kernel_getsockname(sock, addr, addrlen)
#endif
- static inline int lnet_is_route_alive(struct lnet_route *route)
- {
- if (!route->lr_gateway->lpni_alive)
- return 0; /* gateway is down */
- if ((route->lr_gateway->lpni_ping_feats &
- LNET_PING_FEAT_NI_STATUS) == 0)
- return 1; /* no NI status, assume it's alive */
- /* has NI status, check # down NIs */
- return route->lr_downis == 0;
- }
+ bool lnet_is_route_alive(struct lnet_route *route);
+ bool lnet_is_gateway_alive(struct lnet_peer *gw);
static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh)
{
}
static inline int
- lnet_isrouter(struct lnet_peer_ni *lp)
+ lnet_isrouter(struct lnet_peer_ni *lpni)
{
- return lp->lpni_rtr_refcount != 0;
+ return lpni->lpni_peer_net->lpn_peer->lp_rtr_refcount != 0;
}
static inline void
extern unsigned int lnet_recovery_interval;
extern unsigned int lnet_peer_discovery_disabled;
extern unsigned int lnet_drop_asym_route;
+ extern unsigned int router_sensitivity_percentage;
+ extern int alive_router_check_interval;
extern int portal_rotor;
- int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, int alive,
+ void lnet_mt_event_handler(struct lnet_event *event);
+
+ int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, bool alive, bool reset,
time64_t when);
void lnet_notify_locked(struct lnet_peer_ni *lp, int notifylnd, int alive,
time64_t when);
int lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway_nid,
- unsigned int priority);
- int lnet_check_routes(void);
+ __u32 priority, __u32 sensitivity);
int lnet_del_route(__u32 net, lnet_nid_t gw_nid);
void lnet_destroy_routes(void);
int lnet_get_route(int idx, __u32 *net, __u32 *hops,
- lnet_nid_t *gateway, __u32 *alive, __u32 *priority);
+ lnet_nid_t *gateway, __u32 *alive, __u32 *priority,
+ __u32 *sensitivity);
int lnet_get_rtr_pool_cfg(int idx, struct lnet_ioctl_pool_cfg *pool_cfg);
struct lnet_ni *lnet_get_next_ni_locked(struct lnet_net *mynet,
struct lnet_ni *prev);
int lnet_rtrpools_enable(void);
void lnet_rtrpools_disable(void);
void lnet_rtrpools_free(int keep_pools);
+ void lnet_rtr_transfer_to_peer(struct lnet_peer *src,
+ struct lnet_peer *target);
struct lnet_remotenet *lnet_find_rnet_locked(__u32 net);
int lnet_dyn_add_net(struct lnet_ioctl_config_data *conf);
int lnet_dyn_del_net(__u32 net);
int lnet_islocalnid(lnet_nid_t nid);
int lnet_islocalnet(__u32 net);
+ int lnet_islocalnet_locked(__u32 net);
void lnet_msg_attach_md(struct lnet_msg *msg, struct lnet_libmd *md,
unsigned int offset, unsigned int mlen);
int lnet_fault_init(void);
void lnet_fault_fini(void);
- bool lnet_drop_rule_match(struct lnet_hdr *hdr, enum lnet_msg_hstatus *hstatus);
+ bool lnet_drop_rule_match(struct lnet_hdr *hdr, lnet_nid_t local_nid,
+ enum lnet_msg_hstatus *hstatus);
int lnet_delay_rule_add(struct lnet_fault_attr *attr);
int lnet_delay_rule_del(lnet_nid_t src, lnet_nid_t dst, bool shutdown);
int lnet_acceptor_start(void);
void lnet_acceptor_stop(void);
-int lnet_ipif_query(char *name, int *up, __u32 *ip, __u32 *mask);
-int lnet_ipif_enumerate(char ***names);
-void lnet_ipif_free_enumeration(char **names, int n);
int lnet_sock_setbuf(struct socket *socket, int txbufsize, int rxbufsize);
int lnet_sock_getbuf(struct socket *socket, int *txbufsize, int *rxbufsize);
int lnet_sock_getaddr(struct socket *socket, bool remote, __u32 *ip, int *port);
int lnet_peers_start_down(void);
int lnet_peer_buffer_credits(struct lnet_net *net);
