Hi Ira,
On 16:53 Tue 03 Jul , Ira Weiny wrote:
>
>
> When a node drops from the fabric the default behavior was to leave the node
> data in the PerfMgr DB. Add the option (with default set to TRUE) to delete
> these "inactive" or missing nodes from the DB.
>
> Signed-off-by: Ira Weiny <[email protected]>
> ---
> include/opensm/osm_perfmgr.h | 11 +++++++++++
> include/opensm/osm_perfmgr_db.h | 1 +
> include/opensm/osm_subnet.h | 1 +
> opensm/osm_console.c | 22 ++++++++++++++++------
> opensm/osm_perfmgr.c | 4 ++++
> opensm/osm_perfmgr_db.c | 13 +++++++++++++
> opensm/osm_subnet.c | 9 +++++++--
> 7 files changed, 53 insertions(+), 8 deletions(-)
>
> diff --git a/include/opensm/osm_perfmgr.h b/include/opensm/osm_perfmgr.h
> index 0e9f66f..be6f978 100644
> --- a/include/opensm/osm_perfmgr.h
> +++ b/include/opensm/osm_perfmgr.h
> @@ -143,6 +143,7 @@ typedef struct osm_perfmgr {
> monitored_node_t *remove_list;
> ib_net64_t port_guid;
> int16_t local_port;
> + int rm_nodes;
> } osm_perfmgr_t;
> /*
> * FIELDS
> @@ -180,6 +181,16 @@ inline static osm_perfmgr_state_t
> osm_perfmgr_get_state(osm_perfmgr_t * perfmgr)
> return perfmgr->state;
> }
>
> +inline static void osm_perfmgr_set_rm_nodes(osm_perfmgr_t *perfmgr,
> + int rm_nodes)
> +{
> + perfmgr->rm_nodes = rm_nodes;
> +}
> +inline static int osm_perfmgr_get_rm_nodes(osm_perfmgr_t *perfmgr)
> +{
> + return perfmgr->rm_nodes;
> +}
> +
> inline static const char *osm_perfmgr_get_state_str(osm_perfmgr_t *
> p_perfmgr)
> {
> switch (p_perfmgr->state) {
> diff --git a/include/opensm/osm_perfmgr_db.h b/include/opensm/osm_perfmgr_db.h
> index 4c7996d..8231a12 100644
> --- a/include/opensm/osm_perfmgr_db.h
> +++ b/include/opensm/osm_perfmgr_db.h
> @@ -160,6 +160,7 @@ void perfmgr_db_destroy(perfmgr_db_t * db);
> perfmgr_db_err_t perfmgr_db_create_entry(perfmgr_db_t * db, uint64_t guid,
> boolean_t esp0, uint8_t num_ports,
> char *node_name);
> +perfmgr_db_err_t perfmgr_db_delete_entry(perfmgr_db_t * db, uint64_t guid);
>
> perfmgr_db_err_t perfmgr_db_add_err_reading(perfmgr_db_t * db, uint64_t guid,
> uint8_t port,
> diff --git a/include/opensm/osm_subnet.h b/include/opensm/osm_subnet.h
> index abd2158..37314cc 100644
> --- a/include/opensm/osm_subnet.h
> +++ b/include/opensm/osm_subnet.h
> @@ -253,6 +253,7 @@ typedef struct osm_subn_opt {
> uint32_t perfmgr_max_outstanding_queries;
> boolean_t perfmgr_ignore_cas;
> char *event_db_dump_file;
> + int perfmgr_rm_nodes;
> #endif /* ENABLE_OSM_PERF_MGR */
> char *event_plugin_name;
> char *event_plugin_options;
> diff --git a/opensm/osm_console.c b/opensm/osm_console.c
> index 5b602d1..e68be25 100644
> --- a/opensm/osm_console.c
> +++ b/opensm/osm_console.c
> @@ -239,7 +239,7 @@ static void help_update_desc(FILE *out, int detail)
> static void help_perfmgr(FILE * out, int detail)
> {
> fprintf(out,
> - "perfmgr
> [enable|disable|clear_counters|dump_counters|print_counters|dump_redir|clear_redir|sweep_time[seconds]]\n");
