/**
* Updates import \a imp current state to provided \a state value
- * Helper function. Must be called under imp_lock.
+ * Helper function.
*/
-static void __import_set_state(struct obd_import *imp,
- enum lustre_imp_state state)
+static void import_set_state_nolock(struct obd_import *imp,
+ enum lustre_imp_state state)
{
switch (state) {
case LUSTRE_IMP_CLOSED:
break;
default:
imp->imp_replay_state = LUSTRE_IMP_REPLAY;
+ break;
+ }
+
+ /* A CLOSED import should remain so. */
+ if (state == LUSTRE_IMP_CLOSED)
+ return;
+
+ if (imp->imp_state != LUSTRE_IMP_NEW) {
+ CDEBUG(D_HA, "%p %s: changing import state from %s to %s\n",
+ imp, obd2cli_tgt(imp->imp_obd),
+ ptlrpc_import_state_name(imp->imp_state),
+ ptlrpc_import_state_name(state));
}
+
imp->imp_state = state;
imp->imp_state_hist[imp->imp_state_hist_idx].ish_state = state;
imp->imp_state_hist[imp->imp_state_hist_idx].ish_time =
IMP_STATE_HIST_LEN;
}
-/* A CLOSED import should remain so. */
-#define IMPORT_SET_STATE_NOLOCK(imp, state) \
-do { \
- if (imp->imp_state != LUSTRE_IMP_CLOSED) { \
- CDEBUG(D_HA, "%p %s: changing import state from %s to %s\n", \
- imp, obd2cli_tgt(imp->imp_obd), \
- ptlrpc_import_state_name(imp->imp_state), \
- ptlrpc_import_state_name(state)); \
- __import_set_state(imp, state); \
- } \
-} while(0)
-
-#define IMPORT_SET_STATE(imp, state) \
-do { \
- spin_lock(&imp->imp_lock); \
- IMPORT_SET_STATE_NOLOCK(imp, state); \
- spin_unlock(&imp->imp_lock); \
-} while(0)
+static void import_set_state(struct obd_import *imp,
+ enum lustre_imp_state new_state)
+{
+ spin_lock(&imp->imp_lock);
+ import_set_state_nolock(imp, new_state);
+ spin_unlock(&imp->imp_lock);
+}
void ptlrpc_import_enter_resend(struct obd_import *imp)
{
- IMPORT_SET_STATE(imp, LUSTRE_IMP_RECOVER);
+ import_set_state(imp, LUSTRE_IMP_RECOVER);
}
EXPORT_SYMBOL(ptlrpc_import_enter_resend);
*uuid_len -= strlen(UUID_STR);
}
+/* Must be called with imp_lock held! */
+static void ptlrpc_deactivate_import_nolock(struct obd_import *imp)
+{
+ ENTRY;
+
+ assert_spin_locked(&imp->imp_lock);
+ CDEBUG(D_HA, "setting import %s INVALID\n", obd2cli_tgt(imp->imp_obd));
+ imp->imp_invalid = 1;
+ imp->imp_generation++;
+
+ ptlrpc_abort_inflight(imp);
+
+ EXIT;
+}
+
/**
* Returns true if import was FULL, false if import was already not
* connected.
* bulk requests) and if one has already caused a reconnection
* (increasing the import->conn_cnt) the older failure should
* not also cause a reconnection. If zero it forces a reconnect.
+ * @invalid - set import invalid flag
*/
-int ptlrpc_set_import_discon(struct obd_import *imp, __u32 conn_cnt)
+int ptlrpc_set_import_discon(struct obd_import *imp,
+ __u32 conn_cnt, bool invalid)
{
int rc = 0;
(conn_cnt == 0 || conn_cnt == imp->imp_conn_cnt)) {
char *target_start;
int target_len;
+ bool inact = false;
deuuidify(obd2cli_tgt(imp->imp_obd), NULL,
&target_start, &target_len);
+ import_set_state_nolock(imp, LUSTRE_IMP_DISCON);
if (imp->imp_replayable) {
LCONSOLE_WARN("%s: Connection to %.*s (at %s) was "
"lost; in progress operations using this "
"operations using this service will fail\n",
imp->imp_obd->obd_name, target_len, target_start,
obd_import_nid2str(imp));
+ if (invalid) {
+ CDEBUG(D_HA, "import %s@%s for %s not "
+ "replayable, auto-deactivating\n",
+ obd2cli_tgt(imp->imp_obd),
+ imp->imp_connection->c_remote_uuid.uuid,
+ imp->imp_obd->obd_name);
+ ptlrpc_deactivate_import_nolock(imp);
+ inact = true;
+ }
}
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_DISCON);
spin_unlock(&imp->imp_lock);
if (obd_dump_on_timeout)
libcfs_debug_dumplog();
obd_import_event(imp->imp_obd, imp, IMP_EVENT_DISCON);
+
+ if (inact)
+ obd_import_event(imp->imp_obd, imp, IMP_EVENT_INACTIVE);
rc = 1;
} else {
spin_unlock(&imp->imp_lock);
return rc;
}
-/* Must be called with imp_lock held! */
-static void ptlrpc_deactivate_and_unlock_import(struct obd_import *imp)
-{
- ENTRY;
- assert_spin_locked(&imp->imp_lock);
-
- CDEBUG(D_HA, "setting import %s INVALID\n", obd2cli_tgt(imp->imp_obd));
- imp->imp_invalid = 1;
- imp->imp_generation++;
- spin_unlock(&imp->imp_lock);
-
- ptlrpc_abort_inflight(imp);
- obd_import_event(imp->imp_obd, imp, IMP_EVENT_INACTIVE);
-
- EXIT;
-}
-
/*
* This acts as a barrier; all existing requests are rejected, and
* no new requests will be accepted until the import is valid again.
void ptlrpc_deactivate_import(struct obd_import *imp)
{
spin_lock(&imp->imp_lock);
- ptlrpc_deactivate_and_unlock_import(imp);
+ ptlrpc_deactivate_import_nolock(imp);
+ spin_unlock(&imp->imp_lock);
+
+ obd_import_event(imp->imp_obd, imp, IMP_EVENT_INACTIVE);
}
EXPORT_SYMBOL(ptlrpc_deactivate_import);
{
struct list_head *tmp, *n;
struct ptlrpc_request *req;
- struct l_wait_info lwi;
time64_t timeout;
int rc;
CFS_FAIL_TIMEOUT(OBD_FAIL_MGS_CONNECT_NET, 3 * cfs_fail_val / 2);
LASSERT(imp->imp_invalid);
- /* Wait forever until inflight == 0. We really can't do it another
- * way because in some cases we need to wait for very long reply
- * unlink. We can't do anything before that because there is really
- * no guarantee that some rdma transfer is not in progress right now. */
- do {
+ /* Wait forever until inflight == 0. We really can't do it another
+ * way because in some cases we need to wait for very long reply
+ * unlink. We can't do anything before that because there is really
+ * no guarantee that some rdma transfer is not in progress right now.
+ */
+ do {
long timeout_jiffies;
- /* Calculate max timeout for waiting on rpcs to error
- * out. Use obd_timeout if calculated value is smaller
+ /* Calculate max timeout for waiting on rpcs to error
+ * out. Use obd_timeout if calculated value is smaller
* than it.
*/
if (!OBD_FAIL_CHECK(OBD_FAIL_PTLRPC_LONG_REPL_UNLINK)) {
* have been locally cancelled by ptlrpc_abort_inflight.
*/
timeout_jiffies = max_t(long, cfs_time_seconds(timeout), 1);
- lwi = LWI_TIMEOUT_INTERVAL(timeout_jiffies,
- (timeout > 1) ? cfs_time_seconds(1) :
- cfs_time_seconds(1) / 2,
- NULL, NULL);
- rc = l_wait_event(imp->imp_recovery_waitq,
- (atomic_read(&imp->imp_inflight) == 0),
- &lwi);
- if (rc) {
+ rc = wait_event_idle_timeout(
+ imp->imp_recovery_waitq,
+ (atomic_read(&imp->imp_inflight) == 0),
+ timeout_jiffies);
+
+ if (rc == 0) {
const char *cli_tgt = obd2cli_tgt(imp->imp_obd);
- CERROR("%s: rc = %d waiting for callback (%d != 0)\n",
- cli_tgt, rc, atomic_read(&imp->imp_inflight));
+ CERROR("%s: timeout waiting for callback (%d != 0)\n",
+ cli_tgt, atomic_read(&imp->imp_inflight));
spin_lock(&imp->imp_lock);
if (atomic_read(&imp->imp_inflight) == 0) {
/* Let's save one loop as soon as inflight have
* dropped to zero. No new inflights possible at
* this point. */
- rc = 0;
+ rc = 1;
} else {
list_for_each_safe(tmp, n,
&imp->imp_sending_list) {
}
CERROR("%s: Unregistering RPCs found (%d). "
- "Network is sluggish? Waiting them "
+ "Network is sluggish? Waiting for them "
"to error out.\n", cli_tgt,
atomic_read(&imp->imp_unregistering));
}
spin_unlock(&imp->imp_lock);
}
- } while (rc != 0);
+ } while (rc == 0);
/*
* Let's additionally check that no new rpcs added to import in
sptlrpc_import_flush_all_ctx(imp);
atomic_dec(&imp->imp_inval_count);
- wake_up_all(&imp->imp_recovery_waitq);
+ wake_up(&imp->imp_recovery_waitq);
}
EXPORT_SYMBOL(ptlrpc_invalidate_import);
/* unset imp_invalid */
-void ptlrpc_activate_import(struct obd_import *imp)
+void ptlrpc_activate_import(struct obd_import *imp, bool set_state_full)
{
struct obd_device *obd = imp->imp_obd;
spin_lock(&imp->imp_lock);
if (imp->imp_deactive != 0) {
+ LASSERT(imp->imp_state != LUSTRE_IMP_FULL);
+ if (imp->imp_state != LUSTRE_IMP_DISCON)
+ import_set_state_nolock(imp, LUSTRE_IMP_DISCON);
spin_unlock(&imp->imp_lock);
return;
}
+ if (set_state_full)
+ import_set_state_nolock(imp, LUSTRE_IMP_FULL);
imp->imp_invalid = 0;
+
spin_unlock(&imp->imp_lock);
obd_import_event(obd, imp, IMP_EVENT_ACTIVE);
}
void ptlrpc_fail_import(struct obd_import *imp, __u32 conn_cnt)
{
- ENTRY;
-
- LASSERT(!imp->imp_dlm_fake);
+ ENTRY;
- if (ptlrpc_set_import_discon(imp, conn_cnt)) {
- if (!imp->imp_replayable) {
- CDEBUG(D_HA, "import %s@%s for %s not replayable, "
- "auto-deactivating\n",
- obd2cli_tgt(imp->imp_obd),
- imp->imp_connection->c_remote_uuid.uuid,
- imp->imp_obd->obd_name);
- ptlrpc_deactivate_import(imp);
- }
+ LASSERT(!imp->imp_dlm_fake);
+ if (ptlrpc_set_import_discon(imp, conn_cnt, true))
ptlrpc_pinger_force(imp);
- }
+
EXIT;
}
{
#ifdef ENABLE_PINGER
long timeout_jiffies = cfs_time_seconds(obd_timeout);
- struct l_wait_info lwi;
int rc;
ptlrpc_pinger_force(imp);
CDEBUG(D_HA, "%s: recovery started, waiting %u seconds\n",
obd2cli_tgt(imp->imp_obd), obd_timeout);
- lwi = LWI_TIMEOUT(timeout_jiffies, NULL, NULL);
- rc = l_wait_event(imp->imp_recovery_waitq,
- !ptlrpc_import_in_recovery(imp), &lwi);
+ rc = wait_event_idle_timeout(imp->imp_recovery_waitq,
+ !ptlrpc_import_in_recovery(imp),
+ timeout_jiffies);
+ if (rc == 0)
+ rc = -ETIMEDOUT;
+ else
+ rc = 0;
CDEBUG(D_HA, "%s: recovery finished s:%s\n", obd2cli_tgt(imp->imp_obd),
ptlrpc_import_state_name(imp->imp_state));
return rc;
#else
- ptlrpc_set_import_discon(imp, 0);
+ ptlrpc_set_import_discon(imp, 0, false);
/* Force a new connect attempt */
ptlrpc_invalidate_import(imp);
/* Do a fresh connect next time by zeroing the handle */
ptlrpc_disconnect_import(imp, 1);
/* Wait for all invalidate calls to finish */
if (atomic_read(&imp->imp_inval_count) > 0) {
- struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
int rc;
- rc = l_wait_event(imp->imp_recovery_waitq,
- (atomic_read(&imp->imp_inval_count) == 0),
- &lwi);
+ rc = l_wait_event_abortable(
+ imp->imp_recovery_waitq,
+ (atomic_read(&imp->imp_inval_count) == 0));
if (rc)
CERROR("Interrupted, inval=%d\n",
atomic_read(&imp->imp_inval_count));
/* Allow reconnect attempts */
imp->imp_obd->obd_no_recov = 0;
/* Remove 'invalid' flag */
- ptlrpc_activate_import(imp);
+ ptlrpc_activate_import(imp, false);
/* Attempt a new connect */
ptlrpc_recover_import(imp, NULL, 0);
return 0;
imp->imp_conn_current = imp_conn;
}
+ /* The below message is checked in conf-sanity.sh test_35[ab] */
CDEBUG(D_HA, "%s: import %p using connection %s/%s\n",
imp->imp_obd->obd_name, imp, imp_conn->oic_uuid.uuid,
libcfs_nid2str(imp_conn->oic_conn->c_peer.nid));
req = list_entry(tmp, struct ptlrpc_request, rq_replay_list);
*transno = req->rq_transno;
if (req->rq_transno == 0) {
- DEBUG_REQ(D_ERROR, req, "zero transno in committed_list");
+ DEBUG_REQ(D_ERROR, req,
+ "zero transno in committed_list");
LBUG();
}
return 1;
return 0;
}
+int ptlrpc_connect_import(struct obd_import *imp)
+{
+ spin_lock(&imp->imp_lock);
+ return ptlrpc_connect_import_locked(imp);
+}
+
/**
* Attempt to (re)connect import \a imp. This includes all preparations,
* initializing CONNECT RPC request and passing it to ptlrpcd for
* actual sending.
+ *
+ * Assumes imp->imp_lock is held, and releases it.
+ *
* Returns 0 on success or error code.
*/
-int ptlrpc_connect_import(struct obd_import *imp)
+int ptlrpc_connect_import_locked(struct obd_import *imp)
{
struct obd_device *obd = imp->imp_obd;
int initial_connect = 0;
int set_transno = 0;
__u64 committed_before_reconnect = 0;
struct ptlrpc_request *request;
+ struct obd_connect_data ocd;
char *bufs[] = { NULL,
obd2cli_tgt(imp->imp_obd),
obd->obd_uuid.uuid,
(char *)&imp->imp_dlm_handle,
- (char *)&imp->imp_connect_data };
+ (char *)&ocd,
+ NULL };
struct ptlrpc_connect_async_args *aa;
int rc;
ENTRY;
- spin_lock(&imp->imp_lock);
+ assert_spin_locked(&imp->imp_lock);
+
if (imp->imp_state == LUSTRE_IMP_CLOSED) {
spin_unlock(&imp->imp_lock);
CERROR("can't connect to a closed import\n");
RETURN(-EALREADY);
}
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_CONNECTING);
+ import_set_state_nolock(imp, LUSTRE_IMP_CONNECTING);
imp->imp_conn_cnt++;
imp->imp_resend_replay = 0;
/* Reset connect flags to the originally requested flags, in case
* the server is updated on-the-fly we will get the new features. */
- imp->imp_connect_data.ocd_connect_flags = imp->imp_connect_flags_orig;
- imp->imp_connect_data.ocd_connect_flags2 = imp->imp_connect_flags2_orig;
+ ocd = imp->imp_connect_data;
+ ocd.ocd_connect_flags = imp->imp_connect_flags_orig;
+ ocd.ocd_connect_flags2 = imp->imp_connect_flags2_orig;
/* Reset ocd_version each time so the server knows the exact versions */
- imp->imp_connect_data.ocd_version = LUSTRE_VERSION_CODE;
+ ocd.ocd_version = LUSTRE_VERSION_CODE;
imp->imp_msghdr_flags &= ~MSGHDR_AT_SUPPORT;
imp->imp_msghdr_flags &= ~MSGHDR_CKSUM_INCOMPAT18;
rc = obd_reconnect(NULL, imp->imp_obd->obd_self_export, obd,
- &obd->obd_uuid, &imp->imp_connect_data, NULL);
+ &obd->obd_uuid, &ocd, NULL);
if (rc)
GOTO(out, rc);
if (request == NULL)
GOTO(out, rc = -ENOMEM);
+ /* get SELinux policy info if any */
+ rc = sptlrpc_get_sepol(request);
+ if (rc < 0) {
+ ptlrpc_request_free(request);
+ GOTO(out, rc);
+ }
+
+ bufs[5] = request->rq_sepol;
+
+ req_capsule_set_size(&request->rq_pill, &RMF_SELINUX_POL, RCL_CLIENT,
+ strlen(request->rq_sepol) ?
+ strlen(request->rq_sepol) + 1 : 0);
+
rc = ptlrpc_request_bufs_pack(request, LUSTRE_OBD_VERSION,
imp->imp_connect_op, bufs, NULL);
if (rc) {
ptlrpc_request_set_replen(request);
request->rq_interpret_reply = ptlrpc_connect_interpret;
- CLASSERT(sizeof(*aa) <= sizeof(request->rq_async_args));
- aa = ptlrpc_req_async_args(request);
+ aa = ptlrpc_req_async_args(aa, request);
memset(aa, 0, sizeof *aa);
aa->pcaa_peer_committed = committed_before_reconnect;
rc = 0;
out:
if (rc != 0)
- IMPORT_SET_STATE(imp, LUSTRE_IMP_DISCON);
+ import_set_state(imp, LUSTRE_IMP_DISCON);
RETURN(rc);
}
struct client_obd *cli = &imp->imp_obd->u.cli;
spin_lock(&imp->imp_lock);
- list_del(&imp->imp_conn_current->oic_item);
- list_add(&imp->imp_conn_current->oic_item,
- &imp->imp_conn_list);
+ list_move(&imp->imp_conn_current->oic_item,
+ &imp->imp_conn_list);
imp->imp_last_success_conn =
imp->imp_conn_current->oic_last_attempt;
cli->cl_supp_cksum_types = OBD_CKSUM_ADLER;
}
cli->cl_cksum_type = obd_cksum_type_select(imp->imp_obd->obd_name,
- cli->cl_supp_cksum_types);
+ cli->cl_supp_cksum_types,
+ cli->cl_preferred_cksum_type);
if (ocd->ocd_connect_flags & OBD_CONNECT_BRW_SIZE)
cli->cl_max_pages_per_rpc =
* this leads to losing user settings done before such as
* disable lru_resize, etc. */
if (old_connect_flags != exp_connect_flags(exp) || init_connect) {
+ struct ldlm_namespace *ns = imp->imp_obd->obd_namespace;
+ __u64 changed_flags;
+
+ changed_flags =
+ ns->ns_connect_flags ^ ns->ns_orig_connect_flags;
CDEBUG(D_HA, "%s: Resetting ns_connect_flags to server "
"flags: %#llx\n", imp->imp_obd->obd_name,
ocd->ocd_connect_flags);
- imp->imp_obd->obd_namespace->ns_connect_flags =
- ocd->ocd_connect_flags;
- imp->imp_obd->obd_namespace->ns_orig_connect_flags =
- ocd->ocd_connect_flags;
+ ns->ns_connect_flags = (ns->ns_connect_flags & changed_flags) |
+ (ocd->ocd_connect_flags & ~changed_flags);
+ ns->ns_orig_connect_flags = ocd->ocd_connect_flags;
}
if (ocd->ocd_connect_flags & OBD_CONNECT_AT)
* full state for normal operations of disconnect it due to an error.
*/
static int ptlrpc_connect_interpret(const struct lu_env *env,
- struct ptlrpc_request *request,
- void *data, int rc)
+ struct ptlrpc_request *request,
+ void *data, int rc)
{
- struct ptlrpc_connect_async_args *aa = data;
- struct obd_import *imp = request->rq_import;
- struct lustre_handle old_hdl;
- __u64 old_connect_flags;
- int msg_flags;
+ struct ptlrpc_connect_async_args *aa = data;
+ struct obd_import *imp = request->rq_import;
+ struct lustre_handle old_hdl;
+ __u64 old_connect_flags;
+ int msg_flags;
struct obd_connect_data *ocd;
struct obd_export *exp = NULL;
int ret;
RETURN(0);
}
+ imp->imp_connect_error = rc;
if (rc) {
struct ptlrpc_request *free_req;
struct ptlrpc_request *tmp;
spin_lock(&imp->imp_lock);
- /* All imports are pingable */
- imp->imp_pingable = 1;
- imp->imp_force_reconnect = 0;
- imp->imp_force_verify = 0;
+ /* All imports are pingable */
+ imp->imp_pingable = 1;
+ imp->imp_force_reconnect = 0;
+ imp->imp_force_verify = 0;
imp->imp_connect_data = *ocd;
* because may reflect other routing, etc. */
at_reinit(&imp->imp_at.iat_net_latency, 0, 0);
ptlrpc_at_adj_net_latency(request,
- lustre_msg_get_service_time(request->rq_repmsg));
+ lustre_msg_get_service_time(
+ request->rq_repmsg));
/* Import flags should be updated before waking import at FULL state */
rc = ptlrpc_connect_set_flags(imp, ocd, old_connect_flags, exp,
spin_lock(&imp->imp_lock);
if (msg_flags & MSG_CONNECT_REPLAYABLE) {
imp->imp_replayable = 1;
- spin_unlock(&imp->imp_lock);
CDEBUG(D_HA, "connected to replayable target: %s\n",
obd2cli_tgt(imp->imp_obd));
} else {
imp->imp_replayable = 0;
- spin_unlock(&imp->imp_lock);
}
- /* if applies, adjust the imp->imp_msg_magic here
- * according to reply flags */
-
- imp->imp_remote_handle =
- *lustre_msg_get_handle(request->rq_repmsg);
-
- /* Initial connects are allowed for clients with non-random
- * uuids when servers are in recovery. Simply signal the
- * servers replay is complete and wait in REPLAY_WAIT. */
- if (msg_flags & MSG_CONNECT_RECOVERING) {
- CDEBUG(D_HA, "connect to %s during recovery\n",
- obd2cli_tgt(imp->imp_obd));
- IMPORT_SET_STATE(imp, LUSTRE_IMP_REPLAY_LOCKS);
- } else {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_FULL);
- ptlrpc_activate_import(imp);
- }
+ /* if applies, adjust the imp->imp_msg_magic here
+ * according to reply flags
+ */
- GOTO(finish, rc = 0);
- }
+ imp->imp_remote_handle =
+ *lustre_msg_get_handle(request->rq_repmsg);
- /* Determine what recovery state to move the import to. */
- if (MSG_CONNECT_RECONNECT & msg_flags) {
- memset(&old_hdl, 0, sizeof(old_hdl));
- if (!memcmp(&old_hdl, lustre_msg_get_handle(request->rq_repmsg),
- sizeof (old_hdl))) {
- LCONSOLE_WARN("Reconnect to %s (at @%s) failed due "
+ /* Initial connects are allowed for clients with non-random
+ * uuids when servers are in recovery. Simply signal the
+ * servers replay is complete and wait in REPLAY_WAIT.
