* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2015, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* Author: Eric Barton <eric@bartonsoftware.com>
*/
-#include <linux/pci.h>
#include "socklnd.h"
+#include <linux/inetdevice.h>
static struct lnet_lnd the_ksocklnd;
struct ksock_nal_data ksocknal_data;
struct ksock_interface *iface;
for (i = 0; i < net->ksnn_ninterfaces; i++) {
- LASSERT(i < LNET_NUM_INTERFACES);
+ LASSERT(i < LNET_INTERFACES_NUM);
iface = &net->ksnn_interfaces[i];
if (iface->ksni_ipaddr == ip)
struct ksock_interface *iface;
for (i = 0; i < peer_ni->ksnp_n_passive_ips; i++) {
- LASSERT(i < LNET_NUM_INTERFACES);
+ LASSERT(i < LNET_INTERFACES_NUM);
ip = peer_ni->ksnp_passive_ips[i];
iface = ksocknal_ip2iface(peer_ni->ksnp_ni, ip);
}
ksocknal_peer_decref(peer_ni);
- /* NB peer_ni unlinks itself when last conn/route is removed */
+ /* NB peer_ni unlinks itself when last conn/route is removed */
}
static int
ksocknal_del_peer(struct lnet_ni *ni, struct lnet_process_id id, __u32 ip)
{
- struct list_head zombies = LIST_HEAD_INIT(zombies);
+ LIST_HEAD(zombies);
struct list_head *ptmp;
struct list_head *pnxt;
struct ksock_peer_ni *peer_ni;
static struct ksock_sched *
ksocknal_choose_scheduler_locked(unsigned int cpt)
{
- struct ksock_sched_info *info = ksocknal_data.ksnd_sched_info[cpt];
- struct ksock_sched *sched;
+ struct ksock_sched *sched = ksocknal_data.ksnd_schedulers[cpt];
int i;
- if (info->ksi_nthreads == 0) {
- cfs_percpt_for_each(info, i, ksocknal_data.ksnd_sched_info) {
- if (info->ksi_nthreads > 0) {
+ if (sched->kss_nthreads == 0) {
+ cfs_percpt_for_each(sched, i, ksocknal_data.ksnd_schedulers) {
+ if (sched->kss_nthreads > 0) {
CDEBUG(D_NET, "scheduler[%d] has no threads. selected scheduler[%d]\n",
- cpt, info->ksi_cpt);
- goto select_sched;
+ cpt, sched->kss_cpt);
+ return sched;
}
}
return NULL;
}
-select_sched:
- sched = &info->ksi_scheds[0];
- /*
- * NB: it's safe so far, but info->ksi_nthreads could be changed
- * at runtime when we have dynamic LNet configuration, then we
- * need to take care of this.
- */
- for (i = 1; i < info->ksi_nthreads; i++) {
- if (sched->kss_nconns > info->ksi_scheds[i].kss_nconns)
- sched = &info->ksi_scheds[i];
- }
-
return sched;
}
read_lock(&ksocknal_data.ksnd_global_lock);
nip = net->ksnn_ninterfaces;
- LASSERT(nip <= LNET_NUM_INTERFACES);
+ LASSERT(nip <= LNET_INTERFACES_NUM);
/*
* Only offer interfaces for additional connections if I have
write_lock_bh(global_lock);
- LASSERT(n_peerips <= LNET_NUM_INTERFACES);
- LASSERT(net->ksnn_ninterfaces <= LNET_NUM_INTERFACES);
+ LASSERT(n_peerips <= LNET_INTERFACES_NUM);
+ LASSERT(net->ksnn_ninterfaces <= LNET_INTERFACES_NUM);
/* Only match interfaces for additional connections
* if I have > 1 interface */
return;
}
- LASSERT(npeer_ipaddrs <= LNET_NUM_INTERFACES);
+ LASSERT(npeer_ipaddrs <= LNET_INTERFACES_NUM);
for (i = 0; i < npeer_ipaddrs; i++) {
if (newroute != NULL) {
best_nroutes = 0;
best_netmatch = 0;
- LASSERT(net->ksnn_ninterfaces <= LNET_NUM_INTERFACES);
+ LASSERT(net->ksnn_ninterfaces <= LNET_INTERFACES_NUM);
/* Select interface to connect from */
for (j = 0; j < net->ksnn_ninterfaces; j++) {
struct socket *sock, int type)
{
rwlock_t *global_lock = &ksocknal_data.ksnd_global_lock;
- struct list_head zombies = LIST_HEAD_INIT(zombies);
+ LIST_HEAD(zombies);
struct lnet_process_id peerid;
struct list_head *tmp;
u64 incarnation;
atomic_set (&conn->ksnc_tx_nob, 0);
LIBCFS_ALLOC(hello, offsetof(struct ksock_hello_msg,
- kshm_ips[LNET_NUM_INTERFACES]));
+ kshm_ips[LNET_INTERFACES_NUM]));
if (hello == NULL) {
rc = -ENOMEM;
goto failed_1;
* The cpt might have changed if we ended up selecting a non cpt
* native scheduler. So use the scheduler's cpt instead.
