Skip to contentSkip to conversation

Fix: UST subbuffers silently dropped on moderate trace traffic

PATCH Jérémie Galarneau 1 participant 1 message Nov 18, 2014 1 message not in the archive

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

Good catch! Merged in master and all stable branches down to 2.4.

Jérémie

Quoted 41 lines · Mathieu Desnoyers

Well, it looks like we really screwed up on this one.

lttng-tools commit 02b3d1769d5f8a33e4109b1e681141c9295dfda6 introduced an important regression for lttng-ust tracing in the consumer daemon:
after reading a sub-buffer, a check has been added to see whether there are more sub-buffers available to read, and if it is the case, it ensures the wakeup pipe will be awakened again.

The issue lies in the use of ustctl_put_next_subbuf() in this check. This acts as if the sub-buffer has been read, when in reality it has not been read. It therefore trashes the data contained by this sub-buffer.

This check should use ustctl_put_subbuf(), which does not move the consumer position.

This is a severe bug, and the fix needs to be applied to stable-2.6, stable-2.5, and stable-2.4.

Fixes #861

---
 src/common/ust-consumer/ust-consumer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
src/common/ust-consumer/ust-consumer.c +1 -2
index 52b6979..24ba387 100644
@@ -1882,7 +1882,7 @@ static int notify_if_more_data(struct lttng_consumer_stream *stream,
                goto end;
        }
 
-       ret = ustctl_put_next_subbuf(ustream);
+       ret = ustctl_put_subbuf(ustream);
        assert(!ret);
 
        /* This stream still has data. Flag it and wake up the data thread. */
--

2.1.1

Signature · 8 lines
Jérémie Galarneau
EfficiOS Inc.
http://www.efficios.com

_______________________________________________
lttng-dev mailing list
[email protected]
http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev