Revert "dlm_controld: add support for waitplock_recovery switch"
PATCH 1/2 Revert "dlm_controld: add support for waitplock_recovery switch"
This reverts commit 0e9d0a6563f4acef5a27eade8eb29c7e6748c8d2.
--- dlm_controld/action.c | 5 ----- dlm_controld/dlm.conf.5 | 2 -- dlm_controld/dlm_daemon.h | 1 - dlm_controld/main.c | 5 ----- 4 files changed, 13 deletions(-)
dlm_controld/action.c +0 -5
@@ -881,11 +881,6 @@ int setup_configfs_options(void) dlm_options[timewarn_ind].file_set)set_configfs_cluster ("timewarn_cs" ,NULL ,opt (timewarn_ind)); -if (dlm_options[enable_waitplock_recovery_ind].cli_set || - dlm_options[enable_waitplock_recovery_ind].file_set) -set_configfs_cluster ("waitplock_recovery" ,NULL , -opt (enable_waitplock_recovery_ind)); -set_configfs_cluster ("mark" ,NULL ,optu (mark_ind)); proto_name =opts (protocol_ind);
dlm_controld/dlm.conf.5 +0 -2
@@ -46,8 +46,6 @@ debug_logfile .br enable_plock .br -enable_waitplock_recovery -.br plock_debug .br plock_rate_limit
dlm_controld/dlm_daemon.h +0 -1
@@ -102,7 +102,6 @@ enum { mark_ind, enable_fscontrol_ind, enable_plock_ind, - enable_waitplock_recovery_ind, plock_debug_ind, plock_rate_limit_ind, plock_ownership_ind,
dlm_controld/main.c +0 -5
@@ -1768,11 +1768,6 @@ static void set_opt_defaults(void)1 ,NULL ,0 , "enable/disable posix lock support for cluster fs"); -set_opt_default (enable_waitplock_recovery_ind, -"enable_waitplock_recovery" ,'\0' , req_arg_bool, -0 ,NULL ,0 , -"enable/disable posix lock to wait for dlm recovery after lock acquire" ); - set_opt_default(plock_debug_ind, "plock_debug", 'P', no_arg, 0, NULL, 0,
Signature · 1 line
2.26.2
PATCH 2/2 dlm_controld: set SO_RCVBUF for netlink socket
Saw some:
1597148652 uevent recv error -1 errno 105
on a dlm_tool dump. The errno 105 is ENOBUFS on an recv of an AF_NETLINK socket. Further investigations showed that we dropping uevents in such case, see the added comment. The above error message was on a node which hung inside do_uevent() of dlm kernel code which means that the node is waiting for a sysfs write of "event_done". My guess is that dlm_controld dropped some "important" messages and never writes to "event_done" in this case. However we should prevent such ENOBUFS cases in netlink which this patch is trying to do in a simple way.
--- dlm_controld/dlm_daemon.h | 2 ++ dlm_controld/main.c | 19 +++++++++++++++++++ 2 files changed, 21 insertions(+)
dlm_controld/dlm_daemon.h +2 -0
@@ -83,6 +83,8 @@#define DEFAULT_LOGFILE_PRIORITY LOG_INFO#define DEFAULT_LOGFILE LOG_FILE_PATH +#define DEFAULT_NETLINK_RCVBUF (2 * 1024 * 1024) +enum { no_arg =0 , req_arg_bool =1 ,
dlm_controld/main.c +19 -0
@@ -765,6 +765,7 @@ static void process_uevent(int ci)static int setup_uevent (void ) {struct sockaddr_nl snl; +int rcvbuf;int s, rv; s =socket (AF_NETLINK ,SOCK_DGRAM ,NETLINK_KOBJECT_UEVENT );
@@ -773,6 +774,24 @@ static int setup_uevent(void)return s; } +/* man 7 netlink: +* +* However, reliable transmissions from kernel to user are impossible in +* any case. The kernel can't send a netlink message if the socket buffer +* is full: the message will be dropped and the kernel and the user-space +* process will no longer have the same view of kernel state. It is up to +* the application to detect when this happens (via the ENOBUFS error +* returned by recvmsg(2)) and resynchronize. +* +* To prevent ENOBUFS errors we just set the receive buffer to two +* megabyte as other applications do it. This will not ensure that we never +* receive ENOBUFS but it's more unlikely. May it's worth to handle ENOBUFS +* errors on a different way in future. +*/ + rcvbuf =DEFAULT_NETLINK_RCVBUF ; +setsockopt (s,SOL_SOCKET ,SO_RCVBUF , &rcvbuf,sizeof (rcvbuf)); +setsockopt (s,SOL_SOCKET ,SO_RCVBUFFORCE , &rcvbuf,sizeof (rcvbuf)); +memset (&snl,0 ,sizeof (snl)); snl.nl_family =AF_NETLINK ; snl.nl_pid =getpid ();
Signature · 1 line
2.26.2