*/
- cpt = sched->kss_info->ksi_cpt;
+ cpt = sched->kss_cpt;
sched->kss_nconns++;
conn->ksnc_scheduler = sched;
/* Set the deadline for the outgoing HELLO to drain */
conn->ksnc_tx_bufnob = sock->sk->sk_wmem_queued;
conn->ksnc_tx_deadline = ktime_get_seconds() +
- *ksocknal_tunables.ksnd_timeout;
+ lnet_get_lnd_timeout();
smp_mb(); /* order with adding to peer_ni's conn list */
list_add(&conn->ksnc_list, &peer_ni->ksnp_conns);
*/
CDEBUG(D_NET, "New conn %s p %d.x %pI4h -> %pI4h/%d"
- " incarnation:%lld sched[%d:%d]\n",
+ " incarnation:%lld sched[%d]\n",
libcfs_id2str(peerid), conn->ksnc_proto->pro_version,
&conn->ksnc_myipaddr, &conn->ksnc_ipaddr,
- conn->ksnc_port, incarnation, cpt,
- (int)(sched - &sched->kss_info->ksi_scheds[0]));
+ conn->ksnc_port, incarnation, cpt);
if (active) {
/* additional routes after interface exchange? */
}
LIBCFS_FREE(hello, offsetof(struct ksock_hello_msg,
- kshm_ips[LNET_NUM_INTERFACES]));
+ kshm_ips[LNET_INTERFACES_NUM]));
/* setup the socket AFTER I've received hello (it disables
* SO_LINGER). I might call back to the acceptor who may want
failed_1:
if (hello != NULL)
LIBCFS_FREE(hello, offsetof(struct ksock_hello_msg,
- kshm_ips[LNET_NUM_INTERFACES]));
+ kshm_ips[LNET_INTERFACES_NUM]));
LIBCFS_FREE(conn, sizeof(*conn));
/* No more connections to this peer_ni */
if (!list_empty(&peer_ni->ksnp_tx_queue)) {
- struct ksock_tx *tx;
+ struct ksock_tx *tx;
LASSERT(conn->ksnc_proto == &ksocknal_protocol_v3x);
spin_lock_bh(&ksocknal_data.ksnd_reaper_lock);
- list_add_tail(&conn->ksnc_list,
- &ksocknal_data.ksnd_deathrow_conns);
+ list_add_tail(&conn->ksnc_list, &ksocknal_data.ksnd_deathrow_conns);
wake_up(&ksocknal_data.ksnd_reaper_waitq);
spin_unlock_bh(&ksocknal_data.ksnd_reaper_lock);
read_unlock(&ksocknal_data.ksnd_global_lock);
if (notify)
- lnet_notify(peer_ni->ksnp_ni, peer_ni->ksnp_id.nid, 0,
- cfs_time_seconds(last_alive)); /* to jiffies */
+ lnet_notify(peer_ni->ksnp_ni, peer_ni->ksnp_id.nid,
+ false, false, last_alive);
}
void
struct ksock_peer_ni *peer_ni = conn->ksnc_peer;
struct ksock_tx *tx;
struct ksock_tx *tmp;
- struct list_head zlist = LIST_HEAD_INIT(zlist);
+ LIST_HEAD(zlist);
/* NB safe to finalize TXs because closing of socket will
* abort all buffered data */
switch (conn->ksnc_rx_state) {
case SOCKNAL_RX_LNET_PAYLOAD:
last_rcv = conn->ksnc_rx_deadline -
- *ksocknal_tunables.ksnd_timeout;
+ lnet_get_lnd_timeout();
CERROR("Completing partial receive from %s[%d], "
"ip %pI4h:%d, with error, wanted: %d, left: %d, "
"last alive is %lld secs ago\n",
&conn->ksnc_ipaddr, conn->ksnc_port,
conn->ksnc_rx_nob_wanted, conn->ksnc_rx_nob_left,
ktime_get_seconds() - last_rcv);
- lnet_finalize(conn->ksnc_cookie, -EIO);
+ if (conn->ksnc_lnet_msg)
+ conn->ksnc_lnet_msg->msg_health_status =
+ LNET_MSG_STATUS_REMOTE_ERROR;
+ lnet_finalize(conn->ksnc_lnet_msg, -EIO);
break;
case SOCKNAL_RX_LNET_HEADER:
if (conn->ksnc_rx_started)
}
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
-ksocknal_query(struct lnet_ni *ni, lnet_nid_t nid, cfs_time_t *when)
+ksocknal_query(struct lnet_ni *ni, lnet_nid_t nid, time64_t *when)
{
int connect = 1;
time64_t last_alive = 0;
if (bufnob < conn->ksnc_tx_bufnob) {
/* something got ACKed */
conn->ksnc_tx_deadline = ktime_get_seconds() +
- *ksocknal_tunables.ksnd_timeout;
+ lnet_get_lnd_timeout();
peer_ni->ksnp_last_alive = now;
conn->ksnc_tx_bufnob = bufnob;
}
read_unlock(glock);
if (last_alive != 0)
- *when = cfs_time_seconds(last_alive);
+ *when = last_alive;
CDEBUG(D_NET, "peer_ni %s %p, alive %lld secs ago, connect %d\n",
libcfs_nid2str(nid), peer_ni,
ksocknal_launch_all_connections_locked(peer_ni);
write_unlock_bh(glock);
- return;
}
static void
}
read_unlock(&ksocknal_data.ksnd_global_lock);
- if (i == 0) /* no match */
+ if (i <= peer_off) /* no match */
break;
rc = 0;
if (iface != NULL) {
/* silently ignore dups */
rc = 0;
- } else if (net->ksnn_ninterfaces == LNET_NUM_INTERFACES) {
+ } else if (net->ksnn_ninterfaces == LNET_INTERFACES_NUM) {
rc = -ENOSPC;
} else {
iface = &net->ksnn_interfaces[net->ksnn_ninterfaces++];
data->ioc_u32[1] = conn->ksnc_port;
data->ioc_u32[2] = conn->ksnc_myipaddr;
data->ioc_u32[3] = conn->ksnc_type;
- data->ioc_u32[4] = conn->ksnc_scheduler->kss_info->ksi_cpt;
+ data->ioc_u32[4] = conn->ksnc_scheduler->kss_cpt;
data->ioc_u32[5] = rxmem;
data->ioc_u32[6] = conn->ksnc_peer->ksnp_id.pid;
ksocknal_conn_decref(conn);
{
LASSERT (atomic_read(&ksocknal_data.ksnd_nactive_txs) == 0);
- if (ksocknal_data.ksnd_sched_info != NULL) {
- struct ksock_sched_info *info;
- int i;
-
- cfs_percpt_for_each(info, i, ksocknal_data.ksnd_sched_info) {
- if (info->ksi_scheds != NULL) {
- LIBCFS_FREE(info->ksi_scheds,
- info->ksi_nthreads_max *
- sizeof(info->ksi_scheds[0]));
- }
- }
- cfs_percpt_free(ksocknal_data.ksnd_sched_info);
- }
+ if (ksocknal_data.ksnd_schedulers != NULL)
+ cfs_percpt_free(ksocknal_data.ksnd_schedulers);
LIBCFS_FREE (ksocknal_data.ksnd_peers,
sizeof(struct list_head) *
static void
ksocknal_base_shutdown(void)
{
- struct ksock_sched_info *info;
struct ksock_sched *sched;
int i;
- int j;
CDEBUG(D_MALLOC, "before NAL cleanup: kmem %d\n",
atomic_read (&libcfs_kmemory));
LASSERT (ksocknal_data.ksnd_nnets == 0);
- switch (ksocknal_data.ksnd_init) {
- default:
- LASSERT (0);
+ switch (ksocknal_data.ksnd_init) {
+ default:
+ LASSERT(0);
+ /* fallthrough */
- case SOCKNAL_INIT_ALL:
- case SOCKNAL_INIT_DATA:
