One of our customers recently merged some new systems into a large, existing cluster. They requested a mechanism to prevent opensm from sweeping while the new equipment was being added to the IB fabric, and then resume sweeping once they felt confident that the newly added (sub)fabric was correctly cabled, and fully functional. They used the following patch.
Would it be worth adding this (or something with similar functionality) to opensm? Signed-off-by: Dale Talcott <[email protected]> Signed-off-by: Arthur Kepner <[email protected]> --- main.c | 16 ++++++++++++++++ osm_state_mgr.c | 9 ++++++++- osm_trap_rcv.c | 40 ++++++++++++++++++++++++---------------- 3 files changed, 48 insertions(+), 17 deletions(-) diff --git a/opensm/opensm/main.c b/opensm/opensm/main.c index 0093aa7..c3d71bc 100644 --- a/opensm/opensm/main.c +++ b/opensm/opensm/main.c @@ -86,6 +86,12 @@ static void mark_usr1_flag(int signum) osm_usr1_flag = 1; } +int sweeping = 1; +static void toggle_sweeping(int signum) +{ + sweeping = !sweeping; +} + static sigset_t saved_sigset; static void block_signals() @@ -99,6 +105,7 @@ static void block_signals() #ifndef HAVE_OLD_LINUX_THREADS sigaddset(&set, SIGUSR1); #endif + sigaddset(&set, SIGUSR2); pthread_sigmask(SIG_SETMASK, &set, &saved_sigset); } @@ -118,6 +125,8 @@ static void setup_signals() act.sa_handler = mark_usr1_flag; sigaction(SIGUSR1, &act, NULL); #endif + act.sa_handler = toggle_sweeping; + sigaction(SIGUSR2, &act, NULL); pthread_sigmask(SIG_SETMASK, &saved_sigset, NULL); } @@ -498,6 +507,7 @@ static int daemonize(osm_opensm_t * osm) int osm_manager_loop(osm_subn_opt_t * p_opt, osm_opensm_t * p_osm) { int console_init_flag = 0; + int prev_sweeping = sweeping; if (is_console_enabled(p_opt)) { if (!osm_console_init(p_opt, &p_osm->console, &p_osm->log)) @@ -524,6 +534,12 @@ int osm_manager_loop(osm_subn_opt_t * p_opt, osm_opensm_t * p_osm) p_osm->subn.force_heavy_sweep = TRUE; osm_opensm_sweep(p_osm); } + if (prev_sweeping != sweeping) { + prev_sweeping = sweeping; + OSM_LOG(&p_osm->log, OSM_LOG_INFO, + "Sweeping is now %s\n", + (sweeping ? "enabled" : "disabled") ); + } } if (is_console_enabled(p_opt)) osm_console_exit(&p_osm->console, &p_osm->log); diff --git a/opensm/opensm/osm_state_mgr.c b/opensm/opensm/osm_state_mgr.c index e43463f..e8eb47b 100644 --- a/opensm/opensm/osm_state_mgr.c +++ b/opensm/opensm/osm_state_mgr.c @@ -1405,6 +1405,7 @@ static void do_process_mgrp_queue(osm_sm_t * sm) void osm_state_mgr_process(IN osm_sm_t * sm, IN osm_signal_t signal) { + extern int sweeping; CL_ASSERT(sm); OSM_LOG_ENTER(sm->p_log); @@ -1415,7 +1416,13 @@ void osm_state_mgr_process(IN osm_sm_t * sm, IN osm_signal_t signal) switch (signal) { case OSM_SIGNAL_SWEEP: - do_sweep(sm); + if (!sweeping) + OSM_LOG(sm->p_log, OSM_LOG_DEBUG, "sweeping disabled - " + "ignoring signal %s in state %s\n", + osm_get_sm_signal_str(signal), + osm_get_sm_mgr_state_str(sm->p_subn->sm_state)); + else + do_sweep(sm); break; case OSM_SIGNAL_IDLE_TIME_PROCESS_REQUEST: do_process_mgrp_queue(sm); diff --git a/opensm/opensm/osm_trap_rcv.c b/opensm/opensm/osm_trap_rcv.c index bf13239..42e9b32 100644 --- a/opensm/opensm/osm_trap_rcv.c +++ b/opensm/opensm/osm_trap_rcv.c @@ -332,6 +332,7 @@ static void trap_rcv_process_request(IN osm_sm_t * sm, boolean_t physp_change_trap = FALSE; uint64_t event_wheel_timeout = OSM_DEFAULT_TRAP_SUPRESSION_TIMEOUT; boolean_t run_heavy_sweep = FALSE; + extern int sweeping; OSM_LOG_ENTER(sm->p_log); @@ -515,23 +516,30 @@ static void trap_rcv_process_request(IN osm_sm_t * sm, check_sweep: /* do a sweep if we received a trap */ if (sm->p_subn->opt.sweep_on_trap) { - /* if this is trap number 128 or run_heavy_sweep is TRUE - - update the force_heavy_sweep flag of the subnet. - Sweep also on traps 144 - these traps signal a change of - certain port capabilities. - TODO: In the future this can be changed to just getting - PortInfo on this port instead of sweeping the entire subnet. */ - if (ib_notice_is_generic(p_ntci) && - (cl_ntoh16(p_ntci->g_or_v.generic.trap_num) == 128 || - cl_ntoh16(p_ntci->g_or_v.generic.trap_num) == 144 || - run_heavy_sweep)) { - OSM_LOG(sm->p_log, OSM_LOG_VERBOSE, - "Forcing heavy sweep. Received trap:%u\n", - cl_ntoh16(p_ntci->g_or_v.generic.trap_num)); - - sm->p_subn->force_heavy_sweep = TRUE; + if (!sweeping) { + OSM_LOG(sm->p_log, OSM_LOG_DEBUG, + "sweeping disabled - ignoring trap %u\n", + cl_ntoh16(p_ntci->g_or_v.generic.trap_num)); + } else { + /* if this is trap number 128 or run_heavy_sweep is + TRUE - update the force_heavy_sweep flag of the + subnet. Sweep also on traps 144 - these traps signal + a change of certain port capabilities. + TODO: In the future this can be changed to just + getting PortInfo on this port instead of sweeping + the entire subnet. */ + if (ib_notice_is_generic(p_ntci) && + (cl_ntoh16(p_ntci->g_or_v.generic.trap_num) == 128 || + cl_ntoh16(p_ntci->g_or_v.generic.trap_num) == 144 || + run_heavy_sweep)) { + OSM_LOG(sm->p_log, OSM_LOG_VERBOSE, + "Forcing heavy sweep. Received trap:%u\n", + cl_ntoh16(p_ntci->g_or_v.generic.trap_num)); + + sm->p_subn->force_heavy_sweep = TRUE; + } + osm_sm_signal(sm, OSM_SIGNAL_SWEEP); } - osm_sm_signal(sm, OSM_SIGNAL_SWEEP); } /* If we reached here due to trap 129/130/131 - do not need to do -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
