This is not intented to go to mainline, provided just for those
who are interested enough about the algorithm internals during
a test.
Signed-off-by: Ilpo Järvinen <[EMAIL PROTECTED]>
---
include/linux/snmp.h | 19 +++++++++++++++++++
net/ipv4/proc.c | 19 +++++++++++++++++++
net/ipv4/tcp_input.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++--
3 files changed, 86 insertions(+), 2 deletions(-)
diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 89f0c2b..fbcd62d 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -214,6 +214,25 @@ enum
LINUX_MIB_TCPDSACKIGNOREDOLD, /* TCPSACKIgnoredOld */
LINUX_MIB_TCPDSACKIGNOREDNOUNDO, /* TCPSACKIgnoredNoUndo */
LINUX_MIB_TCPSPURIOUSRTOS, /* TCPSpuriousRTOs */
+ LINUX_MIB_TCP_SACK0,
+ LINUX_MIB_TCP_SACK1,
+ LINUX_MIB_TCP_SACK2,
+ LINUX_MIB_TCP_SACK3,
+ LINUX_MIB_TCP_SACK4,
+ LINUX_MIB_TCP_WALKEDSKBS,
+ LINUX_MIB_TCP_WALKEDDSACKS,
+ LINUX_MIB_TCP_SKIPPEDSKBS,
+ LINUX_MIB_TCP_NOCACHE,
+ LINUX_MIB_TCP_HEADWALK,
+ LINUX_MIB_TCP_FULLSKIP,
+ LINUX_MIB_TCP_TAILSKIP,
+ LINUX_MIB_TCP_HEADSKIP_TOHIGH,
+ LINUX_MIB_TCP_TAIL_TOHIGH,
+ LINUX_MIB_TCP_HEADSKIP,
+ LINUX_MIB_TCP_NEWSKIP,
+ LINUX_MIB_TCP_FULLWALK,
+ LINUX_MIB_TCP_TAILWALK,
+ LINUX_MIB_TCP_CACHEREMAINING,
__LINUX_MIB_MAX
};
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index ce34b28..a5e842d 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -227,6 +227,25 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD),
SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO),
SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS),
+ SNMP_MIB_ITEM("TCP_SACK0", LINUX_MIB_TCP_SACK0),
+ SNMP_MIB_ITEM("TCP_SACK1", LINUX_MIB_TCP_SACK1),
+ SNMP_MIB_ITEM("TCP_SACK2", LINUX_MIB_TCP_SACK2),
+ SNMP_MIB_ITEM("TCP_SACK3", LINUX_MIB_TCP_SACK3),
+ SNMP_MIB_ITEM("TCP_SACK4", LINUX_MIB_TCP_SACK4),
+ SNMP_MIB_ITEM("TCP_WALKEDSKBS", LINUX_MIB_TCP_WALKEDSKBS),
+ SNMP_MIB_ITEM("TCP_WALKEDDSACKS", LINUX_MIB_TCP_WALKEDDSACKS),
+ SNMP_MIB_ITEM("TCP_SKIPPEDSKBS", LINUX_MIB_TCP_SKIPPEDSKBS),
+ SNMP_MIB_ITEM("TCP_NOCACHE", LINUX_MIB_TCP_NOCACHE),
+ SNMP_MIB_ITEM("TCP_FULLWALK", LINUX_MIB_TCP_FULLWALK),
+ SNMP_MIB_ITEM("TCP_HEADWALK", LINUX_MIB_TCP_HEADWALK),
+ SNMP_MIB_ITEM("TCP_TAILWALK", LINUX_MIB_TCP_TAILWALK),
+ SNMP_MIB_ITEM("TCP_FULLSKIP", LINUX_MIB_TCP_FULLSKIP),
+ SNMP_MIB_ITEM("TCP_TAILSKIP", LINUX_MIB_TCP_TAILSKIP),
+ SNMP_MIB_ITEM("TCP_HEADSKIP", LINUX_MIB_TCP_HEADSKIP),
+ SNMP_MIB_ITEM("TCP_HEADSKIP_TOHIGH", LINUX_MIB_TCP_HEADSKIP_TOHIGH),
+ SNMP_MIB_ITEM("TCP_TAIL_TOHIGH", LINUX_MIB_TCP_TAIL_TOHIGH),
+ SNMP_MIB_ITEM("TCP_NEWSKIP", LINUX_MIB_TCP_NEWSKIP),
+ SNMP_MIB_ITEM("TCP_CACHEREMAINING", LINUX_MIB_TCP_CACHEREMAINING),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5833b01..87ab327 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1370,6 +1370,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff
*skb, struct sock *sk,
*flag |= tcp_sacktag_one(skb, tp, reord, dup_sack,
*fack_count);
*fack_count += tcp_skb_pcount(skb);
+
+ NET_INC_STATS_BH(LINUX_MIB_TCP_WALKEDSKBS);
+ if (dup_sack)
+ NET_INC_STATS_BH(LINUX_MIB_TCP_WALKEDDSACKS);
}
return skb;
}
@@ -1386,6 +1390,8 @@ static struct sk_buff *tcp_sacktag_skip(struct sk_buff
*skb, struct sock *sk,
if (before(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
break;
+
+ NET_INC_STATS_BH(LINUX_MIB_TCP_SKIPPEDSKBS);
}
return skb;
}
@@ -1434,6 +1440,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
int fack_count;
int i, j;
int first_sack_index;
+ int fullwalk = 1;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
@@ -1523,6 +1530,17 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
cache++;
}
+ switch (used_sacks) {
+ case 0: NET_INC_STATS_BH(LINUX_MIB_TCP_SACK0); break;
+ case 1: NET_INC_STATS_BH(LINUX_MIB_TCP_SACK1); break;
+ case 2: NET_INC_STATS_BH(LINUX_MIB_TCP_SACK2); break;
+ case 3: NET_INC_STATS_BH(LINUX_MIB_TCP_SACK3); break;
+ case 4: NET_INC_STATS_BH(LINUX_MIB_TCP_SACK4); break;
+ }
+
+ if (!tcp_sack_cache_ok(tp, cache))
+ NET_INC_STATS_BH(LINUX_MIB_TCP_NOCACHE);
+
while (i < used_sacks) {
u32 start_seq = sp[i].start_seq;
u32 end_seq = sp[i].end_seq;
@@ -1544,6 +1562,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
/* Can skip some work by looking recv_sack_cache? */
if (tcp_sack_cache_ok(tp, cache) && !dup_sack &&
after(end_seq, cache->start_seq)) {
+ int headskip = 0;
+
+ fullwalk = 0;
/* Head todo? */
if (before(start_seq, cache->start_seq)) {
@@ -1551,12 +1572,18 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
skb = tcp_sacktag_walk(skb, sk, next_dup,
start_seq,
cache->start_seq,
dup_sack,
&fack_count, &reord,
&flag);
- }
+ NET_INC_STATS_BH(LINUX_MIB_TCP_HEADWALK);
+ } else
+ headskip = 1;
/* Rest of the block already fully processed? */
if (!after(end_seq, cache->end_seq)) {
skb = tcp_maybe_skipping_dsack(skb, sk,
next_dup, cache->end_seq,
&fack_count,
&reord, &flag);
+ if (headskip)
+
NET_INC_STATS_BH(LINUX_MIB_TCP_FULLSKIP);
+ else
+
NET_INC_STATS_BH(LINUX_MIB_TCP_TAILSKIP);
goto advance_sp;
}
@@ -1571,24 +1598,37 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
skb = tcp_write_queue_next(sk,
tp->highest_sack);
fack_count = tp->fackets_out;
cache++;
+
+ if (headskip)
+
NET_INC_STATS_BH(LINUX_MIB_TCP_HEADSKIP_TOHIGH);
+ else
+
NET_INC_STATS_BH(LINUX_MIB_TCP_TAIL_TOHIGH);
goto walk;
}
skb = tcp_sacktag_skip(skb, sk, cache->end_seq);
/* Check overlap against next cached too (past this one
already) */
cache++;
+
+ if (headskip)
+ NET_INC_STATS_BH(LINUX_MIB_TCP_HEADSKIP);
continue;
}
if (!before(start_seq, tcp_highest_sack_seq(tp))) {
skb = tcp_write_queue_next(sk, tp->highest_sack);
fack_count = tp->fackets_out;
+ NET_INC_STATS_BH(LINUX_MIB_TCP_NEWSKIP);
}
skb = tcp_sacktag_skip(skb, sk, start_seq);
walk:
skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq,
dup_sack, &fack_count, &reord, &flag);
+ if (fullwalk)
+ NET_INC_STATS_BH(LINUX_MIB_TCP_FULLWALK);
+ else
+ NET_INC_STATS_BH(LINUX_MIB_TCP_TAILWALK);
advance_sp:
/* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct
@@ -1598,15 +1638,21 @@ advance_sp:
flag &= ~FLAG_ONLY_ORIG_SACKED;
i++;
+ fullwalk = 1;
}
+ if (tcp_sack_cache_ok(tp, cache))
+ NET_INC_STATS_BH(LINUX_MIB_TCP_CACHEREMAINING);
+
/* Clear the head of the cache sack blocks so we can skip it next time
*/
for (i = 0; i < ARRAY_SIZE(tp->recv_sack_cache) - used_sacks; i++) {
tp->recv_sack_cache[i].start_seq = 0;
tp->recv_sack_cache[i].end_seq = 0;
}
- for (j = 0; j < used_sacks; j++)
+ for (j = 0; j < used_sacks; j++) {
+ WARN_ON(i >= ARRAY_SIZE(tp->recv_sack_cache));
tp->recv_sack_cache[i++] = sp[j];
+ }
flag |= tcp_mark_lost_retrans(sk);
--
1.5.0.6
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