- LASSERT (ksocknal_data.ksnd_peers != NULL);
- for (i = 0; i < ksocknal_data.ksnd_peer_hash_size; i++) {
+ case SOCKNAL_INIT_ALL:
+ case SOCKNAL_INIT_DATA:
+ LASSERT(ksocknal_data.ksnd_peers != NULL);
+ for (i = 0; i < ksocknal_data.ksnd_peer_hash_size; i++)
LASSERT(list_empty(&ksocknal_data.ksnd_peers[i]));
- }
LASSERT(list_empty(&ksocknal_data.ksnd_nets));
LASSERT(list_empty(&ksocknal_data.ksnd_enomem_conns));
LASSERT(list_empty(&ksocknal_data.ksnd_connd_connreqs));
LASSERT(list_empty(&ksocknal_data.ksnd_connd_routes));
- if (ksocknal_data.ksnd_sched_info != NULL) {
- cfs_percpt_for_each(info, i,
- ksocknal_data.ksnd_sched_info) {
- if (info->ksi_scheds == NULL)
- continue;
-
- for (j = 0; j < info->ksi_nthreads_max; j++) {
+ if (ksocknal_data.ksnd_schedulers != NULL) {
+ cfs_percpt_for_each(sched, i,
+ ksocknal_data.ksnd_schedulers) {
- sched = &info->ksi_scheds[j];
- LASSERT(list_empty(&sched->\
- kss_tx_conns));
- LASSERT(list_empty(&sched->\
- kss_rx_conns));
- LASSERT(list_empty(&sched-> \
- kss_zombie_noop_txs));
- LASSERT(sched->kss_nconns == 0);
- }
+ LASSERT(list_empty(&sched->kss_tx_conns));
+ LASSERT(list_empty(&sched->kss_rx_conns));
+ LASSERT(list_empty(&sched->kss_zombie_noop_txs));
+ LASSERT(sched->kss_nconns == 0);
}
}
wake_up_all(&ksocknal_data.ksnd_connd_waitq);
wake_up_all(&ksocknal_data.ksnd_reaper_waitq);
- if (ksocknal_data.ksnd_sched_info != NULL) {
- cfs_percpt_for_each(info, i,
- ksocknal_data.ksnd_sched_info) {
- if (info->ksi_scheds == NULL)
- continue;
-
- for (j = 0; j < info->ksi_nthreads_max; j++) {
- sched = &info->ksi_scheds[j];
+ if (ksocknal_data.ksnd_schedulers != NULL) {
+ cfs_percpt_for_each(sched, i,
+ ksocknal_data.ksnd_schedulers)
wake_up_all(&sched->kss_waitq);
- }
- }
}
i = 4;
static int
ksocknal_base_startup(void)
{
- struct ksock_sched_info *info;
- int rc;
- int i;
+ struct ksock_sched *sched;
+ int rc;
+ int i;
LASSERT (ksocknal_data.ksnd_init == SOCKNAL_INIT_NOTHING);
LASSERT (ksocknal_data.ksnd_nnets == 0);
ksocknal_data.ksnd_init = SOCKNAL_INIT_DATA;
try_module_get(THIS_MODULE);
- ksocknal_data.ksnd_sched_info = cfs_percpt_alloc(lnet_cpt_table(),
- sizeof(*info));
- if (ksocknal_data.ksnd_sched_info == NULL)
+ /* Create a scheduler block per available CPT */
+ ksocknal_data.ksnd_schedulers = cfs_percpt_alloc(lnet_cpt_table(),
+ sizeof(*sched));
+ if (ksocknal_data.ksnd_schedulers == NULL)
goto failed;
- cfs_percpt_for_each(info, i, ksocknal_data.ksnd_sched_info) {
- struct ksock_sched *sched;
+ cfs_percpt_for_each(sched, i, ksocknal_data.ksnd_schedulers) {
int nthrs;
+ /*
+ * make sure not to allocate more threads than there are
+ * cores/CPUs in teh CPT
+ */
nthrs = cfs_cpt_weight(lnet_cpt_table(), i);
