[Gluster-devel] Regression: Core generated by fdl-overflow.t

[Jeff Darcy]

> In few of the regression runs, found that ./tests/features/fdl-overflow.t is
> causing a core dump.
>
> Here is the bt:
> /build/install/lib/libglusterfs.so.0(_gf_msg_backtrace_nomem+0xf2)[0x7f4905e5e3f6]
> /build/install/lib/libglusterfs.so.0(gf_print_trace+0x22b)[0x7f4905e64381]
> /build/install/sbin/glusterfsd(glusterfsd_print_trace+0x1f)[0x4099f2]
> /lib64/libc.so.6(+0x326a0)[0x7f49049f06a0]
> /build/install/lib/glusterfs/3.8dev/xlator/experimental/fdl.so(fdl_worker+0x69)[0x7f48f3395529]
> /lib64/libpthread.so.0(+0x7aa1)[0x7f490513daa1]
> /lib64/libc.so.6(clone+0x6d)[0x7f4904aa693d]
>
> Regression link:
> https://build.gluster.org/job/rackspace-regression-2GB-triggered/18986/consoleFull
>
> Can you please take a look into it?

Looks pretty straightforward.  The worker thread is actually starting to
run in the very small window between calling pthread_create and setting
this->private in fdl_init.  This is a pretty rare case (in fact I don't
think it should *ever* happen when multiple cores are present) but it's
a race nonetheless.  I'll send a patch very soon.