[lustre-devel] [PATCH 20/24] lustre: lnet: add "lnetctl ping" command
NeilBrown
neilb at suse.com
Sun Oct 7 16:19:38 PDT 2018
From: Olaf Weber <olaf at sgi.com>
Adds function jt_ping() in lnetctl.c and
lustre_lnet_ping_nid() in liblnetconfig.c file.
The output of "lnetctl ping" is similar to
"lnetctl peer show".
Function jt_ping() in lnetctl.c calls lustre_lnet_ping_nid()
to implement "lnetctl ping". Adds a function infra_ping_nid()
to be later reused for the ping similar lnetctl commands.
Uses a new ioctl call, IOC_LIBCFS_PING_PEER for "lnetctl ping".
With "lnetctl ping", multiple nids can be pinged. Uses a new
struct(lnet_ioctl_ping_data in lib-dlc.h) to pass the data
from kernel to user space for ping. Also changes lnet_ping()
function and its input parameters in drivers/staging/lustre/lnet/lnet/api-ni.c
WC-bug-id: https://jira.whamcloud.com/browse/LU-9480
Signed-off-by: Sonia Sharma <sonia.sharma at intel.com>
Signed-off-by: Olaf Weber <olaf at sgi.com>
Reviewed-on: https://review.whamcloud.com/25791
Reviewed-by: Amir Shehata <amir.shehata at intel.com>
Tested-by: Amir Shehata <amir.shehata at intel.com>
Signed-off-by: NeilBrown <neilb at suse.com>
---
.../staging/lustre/include/linux/lnet/lib-lnet.h | 5 +-
.../lustre/include/uapi/linux/lnet/libcfs_ioctl.h | 2 -
.../lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c | 2 -
.../lustre/lnet/klnds/socklnd/socklnd_modparams.c | 2 -
drivers/staging/lustre/lnet/lnet/api-ni.c | 55 +++++++++++++++-----
drivers/staging/lustre/lnet/lnet/peer.c | 2 -
6 files changed, 47 insertions(+), 21 deletions(-)
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
index 58e3a9c4e39f..adb4d0551ef5 100644
--- a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
@@ -76,8 +76,8 @@ extern struct lnet the_lnet; /* THE network */
#define LNET_ACCEPTOR_MIN_RESERVED_PORT 512
#define LNET_ACCEPTOR_MAX_RESERVED_PORT 1023
-/* Discovery timeout - same as default peer_timeout */
-#define DISCOVERY_TIMEOUT 180
+/* default timeout */
+#define DEFAULT_PEER_TIMEOUT 180
static inline int lnet_is_route_alive(struct lnet_route *route)
{
@@ -716,6 +716,7 @@ 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_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);
lnet_nid_t lnet_peer_primary_nid_locked(lnet_nid_t nid);
int lnet_discover_peer_locked(struct lnet_peer_ni *lpni, int cpt, bool block);
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h b/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h
index 2607620e8ef8..3d89202bd396 100644
--- a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h
+++ b/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h
@@ -102,7 +102,7 @@ struct libcfs_debug_ioctl_data {
#define IOC_LIBCFS_CONFIGURE _IOWR('e', 59, IOCTL_LIBCFS_TYPE)
#define IOC_LIBCFS_TESTPROTOCOMPAT _IOWR('e', 60, IOCTL_LIBCFS_TYPE)
#define IOC_LIBCFS_PING _IOWR('e', 61, IOCTL_LIBCFS_TYPE)
-/* IOC_LIBCFS_DEBUG_PEER _IOWR('e', 62, IOCTL_LIBCFS_TYPE) */
+#define IOC_LIBCFS_PING_PEER _IOWR('e', 62, IOCTL_LIBCFS_TYPE)
#define IOC_LIBCFS_LNETST _IOWR('e', 63, IOCTL_LIBCFS_TYPE)
#define IOC_LIBCFS_LNET_FAULT _IOWR('e', 64, IOCTL_LIBCFS_TYPE)
/* lnd ioctls */
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c
index 0f2ad9110dc9..13b19f3eabf0 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c
@@ -83,7 +83,7 @@ static int peer_buffer_credits;
module_param(peer_buffer_credits, int, 0444);
MODULE_PARM_DESC(peer_buffer_credits, "# per-peer router buffer credits");
-static int peer_timeout = 180;
+static int peer_timeout = DEFAULT_PEER_TIMEOUT;
module_param(peer_timeout, int, 0444);
MODULE_PARM_DESC(peer_timeout, "Seconds without aliveness news to declare peer dead (<=0 to disable)");
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_modparams.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_modparams.c
index 5663a4ca94d4..da5910049fc1 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_modparams.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_modparams.c
@@ -35,7 +35,7 @@ static int peer_buffer_credits;
module_param(peer_buffer_credits, int, 0444);
MODULE_PARM_DESC(peer_buffer_credits, "# per-peer router buffer credits");
-static int peer_timeout = 180;
+static int peer_timeout = DEFAULT_PEER_TIMEOUT;