if (*ksocknal_tunables.ksnd_nscheds > 0) {
nthrs = min(nthrs, *ksocknal_tunables.ksnd_nscheds);
} else {
- /* max to half of CPUs, assume another half should be
- * reserved for upper layer modules */
+ /*
+ * max to half of CPUs, assume another half should be
+ * reserved for upper layer modules
+ */
nthrs = min(max(SOCKNAL_NSCHEDS, nthrs >> 1), nthrs);
}
- info->ksi_nthreads_max = nthrs;
- info->ksi_cpt = i;
-
- if (nthrs != 0) {
- LIBCFS_CPT_ALLOC(info->ksi_scheds, lnet_cpt_table(), i,
- info->ksi_nthreads_max *
- sizeof(*sched));
- if (info->ksi_scheds == NULL)
- goto failed;
-
- for (; nthrs > 0; nthrs--) {
- sched = &info->ksi_scheds[nthrs - 1];
-
- sched->kss_info = info;
- spin_lock_init(&sched->kss_lock);
- INIT_LIST_HEAD(&sched->kss_rx_conns);
- INIT_LIST_HEAD(&sched->kss_tx_conns);
- INIT_LIST_HEAD(&sched->kss_zombie_noop_txs);
- init_waitqueue_head(&sched->kss_waitq);
- }
- }
+ sched->kss_nthreads_max = nthrs;
+ sched->kss_cpt = i;
+
+ spin_lock_init(&sched->kss_lock);
+ INIT_LIST_HEAD(&sched->kss_rx_conns);
+ INIT_LIST_HEAD(&sched->kss_tx_conns);
+ INIT_LIST_HEAD(&sched->kss_zombie_noop_txs);
+ init_waitqueue_head(&sched->kss_waitq);
}
ksocknal_data.ksnd_connd_starting = 0;
read_lock(&ksocknal_data.ksnd_global_lock);
- for (i = 0; i < ksocknal_data.ksnd_peer_hash_size; i++) {
+ for (i = 0; i < ksocknal_data.ksnd_peer_hash_size; i++) {
list_for_each(tmp, &ksocknal_data.ksnd_peers[i]) {
peer_ni = list_entry(tmp, struct ksock_peer_ni, ksnp_list);
- if (peer_ni->ksnp_ni == ni) break;
+ if (peer_ni->ksnp_ni == ni)
+ break;
- peer_ni = NULL;
- }
- }
+ peer_ni = NULL;
+ }
+ }
if (peer_ni != NULL) {
struct ksock_route *route;
struct ksock_conn *conn;
- CWARN ("Active peer_ni on shutdown: %s, ref %d, scnt %d, "
- "closing %d, accepting %d, err %d, zcookie %llu, "
- "txq %d, zc_req %d\n", libcfs_id2str(peer_ni->ksnp_id),
- atomic_read(&peer_ni->ksnp_refcount),
- peer_ni->ksnp_sharecount, peer_ni->ksnp_closing,
- peer_ni->ksnp_accepting, peer_ni->ksnp_error,
- peer_ni->ksnp_zc_next_cookie,
- !list_empty(&peer_ni->ksnp_tx_queue),
- !list_empty(&peer_ni->ksnp_zc_req_list));
+ CWARN("Active peer_ni on shutdown: %s, ref %d, "
+ "closing %d, accepting %d, err %d, zcookie %llu, "
+ "txq %d, zc_req %d\n", libcfs_id2str(peer_ni->ksnp_id),
+ atomic_read(&peer_ni->ksnp_refcount),
+ peer_ni->ksnp_closing,
+ peer_ni->ksnp_accepting, peer_ni->ksnp_error,
+ peer_ni->ksnp_zc_next_cookie,
+ !list_empty(&peer_ni->ksnp_tx_queue),
+ !list_empty(&peer_ni->ksnp_zc_req_list));
list_for_each(tmp, &peer_ni->ksnp_routes) {
route = list_entry(tmp, struct ksock_route, ksnr_list);
- CWARN ("Route: ref %d, schd %d, conn %d, cnted %d, "
- "del %d\n", atomic_read(&route->ksnr_refcount),