+ void lnet_consolidate_routes_locked(struct lnet_peer *orig_lp,
+ struct lnet_peer *new_lp);
+ void lnet_router_discovery_complete(struct lnet_peer *lp);
int lnet_monitor_thr_start(void);
void lnet_monitor_thr_stop(void);
bool lnet_router_checker_active(void);
void lnet_check_routers(void);
- int lnet_router_pre_mt_start(void);
- void lnet_router_post_mt_start(void);
- void lnet_prune_rc_data(int wait_unlink);
- void lnet_router_cleanup(void);
- void lnet_router_ni_update_locked(struct lnet_peer_ni *gw, __u32 net);
+ void lnet_wait_router_start(void);
void lnet_swap_pinginfo(struct lnet_ping_buffer *pbuf);
int lnet_ping_info_validate(struct lnet_ping_info *pinfo);
bool lnet_ni_unique_net(struct list_head *nilist, char *iface);
void lnet_incr_dlc_seq(void);
__u32 lnet_get_dlc_seq_locked(void);
+ int lnet_get_net_count(void);
+ struct lnet_peer_net *lnet_get_next_peer_net_locked(struct lnet_peer *lp,
+ __u32 prev_lpn_id);
struct lnet_peer_ni *lnet_get_next_peer_ni_locked(struct lnet_peer *peer,
struct lnet_peer_net *peer_net,
struct lnet_peer_ni *prev);
struct lnet_peer_ni *lnet_nid2peerni_locked(lnet_nid_t nid, lnet_nid_t pref,
int cpt);
struct lnet_peer_ni *lnet_nid2peerni_ex(lnet_nid_t nid, int cpt);
+ struct lnet_peer_ni *lnet_peer_get_ni_locked(struct lnet_peer *lp,
+ lnet_nid_t nid);
struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid);
struct lnet_peer *lnet_find_peer(lnet_nid_t nid);
void lnet_peer_net_added(struct lnet_net *net);
return NULL;
}
- static inline void
- lnet_peer_set_alive(struct lnet_peer_ni *lp)
- {
- lp->lpni_last_alive = ktime_get_seconds();
- lp->lpni_last_query = lp->lpni_last_alive;
- if (!lp->lpni_alive)
- lnet_notify_locked(lp, 0, 1, lp->lpni_last_alive);
- }
-
static inline bool
lnet_peer_is_multi_rail(struct lnet_peer *lp)
{
}
bool lnet_peer_is_uptodate(struct lnet_peer *lp);
+ bool lnet_is_discovery_disabled(struct lnet_peer *lp);
+ bool lnet_peer_gw_discovery(struct lnet_peer *lp);
static inline bool
lnet_peer_needs_push(struct lnet_peer *lp)
return true;
if (lp->lp_state & LNET_PEER_NO_DISCOVERY)
return false;
+ /* if discovery is not enabled then no need to push */
+ if (lnet_peer_discovery_disabled)
+ return false;
if (lp->lp_node_seqno < atomic_read(&the_lnet.ln_ping_target_seqno))
return true;
return false;
}
+ /*
+ * A peer is alive if it satisfies the following two conditions:
+ * 1. peer health >= LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage
+ * 2. the cached NI status received when we discover the peer is UP
+ */
+ static inline bool
+ lnet_is_peer_ni_alive(struct lnet_peer_ni *lpni)
+ {
+ bool halive = false;
+
+ halive = (atomic_read(&lpni->lpni_healthv) >=
+ (LNET_MAX_HEALTH_VALUE * router_sensitivity_percentage / 100));
+
+ return halive && lpni->lpni_ns_status == LNET_NI_STATUS_UP;
+ }
+
+ static inline void
+ lnet_set_healthv(atomic_t *healthv, int value)
+ {
+ atomic_set(healthv, value);
+ }
+
static inline void
lnet_inc_healthv(atomic_t *healthv)
{
read_unlock(&ksocknal_data.ksnd_global_lock);
if (notify)
- lnet_notify(peer_ni->ksnp_ni, peer_ni->ksnp_id.nid, 0,
- last_alive);
+ lnet_notify(peer_ni->ksnp_ni, peer_ni->ksnp_id.nid,
+ false, false, last_alive);
}
void
}
void
- ksocknal_notify(struct lnet_ni *ni, lnet_nid_t gw_nid, int alive)
+ ksocknal_notify_gw_down(lnet_nid_t gw_nid)
{
/* The router is telling me she's been notified of a change in
* gateway state....
