72a3effaf6
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>
103 lines
2.9 KiB
C
103 lines
2.9 KiB
C
/*
|
|
* NET Generic infrastructure for Network protocols.
|
|
*
|
|
* Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
|
|
*
|
|
* From code originally in include/net/tcp.h
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/random.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/string.h>
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <net/request_sock.h>
|
|
|
|
/*
|
|
* Maximum number of SYN_RECV sockets in queue per LISTEN socket.
|
|
* One SYN_RECV socket costs about 80bytes on a 32bit machine.
|
|
* It would be better to replace it with a global counter for all sockets
|
|
* but then some measure against one socket starving all other sockets
|
|
* would be needed.
|
|
*
|
|
* It was 128 by default. Experiments with real servers show, that
|
|
* 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).
|
|
* Note : Dont forget somaxconn that may limit backlog too.
|
|
*/
|
|
int sysctl_max_syn_backlog = 256;
|
|
|
|
int reqsk_queue_alloc(struct request_sock_queue *queue,
|
|
unsigned int nr_table_entries)
|
|
{
|
|
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 = 3;
|
|
(1 << lopt->max_qlen_log) < nr_table_entries;
|
|
lopt->max_qlen_log++);
|
|
|
|
get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
|
|
rwlock_init(&queue->syn_wait_lock);
|
|
queue->rskq_accept_head = NULL;
|
|
lopt->nr_table_entries = nr_table_entries;
|
|
|
|
write_lock_bh(&queue->syn_wait_lock);
|
|
queue->listen_opt = lopt;
|
|
write_unlock_bh(&queue->syn_wait_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
EXPORT_SYMBOL(reqsk_queue_alloc);
|
|
|
|
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) {
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < lopt->nr_table_entries; i++) {
|
|
struct request_sock *req;
|
|
|
|
while ((req = lopt->syn_table[i]) != NULL) {
|
|
lopt->syn_table[i] = req->dl_next;
|
|
lopt->qlen--;
|
|
reqsk_free(req);
|
|
}
|
|
}
|
|
}
|
|
|
|
BUG_TRAP(lopt->qlen == 0);
|
|
if (lopt_size > PAGE_SIZE)
|
|
vfree(lopt);
|
|
else
|
|
kfree(lopt);
|
|
}
|
|
|
|
EXPORT_SYMBOL(reqsk_queue_destroy);
|