- route->ksnr_scheduled, route->ksnr_connecting,
- route->ksnr_connected, route->ksnr_deleted);
+ CWARN("Route: ref %d, schd %d, conn %d, cnted %d, "
+ "del %d\n", atomic_read(&route->ksnr_refcount),
+ route->ksnr_scheduled, route->ksnr_connecting,
+ route->ksnr_connected, route->ksnr_deleted);
}
list_for_each(tmp, &peer_ni->ksnp_conns) {
conn = list_entry(tmp, struct ksock_conn, ksnc_list);
- CWARN ("Conn: ref %d, sref %d, t %d, c %d\n",
- atomic_read(&conn->ksnc_conn_refcount),
- atomic_read(&conn->ksnc_sock_refcount),
- conn->ksnc_type, conn->ksnc_closing);
+ CWARN("Conn: ref %d, sref %d, t %d, c %d\n",
+ atomic_read(&conn->ksnc_conn_refcount),
+ atomic_read(&conn->ksnc_sock_refcount),
+ conn->ksnc_type, conn->ksnc_closing);
}
}
read_unlock(&ksocknal_data.ksnd_global_lock);
- return;
}
void
}
static int
-ksocknal_enumerate_interfaces(struct ksock_net *net)
-{
- char **names;
- int i;
- int j;
- int rc;
- int n;
-
- n = lnet_ipif_enumerate(&names);
- if (n <= 0) {
- CERROR("Can't enumerate interfaces: %d\n", n);
- return n;
- }
-
- for (i = j = 0; i < n; i++) {
- int up;
- __u32 ip;
- __u32 mask;
-
- if (!strcmp(names[i], "lo")) /* skip the loopback IF */
- continue;
-
- rc = lnet_ipif_query(names[i], &up, &ip, &mask);
- if (rc != 0) {
- CWARN("Can't get interface %s info: %d\n",
- names[i], rc);
- continue;
- }
-
- if (!up) {
- CWARN("Ignoring interface %s (down)\n",
- names[i]);
- continue;
- }
-
- if (j == LNET_NUM_INTERFACES) {
- CWARN("Ignoring interface %s (too many interfaces)\n",
- names[i]);
- continue;
- }
-
- net->ksnn_interfaces[j].ksni_ipaddr = ip;
- net->ksnn_interfaces[j].ksni_netmask = mask;
- strlcpy(net->ksnn_interfaces[j].ksni_name,
- names[i], sizeof(net->ksnn_interfaces[j].ksni_name));
- j++;
- }
-
- lnet_ipif_free_enumeration(names, n);
-
- if (j == 0)
- CERROR("Can't find any usable interfaces\n");
-
- return j;
-}
-
-static int
ksocknal_search_new_ipif(struct ksock_net *net)
{
int new_ipif = 0;
}
static int
-ksocknal_start_schedulers(struct ksock_sched_info *info)
+ksocknal_start_schedulers(struct ksock_sched *sched)
{
int nthrs;
int rc = 0;
int i;
- if (info->ksi_nthreads == 0) {
+ if (sched->kss_nthreads == 0) {
if (*ksocknal_tunables.ksnd_nscheds > 0) {
- nthrs = info->ksi_nthreads_max;
+ nthrs = sched->kss_nthreads_max;
} else {
nthrs = cfs_cpt_weight(lnet_cpt_table(),
- info->ksi_cpt);
+ sched->kss_cpt);
nthrs = min(max(SOCKNAL_NSCHEDS, nthrs >> 1), nthrs);
nthrs = min(SOCKNAL_NSCHEDS_HIGH, nthrs);
}
- nthrs = min(nthrs, info->ksi_nthreads_max);
+ nthrs = min(nthrs, sched->kss_nthreads_max);
} else {
- LASSERT(info->ksi_nthreads <= info->ksi_nthreads_max);
+ LASSERT(sched->kss_nthreads <= sched->kss_nthreads_max);
/* increase two threads if there is new interface */
