static bool
lnet_fault_attr_match(struct lnet_fault_attr *attr, lnet_nid_t src,
- lnet_nid_t dst, unsigned int type, unsigned int portal)
+ lnet_nid_t local_nid, lnet_nid_t dst,
+ unsigned int type, unsigned int portal)
{
if (!lnet_fault_nid_match(attr->fa_src, src) ||
- !lnet_fault_nid_match(attr->fa_dst, dst))
+ !lnet_fault_nid_match(attr->fa_dst, dst) ||
+ !lnet_fault_nid_match(attr->fa_local_nid, local_nid))
return false;
if (!(attr->fa_msg_mask & (1 << type)))
EXIT;
}
+static void
+lnet_fault_match_health(enum lnet_msg_hstatus *hstatus, __u32 mask)
+{
+ unsigned int random;
+ int choice;
+ int delta;
+ int best_delta;
+ int i;
+
+ /* assign a random failure */
+ random = cfs_rand();
+ choice = random % (LNET_MSG_STATUS_END - LNET_MSG_STATUS_OK);
+ if (choice == 0)
+ choice++;
+
+ if (mask == HSTATUS_RANDOM) {
+ *hstatus = choice;
+ return;
+ }
+
+ if (mask & (1 << choice)) {
+ *hstatus = choice;
+ return;
+ }
+
+ /* round to the closest ON bit */
+ i = HSTATUS_END;
+ best_delta = HSTATUS_END;
+ while (i > 0) {
+ if (mask & (1 << i)) {
+ delta = choice - i;
+ if (delta < 0)
+ delta *= -1;
+ if (delta < best_delta) {
+ best_delta = delta;
+ choice = i;
+ }
+ }
+ i--;
+ }
+
+ *hstatus = choice;
+}
+
/**
* check source/destination NID, portal, message type and drop rate,
* decide whether should drop this message or not
*/
static bool
drop_rule_match(struct lnet_drop_rule *rule, lnet_nid_t src,
- lnet_nid_t dst, unsigned int type, unsigned int portal)
+ lnet_nid_t local_nid, lnet_nid_t dst,
+ unsigned int type, unsigned int portal,
+ enum lnet_msg_hstatus *hstatus)
{
struct lnet_fault_attr *attr = &rule->dr_attr;
bool drop;
- if (!lnet_fault_attr_match(attr, src, dst, type, portal))
+ if (!lnet_fault_attr_match(attr, src, local_nid, dst, type, portal))
+ return false;
+
+ if (attr->u.drop.da_drop_all) {
+ CDEBUG(D_NET, "set to drop all messages\n");
+ drop = true;
+ goto drop_matched;
+ }
+
+ /*
+ * if we're trying to match a health status error but it hasn't
+ * been set in the rule, then don't match
+ */
+ if ((hstatus && !attr->u.drop.da_health_error_mask) ||
+ (!hstatus && attr->u.drop.da_health_error_mask))
return false;
/* match this rule, check drop rate now */
spin_lock(&rule->dr_lock);
- if (rule->dr_drop_time != 0) { /* time based drop */
+ if (attr->u.drop.da_random) {
+ int value = cfs_rand() % attr->u.drop.da_interval;
+ if (value >= (attr->u.drop.da_interval / 2))
+ drop = true;
+ else
+ drop = false;
+ } else if (rule->dr_drop_time != 0) { /* time based drop */
time64_t now = ktime_get_seconds();
rule->dr_stat.fs_count++;
}
}
+drop_matched:
+
if (drop) { /* drop this message, update counters */
+ if (hstatus)
+ lnet_fault_match_health(hstatus,
+ attr->u.drop.da_health_error_mask);
lnet_fault_stat_inc(&rule->dr_stat, type);
rule->dr_stat.u.drop.ds_dropped++;
}
* Check if message from \a src to \a dst can match any existed drop rule
*/
bool
-lnet_drop_rule_match(struct lnet_hdr *hdr)
+lnet_drop_rule_match(struct lnet_hdr *hdr,
+ lnet_nid_t local_nid,
+ enum lnet_msg_hstatus *hstatus)
{
- struct lnet_drop_rule *rule;
- lnet_nid_t src = le64_to_cpu(hdr->src_nid);
- lnet_nid_t dst = le64_to_cpu(hdr->dest_nid);
- unsigned int typ = le32_to_cpu(hdr->type);
- unsigned int ptl = -1;
- bool drop = false;
- int cpt;
+ lnet_nid_t src = le64_to_cpu(hdr->src_nid);
+ lnet_nid_t dst = le64_to_cpu(hdr->dest_nid);
+ unsigned int typ = le32_to_cpu(hdr->type);
+ struct lnet_drop_rule *rule;
+ unsigned int ptl = -1;
+ bool drop = false;
+ int cpt;
/* NB: if Portal is specified, then only PUT and GET will be
* filtered by drop rule */
cpt = lnet_net_lock_current();
list_for_each_entry(rule, &the_lnet.ln_drop_rules, dr_link) {
- drop = drop_rule_match(rule, src, dst, typ, ptl);
+ drop = drop_rule_match(rule, src, local_nid, dst, typ, ptl,
+ hstatus);
if (drop)
break;
}
-
lnet_net_unlock(cpt);
+
return drop;
}
struct lnet_fault_attr *attr = &rule->dl_attr;
bool delay;
- if (!lnet_fault_attr_match(attr, src, dst, type, portal))
+ if (!lnet_fault_attr_match(attr, src, LNET_NID_ANY,
+ dst, type, portal))
return false;
/* match this rule, check delay rate now */
}
static void
-delay_timer_cb(unsigned long arg)
+delay_timer_cb(cfs_timer_cb_arg_t data)
{
- struct lnet_delay_rule *rule = (struct lnet_delay_rule *)arg;
+ struct lnet_delay_rule *rule = cfs_from_timer(rule, data, dl_timer);
spin_lock_bh(&delay_dd.dd_lock);
if (list_empty(&rule->dl_sched_link) && delay_dd.dd_running) {
wait_event(delay_dd.dd_ctl_waitq, delay_dd.dd_running);
}
- init_timer(&rule->dl_timer);
- rule->dl_timer.function = delay_timer_cb;
- rule->dl_timer.data = (unsigned long)rule;
+ cfs_timer_setup(&rule->dl_timer, delay_timer_cb,
+ (unsigned long)rule, 0);
spin_lock_init(&rule->dl_lock);
INIT_LIST_HEAD(&rule->dl_msg_list);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff