[lustre-devel] [PATCH 159/622] lnet: separate ni state from recovery
James Simmons
jsimmons at infradead.org
Thu Feb 27 13:10:27 PST 2020
From: Amir Shehata <ashehata at whamcloud.com>
To make the code more readable we make the ni_state an
enumerated type, and create a separate bit filed to track
the recovery state. Both of these are protected by the
lnet_ni_lock()
WC-bug-id: https://jira.whamcloud.com/browse/LU-11514
Lustre-commit: 2be10428ac22 ("LU-11514 lnet: separate ni state from recovery")
Signed-off-by: Amir Shehata <ashehata at whamcloud.com>
Reviewed-on: https://review.whamcloud.com/33361
Reviewed-by: Sonia Sharma <sharmaso at whamcloud.com>
Reviewed-by: Doug Oucharek <dougso at me.com>
Reviewed-by: Olaf Weber <olaf.weber at hpe.com>
Reviewed-by: Oleg Drokin <green at whamcloud.com>
Signed-off-by: James Simmons <jsimmons at infradead.org>
---
include/linux/lnet/lib-types.h | 24 ++++++++++++++++--------
net/lnet/lnet/api-ni.c | 8 +++-----
net/lnet/lnet/config.c | 2 +-
net/lnet/lnet/lib-move.c | 23 +++++++++++++----------
4 files changed, 33 insertions(+), 24 deletions(-)
diff --git a/include/linux/lnet/lib-types.h b/include/linux/lnet/lib-types.h
index ce0caa9..b1a6f6a 100644
--- a/include/linux/lnet/lib-types.h
+++ b/include/linux/lnet/lib-types.h
@@ -315,12 +315,17 @@ struct lnet_tx_queue {
struct list_head tq_delayed; /* delayed TXs */
};
-#define LNET_NI_STATE_INIT (1 << 0)
-#define LNET_NI_STATE_ACTIVE (1 << 1)
-#define LNET_NI_STATE_FAILED (1 << 2)
-#define LNET_NI_STATE_RECOVERY_PENDING (1 << 3)
-#define LNET_NI_STATE_RECOVERY_FAILED BIT(4)
-#define LNET_NI_STATE_DELETING BIT(5)
+enum lnet_ni_state {
+ /* initial state when NI is created */
+ LNET_NI_STATE_INIT = 0,
+ /* set when NI is brought up */
+ LNET_NI_STATE_ACTIVE,
+ /* set when NI is being shutdown */
+ LNET_NI_STATE_DELETING,
+};
+
+#define LNET_NI_RECOVERY_PENDING BIT(0)
+#define LNET_NI_RECOVERY_FAILED BIT(1)
enum lnet_stats_type {
LNET_STATS_TYPE_SEND = 0,
@@ -435,8 +440,11 @@ struct lnet_ni {
/* my health status */
struct lnet_ni_status *ni_status;
- /* NI FSM */
- u32 ni_state;
+ /* NI FSM. Protected by lnet_ni_lock() */
+ enum lnet_ni_state ni_state;
+
+ /* Recovery state. Protected by lnet_ni_lock() */
+ u32 ni_recovery_state;
/* per NI LND tunables */
struct lnet_lnd_tunables ni_lnd_tunables;
diff --git a/net/lnet/lnet/api-ni.c b/net/lnet/lnet/api-ni.c
index c4f698d..25592db 100644
--- a/net/lnet/lnet/api-ni.c
+++ b/net/lnet/lnet/api-ni.c
@@ -1823,7 +1823,7 @@ static void lnet_push_target_fini(void)
list_del_init(&ni->ni_netlist);
/* the ni should be in deleting state. If it's not it's
* a bug */
- LASSERT(ni->ni_state & LNET_NI_STATE_DELETING);
+ LASSERT(ni->ni_state == LNET_NI_STATE_DELETING);
cfs_percpt_for_each(ref, j, ni->ni_refs) {
if (!*ref)
continue;
@@ -1871,8 +1871,7 @@ static void lnet_push_target_fini(void)
lnet_net_lock(LNET_LOCK_EX);
lnet_ni_lock(ni);
- ni->ni_state |= LNET_NI_STATE_DELETING;
- ni->ni_state &= ~LNET_NI_STATE_ACTIVE;
+ ni->ni_state = LNET_NI_STATE_DELETING;
lnet_ni_unlock(ni);
lnet_ni_unlink_locked(ni);
lnet_incr_dlc_seq();