.pid = LNET_PID_ANY,
};
- CDEBUG (D_NET, "gw %s %s\n", libcfs_nid2str(gw_nid),
- alive ? "up" : "down");
+ CDEBUG(D_NET, "gw %s down\n", libcfs_nid2str(gw_nid));
- if (!alive) {
- /* If the gateway crashed, close all open connections... */
- ksocknal_close_matching_conns (id, 0);
- return;
- }
+ /* If the gateway crashed, close all open connections... */
+ ksocknal_close_matching_conns(id, 0);
+ return;
- /* ...otherwise do nothing. We can only establish new connections
- * if we have autroutes, and these connect on demand. */
+ /* We can only establish new connections
+ * if we have autroutes, and these connect on demand. */
}
void
}
static int
-ksocknal_enumerate_interfaces(struct ksock_net *net)
+ksocknal_enumerate_interfaces(struct ksock_net *net, char *iname)
{
- int j = 0;
struct net_device *dev;
rtnl_lock();
for_each_netdev(&init_net, dev) {
- const char *name = dev->name;
+ /* The iname specified by an user land configuration can
+ * map to an ifa_label so always treat iname as an ifa_label.
+ * If iname is NULL then fall back to the net device name.
+ */
+ const char *name = iname ? iname : dev->name;
struct in_device *in_dev;
- struct ksock_interface *ksi;
- if (strcmp(name, "lo") == 0) /* skip the loopback IF */
+ if (strcmp(dev->name, "lo") == 0) /* skip the loopback IF */
continue;
if (!(dev_get_flags(dev) & IFF_UP)) {
- CWARN("Ignoring interface %s (down)\n", name);
- continue;
- }
-
- if (j == LNET_INTERFACES_NUM) {
- CWARN("Ignoring interface %s (too many interfaces)\n",
- name);
+ CWARN("Ignoring interface %s (down)\n", dev->name);
continue;
}
in_dev = __in_dev_get_rtnl(dev);
if (!in_dev) {
- CWARN("Interface %s has no IPv4 status.\n", name);
+ CWARN("Interface %s has no IPv4 status.\n", dev->name);
continue;
}
- ksi = &net->ksnn_interfaces[j];
+ for_ifa(in_dev)
+ if (strcmp(name, ifa->ifa_label) == 0) {
+ int idx = net->ksnn_ninterfaces;
+ struct ksock_interface *ksi;
- for_primary_ifa(in_dev)
- if (strcmp(ifa->ifa_label, name) == 0) {
+ if (idx >= ARRAY_SIZE(net->ksnn_interfaces)) {
+ rtnl_unlock();
+ return -E2BIG;
+ }
+
+ ksi = &net->ksnn_interfaces[idx];
ksi->ksni_ipaddr = ntohl(ifa->ifa_local);
ksi->ksni_netmask = ifa->ifa_mask;
strlcpy(ksi->ksni_name,
name, sizeof(ksi->ksni_name));
- j++;
+ net->ksnn_ninterfaces++;
break;
}
endfor_ifa(in_dev);
}
-
rtnl_unlock();
- if (j == 0)
+ if (net->ksnn_ninterfaces == 0)
CERROR("Can't find any usable interfaces\n");
- return j;
+ return net->ksnn_ninterfaces > 0 ? 0 : -ENOENT;
}
static int
net_tunables->lct_peer_rtr_credits =
*ksocknal_tunables.ksnd_peerrtrcredits;
- if (ni->ni_interfaces[0] == NULL) {
- rc = ksocknal_enumerate_interfaces(net);
- if (rc <= 0)
+ if (!ni->ni_interfaces[0]) {
+ rc = ksocknal_enumerate_interfaces(net, NULL);
+ if (rc < 0)
goto fail_1;
-
- net->ksnn_ninterfaces = 1;
} else {
+ /* Before Multi-Rail ksocklnd would manage
+ * multiple interfaces with its own tcp bonding.
+ * If we encounter an old configuration using
+ * this tcp bonding approach then we need to
+ * handle more than one ni_interfaces.
+ *
+ * In Multi-Rail configuration only ONE ni_interface
+ * should exist. Each IP alias should be mapped to
+ * each 'struct net_ni'.
