ocfs2: return -EAGAIN instead of EAGAIN in dlm
PATCH 1/1 ocfs2: return -EAGAIN instead of EAGAIN in dlm
We used to return positive EAGAIN to indicate a retry action is needed in dlm_begin_reco_handler(). Now we use negative -EAGAIN to erase the confusion caused by this error code.
--- fs/ocfs2/dlm/dlmrecovery.c | 19 ++++++++++--------- 1 files changed, 10 insertions(+), 9 deletions(-)
fs/ocfs2/dlm/dlmrecovery.c +10 -9
@@ -2589,6 +2589,15 @@ retry: "begin reco msg (%d)\n", dlm->name, nodenum, ret); ret =0 ; } +if (ret == -EAGAIN ) { +mlog (0 ,"%s: trying to start recovery of node " +"%u, but node %u is waiting for last recovery " +"to complete, backoff for a bit\n" , dlm->name, + dead_node, nodenum); +/*TODO Look into replacing msleep with cond_resched()*/ +msleep (100 ); + goto retry; + }if (ret <0 ) {struct dlm_lock_resource *res;/* this is now a serious problem, possibly ENOMEM
@@ -2608,14 +2617,6 @@ retry:* another ENOMEM */ msleep (100 ); goto retry; - }else if (ret ==EAGAIN ) { -mlog (0 ,"%s: trying to start recovery of node " -"%u, but node %u is waiting for last recovery " -"to complete, backoff for a bit\n" , dlm->name, - dead_node, nodenum); -/* TODO Look into replacing msleep with cond_resched() */ -msleep (100 ); - goto retry; } }
@@ -2639,7 +2640,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, dlm->name, br->node_idx, br->dead_node, dlm->reco.dead_node, dlm->reco.new_master);spin_unlock (&dlm->spinlock); -return EAGAIN ; +return -EAGAIN ; }spin_unlock (&dlm->spinlock);
Signature · 1 line
1.6.2.5
PATCH 1/1 ocfs2: return -EAGAIN instead of EAGAIN in dlm
comments inlined
Quoted 14 lines · Tiger Yang
We used to return positive EAGAIN to indicate a retry action is needed in
dlm_begin_reco_handler(). Now we use negative-EAGAINto erase the confusion caused by this error code.Signed-off-by Tiger Yang <[email protected]>--- fs/ocfs2/dlm/dlmrecovery.c | 19 ++++++++++--------- 1 files changed, 10 insertions(+), 9 deletions(-)fs/ocfs2/dlm/dlmrecovery.c +0
-0
fs/ocfs2/dlm/dlmrecovery.c retry: · line 2597
Quoted 9 lines
fs/ocfs2/dlm/dlmrecovery.c +6
-0@@ -2589,6 +2589,15 @@ retry: "begin reco msg (%d)\n", dlm->name, nodenum, ret); ret =0 ; } +if (ret == -EAGAIN ) { +mlog (0 ,"%s: trying to start recovery of node " +"%u, but node %u is waiting for last recovery " +"to complete, backoff for a bit\n" , dlm->name, + dead_node, nodenum); +/*TODO Look into replacing msleep with cond_resched()*/
This comment can be removed. We cannot replace the msleep with cond_resched().
If anything we may want to increase the msleep to 1 sec. But leave that as is for now.
Quoted 22 lines
fs/ocfs2/dlm/dlmrecovery.c +3
-8+msleep (100 ); + goto retry; + }if (ret <0 ) {struct dlm_lock_resource *res;/* this is now a serious problem, possibly ENOMEM @@ -2608,14 +2617,6 @@ retry:* another ENOMEM */ msleep (100 ); goto retry; - }else if (ret ==EAGAIN ) { -mlog (0 ,"%s: trying to start recovery of node " -"%u, but node %u is waiting for last recovery " -"to complete, backoff for a bit\n" , dlm->name, - dead_node, nodenum); -/* TODO Look into replacing msleep with cond_resched() */ -msleep (100 ); - goto retry; } }
fs/ocfs2/dlm/dlmrecovery.c int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, · line 2646
Quoted 8 lines
fs/ocfs2/dlm/dlmrecovery.c +1
-1@@ -2639,7 +2640,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, dlm->name, br->node_idx, br->dead_node, dlm->reco.dead_node, dlm->reco.new_master);spin_unlock (&dlm->spinlock); -return EAGAIN ; +return -EAGAIN ; }spin_unlock (&dlm->spinlock);
This looks sane. Though I would like someone else to review it too as we have no real way of testing this.