- nthrs = min(2, info->ksi_nthreads_max - info->ksi_nthreads);
+ nthrs = min(2, sched->kss_nthreads_max - sched->kss_nthreads);
}
for (i = 0; i < nthrs; i++) {
long id;
char name[20];
- struct ksock_sched *sched;
- id = KSOCK_THREAD_ID(info->ksi_cpt, info->ksi_nthreads + i);
- sched = &info->ksi_scheds[KSOCK_THREAD_SID(id)];
+ id = KSOCK_THREAD_ID(sched->kss_cpt, sched->kss_nthreads + i);
snprintf(name, sizeof(name), "socknal_sd%02d_%02d",
- info->ksi_cpt, (int)(sched - &info->ksi_scheds[0]));
+ sched->kss_cpt, (int)KSOCK_THREAD_SID(id));
rc = ksocknal_thread_start(ksocknal_scheduler,
(void *)id, name);
continue;
CERROR("Can't spawn thread %d for scheduler[%d]: %d\n",
- info->ksi_cpt, info->ksi_nthreads + i, rc);
+ sched->kss_cpt, (int) KSOCK_THREAD_SID(id), rc);
break;
}
- info->ksi_nthreads += i;
+ sched->kss_nthreads += i;
return rc;
}
return -EINVAL;
for (i = 0; i < ncpts; i++) {
- struct ksock_sched_info *info;
+ struct ksock_sched *sched;
int cpt = (cpts == NULL) ? i : cpts[i];
LASSERT(cpt < cfs_cpt_number(lnet_cpt_table()));
- info = ksocknal_data.ksnd_sched_info[cpt];
+ sched = ksocknal_data.ksnd_schedulers[cpt];
- if (!newif && info->ksi_nthreads > 0)
+ if (!newif && sched->kss_nthreads > 0)
continue;
- rc = ksocknal_start_schedulers(info);
+ rc = ksocknal_start_schedulers(sched);
if (rc != 0)
return rc;
}
ksocknal_startup(struct lnet_ni *ni)
{
struct ksock_net *net;
+ struct lnet_ioctl_config_lnd_cmn_tunables *net_tunables;
+ struct ksock_interface *ksi = NULL;
+ struct lnet_inetdev *ifaces = NULL;
+ int i = 0;
int rc;
- int i;
- struct net_device *net_dev;
- int node_id;
LASSERT (ni->ni_net->net_lnd == &the_ksocklnd);
spin_lock_init(&net->ksnn_lock);
net->ksnn_incarnation = ktime_get_real_ns();
ni->ni_data = net;
- if (!ni->ni_net->net_tunables_set) {
- ni->ni_net->net_tunables.lct_peer_timeout =
+ net_tunables = &ni->ni_net->net_tunables;
+
+ if (net_tunables->lct_peer_timeout == -1)
+ net_tunables->lct_peer_timeout =
*ksocknal_tunables.ksnd_peertimeout;
- ni->ni_net->net_tunables.lct_max_tx_credits =
+
+ if (net_tunables->lct_max_tx_credits == -1)
+ net_tunables->lct_max_tx_credits =
*ksocknal_tunables.ksnd_credits;
- ni->ni_net->net_tunables.lct_peer_tx_credits =
+
+ if (net_tunables->lct_peer_tx_credits == -1)
+ net_tunables->lct_peer_tx_credits =
*ksocknal_tunables.ksnd_peertxcredits;
- ni->ni_net->net_tunables.lct_peer_rtr_credits =
+
+ if (net_tunables->lct_peer_tx_credits >
+ net_tunables->lct_max_tx_credits)
+ net_tunables->lct_peer_tx_credits =
+ net_tunables->lct_max_tx_credits;
+
+ if (net_tunables->lct_peer_rtr_credits == -1)
+ net_tunables->lct_peer_rtr_credits =
*ksocknal_tunables.ksnd_peerrtrcredits;