+ */
for (i = 0; i < LNET_INTERFACES_NUM; i++) {
- int up;
+ int j;
- if (ni->ni_interfaces[i] == NULL)
+ if (!ni->ni_interfaces[i])
break;
- rc = lnet_ipif_query(ni->ni_interfaces[i], &up,
- &net->ksnn_interfaces[i].ksni_ipaddr,
- &net->ksnn_interfaces[i].ksni_netmask);
+ for (j = 0; j < net->ksnn_ninterfaces; j++) {
+ struct ksock_interface *ksi;
- if (rc != 0) {
- CERROR("Can't get interface %s info: %d\n",
- ni->ni_interfaces[i], rc);
- goto fail_1;
- }
+ ksi = &net->ksnn_interfaces[j];
- if (!up) {
- CERROR("Interface %s is down\n",
- ni->ni_interfaces[i]);
- goto fail_1;
+ if (strcmp(ni->ni_interfaces[i],
+ ksi->ksni_name) == 0) {
+ CERROR("found duplicate %s\n",
+ ksi->ksni_name);
+ rc = -EEXIST;
+ goto fail_1;
+ }
}
- strlcpy(net->ksnn_interfaces[i].ksni_name,
- ni->ni_interfaces[i],
- sizeof(net->ksnn_interfaces[i].ksni_name));
-
+ rc = ksocknal_enumerate_interfaces(net, ni->ni_interfaces[i]);
+ if (rc < 0)
+ goto fail_1;
}
- net->ksnn_ninterfaces = i;
}
net_dev = dev_get_by_name(&init_net,
the_ksocklnd.lnd_ctl = ksocknal_ctl;
the_ksocklnd.lnd_send = ksocknal_send;
the_ksocklnd.lnd_recv = ksocknal_recv;
- the_ksocklnd.lnd_notify = ksocknal_notify;
+ the_ksocklnd.lnd_notify_peer_down = ksocknal_notify_gw_down;
the_ksocklnd.lnd_query = ksocknal_query;
the_ksocklnd.lnd_accept = ksocknal_accept;
}
if (route != NULL) {
- __u32 net = rnet->lrn_net;
- __u32 hops = route->lr_hops;
- unsigned int priority = route->lr_priority;
- lnet_nid_t nid = route->lr_gateway->lpni_nid;
- int alive = lnet_is_route_alive(route);
+ __u32 net = rnet->lrn_net;
+ __u32 hops = route->lr_hops;
+ unsigned int priority = route->lr_priority;
+ int alive = lnet_is_route_alive(route);
s += snprintf(s, tmpstr + tmpsiz - s,
"%-8s %4d %8u %7s %s\n",
libcfs_net2str(net), hops,
priority,
alive ? "up" : "down",
- libcfs_nid2str(nid));
+ libcfs_nid2str(route->lr_nid));
LASSERT(tmpstr + tmpsiz - s > 0);
}
if (*ppos == 0) {
s += snprintf(s, tmpstr + tmpsiz - s,
- "%-4s %7s %9s %6s %12s %9s %8s %7s %s\n",
- "ref", "rtr_ref", "alive_cnt", "state",
- "last_ping", "ping_sent", "deadline",
- "down_ni", "router");
+ "%-4s %7s %5s %s\n",
+ "ref", "rtr_ref", "alive", "router");
LASSERT(tmpstr + tmpsiz - s > 0);
lnet_net_lock(0);
*ppos = LNET_PROC_POS_MAKE(0, ver, 0, off);
} else {
struct list_head *r;
- struct lnet_peer_ni *peer = NULL;
+ struct lnet_peer *peer = NULL;
int skip = off - 1;
lnet_net_lock(0);
r = the_lnet.ln_routers.next;
while (r != &the_lnet.ln_routers) {
- struct lnet_peer_ni *lp =
- list_entry(r, struct lnet_peer_ni,
- lpni_rtr_list);
+ struct lnet_peer *lp =
+ list_entry(r, struct lnet_peer,
+ lp_rtr_list);
if (skip == 0) {
peer = lp;
}
if (peer != NULL) {
- lnet_nid_t nid = peer->lpni_nid;
- time64_t now = ktime_get_seconds();
- time64_t deadline = peer->lpni_ping_deadline;
- int nrefs = atomic_read(&peer->lpni_refcount);
- int nrtrrefs = peer->lpni_rtr_refcount;
- int alive_cnt = peer->lpni_alive_count;
- int alive = peer->lpni_alive;
- int pingsent = !peer->lpni_ping_notsent;
- time64_t last_ping = now - peer->lpni_ping_timestamp;
- int down_ni = 0;
- struct lnet_route *rtr;
-
- if ((peer->lpni_ping_feats &
- LNET_PING_FEAT_NI_STATUS) != 0) {
- list_for_each_entry(rtr, &peer->lpni_routes,
- lr_gwlist) {
- /* downis on any route should be the
- * number of downis on the gateway */
- if (rtr->lr_downis != 0) {
- down_ni = rtr->lr_downis;
- break;
- }
- }
- }
+ lnet_nid_t nid = peer->lp_primary_nid;
+ int nrefs = atomic_read(&peer->lp_refcount);
+ int nrtrrefs = peer->lp_rtr_refcount;
+ int alive = lnet_is_gateway_alive(peer);
- if (deadline == 0)
- s += snprintf(s, tmpstr + tmpsiz - s,
- "%-4d %7d %9d %6s %12llu %9d %8s %7d %s\n",
- nrefs, nrtrrefs, alive_cnt,
- alive ? "up" : "down", last_ping,
- pingsent, "NA", down_ni,
- libcfs_nid2str(nid));
- else
- s += snprintf(s, tmpstr + tmpsiz - s,
- "%-4d %7d %9d %6s %12llu %9d %8llu %7d %s\n",
- nrefs, nrtrrefs, alive_cnt,
- alive ? "up" : "down", last_ping,
- pingsent,
- deadline - now,
- down_ni, libcfs_nid2str(nid));
- LASSERT(tmpstr + tmpsiz - s > 0);
+ s += snprintf(s, tmpstr + tmpsiz - s,
+ "%-4d %7d %5s %s\n",
+ nrefs, nrtrrefs,
+ alive ? "up" : "down",
+ libcfs_nid2str(nid));
}
lnet_net_unlock(0);
if (lnet_isrouter(peer) ||
lnet_peer_aliveness_enabled(peer))
- aliveness = peer->lpni_alive ? "up" : "down";
-
- if (lnet_peer_aliveness_enabled(peer)) {
- time64_t now = ktime_get_seconds();
-
- lastalive = now - peer->lpni_last_alive;
-
- /* No need to mess up peers contents with
- * arbitrarily long integers - it suffices to
- * know that lastalive is more than 10000s old
- */
- if (lastalive >= 10000)
- lastalive = 9999;
- }
+ aliveness = lnet_is_peer_ni_alive(peer) ?
+ "up" : "down";
lnet_net_unlock(cpt);
int j;
if (the_lnet.ln_routing)
- last_alive = now - ni->ni_last_alive;
+ last_alive = now - ni->ni_net->net_last_alive;
- /* @lo forever alive */
- if (ni->ni_net->net_lnd->lnd_type == LOLND)
- last_alive = 0;
-
lnet_ni_lock(ni);
LASSERT(ni->ni_status != NULL);
stat = (ni->ni_status->ns_status ==
LNET_NI_STATUS_UP) ? "up" : "down";
lnet_ni_unlock(ni);
+ /* @lo forever alive */
+ if (ni->ni_net->net_lnd->lnd_type == LOLND) {
+ last_alive = 0;
+ stat = "up";
+ }
+
/* we actually output credits information for
* TX queue of each partition */
cfs_percpt_for_each(tq, i, ni->ni_tx_queues) {
}
run_test 27b "create and write to two stripe file"
+# 27c family tests specific striping, setstripe -o
+test_27ca() {
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "skipping 2-stripe test"
+ test_mkdir -p $DIR/$tdir
+ local osts="1"
+
+ $LFS setstripe -o $osts $DIR/$tdir/$tfile || error "setstripe failed"
+ $LFS getstripe -i $DIR/$tdir/$tfile
+ [ $($LFS getstripe -i $DIR/$tdir/$tfile ) -eq $osts ] ||
+ error "stripe not on specified OST"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 || error "dd failed"
+}
+run_test 27ca "one stripe on specified OST"
+
+test_27cb() {
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "skipping 2-stripe test"
+ test_mkdir -p $DIR/$tdir
+ local osts="1,0"
+ $LFS setstripe -o $osts $DIR/$tdir/$tfile || error "setstripe failed"
+ local getstripe=$($LFS getstripe $DIR/$tdir/$tfile)
+ echo "$getstripe"
+
+ # Strip getstripe output to a space separated list of OSTs
+ local getstripe_osts=$(echo "$getstripe" | sed -e '1,/obdidx/d' |\
+ awk '{print $1}' | tr '\n' '\ ' | sed -e 's/[[:space:]]*$//')
+ [ "$getstripe_osts" = "${osts//,/ }" ] ||
+ error "stripes not on specified OSTs"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 || error "dd failed"
+}
+run_test 27cb "two stripes on specified OSTs"
+
+test_27cc() {
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "skipping 2-stripe test"
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+
+ test_mkdir -p $DIR/$tdir
+ local osts="0,0"
+ $LFS setstripe -o $osts $DIR/$tdir/$tfile || error "setstripe failed"
+ local getstripe=$($LFS getstripe $DIR/$tdir/$tfile)