> + "perfmgr
> [enable|disable|clear_counters|dump_counters|print_counters|dump_redir|clear_redir|set_rm_nodes|clear_rm_nodes|sweep_time[seconds]]\n");
> if (detail) {
> fprintf(out,
> "perfmgr -- print the performance manager state\n");
> @@ -257,6 +257,9 @@ static void help_perfmgr(FILE * out, int detail)
> " [dump_redir [<nodename|nodeguid>]] -- dump the
> redirection table\n");
> fprintf(out,
> " [clear_redir [<nodename|nodeguid>]] -- clear the
> redirection table\n");
> + fprintf(out,
> + " [[set|clear]_rm_nodes] -- enable/disable the
> removal of \"inactive\" nodes from the DB\n"
> + " Inactive nodes are those
> which no longer appear on the fabric\n");
> }
> }
> #endif /* ENABLE_OSM_PERF_MGR */
> @@ -1443,6 +1446,10 @@ static void perfmgr_parse(char **p_last, osm_opensm_t
> * p_osm, FILE * out)
> PERFMGR_STATE_DISABLE);
> } else if (strcmp(p_cmd, "clear_counters") == 0) {
> osm_perfmgr_clear_counters(&p_osm->perfmgr);
> + } else if (strcmp(p_cmd, "set_rm_nodes") == 0) {
> + osm_perfmgr_set_rm_nodes(&p_osm->perfmgr, 1);
> + } else if (strcmp(p_cmd, "clear_rm_nodes") == 0) {
> + osm_perfmgr_set_rm_nodes(&p_osm->perfmgr, 0);
> } else if (strcmp(p_cmd, "dump_counters") == 0) {
> p_cmd = next_token(p_last);
> if (p_cmd && (strcmp(p_cmd, "mach") == 0)) {
> @@ -1491,15 +1498,18 @@ static void perfmgr_parse(char **p_last, osm_opensm_t
> * p_osm, FILE * out)
> }
> } else {
> fprintf(out, "Performance Manager status:\n"
> - "state : %s\n"
> - "sweep state : %s\n"
> - "sweep time : %us\n"
> - "outstanding queries/max : %d/%u\n",
> + "state : %s\n"
> + "sweep state : %s\n"
> + "sweep time : %us\n"
> + "outstanding queries/max : %d/%u\n"
> + "remove missing nodes from DB : %s\n",
> osm_perfmgr_get_state_str(&p_osm->perfmgr),
> osm_perfmgr_get_sweep_state_str(&p_osm->perfmgr),
> osm_perfmgr_get_sweep_time_s(&p_osm->perfmgr),
> p_osm->perfmgr.outstanding_queries,
> - p_osm->perfmgr.max_outstanding_queries);
> + p_osm->perfmgr.max_outstanding_queries,
> + osm_perfmgr_get_rm_nodes(&p_osm->perfmgr)
> + ? "TRUE" : "FALSE");
> }
> }
> #endif /* ENABLE_OSM_PERF_MGR */
> diff --git a/opensm/osm_perfmgr.c b/opensm/osm_perfmgr.c
> index e213b3a..bec2381 100644
> --- a/opensm/osm_perfmgr.c
> +++ b/opensm/osm_perfmgr.c
> @@ -146,6 +146,9 @@ static void remove_marked_nodes(osm_perfmgr_t * pm)
> cl_qmap_remove_item(&pm->monitored_map,
> (cl_map_item_t *) (pm->remove_list));
>
> + if (pm->rm_nodes)
> + perfmgr_db_delete_entry(pm->db, pm->remove_list->guid);
> +
> if (pm->remove_list->name)
> free(pm->remove_list->name);
> free(pm->remove_list);
> @@ -1381,6 +1384,7 @@ ib_api_status_t osm_perfmgr_init(osm_perfmgr_t * pm,
> osm_opensm_t * osm,
> if (pm->state == PERFMGR_STATE_ENABLED)
> cl_timer_start(&pm->sweep_timer, pm->sweep_time_s * 1000);
>
> + pm->rm_nodes = p_opt->perfmgr_rm_nodes;
> status = IB_SUCCESS;
> Exit:
> OSM_LOG_EXIT(pm->log);