module_param(peer_timeout, int, 0444);
MODULE_PARM_DESC(peer_timeout, "Seconds without aliveness news to declare peer dead (<=0 to disable)");
diff --git a/drivers/staging/lustre/lnet/lnet/api-ni.c b/drivers/staging/lustre/lnet/lnet/api-ni.c
index f624abe7db80..37f47bd1511f 100644
--- a/drivers/staging/lustre/lnet/lnet/api-ni.c
+++ b/drivers/staging/lustre/lnet/lnet/api-ni.c
@@ -3181,24 +3181,50 @@ LNetCtl(unsigned int cmd, void *arg)
id.nid = data->ioc_nid;
id.pid = data->ioc_u32[0];
- /* Don't block longer than 2 minutes */
- if (data->ioc_u32[1] > 120 * MSEC_PER_SEC)
- return -EINVAL;
-
- /* If timestamp is negative then disable timeout */
- if ((s32)data->ioc_u32[1] < 0)
- timeout = MAX_SCHEDULE_TIMEOUT;
+ /* If timeout is negative then set default of 3 minutes */
+ if (((s32)data->ioc_u32[1] <= 0) ||
+ data->ioc_u32[1] > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
+ timeout = DEFAULT_PEER_TIMEOUT * HZ;
else
timeout = msecs_to_jiffies(data->ioc_u32[1]);
rc = lnet_ping(id, timeout, data->ioc_pbuf1,
data->ioc_plen1 / sizeof(struct lnet_process_id));
+
if (rc < 0)
return rc;
+
data->ioc_count = rc;
return 0;
}
+ case IOC_LIBCFS_PING_PEER: {
+ struct lnet_ioctl_ping_data *ping = arg;
+ struct lnet_peer *lp;
+ signed long timeout;
+
+ /* If timeout is negative then set default of 3 minutes */
+ if (((s32)ping->op_param) <= 0 ||
+ ping->op_param > (DEFAULT_PEER_TIMEOUT * MSEC_PER_SEC))
+ timeout = DEFAULT_PEER_TIMEOUT * HZ;
+ else
+ timeout = msecs_to_jiffies(ping->op_param);
+
+ rc = lnet_ping(ping->ping_id, timeout,
+ ping->ping_buf,
+ ping->ping_count);
+ if (rc < 0)
+ return rc;
+
+ lp = lnet_find_peer(ping->ping_id.nid);
+ if (lp) {
+ ping->ping_id.nid = lp->lp_primary_nid;
+ ping->mr_info = lnet_peer_is_multi_rail(lp);
+ }
+ ping->ping_count = rc;
+ return 0;
+ }
+
default:
ni = lnet_net2ni_addref(data->ioc_net);
if (!ni)
@@ -3301,7 +3327,7 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
/* initialize md content */
md.start = &pbuf->pb_info;
md.length = LNET_PING_INFO_SIZE(n_ids);
- md.threshold = 2; /*GET/REPLY*/
+ md.threshold = 2; /* GET/REPLY */
md.max_size = 0;
md.options = LNET_MD_TRUNCATE;
md.user_ptr = NULL;
@@ -3319,7 +3345,6 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
if (rc) {
/* Don't CERROR; this could be deliberate! */
-
rc2 = LNetMDUnlink(mdh);
LASSERT(!rc2);
@@ -3363,7 +3388,6 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
replied = 1;
rc = event.mlength;
}
-
} while (rc2 <= 0 || !event.unlinked);
if (!replied) {
@@ -3377,10 +3401,9 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
nob = rc;
LASSERT(nob >= 0 && nob <= LNET_PING_INFO_SIZE(n_ids));
- rc = -EPROTO; /* if I can't parse... */
+ rc = -EPROTO; /* if I can't parse... */
if (nob < 8) {
- /* can't check magic/version */
CERROR("%s: ping info too short %d\n",
libcfs_id2str(id), nob);
goto fail_free_eq;
@@ -3401,7 +3424,8 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
}
if (nob < LNET_PING_INFO_SIZE(0)) {
- CERROR("%s: Short reply %d(%d min)\n", libcfs_id2str(id),
+ CERROR("%s: Short reply %d(%d min)\n",
+ libcfs_id2str(id),
nob, (int)LNET_PING_INFO_SIZE(0));
goto fail_free_eq;
}
@@ -3410,12 +3434,13 @@ static int lnet_ping(struct lnet_process_id id, signed long timeout,
n_ids = pbuf->pb_info.pi_nnis;
if (nob < LNET_PING_INFO_SIZE(n_ids)) {
- CERROR("%s: Short reply %d(%d expected)\n", libcfs_id2str(id),
+ CERROR("%s: Short reply %d(%d expected)\n",
+ libcfs_id2str(id),
nob, (int)LNET_PING_INFO_SIZE(n_ids));
goto fail_free_eq;
}
- rc = -EFAULT; /* If I SEGV... */
+ rc = -EFAULT; /* if I segv in copy_to_user()... */
memset(&tmpid, 0, sizeof(tmpid));
for (i = 0; i < n_ids; i++) {
diff --git a/drivers/staging/lustre/lnet/lnet/peer.c b/drivers/staging/lustre/lnet/lnet/peer.c
index 8dff3b767577..95f72ae39a89 100644
--- a/drivers/staging/lustre/lnet/lnet/peer.c
+++ b/drivers/staging/lustre/lnet/lnet/peer.c
@@ -2905,7 +2905,7 @@ static struct lnet_peer *lnet_peer_dc_timed_out(time64_t now)
return NULL;
lp = list_first_entry(&the_lnet.ln_dc_working,
struct lnet_peer, lp_dc_list);
- if (now < lp->lp_last_queued + DISCOVERY_TIMEOUT)
+ if (now < lp->lp_last_queued + DEFAULT_PEER_TIMEOUT)
return NULL;
return lp;
}
More information about the lustre-devel
mailing list