From: Simon Kirby <sim@netnation.com>
Date: Mon, 16 Jun 2003 15:37:14 -0700
So, which kernels shall I try? When I set the thing up I was using
2.5.70-bk14, but I am compiling 2.5.71, and I will try with your patch
above and with Alexey's.
Thanks for your profiles.
I pushed all of our current work to Linus's tree.
But for your convenience here are the routing diffs
against plain 2.5.71
# This is a BitKeeper generated patch for the following project:
# Project Name: Linux kernel tree
# This patch format is intended for GNU patch command version 2.5 or higher.
# This patch includes the following deltas:
# ChangeSet 1.1318.1.15 -> 1.1318.1.16
# net/ipv4/route.c 1.63 -> 1.64
#
# The following is the BitKeeper ChangeSet Log
# --------------------------------------------
# 03/06/16 kuznet@ms2.inr.ac.ru 1.1318.1.16
# [IPV4]: More sane rtcache behavior.
# 1) More reasonable ip_rt_gc_min_interval default
# 2) Trim less valuable entries in hash chain during
# rt_intern_hash when such chains grow too long.
# --------------------------------------------
#
diff -Nru a/net/ipv4/route.c b/net/ipv4/route.c
--- a/net/ipv4/route.c Mon Jun 16 15:45:20 2003
+++ b/net/ipv4/route.c Mon Jun 16 15:45:20 2003
@@ -111,7 +111,7 @@
int ip_rt_max_size;
int ip_rt_gc_timeout = RT_GC_TIMEOUT;
int ip_rt_gc_interval = 60 * HZ;
-int ip_rt_gc_min_interval = 5 * HZ;
+int ip_rt_gc_min_interval = HZ / 2;
int ip_rt_redirect_number = 9;
int ip_rt_redirect_load = HZ / 50;
int ip_rt_redirect_silence = ((HZ / 50) << (9 + 1));
@@ -456,6 +456,25 @@
out: return ret;
}
+/* Bits of score are:
+ * 31: very valuable
+ * 30: not quite useless
+ * 29..0: usage counter
+ */
+static inline u32 rt_score(struct rtable *rt)
+{
+ u32 score = rt->u.dst.__use;
+
+ if (rt_valuable(rt))
+ score |= (1<<31);
+
+ if (!rt->fl.iif ||
+ !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
+ score |= (1<<30);
+
+ return score;
+}
+
/* This runs via a timer and thus is always in BH context. */
static void rt_check_expire(unsigned long dummy)
{
@@ -721,6 +740,9 @@
{
struct rtable *rth, **rthp;
unsigned long now = jiffies;
+ struct rtable *cand = NULL, **candp = NULL;
+ u32 min_score = ~(u32)0;
+ int chain_length = 0;
int attempts = !in_softirq();
restart:
@@ -755,7 +777,33 @@
return 0;
}
+ if (!atomic_read(&rth->u.dst.__refcnt)) {
+ u32 score = rt_score(rth);
+
+ if (score <= min_score) {
+ cand = rth;
+ candp = rthp;
+ min_score = score;
+ }
+ }
+
+ chain_length++;
+
rthp = &rth->u.rt_next;
+ }
+
+ if (cand) {
+ /* ip_rt_gc_elasticity used to be average length of chain
+ * length, when exceeded gc becomes really aggressive.
+ *
+ * The second limit is less certain. At the moment it allows
+ * only 2 entries per bucket. We will see.
+ */
+ if (chain_length > ip_rt_gc_elasticity ||
+ (chain_length > 1 && !(min_score & (1<<31)))) {
+ *candp = cand->u.rt_next;
+ rt_free(cand);
+ }
}
/* Try to bind route to arp only if it is output
# This is a BitKeeper generated patch for the following project:
# Project Name: Linux kernel tree
# This patch format is intended for GNU patch command version 2.5 or higher.
# This patch includes the following deltas:
# ChangeSet 1.1320.1.1 -> 1.1320.1.2
# net/ipv4/route.c 1.64 -> 1.65
#
# The following is the BitKeeper ChangeSet Log
# --------------------------------------------
# 03/06/16 robert.olsson@data.slu.se 1.1320.1.2
# [IPV4]: In rt_intern_hash, reinit all state vars on branch to "restart".
# --------------------------------------------
#
diff -Nru a/net/ipv4/route.c b/net/ipv4/route.c
--- a/net/ipv4/route.c Mon Jun 16 15:46:05 2003
+++ b/net/ipv4/route.c Mon Jun 16 15:46:05 2003
@@ -739,13 +739,19 @@
static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
{
struct rtable *rth, **rthp;
- unsigned long now = jiffies;
- struct rtable *cand = NULL, **candp = NULL;
- u32 min_score = ~(u32)0;
- int chain_length = 0;
+ unsigned long now;
+ struct rtable *cand, **candp;
+ u32 min_score;
+ int chain_length;
int attempts = !in_softirq();
restart:
+ chain_length = 0;
+ min_score = ~(u32)0;
+ cand = NULL;
+ candp = NULL;
+ now = jiffies;
+
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(&rt_hash_table[hash].lock);
-
: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