+ */
+ if (msg_flags & MSG_CONNECT_RECOVERING) {
+ CDEBUG(D_HA, "connect to %s during recovery\n",
+ obd2cli_tgt(imp->imp_obd));
+ import_set_state_nolock(imp, LUSTRE_IMP_REPLAY_LOCKS);
+ spin_unlock(&imp->imp_lock);
+ } else {
+ spin_unlock(&imp->imp_lock);
+ ptlrpc_activate_import(imp, true);
+ }
+
+ GOTO(finish, rc = 0);
+ }
+
+ /* Determine what recovery state to move the import to. */
+ if (MSG_CONNECT_RECONNECT & msg_flags) {
+ memset(&old_hdl, 0, sizeof(old_hdl));
+ if (!memcmp(&old_hdl, lustre_msg_get_handle(request->rq_repmsg),
+ sizeof(old_hdl))) {
+ LCONSOLE_WARN("Reconnect to %s (at @%s) failed due "
"bad handle %#llx\n",
- obd2cli_tgt(imp->imp_obd),
- imp->imp_connection->c_remote_uuid.uuid,
- imp->imp_dlm_handle.cookie);
- GOTO(out, rc = -ENOTCONN);
- }
+ obd2cli_tgt(imp->imp_obd),
+ imp->imp_connection->c_remote_uuid.uuid,
+ imp->imp_dlm_handle.cookie);
+ GOTO(out, rc = -ENOTCONN);
+ }
- if (memcmp(&imp->imp_remote_handle,
- lustre_msg_get_handle(request->rq_repmsg),
- sizeof(imp->imp_remote_handle))) {
- int level = msg_flags & MSG_CONNECT_RECOVERING ?
- D_HA : D_WARNING;
-
- /* Bug 16611/14775: if server handle have changed,
- * that means some sort of disconnection happened.
- * If the server is not in recovery, that also means it
- * already erased all of our state because of previous
- * eviction. If it is in recovery - we are safe to
- * participate since we can reestablish all of our state
- * with server again */
- if ((MSG_CONNECT_RECOVERING & msg_flags)) {
- CDEBUG(level,"%s@%s changed server handle from "
+ if (memcmp(&imp->imp_remote_handle,
+ lustre_msg_get_handle(request->rq_repmsg),
+ sizeof(imp->imp_remote_handle))) {
+ int level = msg_flags & MSG_CONNECT_RECOVERING ?
+ D_HA : D_WARNING;
+
+ /* Bug 16611/14775: if server handle have changed,
+ * that means some sort of disconnection happened.
+ * If the server is not in recovery, that also means it
+ * already erased all of our state because of previous
+ * eviction. If it is in recovery - we are safe to
+ * participate since we can reestablish all of our state
+ * with server again
+ */
+ if ((MSG_CONNECT_RECOVERING & msg_flags)) {
+ CDEBUG(level,
+ "%s@%s changed server handle from "
"%#llx to %#llx"
- " but is still in recovery\n",
- obd2cli_tgt(imp->imp_obd),
- imp->imp_connection->c_remote_uuid.uuid,
- imp->imp_remote_handle.cookie,
- lustre_msg_get_handle(
- request->rq_repmsg)->cookie);
- } else {
- LCONSOLE_WARN("Evicted from %s (at %s) "
- "after server handle changed from "
+ " but is still in recovery\n",
+ obd2cli_tgt(imp->imp_obd),
+ imp->imp_connection->c_remote_uuid.uuid,
+ imp->imp_remote_handle.cookie,
+ lustre_msg_get_handle(
+ request->rq_repmsg)->cookie);
+ } else {
+ LCONSOLE_WARN("Evicted from %s (at %s) "
+ "after server handle changed from "
"%#llx to %#llx\n",
- obd2cli_tgt(imp->imp_obd),
- imp->imp_connection-> \
- c_remote_uuid.uuid,
- imp->imp_remote_handle.cookie,
- lustre_msg_get_handle(
- request->rq_repmsg)->cookie);
- }
-
-
- imp->imp_remote_handle =
- *lustre_msg_get_handle(request->rq_repmsg);
+ obd2cli_tgt(imp->imp_obd),
+ imp->imp_connection->
+ c_remote_uuid.uuid,
+ imp->imp_remote_handle.cookie,
+ lustre_msg_get_handle(
+ request->rq_repmsg)->cookie);
+ }
- if (!(MSG_CONNECT_RECOVERING & msg_flags)) {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_EVICTED);
- GOTO(finish, rc = 0);
- }
+ imp->imp_remote_handle =
+ *lustre_msg_get_handle(request->rq_repmsg);
- } else {
- CDEBUG(D_HA, "reconnected to %s@%s after partition\n",
- obd2cli_tgt(imp->imp_obd),
- imp->imp_connection->c_remote_uuid.uuid);
- }
+ if (!(MSG_CONNECT_RECOVERING & msg_flags)) {