> diff --git a/opensm/osm_perfmgr_db.c b/opensm/osm_perfmgr_db.c
> index 98bf59c..b04be27 100644
> --- a/opensm/osm_perfmgr_db.c
> +++ b/opensm/osm_perfmgr_db.c
> @@ -194,6 +194,19 @@ Exit:
> return rc;
> }
>
> +perfmgr_db_err_t
> +perfmgr_db_delete_entry(perfmgr_db_t * db, uint64_t guid)
> +{
> + cl_map_item_t * rc = cl_qmap_remove(&db->pc_data, guid);
> +
> + if (rc == cl_qmap_end(&db->pc_data))
> + return(PERFMGR_EVENT_DB_GUIDNOTFOUND);
> +
> + db_node_t *pc_node = (db_node_t *)rc;
> + free_node(pc_node);
> + return(PERFMGR_EVENT_DB_SUCCESS);
> +}
> +
> /**********************************************************************
> * Dump a reading vs the previous reading to stdout
> **********************************************************************/
> diff --git a/opensm/osm_subnet.c b/opensm/osm_subnet.c
> index 662e591..06efa9c 100644
> --- a/opensm/osm_subnet.c
> +++ b/opensm/osm_subnet.c
> @@ -493,6 +493,7 @@ static const opt_rec_t opt_tbl[] = {
> { "perfmgr_max_outstanding_queries",
> OPT_OFFSET(perfmgr_max_outstanding_queries), opts_parse_uint32, NULL, 0 },
> { "perfmgr_ignore_cas", OPT_OFFSET(perfmgr_ignore_cas),
> opts_parse_boolean, NULL, 0 },
> { "event_db_dump_file", OPT_OFFSET(event_db_dump_file),
> opts_parse_charp, NULL, 0 },
> + { "perfmgr_rm_nodes", OPT_OFFSET(perfmgr_rm_nodes), opts_parse_boolean,
> NULL, 0 },
I guess that this option can be enabled to be changed on the fly, as it might
be changed also via the console.
> #endif /* ENABLE_OSM_PERF_MGR */
> { "event_plugin_name", OPT_OFFSET(event_plugin_name), opts_parse_charp,
> NULL, 0 },
> { "event_plugin_options", OPT_OFFSET(event_plugin_options),
> opts_parse_charp, NULL, 0 },
> @@ -985,6 +986,7 @@ void osm_subn_set_default_opt(IN osm_subn_opt_t * p_opt)
> OSM_PERFMGR_DEFAULT_MAX_OUTSTANDING_QUERIES;
> p_opt->perfmgr_ignore_cas = FALSE;
> p_opt->event_db_dump_file = NULL; /* use default */
> + p_opt->perfmgr_rm_nodes = TRUE;
Here you change the default behavior. Any thoughts what is the added value to
leave disconnected nodes in the DB?
> #endif /* ENABLE_OSM_PERF_MGR */
>
> p_opt->event_plugin_name = NULL;
> @@ -2009,12 +2011,15 @@ int osm_subn_output_conf(FILE *out, IN osm_subn_opt_t
> * p_opts)
> "perfmgr_sweep_time_s %u\n\n"
> "# Max outstanding queries\n"
> "perfmgr_max_outstanding_queries %u\n"
> - "perfmgr_ignore_cas %s\n\n",
> + "perfmgr_ignore_cas %s\n\n"
> + "# Remove missing nodes from DB\n"
> + "perfmgr_rm_nodes %s\n",
> p_opts->perfmgr ? "TRUE" : "FALSE",
> p_opts->perfmgr_redir ? "TRUE" : "FALSE",
> p_opts->perfmgr_sweep_time_s,
> p_opts->perfmgr_max_outstanding_queries,
> - p_opts->perfmgr_ignore_cas ? "TRUE" : "FALSE");
> + p_opts->perfmgr_ignore_cas ? "TRUE" : "FALSE",
> + p_opts->perfmgr_rm_nodes ? "TRUE" : "FALSE");
>
> fprintf(out,
> "#\n# Event DB Options\n#\n"
> --
> 1.7.1
>
> --
> 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
--
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