@@ -2005,8 +2004,7 @@ static void lnet_push_target_fini(void)
}
lnet_ni_lock(ni);
- ni->ni_state |= LNET_NI_STATE_ACTIVE;
- ni->ni_state &= ~LNET_NI_STATE_INIT;
+ ni->ni_state = LNET_NI_STATE_ACTIVE;
lnet_ni_unlock(ni);
/* We keep a reference on the loopback net through the loopback NI */
diff --git a/net/lnet/lnet/config.c b/net/lnet/lnet/config.c
index ea62d36..5e0831a 100644
--- a/net/lnet/lnet/config.c
+++ b/net/lnet/lnet/config.c
@@ -467,7 +467,7 @@ struct lnet_net *
ni->ni_net_ns = NULL;
ni->ni_last_alive = ktime_get_real_seconds();
- ni->ni_state |= LNET_NI_STATE_INIT;
+ ni->ni_state = LNET_NI_STATE_INIT;
list_add_tail(&ni->ni_netlist, &net->net_ni_added);
/*
diff --git a/net/lnet/lnet/lib-move.c b/net/lnet/lnet/lib-move.c
index 434aa09..eacda4c 100644
--- a/net/lnet/lnet/lib-move.c
+++ b/net/lnet/lnet/lib-move.c
@@ -2651,7 +2651,8 @@ struct lnet_mt_event_info {
LNetInvalidateMDHandle(&recovery_mdh);
- if (ni->ni_state & LNET_NI_STATE_RECOVERY_PENDING || force) {
+ if (ni->ni_recovery_state & LNET_NI_RECOVERY_PENDING ||
+ force) {
recovery_mdh = ni->ni_ping_mdh;
LNetInvalidateMDHandle(&ni->ni_ping_mdh);
}
@@ -2702,7 +2703,7 @@ struct lnet_mt_event_info {
lnet_net_lock(0);
lnet_ni_lock(ni);
- if (!(ni->ni_state & LNET_NI_STATE_ACTIVE) ||
+ if (ni->ni_state != LNET_NI_STATE_ACTIVE ||
healthv == LNET_MAX_HEALTH_VALUE) {
list_del_init(&ni->ni_recovery);
lnet_unlink_ni_recovery_mdh_locked(ni, 0, false);
@@ -2716,9 +2717,9 @@ struct lnet_mt_event_info {
* But we want to keep the local_ni on the recovery queue
* so we can continue the attempts to recover it.
*/
- if (ni->ni_state & LNET_NI_STATE_RECOVERY_FAILED) {
+ if (ni->ni_recovery_state & LNET_NI_RECOVERY_FAILED) {
lnet_unlink_ni_recovery_mdh_locked(ni, 0, true);
- ni->ni_state &= ~LNET_NI_STATE_RECOVERY_FAILED;
+ ni->ni_recovery_state &= ~LNET_NI_RECOVERY_FAILED;
}
lnet_ni_unlock(ni);
@@ -2728,8 +2729,8 @@ struct lnet_mt_event_info {
libcfs_nid2str(ni->ni_nid));
lnet_ni_lock(ni);
- if (!(ni->ni_state & LNET_NI_STATE_RECOVERY_PENDING)) {
- ni->ni_state |= LNET_NI_STATE_RECOVERY_PENDING;
+ if (!(ni->ni_recovery_state & LNET_NI_RECOVERY_PENDING)) {
+ ni->ni_recovery_state |= LNET_NI_RECOVERY_PENDING;
lnet_ni_unlock(ni);
ev_info = kzalloc(sizeof(*ev_info), GFP_NOFS);
@@ -2737,7 +2738,8 @@ struct lnet_mt_event_info {
CERROR("out of memory. Can't recover %s\n",
libcfs_nid2str(ni->ni_nid));
lnet_ni_lock(ni);
- ni->ni_state &= ~LNET_NI_STATE_RECOVERY_PENDING;
+ ni->ni_recovery_state &=
+ ~LNET_NI_RECOVERY_PENDING;
lnet_ni_unlock(ni);
continue;
}
@@ -2806,7 +2808,8 @@ struct lnet_mt_event_info {
lnet_ni_lock(ni);
if (rc)
- ni->ni_state &= ~LNET_NI_STATE_RECOVERY_PENDING;
+ ni->ni_recovery_state &=
+ ~LNET_NI_RECOVERY_PENDING;
}
lnet_ni_unlock(ni);
}
@@ -3210,9 +3213,9 @@ struct lnet_mt_event_info {
return;
}
lnet_ni_lock(ni);
- ni->ni_state &= ~LNET_NI_STATE_RECOVERY_PENDING;
+ ni->ni_recovery_state &= ~LNET_NI_RECOVERY_PENDING;
if (status)
- ni->ni_state |= LNET_NI_STATE_RECOVERY_FAILED;
+ ni->ni_recovery_state |= LNET_NI_RECOVERY_FAILED;
lnet_ni_unlock(ni);
lnet_net_unlock(0);
--
1.8.3.1
More information about the lustre-devel
mailing list