- ni->ni_net->net_tunables_set = true;
- }
+ rc = lnet_inet_enumerate(&ifaces, ni->ni_net_ns);
+ if (rc < 0)
+ goto fail_1;
- if (ni->ni_interfaces[0] == NULL) {
- rc = ksocknal_enumerate_interfaces(net);
- if (rc <= 0)
- goto fail_1;
+ if (!ni->ni_interfaces[0]) {
+ ksi = &net->ksnn_interfaces[0];
+ /* Use the first discovered interface */
net->ksnn_ninterfaces = 1;
+ ni->ni_dev_cpt = ifaces[0].li_cpt;
+ ksi->ksni_ipaddr = ifaces[0].li_ipaddr;
+ ksi->ksni_netmask = ifaces[0].li_netmask;
+ strlcpy(ksi->ksni_name, ifaces[0].li_name,
+ sizeof(ksi->ksni_name));
} else {
- for (i = 0; i < LNET_NUM_INTERFACES; i++) {
- int up;
+ /* 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 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);
-
- if (rc != 0) {
- CERROR("Can't get interface %s info: %d\n",
- ni->ni_interfaces[i], rc);
- goto fail_1;
- }
-
- if (!up) {
- CERROR("Interface %s is down\n",
- ni->ni_interfaces[i]);
- goto fail_1;
+ for (j = 0; j < LNET_INTERFACES_NUM; j++) {
+ if (i != j && ni->ni_interfaces[j] &&
+ strcmp(ni->ni_interfaces[i],
+ ni->ni_interfaces[j]) == 0) {
+ rc = -EEXIST;
+ CERROR("ksocklnd: found duplicate %s at %d and %d, rc = %d\n",
+ ni->ni_interfaces[i], i, j, rc);
+ goto fail_1;
+ }
}
- strlcpy(net->ksnn_interfaces[i].ksni_name,
- ni->ni_interfaces[i],
- sizeof(net->ksnn_interfaces[i].ksni_name));
+ for (j = 0; j < rc; j++) {
+ if (strcmp(ifaces[j].li_name,
+ ni->ni_interfaces[i]) != 0)
+ continue;
+ ksi = &net->ksnn_interfaces[j];
+ ni->ni_dev_cpt = ifaces[j].li_cpt;
+ ksi->ksni_ipaddr = ifaces[j].li_ipaddr;
+ ksi->ksni_netmask = ifaces[j].li_netmask;
+ strlcpy(ksi->ksni_name, ifaces[j].li_name,
+ sizeof(ksi->ksni_name));
+ net->ksnn_ninterfaces++;
+ break;
+ }
+ }
+ /* ni_interfaces don't map to all network interfaces */
+ if (!ksi || net->ksnn_ninterfaces != i) {
+ CERROR("ksocklnd: requested %d but only %d interfaces found\n",
+ i, net->ksnn_ninterfaces);
+ goto fail_1;
}
- net->ksnn_ninterfaces = i;
- }
-
- net_dev = dev_get_by_name(&init_net,
- net->ksnn_interfaces[0].ksni_name);
- if (net_dev != NULL) {
- node_id = dev_to_node(&net_dev->dev);
- ni->ni_dev_cpt = cfs_cpt_of_node(lnet_cpt_table(), node_id);
- dev_put(net_dev);
- } else {
- ni->ni_dev_cpt = CFS_CPT_ANY;
}
/* call it before add it to ksocknal_data.ksnd_nets */
if (rc != 0)
goto fail_1;
- ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid),
- net->ksnn_interfaces[0].ksni_ipaddr);
+ LASSERT(ksi);
+ ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid), ksi->ksni_ipaddr);
list_add(&net->ksnn_list, &ksocknal_data.ksnd_nets);
ksocknal_data.ksnd_nnets++;
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;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff