(lopt); + else + kfree(lopt); } EXPORT_SYMBOL(reqsk_queue_destroy); |