From 1c4284c7395f23cefa61a407db74cf5067aee2aa Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Thu, 21 Aug 2014 19:55:06 +0000 Subject: pthreadpool: Slightly serialize jobs Using the new msg_source program with 1.500 instances against a single msg_sink I found the msg_source process to spawn two worker threads for synchronously sending the data towards the receiving socket. This should not happen: Per destination node we only create one queue. We strictly only add pthreadpool jobs one after the other, so a single helper thread should be perfectly sufficient. It turned out that under heavy overload the main sending thread was scheduled before the thread that just had finished its send() job. So the helper thread was not able to increment the pool->num_idle variable indicating that we don't have to create a new thread when the new job is added. This patch moves the signalling write under the mutex. This means that indicating readiness via the pipe and the pool->num_idle variable happen both under the same mutex lock and thus are atomic. No superfluous threads anymore. Signed-off-by: Volker Lendecke Reviewed-by: Jeremy Allison --- source3/lib/pthreadpool/pthreadpool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/source3/lib/pthreadpool/pthreadpool.c b/source3/lib/pthreadpool/pthreadpool.c index 4436ab3289..d683578617 100644 --- a/source3/lib/pthreadpool/pthreadpool.c +++ b/source3/lib/pthreadpool/pthreadpool.c @@ -536,11 +536,11 @@ static void *pthreadpool_server(void *arg) assert(res == 0); job.fn(job.private_data); - written = write(sig_pipe, &job.id, sizeof(job.id)); res = pthread_mutex_lock(&pool->mutex); assert(res == 0); + written = write(sig_pipe, &job.id, sizeof(job.id)); if (written != sizeof(int)) { pthreadpool_server_exit(pool); pthread_mutex_unlock(&pool->mutex); -- cgit