PATCH 1/1 ocfs2: return -EAGAIN instead of EAGAIN in dlm
We used to return positive EAGAIN to indicate a retry action is needed in dlm_begin_reco_handler(). Now we return negative -EAGAIN to erase the confusion caused by this error code.
--- fs/ocfs2/dlm/dlmrecovery.c | 18 +++++++++--------- 1 files changed, 9 insertions(+), 9 deletions(-)
fs/ocfs2/dlm/dlmrecovery.c +9 -9
@@ -2589,6 +2589,14 @@ retry: "begin reco msg (%d)\n", dlm->name, nodenum, ret); ret =0 ; } +if (ret == -EAGAIN ) { +mlog (0 ,"%s: trying to start recovery of node " +"%u, but node %u is waiting for last recovery " +"to complete, backoff for a bit\n" , dlm->name, + dead_node, nodenum); +msleep (100 ); + goto retry; + }if (ret <0 ) {struct dlm_lock_resource *res;/* this is now a serious problem, possibly ENOMEM
@@ -2608,14 +2616,6 @@ retry:* another ENOMEM */ msleep (100 ); goto retry; - }else if (ret ==EAGAIN ) { -mlog (0 ,"%s: trying to start recovery of node " -"%u, but node %u is waiting for last recovery " -"to complete, backoff for a bit\n" , dlm->name, - dead_node, nodenum); -/* TODO Look into replacing msleep with cond_resched() */ -msleep (100 ); - goto retry; } }
@@ -2639,7 +2639,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, dlm->name, br->node_idx, br->dead_node, dlm->reco.dead_node, dlm->reco.new_master);spin_unlock (&dlm->spinlock); -return EAGAIN ; +return -EAGAIN ; }spin_unlock (&dlm->spinlock);
Signature · 1 line
1.6.2.5
PATCH 1/1 ocfs2: return -EAGAIN instead of EAGAIN in dlm
ack
Quoted 53 lines · Tiger Yang
We used to return positive EAGAIN to indicate a retry action is needed in
dlm_begin_reco_handler(). Now we return negative-EAGAINto erase the confusion caused by this error code.Signed-off-by Tiger Yang <[email protected]>--- fs/ocfs2/dlm/dlmrecovery.c | 18 +++++++++--------- 1 files changed, 9 insertions(+), 9 deletions(-)fs/ocfs2/dlm/dlmrecovery.c +9
-9@@ -2589,6 +2589,14 @@ retry: "begin reco msg (%d)\n", dlm->name, nodenum, ret); ret =0 ; } +if (ret == -EAGAIN ) { +mlog (0 ,"%s: trying to start recovery of node " +"%u, but node %u is waiting for last recovery " +"to complete, backoff for a bit\n" , dlm->name, + dead_node, nodenum); +msleep (100 ); + goto retry; + }if (ret <0 ) {struct dlm_lock_resource *res;/* this is now a serious problem, possibly ENOMEM @@ -2608,14 +2616,6 @@ retry:* another ENOMEM */ msleep (100 ); goto retry; - }else if (ret ==EAGAIN ) { -mlog (0 ,"%s: trying to start recovery of node " -"%u, but node %u is waiting for last recovery " -"to complete, backoff for a bit\n" , dlm->name, - dead_node, nodenum); -/* TODO Look into replacing msleep with cond_resched() */ -msleep (100 ); - goto retry; } }@@ -2639,7 +2639,7 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data, dlm->name, br->node_idx, br->dead_node, dlm->reco.dead_node, dlm->reco.new_master);spin_unlock (&dlm->spinlock); -return EAGAIN ; +return -EAGAIN ; }spin_unlock (&dlm->spinlock);
PATCH 1/1 ocfs2: return -EAGAIN instead of EAGAIN in dlm
In reply to Tiger YangQuoted 5 lines · Tiger Yang
We used to return positive EAGAIN to indicate a retry action is needed in
dlm_begin_reco_handler(). Now we return negative-EAGAINto erase the confusion caused by this error code.Signed-off-by Tiger Yang <[email protected]>
This is now in the 'merge-window' branch of ocfs2.git.
Joel
Signature · 9 lines
"I always thought the hardest questions were those I could not answer. Now I know they are the ones I can never ask." - Charlie Watkins Joel Becker Principal Software Developer Oracle E-mail: joel.becker at oracle.com Phone: (650) 506-8127