diff mbox

batman-adv: Add last-seen in originator table

Message ID 1277867781-10472-1-git-send-email-linus.luessing@web.de
State Accepted, archived
Commit f4ba126cfb6b1ee9d45dcdf8641cc08dd40d086c
Headers show

Commit Message

Linus Lüssing June 30, 2010, 3:16 a.m. UTC
From: mesh-node <mesh-node@mesh-node1.(none)>

Right now, there is no easy/intuitive way to find out whether a node
might have vanished. This commit adds the time when a node was last seen
to the originator table output, so that a common user is able to tell
whether a node might have gone without having to wait PURGE_TIMEOUT
seconds until that node gets "garbe-collected".

Signed-off-by: Linus Lüssing <linus.luessing@web.de>
---
 originator.c |   22 +++++++++++++++-------
 1 files changed, 15 insertions(+), 7 deletions(-)

Comments

Sven Eckelmann June 30, 2010, 10:21 a.m. UTC | #1
Linus Lüssing wrote:
> From: mesh-node <mesh-node@mesh-node1.(none)>
I think the person who applies this should remove the From and the next empty 
line... or do you have a secret dwarf named mesh-node who works for you? :D


> Right now, there is no easy/intuitive way to find out whether a node
> might have vanished. This commit adds the time when a node was last seen
> to the originator table output, so that a common user is able to tell
> whether a node might have gone without having to wait PURGE_TIMEOUT
> seconds until that node gets "garbe-collected".

The rest looks good, but was a little bit irritated about the change of the 
table header (which makes sense to split it in two lines, but didn't expected 
that this patch does that).

Best regards,
	Sven
Linus Lüssing June 30, 2010, 6:23 p.m. UTC | #2
On Wed, Jun 30, 2010 at 12:21:08PM +0200, Sven Eckelmann wrote:
> Linus Lüssing wrote:
> > From: mesh-node <mesh-node@mesh-node1.(none)>
> I think the person who applies this should remove the From and the next empty 
> line... or do you have a secret dwarf named mesh-node who works for you? :D
Ah no, I wanted to keep this a secret... I also just noticed this
when I reread my post here, didn't notice the wrong From in
the patch file. Hope the commiter doesn't mind changing that to
not make other kernel devs jealous about my dwarf? :)
> 
> 
> > Right now, there is no easy/intuitive way to find out whether a node
> > might have vanished. This commit adds the time when a node was last seen
> > to the originator table output, so that a common user is able to tell
> > whether a node might have gone without having to wait PURGE_TIMEOUT
> > seconds until that node gets "garbe-collected".
> 
> The rest looks good, but was a little bit irritated about the change of the 
> table header (which makes sense to split it in two lines, but didn't expected 
> that this patch does that).
Oki doki, just did that in the same patch because the extra info
made the line a little bit long. Is adding a line like this fine?

"It also puts the the versioning information in an extra line, as
the first one of this debug output would otherwise get too long."
> 
> Best regards,
> 	Sven
Thanks for reviewing, Sven

Cheers, Linus
Marek Lindner July 1, 2010, 8:32 p.m. UTC | #3
On Wednesday 30 June 2010 05:16:21 Linus Lüssing wrote:
> Right now, there is no easy/intuitive way to find out whether a node
> might have vanished. This commit adds the time when a node was last seen
> to the originator table output, so that a common user is able to tell
> whether a node might have gone without having to wait PURGE_TIMEOUT
> seconds until that node gets "garbe-collected".

I applied your patch in revision 1731 with the commit message modifications you 
suggested.

Thanks,
Marek
diff mbox

Patch

diff --git a/originator.c b/originator.c
index c28c4f5..5343ab2 100644
--- a/originator.c
+++ b/originator.c
@@ -296,6 +296,8 @@  int orig_seq_print_text(struct seq_file *seq, void *offset)
 	struct orig_node *orig_node;
 	struct neigh_node *neigh_node;
 	int batman_count = 0;
+	int last_seen_secs;
+	int last_seen_msecs;
 	unsigned long flags;
 	char orig_str[ETH_STR_LEN], router_str[ETH_STR_LEN];
 
@@ -312,12 +314,13 @@  int orig_seq_print_text(struct seq_file *seq, void *offset)
 	}
 
 	rcu_read_lock();
-	seq_printf(seq, "  %-14s (%s/%i) %17s [%10s]: %20s "
-		   "... [B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%s (%s)]\n",
-		   "Originator", "#", TQ_MAX_VALUE, "Nexthop", "outgoingIF",
-		   "Potential nexthops", SOURCE_VERSION, REVISION_VERSION_STR,
+	seq_printf(seq, "[B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%s (%s)]\n",
+		   SOURCE_VERSION, REVISION_VERSION_STR,
 		   bat_priv->primary_if->dev, bat_priv->primary_if->addr_str,
 		   net_dev->name);
+	seq_printf(seq, "  %-15s %s (%s/%i) %17s [%10s]: %20s ...\n",
+		   "Originator", "last-seen", "#", TQ_MAX_VALUE, "Nexthop",
+		   "outgoingIF", "Potential nexthops");
 	rcu_read_unlock();
 
 	spin_lock_irqsave(&orig_hash_lock, flags);
@@ -334,9 +337,14 @@  int orig_seq_print_text(struct seq_file *seq, void *offset)
 
 		addr_to_string(orig_str, orig_node->orig);
 		addr_to_string(router_str, orig_node->router->addr);
-
-		seq_printf(seq, "%-17s  (%3i) %17s [%10s]:",
-			   orig_str, orig_node->router->tq_avg, router_str,
+		last_seen_secs = jiffies_to_msecs(jiffies -
+						orig_node->last_valid) / 1000;
+		last_seen_msecs = jiffies_to_msecs(jiffies -
+						orig_node->last_valid) % 1000;
+
+		seq_printf(seq, "%-17s %4i.%03is   (%3i) %17s [%10s]:",
+			   orig_str, last_seen_secs, last_seen_msecs,
+			   orig_node->router->tq_avg, router_str,
 			   orig_node->router->if_incoming->dev);
 
 		list_for_each_entry(neigh_node, &orig_node->neigh_list, list) {