diff options
| author |   Andrew Yourtchenko <ayourtch@gmail.com> | 2018-02-07 16:21:48 +0100 |
|---|---|---|
| committer |   Damjan Marion <dmarion.lists@gmail.com> | 2018-02-07 19:16:02 +0000 |
| commit | fe99a7eeb996633051942b6555b4806592dd8ad0 (patch) | |
| tree | 3e5985adff76bb9ca299a267242f7bcfef5db4c3 /src | |
| parent | d3cb7ba2ab042cbfb580ea3f01e41e98d41d0508 (diff) | |
acl-plugin: multicore: send the interrupts to thread0 too
The thread0 in some configurations can handle the traffic.
Some of the previous fixes accomodated for that, but
the interrupt sending for connection clearing
was not adapted to that, resulting in a deadlock
during clearing of all connections...
Change-Id: I32b4c7bac09c91c22b796baab843bdaf41f7045c
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
Diffstat (limited to 'src')
| -rw-r--r-- | src/plugins/acl/fa_node.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/plugins/acl/fa_node.c b/src/plugins/acl/fa_node.c index fb23a354358..3ac45c297ff 100644 --- a/src/plugins/acl/fa_node.c +++ b/src/plugins/acl/fa_node.c @@ -1516,7 +1516,7 @@ send_interrupts_to_workers (vlib_main_t * vm, acl_main_t *am) int i; /* Can't use vec_len(am->per_worker_data) since the threads might not have come up yet; */ int n_threads = vec_len(vlib_mains); - for (i = n_threads > 1 ? 1 : 0; i < n_threads; i++) { + for (i = 0; i < n_threads; i++) { send_one_worker_interrupt(vm, am, i); } } |