From: Patrick McHardy <kaber@trash.net>
To: netfilter-devel@lists.netfilter.org
Cc: Patrick McHardy <kaber@trash.net>
Subject: [NETFILTER 17/20]: nf_conntrack: early_drop improvement
Date: Fri, 29 Jun 2007 02:45:20 +0200 (MEST) [thread overview]
Message-ID: <20070629004418.25566.8938.sendpatchset@localhost.localdomain> (raw)
In-Reply-To: <20070629004354.25566.59266.sendpatchset@localhost.localdomain>
[NETFILTER]: nf_conntrack: early_drop improvement
When the maximum number of conntrack entries is reached and a new
one needs to be allocated, conntrack tries to drop an unassured
connection from the same hash bucket the new conntrack would hash
to. Since with a properly sized hash the average number of entries
per bucket is 1, the chances of actually finding one are not very
good. This patch makes it walk the hash until a minimum number of
8 entries are checked.
Based on patch by Vasily Averin <vvs@sw.ru>.
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
commit 7a171312164be3cc200fbc04c8c93c32dc4f0649
tree 4efac6249264b9e45e47020aafd9564ac207683b
parent 5c63a5d17f6f9e49fcdfa80e1b86c281fa496e34
author Patrick McHardy <kaber@trash.net> Fri, 29 Jun 2007 02:19:57 +0200
committer Patrick McHardy <kaber@trash.net> Fri, 29 Jun 2007 02:19:57 +0200
net/netfilter/nf_conntrack_core.c | 24 ++++++++++++++++--------
1 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index d1fc019..e76fd28 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -377,21 +377,30 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}
EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
+#define NF_CT_EVICTION_RANGE 8
+
/* There's a small race here where we may free a just-assured
connection. Too bad: we're in trouble anyway. */
-static int early_drop(struct hlist_head *chain)
+static int early_drop(unsigned int hash)
{
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct = NULL, *tmp;
struct hlist_node *n;
- int dropped = 0;
+ unsigned int i;
+ int dropped = 0, cnt = 0;
read_lock_bh(&nf_conntrack_lock);
- hlist_for_each_entry(h, n, chain, hnode) {
- tmp = nf_ct_tuplehash_to_ctrack(h);
- if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
- ct = tmp;
+ for (i = 0; i < nf_conntrack_htable_size; i++) {
+ hlist_for_each_entry(h, n, &nf_conntrack_hash[hash], hnode) {
+ tmp = nf_ct_tuplehash_to_ctrack(h);
+ if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
+ ct = tmp;
+ cnt++;
+ }
+ if (ct || cnt >= NF_CT_EVICTION_RANGE)
+ break;
+ hash = (hash + 1) % nf_conntrack_htable_size;
}
if (ct)
atomic_inc(&ct->ct_general.use);
@@ -425,8 +434,7 @@ struct nf_conn *nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
if (nf_conntrack_max
&& atomic_read(&nf_conntrack_count) > nf_conntrack_max) {
unsigned int hash = hash_conntrack(orig);
- /* Try dropping from this hash chain. */
- if (!early_drop(&nf_conntrack_hash[hash])) {
+ if (!early_drop(hash)) {
atomic_dec(&nf_conntrack_count);
if (net_ratelimit())
printk(KERN_WARNING
next prev parent reply other threads:[~2007-06-29 0:45 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-06-29 0:44 [NETFILTER 00/20]: Pending netfilter patches Patrick McHardy
2007-06-29 0:44 ` [NETFILTER 01/20]: nf_conntrack: use hlists for conntrack hash Patrick McHardy
2007-06-29 0:44 ` [NETFILTER 02/20]: nf_conntrack: remove 'ignore_conntrack' argument from nf_conntrack_find_get Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 03/20]: nf_conntrack: export hash allocation/destruction functions Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 04/20]: nf_nat: use hlists for bysource hash Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 05/20]: nf_conntrack_expect: function naming unification Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 06/20]: nf_conntrack_ftp: use nf_ct_expect_init Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 07/20]: nf_conntrack: reduce masks to a subset of tuples Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 08/20]: nf_conntrack_expect: avoid useless list walking Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 09/20]: nf_conntrack_netlink: sync expectation dumping with conntrack table dumping Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 10/20]: nf_conntrack: move expectaton related init code to nf_conntrack_expect.c Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 11/20]: nf_conntrack: use hashtable for expectations Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 12/20]: nf_conntrack_expect: convert proc functions to hash Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 13/20]: nf_conntrack_helper/nf_conntrack_netlink: convert to expectation hash Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 14/20]: nf_conntrack_expect: maintain per conntrack expectation list Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 15/20]: nf_conntrack_helper: use hashtable for conntrack helpers Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 16/20]: nf_conntrack: mark helpers __read_mostly Patrick McHardy
2007-06-29 0:45 ` Patrick McHardy [this message]
2007-06-29 0:45 ` [NETFILTER 18/20]: ipt_SAME: add to feature-removal-schedule Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 19/20]: ipt_CLUSTERIP: add compat code Patrick McHardy
2007-06-29 0:45 ` [NETFILTER 20/20]: nf_conntrack_h323: turn some printks into DEBUGPs Patrick McHardy
2007-06-29 7:43 ` Jan Engelhardt
2007-06-29 10:08 ` Patrick McHardy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20070629004418.25566.8938.sendpatchset@localhost.localdomain \
--to=kaber@trash.net \
--cc=netfilter-devel@lists.netfilter.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.