From: David Goulet <dgoulet@efficios.com>
Date: Wed, 24 Oct 2012 16:40:59 +0000 (-0400)
Subject: Fix: Delete stream on write error in consumer
X-Git-Tag: v2.1.0-rc6~26
X-Git-Url: https://git.lttng.org./?a=commitdiff_plain;h=ab1027f48fa7e2dd29b3c85548ec42f26d06be25;p=lttng-tools.git

Fix: Delete stream on write error in consumer

Whenever a write() error occured, both on network or local trace file,
the consumer thread just died considering the error a fatal one.

This commit fixes that by simply deleting the stream, removing it from
the poll set of the thread and freeing it.

Furthermore, on a write() error, a SIGPIPE is usually raised if the FD
is invalid. The consumer is catching this signal but was initiating a
should exit action thus ultimately cleaning all threads. We now still
catch SIGPIPE but don't set the should quit flag so normal cleanup can
be done by the threads.

Signed-off-by: David Goulet <dgoulet@efficios.com>
---

diff --git a/src/bin/lttng-consumerd/lttng-consumerd.c b/src/bin/lttng-consumerd/lttng-consumerd.c
index 1cc11d2d5..4d02c8427 100644
--- a/src/bin/lttng-consumerd/lttng-consumerd.c
+++ b/src/bin/lttng-consumerd/lttng-consumerd.c
@@ -79,6 +79,14 @@ static void sighandler(int sig)
 		return;
 	}
 
+	/*
+	 * Ignore SIGPIPE because it should not stop the consumer whenever a
+	 * SIGPIPE is catched through a FD operation.
+	 */
+	if (sig == SIGPIPE) {
+		return;
+	}
+
 	lttng_consumer_should_exit(ctx);
 }
 
diff --git a/src/common/consumer.c b/src/common/consumer.c
index 295e7be5d..53c618067 100644
--- a/src/common/consumer.c
+++ b/src/common/consumer.c
@@ -923,6 +923,8 @@ void lttng_consumer_should_exit(struct lttng_consumer_local_data *ctx)
 	if (ret < 0) {
 		PERROR("write consumer quit");
 	}
+
+	DBG("Consumer flag that it should quit");
 }
 
 void lttng_consumer_sync_trace_file(struct lttng_consumer_stream *stream,
@@ -1084,6 +1086,8 @@ void lttng_consumer_destroy(struct lttng_consumer_local_data *ctx)
 {
 	int ret;
 
+	DBG("Consumer destroying it. Closing everything.");
+
 	ret = close(ctx->consumer_error_socket);
 	if (ret) {
 		PERROR("close");
@@ -1916,8 +1920,9 @@ restart:
 				len = ctx->on_buffer_ready(stream, ctx);
 				/* It's ok to have an unavailable sub-buffer */
 				if (len < 0 && len != -EAGAIN && len != -ENODATA) {
-					rcu_read_unlock();
-					goto end;
+					/* Clean up stream from consumer and free it. */
+					lttng_poll_del(&events, stream->wait_fd);
+					consumer_del_metadata_stream(stream, metadata_ht);
 				} else if (len > 0) {
 					stream->data_read = 1;
 				}
@@ -2084,7 +2089,8 @@ void *consumer_thread_data_poll(void *data)
 				len = ctx->on_buffer_ready(local_stream[i], ctx);
 				/* it's ok to have an unavailable sub-buffer */
 				if (len < 0 && len != -EAGAIN && len != -ENODATA) {
-					goto end;
+					/* Clean the stream and free it. */
+					consumer_del_stream(local_stream[i], data_ht);
 				} else if (len > 0) {
 					local_stream[i]->data_read = 1;
 				}
@@ -2107,7 +2113,8 @@ void *consumer_thread_data_poll(void *data)
 				len = ctx->on_buffer_ready(local_stream[i], ctx);
 				/* it's ok to have an unavailable sub-buffer */
 				if (len < 0 && len != -EAGAIN && len != -ENODATA) {
-					goto end;
+					/* Clean the stream and free it. */
+					consumer_del_stream(local_stream[i], data_ht);
 				} else if (len > 0) {
 					local_stream[i]->data_read = 1;
 				}