+ import_set_state(imp, LUSTRE_IMP_EVICTED);
+ GOTO(finish, rc = 0);
+ }
+ } else {
+ CDEBUG(D_HA, "reconnected to %s@%s after partition\n",
+ obd2cli_tgt(imp->imp_obd),
+ imp->imp_connection->c_remote_uuid.uuid);
+ }
- if (imp->imp_invalid) {
- CDEBUG(D_HA, "%s: reconnected but import is invalid; "
- "marking evicted\n", imp->imp_obd->obd_name);
- IMPORT_SET_STATE(imp, LUSTRE_IMP_EVICTED);
- } else if (MSG_CONNECT_RECOVERING & msg_flags) {
- CDEBUG(D_HA, "%s: reconnected to %s during replay\n",
- imp->imp_obd->obd_name,
- obd2cli_tgt(imp->imp_obd));
+ if (imp->imp_invalid) {
+ CDEBUG(D_HA, "%s: reconnected but import is invalid; "
+ "marking evicted\n", imp->imp_obd->obd_name);
+ import_set_state(imp, LUSTRE_IMP_EVICTED);
+ } else if (MSG_CONNECT_RECOVERING & msg_flags) {
+ CDEBUG(D_HA, "%s: reconnected to %s during replay\n",
+ imp->imp_obd->obd_name,
+ obd2cli_tgt(imp->imp_obd));
spin_lock(&imp->imp_lock);
imp->imp_resend_replay = 1;
spin_unlock(&imp->imp_lock);
- IMPORT_SET_STATE(imp, imp->imp_replay_state);
- } else {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_RECOVER);
- }
- } else if ((MSG_CONNECT_RECOVERING & msg_flags) && !imp->imp_invalid) {
- LASSERT(imp->imp_replayable);
- imp->imp_remote_handle =
- *lustre_msg_get_handle(request->rq_repmsg);
- imp->imp_last_replay_transno = 0;
+ import_set_state(imp, imp->imp_replay_state);
+ } else {
+ import_set_state(imp, LUSTRE_IMP_RECOVER);
+ }
+ } else if ((MSG_CONNECT_RECOVERING & msg_flags) && !imp->imp_invalid) {
+ LASSERT(imp->imp_replayable);
+ imp->imp_remote_handle =
+ *lustre_msg_get_handle(request->rq_repmsg);
+ imp->imp_last_replay_transno = 0;
imp->imp_replay_cursor = &imp->imp_committed_list;
- IMPORT_SET_STATE(imp, LUSTRE_IMP_REPLAY);
- } else {
- DEBUG_REQ(D_HA, request, "%s: evicting (reconnect/recover flags"
- " not set: %x)", imp->imp_obd->obd_name, msg_flags);
- imp->imp_remote_handle =
- *lustre_msg_get_handle(request->rq_repmsg);
- IMPORT_SET_STATE(imp, LUSTRE_IMP_EVICTED);
- }
+ import_set_state(imp, LUSTRE_IMP_REPLAY);
+ } else if ((ocd->ocd_connect_flags & OBD_CONNECT_LIGHTWEIGHT) != 0 &&
+ !imp->imp_invalid) {
+
+ obd_import_event(imp->imp_obd, imp, IMP_EVENT_INVALIDATE);
+ /* The below message is checked in recovery-small.sh test_106 */
+ DEBUG_REQ(D_HA, request, "%s: lwp recover",
+ imp->imp_obd->obd_name);
+ imp->imp_remote_handle =
+ *lustre_msg_get_handle(request->rq_repmsg);
+ import_set_state(imp, LUSTRE_IMP_RECOVER);
+ } else {
+ DEBUG_REQ(D_HA, request,
+ "%s: evicting (reconnect/recover flags not set: %x)",
+ imp->imp_obd->obd_name, msg_flags);
+ imp->imp_remote_handle =
+ *lustre_msg_get_handle(request->rq_repmsg);
+ import_set_state(imp, LUSTRE_IMP_EVICTED);
+ }
- /* Sanity checks for a reconnected import. */
- if (!(imp->imp_replayable) != !(msg_flags & MSG_CONNECT_REPLAYABLE)) {
- CERROR("imp_replayable flag does not match server "
- "after reconnect. We should LBUG right here.\n");
- }
+ /* Sanity checks for a reconnected import. */
+ if (!(imp->imp_replayable) != !(msg_flags & MSG_CONNECT_REPLAYABLE))
+ CERROR("imp_replayable flag does not match server after reconnect. We should LBUG right here.\n");
+
+ if (lustre_msg_get_last_committed(request->rq_repmsg) > 0 &&
+ lustre_msg_get_last_committed(request->rq_repmsg) <
+ aa->pcaa_peer_committed) {
+ static bool printed;
- if (lustre_msg_get_last_committed(request->rq_repmsg) > 0 &&
- lustre_msg_get_last_committed(request->rq_repmsg) <
- aa->pcaa_peer_committed) {
- CERROR("%s went back in time (transno %lld"
- " was previously committed, server now claims %lld"
- ")! See https://bugzilla.lustre.org/show_bug.cgi?"