+ echo "$getstripe"
+
+ # Strip getstripe output to a space separated list of OSTs
+ local getstripe_osts=$(echo "$getstripe" | sed -e '1,/obdidx/d' |\
+ awk '{print $1}' | tr '\n' '\ ' | sed -e 's/[[:space:]]*$//')
+ [ "$getstripe_osts" = "${osts//,/ }" ] ||
+ error "stripes not on specified OSTs"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 || error "dd failed"
+}
+run_test 27cc "two stripes on the same OST"
+
+test_27cd() {
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "skipping 2-stripe test"
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ test_mkdir -p $DIR/$tdir
+ local osts="0,1,1,0"
+ $LFS setstripe -o $osts $DIR/$tdir/$tfile || error "setstripe failed"
+ local getstripe=$($LFS getstripe $DIR/$tdir/$tfile)
+ echo "$getstripe"
+
+ # Strip getstripe output to a space separated list of OSTs
+ local getstripe_osts=$(echo "$getstripe" | sed -e '1,/obdidx/d' |\
+ awk '{print $1}' | tr '\n' '\ ' | sed -e 's/[[:space:]]*$//')
+ [ "$getstripe_osts" = "${osts//,/ }" ] ||
+ error "stripes not on specified OSTs"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 || error "dd failed"
+}
+run_test 27cd "four stripes on two OSTs"
+
+test_27ce() {
+ [[ $OSTCOUNT -ge $(($LOV_MAX_STRIPE_COUNT / 2)) ]] &&
+ skip_env "too many osts, skipping"
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ # We do one more stripe than we have OSTs
+ [ $OSTCOUNT -ge 159 ] || large_xattr_enabled ||
+ skip_env "ea_inode feature disabled"
+
+ test_mkdir -p $DIR/$tdir
+ local osts=""
+ for i in $(seq 0 $OSTCOUNT);
+ do
+ osts=$osts"0"
+ if [ $i -ne $OSTCOUNT ]; then
+ osts=$osts","
+ fi
+ done
+ $LFS setstripe -o $osts $DIR/$tdir/$tfile || error "setstripe failed"
+ local getstripe=$($LFS getstripe $DIR/$tdir/$tfile)
+ echo "$getstripe"
+
+ # Strip getstripe output to a space separated list of OSTs
+ local getstripe_osts=$(echo "$getstripe" | sed -e '1,/obdidx/d' |\
+ awk '{print $1}' | tr '\n' '\ ' | sed -e 's/[[:space:]]*$//')
+ [ "$getstripe_osts" = "${osts//,/ }" ] ||
+ error "stripes not on specified OSTs"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 || error "dd failed"
+}
+run_test 27ce "more stripes than OSTs with -o"
+
test_27d() {
test_mkdir $DIR/$tdir
$LFS setstripe -c 0 -i -1 -S 0 $DIR/$tdir/$tfile ||
}
run_test 27B "call setstripe on open unlinked file/rename victim"
-test_27C() { #LU-2871
+# 27C family tests full striping and overstriping
+test_27Ca() { #LU-2871
[[ $OSTCOUNT -lt 2 ]] && skip_env "needs >= 2 OSTs"
declare -a ost_idx
done
done
}
-run_test 27C "check full striping across all OSTs"
+run_test 27Ca "check full striping across all OSTs"
+
+test_27Cb() {
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ [[ $OSTCOUNT -ge $(($LOV_MAX_STRIPE_COUNT / 2)) ]] &&
+ skip_env "too many osts, skipping"
+
+ test_mkdir -p $DIR/$tdir
+ local setcount=$(($OSTCOUNT * 2))
+ [ $setcount -ge 160 ] || large_xattr_enabled ||
+ skip_env "ea_inode feature disabled"
+
+ $LFS setstripe -C $setcount $DIR/$tdir/$tfile ||
+ error "setstripe failed"
+
+ local count=$($LFS getstripe -c $DIR/$tdir/$tfile)
+ [ $count -eq $setcount ] ||
+ error "stripe count $count, should be $setcount"
+
+ $LFS getstripe $DIR/$tdir/$tfile 2>&1 | grep "overstriped" ||
+ error "overstriped should be set in pattern"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 conv=notrunc ||
+ error "dd failed"
+}
+run_test 27Cb "more stripes than OSTs with -C"
+
+test_27Cc() {
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "need > 1 OST"
+
+ test_mkdir -p $DIR/$tdir
+ local setcount=$(($OSTCOUNT - 1))
+
+ [ $setcount -ge 160 ] || large_xattr_enabled ||
+ skip_env "ea_inode feature disabled"
+
+ $LFS setstripe -C $setcount $DIR/$tdir/$tfile ||
+ error "setstripe failed"
+
+ local count=$($LFS getstripe -c $DIR/$tdir/$tfile)
+ [ $count -eq $setcount ] ||
+ error "stripe count $count, should be $setcount"
+
+ $LFS getstripe $DIR/$tdir/$tfile 2>&1 | grep "overstriped" &&
+ error "overstriped should not be set in pattern"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 conv=notrunc ||
+ error "dd failed"
+}
+run_test 27Cc "fewer stripes than OSTs does not set overstriping"
+
+test_27Cd() {
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ [[ $OSTCOUNT -lt 2 ]] && skip_env "need > 1 OST"
+ large_xattr_enabled || skip_env "ea_inode feature disabled"
+
+ test_mkdir -p $DIR/$tdir
+ local setcount=$LOV_MAX_STRIPE_COUNT
+
+ $LFS setstripe -C $setcount $DIR/$tdir/$tfile ||
+ error "setstripe failed"
+
+ local count=$($LFS getstripe -c $DIR/$tdir/$tfile)
+ [ $count -eq $setcount ] ||
+ error "stripe count $count, should be $setcount"
+
+ $LFS getstripe $DIR/$tdir/$tfile 2>&1 | grep "overstriped" ||
+ error "overstriped should be set in pattern"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 conv=notrunc ||
+ error "dd failed"
+
+ rm -f $DIR/$tdir/$tfile || error "Delete $tfile failed"
+}
+run_test 27Cd "test maximum stripe count"
+
+test_27Ce() {
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ test_mkdir -p $DIR/$tdir
+
+ pool_add $TESTNAME || error "Pool creation failed"
+ pool_add_targets $TESTNAME 0 || error "pool_add_targets failed"
+
+ local setcount=8
+
+ $LFS setstripe -C $setcount -p "$TESTNAME" $DIR/$tdir/$tfile ||
+ error "setstripe failed"
+
+ local count=$($LFS getstripe -c $DIR/$tdir/$tfile)
+ [ $count -eq $setcount ] ||
+ error "stripe count $count, should be $setcount"
+
+ $LFS getstripe $DIR/$tdir/$tfile 2>&1 | grep "overstriped" ||
+ error "overstriped should be set in pattern"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 conv=notrunc ||
+ error "dd failed"
+
+ rm -f $DIR/$tdir/$tfile || error "Delete $tfile failed"
+}
+run_test 27Ce "test pool with overstriping"
+
+test_27Cf() {
+ [[ $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ]] ||
+ skip "server does not support overstriping"
+ [[ $OSTCOUNT -ge $(($LOV_MAX_STRIPE_COUNT / 2)) ]] &&
+ skip_env "too many osts, skipping"
+
+ test_mkdir -p $DIR/$tdir
+
+ local setcount=$(($OSTCOUNT * 2))
+ [ $setcount -ge 160 ] || large_xattr_enabled ||
+ skip_env "ea_inode feature disabled"
+
+ $LFS setstripe -C $setcount $DIR/$tdir/ ||
+ error "setstripe failed"
+
+ echo 1 > $DIR/$tdir/$tfile
+
+ local count=$($LFS getstripe -c $DIR/$tdir/$tfile)
+ [ $count -eq $setcount ] ||
+ error "stripe count $count, should be $setcount"
+
+ $LFS getstripe $DIR/$tdir/$tfile 2>&1 | grep "overstriped" ||
+ error "overstriped should be set in pattern"
+
+ dd if=/dev/zero of=$DIR/$tdir/$tfile bs=1M count=4 conv=notrunc ||
+ error "dd failed"
+
+ rm -f $DIR/$tdir/$tfile || error "Delete $tfile failed"
+}
+run_test 27Cf "test default inheritance with overstriping"
test_27D() {
[ $OSTCOUNT -lt 2 ] && skip_env "needs >= 2 OSTs"
[ $MDS1_VERSION -lt $(version_code 2.9.55) ] ||
[ $CLIENT_VERSION -lt $(version_code 2.9.55) ] &&
skip27D+=" -s 30,31"
+ [[ ! $($LCTL get_param mdc.*.import) =~ connect_flags.*overstriping ||
