From 07bd1a22e2ae42578d2a1854de8430cd1af13227 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 26 Dec 2012 12:18:06 -0500 Subject: [PATCH] Discourage use of pthread_atfork() for call_rcu handlers Discourage use of glibc pthread_atfork() for call_rcu handlers due to its inappropriate assumptions about single-threadedness while pthread atfork handlers are executing. This results in hangs within the glibc memory allocator. Reviewed-by: Paul E. McKenney Signed-off-by: Mathieu Desnoyers --- README | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/README b/README index 83330ea..2d29c1d 100644 --- a/README +++ b/README @@ -273,7 +273,20 @@ Interaction with fork() must invoke call_rcu_before_fork() before the fork() and call_rcu_after_fork_parent() after the fork(). The child process must invoke call_rcu_after_fork_child(). - These three APIs are suitable for passing to pthread_atfork(). + Even though these three APIs are suitable for passing to + pthread_atfork(), use of pthread_atfork() is *STRONGLY + DISCOURAGED* for programs calling the glibc memory allocator + (malloc(), calloc(), free(), ...) within call_rcu callbacks. + This is due to limitations in the way glibc memory allocator + handles calls to the memory allocator from concurrent threads + while the pthread_atfork() handlers are executing. + Combining e.g.: + * call to free() from callbacks executed within call_rcu worker + threads, + * executing call_rcu atfork handlers within the glibc pthread + atfork mechanism, + will sometimes trigger interesting process hangs. This usually + hangs on a memory allocator lock within glibc. Thread Local Storage (TLS) -- 2.34.1