[PATCH] post 3.1 xlator/io-threads instability on NetBSD

[manu@xxxxxxxxxx (Emmanuel Dreyfus)]

Emmanuel Dreyfus <manu@xxxxxxxxxx> wrote:

> It seems there have been some refactoring of xlatorx/io-threads since 3.1.
> It does not use sem_timedwait() anymore, that was replaced by 
> pthread_cond_timedwait(). 

Here is the fix. You were quite lucky that Linux managed to get it
working.

--- xlators/performance/io-threads/src/io-threads.c.orig
+++ xlators/performance/io-threads/src/io-threads.c
@@ -2181,8 +2181,20 @@
                         "out of memory");
                 goto out;
         }
 
+       if ((ret = pthread_cond_init(&conf->cond, NULL)) != 0) {
+                gf_log (this->name, GF_LOG_ERROR,
+                        "pthread_cond_init failed (%d)", ret);
+                goto out;
+       }
+
+       if ((ret = pthread_mutex_init(&conf->mutex, NULL)) != 0) {
+                gf_log (this->name, GF_LOG_ERROR,
+                        "pthread_mutex_init failed (%d)", ret);
+                goto out;
+       }
+
         set_stack_size (conf);
 
         thread_count = IOT_DEFAULT_THREADS;
 


-- 
Emmanuel Dreyfus
http://hcpnet.free.fr/pubz
manu@xxxxxxxxxx