+ $OSTCOUNT -ge $(($LOV_MAX_STRIPE_COUNT / 2)) ]] &&
+ skip27D+=" -s 32,33"
llapi_layout_test -d$DIR/$tdir -p$POOL -o$OSTCOUNT $skip27D ||
error "llapi_layout_test failed"
}
run_test 60g "transaction abort won't cause MDT hung"
+test_60h() {
+ [ $MDS1_VERSION -le $(version_code 2.12.52) ] ||
+ skip "Need MDS version at least 2.12.52"
+ [ $MDSCOUNT -le 2 ] || skip "Need >= 2 MDTs"
+
+ local f
+
+ #define OBD_FAIL_MDS_STRIPE_CREATE 0x188
+ #define OBD_FAIL_MDS_STRIPE_FID 0x189
+ for fail_loc in 0x80000188 0x80000189; do
+ do_facet mds1 "$LCTL set_param fail_loc=$fail_loc"
+ $LFS mkdir -c $MDSCOUNT -i 0 $DIR/$tdir-$fail_loc ||
+ error "mkdir $dir-$fail_loc failed"
+ for i in {0..10}; do
+ # create may fail on missing stripe
+ echo $i > $DIR/$tdir-$fail_loc/$i
+ done
+ $LFS getdirstripe $DIR/$tdir-$fail_loc ||
+ error "getdirstripe $tdir-$fail_loc failed"
+ $LFS migrate -m 1 $DIR/$tdir-$fail_loc ||
+ error "migrate $tdir-$fail_loc failed"
+ $LFS getdirstripe $DIR/$tdir-$fail_loc ||
+ error "getdirstripe $tdir-$fail_loc failed"
+ pushd $DIR/$tdir-$fail_loc
+ for f in *; do
+ echo $f | cmp $f - || error "$f data mismatch"
+ done
+ popd
+ rm -rf $DIR/$tdir-$fail_loc
+ done
+}
+run_test 60h "striped directory with missing stripes can be accessed"
+
test_61a() {
[ $PARALLEL == "yes" ] && skip "skip parallel run"
if [[ $STRIPECOUNT -le 0 ]]; then
sc=1
- elif [[ $STRIPECOUNT -gt 2000 ]]; then
-#LOV_MAX_STRIPE_COUNT is 2000
- [[ $OSTCOUNT -gt 2000 ]] && sc=2000 || sc=$(($OSTCOUNT - 1))
+ elif [[ $STRIPECOUNT -gt $LOV_MAX_STRIPE_COUNT ]]; then
+ [[ $OSTCOUNT -gt $LOV_MAX_STRIPE_COUNT ]] &&
+ sc=$LOV_MAX_STRIPE_COUNT || sc=$(($OSTCOUNT - 1))
else
sc=$(($STRIPECOUNT - 1))
fi
# where ref > 0, rtr_ref > 0, alive_cnt >= 0, state is up/down,
# last_ping >= 0, ping_sent is boolean (0/1), deadline and down_ni are
# numeric (0 or >0 or <0), router is a string like 192.168.1.1@tcp2
- L1="^ref +rtr_ref +alive_cnt +state +last_ping +ping_sent +deadline +down_ni +router$"
- BR="^$P +$P +$N +(up|down) +$N +(0|1) +$I +$I +$NID$"
+ L1="^ref +rtr_ref +alive +router$"
+ BR="^$P +$P +(up|down) +$NID$"
create_lnet_proc_files "routers"
check_lnet_proc_entry "routers.sys" "lnet.routers" "$BR" "$L1"
remove_lnet_proc_files "routers"
}
run_test 271f "DoM: read on open (200K file and read tail)"
+test_271g() {
+ [[ $($LCTL get_param mdc.*.import) =~ async_discard ]] ||
+ skip "Skipping due to old client or server version"
+
+ $LFS setstripe -E 1024K -L mdt -E EOF $DIR1/$tfile
+ # to get layout
+ $CHECKSTAT -t file $DIR1/$tfile
+
+ $MULTIOP $DIR1/$tfile Ow40960_w4096c &
+ MULTIOP_PID=$!
+ sleep 1
+ #define OBD_FAIL_LDLM_CANCEL_BL_CB_RACE
+ $LCTL set_param fail_loc=0x80000314
+ rm $DIR1/$tfile || error "Unlink fails"
+ RC=$?
+ kill -USR1 $MULTIOP_PID && wait $MULTIOP_PID || error "multiop failure"
+ [ $RC -eq 0 ] || error "Failed write to stale object"
+}
+run_test 271g "Discard DoM data vs client flush race"
+
test_272a() {
[ $MDS1_VERSION -lt $(version_code 2.11.50) ] &&
skip "Need MDS version at least 2.11.50"
}
run_test 813 "File heat verfication"
+test_814()
+{
+ dd of=$DIR/$tfile seek=128 bs=1k < /dev/null
+ echo -n y >> $DIR/$tfile
+ cp --sparse=always $DIR/$tfile $DIR/${tfile}.cp || error "copy failed"
+ diff $DIR/$tfile $DIR/${tfile}.cp || error "files should be same"
+}
+run_test 814 "sparse cp works as expected (LU-12361)"
+
#
# tests that do cleanup/setup should be run at the end
#