- "id=9646\n",
- obd2cli_tgt(imp->imp_obd), aa->pcaa_peer_committed,
+ /* The below message is checked in recovery-small.sh test_54 */
+ CERROR("%s: went back in time (transno %lld was previously committed, server now claims %lld)!\n",
+ obd2cli_tgt(imp->imp_obd), aa->pcaa_peer_committed,
lustre_msg_get_last_committed(request->rq_repmsg));
+ if (!printed) {
+ CERROR("For further information, see http://doc.lustre.org/lustre_manual.xhtml#went_back_in_time\n");
+ printed = true;
+ }
}
finish:
}
out:
- spin_lock(&imp->imp_lock);
- imp->imp_connected = 0;
- imp->imp_connect_tried = 1;
- spin_unlock(&imp->imp_lock);
-
if (exp != NULL)
class_export_put(exp);
- if (rc != 0) {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_DISCON);
- if (rc == -EACCES) {
- /*
- * Give up trying to reconnect
- * EACCES means client has no permission for connection
- */
- imp->imp_obd->obd_no_recov = 1;
- ptlrpc_deactivate_import(imp);
- }
-
- if (rc == -EPROTO) {
- struct obd_connect_data *ocd;
+ spin_lock(&imp->imp_lock);
+ imp->imp_connected = 0;
+ imp->imp_connect_tried = 1;
- /* reply message might not be ready */
- if (request->rq_repmsg == NULL)
- RETURN(-EPROTO);
+ if (rc != 0) {
+ bool inact = false;
+
+ import_set_state_nolock(imp, LUSTRE_IMP_DISCON);
+ if (rc == -EACCES) {
+ /*
+ * Give up trying to reconnect
+ * EACCES means client has no permission for connection
+ */
+ imp->imp_obd->obd_no_recov = 1;
+ ptlrpc_deactivate_import_nolock(imp);
+ inact = true;
+ } else if (rc == -EPROTO) {
+ struct obd_connect_data *ocd;
+
+ /* reply message might not be ready */
+ if (request->rq_repmsg == NULL) {
+ spin_unlock(&imp->imp_lock);
+ RETURN(-EPROTO);
+ }
ocd = req_capsule_server_get(&request->rq_pill,
&RMF_CONNECT_DATA);
if (ocd &&
(ocd->ocd_connect_flags & OBD_CONNECT_VERSION) &&
(ocd->ocd_version != LUSTRE_VERSION_CODE)) {
- LCONSOLE_ERROR_MSG(0x16a, "Server %s version "
- "(%d.%d.%d.%d)"
- " refused connection from this client "
- "with an incompatible version (%s). "
- "Client must be recompiled\n",
- obd2cli_tgt(imp->imp_obd),
- OBD_OCD_VERSION_MAJOR(ocd->ocd_version),
- OBD_OCD_VERSION_MINOR(ocd->ocd_version),
- OBD_OCD_VERSION_PATCH(ocd->ocd_version),
- OBD_OCD_VERSION_FIX(ocd->ocd_version),
- LUSTRE_VERSION_STRING);
- ptlrpc_deactivate_import(imp);
- IMPORT_SET_STATE(imp, LUSTRE_IMP_CLOSED);
- }
- RETURN(-EPROTO);
- }
+ LCONSOLE_ERROR_MSG(0x16a, "Server %s version "
+ "(%d.%d.%d.%d)"
+ " refused connection from this client "
+ "with an incompatible version (%s). "
+ "Client must be recompiled\n",
+ obd2cli_tgt(imp->imp_obd),
+ OBD_OCD_VERSION_MAJOR(ocd->ocd_version),
+ OBD_OCD_VERSION_MINOR(ocd->ocd_version),
+ OBD_OCD_VERSION_PATCH(ocd->ocd_version),
+ OBD_OCD_VERSION_FIX(ocd->ocd_version),
+ LUSTRE_VERSION_STRING);
+ ptlrpc_deactivate_import_nolock(imp);
+ import_set_state_nolock(imp, LUSTRE_IMP_CLOSED);
+ inact = true;
+ }
+ }
+ spin_unlock(&imp->imp_lock);
+
+ if (inact)
+ obd_import_event(imp->imp_obd, imp, IMP_EVENT_INACTIVE);
+
+ if (rc == -EPROTO)
+ RETURN(rc);
ptlrpc_maybe_ping_import_soon(imp);
CDEBUG(D_HA, "recovery of %s on %s failed (%d)\n",
obd2cli_tgt(imp->imp_obd),
(char *)imp->imp_connection->c_remote_uuid.uuid, rc);
+ } else {
+ spin_unlock(&imp->imp_lock);
}
- wake_up_all(&imp->imp_recovery_waitq);
+ wake_up(&imp->imp_recovery_waitq);
RETURN(rc);
}
libcfs_debug_dumplog();
}
- IMPORT_SET_STATE(imp, LUSTRE_IMP_RECOVER);
+ import_set_state(imp, LUSTRE_IMP_RECOVER);
ptlrpc_import_recovery_state_machine(imp);
class_import_put(imp);
rc = ptlrpc_replay_next(imp, &inflight);
if (inflight == 0 &&
atomic_read(&imp->imp_replay_inflight) == 0) {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_REPLAY_LOCKS);
+ import_set_state(imp, LUSTRE_IMP_REPLAY_LOCKS);
rc = ldlm_replay_locks(imp);
if (rc)
GOTO(out, rc);
if (imp->imp_state == LUSTRE_IMP_REPLAY_LOCKS) {
if (atomic_read(&imp->imp_replay_inflight) == 0) {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_REPLAY_WAIT);
+ import_set_state(imp, LUSTRE_IMP_REPLAY_WAIT);
rc = signal_completed_replay(imp);
if (rc)
GOTO(out, rc);
if (imp->imp_state == LUSTRE_IMP_REPLAY_WAIT) {
if (atomic_read(&imp->imp_replay_inflight) == 0) {
- IMPORT_SET_STATE(imp, LUSTRE_IMP_RECOVER);
+ import_set_state(imp, LUSTRE_IMP_RECOVER);
}
}
- if (imp->imp_state == LUSTRE_IMP_RECOVER) {
+ if (imp->imp_state == LUSTRE_IMP_RECOVER) {
struct ptlrpc_connection *conn = imp->imp_connection;
- rc = ptlrpc_resend(imp);
- if (rc)
- GOTO(out, rc);
- IMPORT_SET_STATE(imp, LUSTRE_IMP_FULL);
- ptlrpc_activate_import(imp);
-
- LCONSOLE_INFO("%s: Connection restored to %s (at %s)\n",
- imp->imp_obd->obd_name,
- obd_uuid2str(&conn->c_remote_uuid),
- obd_import_nid2str(imp));
- }
+ rc = ptlrpc_resend(imp);
+ if (rc)
+ GOTO(out, rc);
+ ptlrpc_activate_import(imp, true);
+
+ CDEBUG_LIMIT(imp->imp_was_idle ?
+ imp->imp_idle_debug : D_CONSOLE,
+ "%s: Connection restored to %s (at %s)\n",
+ imp->imp_obd->obd_name,
+ obd_uuid2str(&conn->c_remote_uuid),
+ obd_import_nid2str(imp));
+ spin_lock(&imp->imp_lock);
+ imp->imp_was_idle = 0;
+ spin_unlock(&imp->imp_lock);
+ }
if (imp->imp_state == LUSTRE_IMP_FULL) {
- wake_up_all(&imp->imp_recovery_waitq);
+ wake_up(&imp->imp_recovery_waitq);
ptlrpc_wake_delayed(imp);
}
req = ptlrpc_request_alloc_pack(imp, &RQF_MDS_DISCONNECT,
LUSTRE_OBD_VERSION, rq_opc);
if (req == NULL)
- RETURN(NULL);
+ RETURN(ERR_PTR(-ENOMEM));
/* We are disconnecting, do not retry a failed DISCONNECT rpc if
* it fails. We can get through the above with a down server
req->rq_timeout = min_t(int, req->rq_timeout,
INITIAL_CONNECT_TIMEOUT);
- IMPORT_SET_STATE(imp, LUSTRE_IMP_CONNECTING);
+ import_set_state(imp, LUSTRE_IMP_CONNECTING);
req->rq_send_state = LUSTRE_IMP_CONNECTING;
ptlrpc_request_set_replen(req);
spin_unlock(&imp->imp_lock);
if (ptlrpc_import_in_recovery(imp)) {
- struct l_wait_info lwi;
long timeout_jiffies;
time64_t timeout;
req_portal = imp->imp_client->cli_request_portal;
idx = import_at_get_index(imp, req_portal);
timeout = at_get(&imp->imp_at.iat_service_estimate[idx]);
- }
+ }
timeout_jiffies = cfs_time_seconds(timeout);
- lwi = LWI_TIMEOUT_INTR(max_t(long, timeout_jiffies, 1),
- back_to_sleep, LWI_ON_SIGNAL_NOOP, NULL);
- rc = l_wait_event(imp->imp_recovery_waitq,
- !ptlrpc_import_in_recovery(imp), &lwi);
-
- }
+ if (wait_event_idle_timeout(imp->imp_recovery_waitq,
+ !ptlrpc_import_in_recovery(imp),
+ timeout_jiffies) == 0 &&
+ l_wait_event_abortable(imp->imp_recovery_waitq,
+ !ptlrpc_import_in_recovery(imp)) < 0)
+ rc = -EINTR;
+ }
spin_lock(&imp->imp_lock);
if (imp->imp_state != LUSTRE_IMP_FULL)
spin_lock(&imp->imp_lock);
out:
if (noclose)
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_DISCON);
+ import_set_state_nolock(imp, LUSTRE_IMP_DISCON);
else
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_CLOSED);
+ import_set_state_nolock(imp, LUSTRE_IMP_CLOSED);
memset(&imp->imp_remote_handle, 0, sizeof(imp->imp_remote_handle));
spin_unlock(&imp->imp_lock);
}
EXPORT_SYMBOL(ptlrpc_disconnect_import);
+static void ptlrpc_reset_reqs_generation(struct obd_import *imp)
+{
+ struct ptlrpc_request *old, *tmp;
+
+ /* tag all resendable requests generated before disconnection
+ * notice this code is part of disconnect-at-idle path only */
+ list_for_each_entry_safe(old, tmp, &imp->imp_delayed_list,
+ rq_list) {
+ spin_lock(&old->rq_lock);
+ if (old->rq_import_generation == imp->imp_generation - 1 &&
+ ((imp->imp_initiated_at == imp->imp_generation) ||
+ !old->rq_no_resend))
+ old->rq_import_generation = imp->imp_generation;
+ spin_unlock(&old->rq_lock);
+ }
+}
+
static int ptlrpc_disconnect_idle_interpret(const struct lu_env *env,
struct ptlrpc_request *req,
void *args, int rc)
struct obd_import *imp = req->rq_import;
int connect = 0;
- DEBUG_REQ(D_HA, req, "inflight=%d, refcount=%d: rc = %d\n",
+ DEBUG_REQ(D_HA, req, "inflight=%d, refcount=%d: rc = %d",
atomic_read(&imp->imp_inflight),
atomic_read(&imp->imp_refcount), rc);
if (atomic_read(&imp->imp_inflight) > 1) {
imp->imp_generation++;
imp->imp_initiated_at = imp->imp_generation;
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_NEW);
+ import_set_state_nolock(imp, LUSTRE_IMP_NEW);
+ ptlrpc_reset_reqs_generation(imp);
connect = 1;
}
}
- spin_unlock(&imp->imp_lock);
if (connect) {
- rc = ptlrpc_connect_import(imp);
+ rc = ptlrpc_connect_import_locked(imp);
if (rc >= 0)
ptlrpc_pinger_add_import(imp);
+ } else {
+ spin_unlock(&imp->imp_lock);
}
return 0;
CDEBUG_LIMIT(imp->imp_idle_debug, "%s: disconnect after %llus idle\n",
imp->imp_obd->obd_name,
ktime_get_real_seconds() - imp->imp_last_reply_time);
+
+ /* don't make noise at reconnection */
+ spin_lock(&imp->imp_lock);
+ imp->imp_was_idle = 1;
+ spin_unlock(&imp->imp_lock);
+
req->rq_interpret_reply = ptlrpc_disconnect_idle_interpret;
ptlrpcd_add_req(req);
ENTRY;
spin_lock(&imp->imp_lock);
- IMPORT_SET_STATE_NOLOCK(imp, LUSTRE_IMP_CLOSED);
+
+ import_set_state_nolock(imp, LUSTRE_IMP_CLOSED);
imp->imp_generation++;
- spin_unlock(&imp->imp_lock);
ptlrpc_abort_inflight(imp);
+ spin_unlock(&imp->imp_lock);
+
EXIT;
}
/* Adaptive Timeout utils */
-extern unsigned int at_min, at_max, at_history;
/* Update at_current with the specified value (bounded by at_min and at_max),
* as well as the AT history "bins".
git://git.whamcloud.com / fs / lustre-release.git / blobdiff