From 4875647a08e35f77274838d97ca8fa44158d50e2 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Thu, 26 Apr 2012 15:54:29 -0500 Subject: dlm: fixes for nodir mode The "nodir" mode (statically assign master nodes instead of using the resource directory) has always been highly experimental, and never seriously used. This commit fixes a number of problems, making nodir much more usable. - Major change to recovery: recover all locks and restart all in-progress operations after recovery. In some cases it's not possible to know which in-progess locks to recover, so recover all. (Most require recovery in nodir mode anyway since rehashing changes most master nodes.) - Change the way nodir mode is enabled, from a command line mount arg passed through gfs2, into a sysfs file managed by dlm_controld, consistent with the other config settings. - Allow recovering MSTCPY locks on an rsb that has not yet been turned into a master copy. - Ignore RCOM_LOCK and RCOM_LOCK_REPLY recovery messages from a previous, aborted recovery cycle. Base this on the local recovery status not being in the state where any nodes should be sending LOCK messages for the current recovery cycle. - Hold rsb lock around dlm_purge_mstcpy_locks() because it may run concurrently with dlm_recover_master_copy(). - Maintain highbast on process-copy lkb's (in addition to the master as is usual), because the lkb can switch back and forth between being a master and being a process copy as the master node changes in recovery. - When recovering MSTCPY locks, flag rsb's that have non-empty convert or waiting queues for granting at the end of recovery. (Rename flag from LOCKS_PURGED to RECOVER_GRANT and similar for the recovery function, because it's not only resources with purged locks that need grant a grant attempt.) - Replace a couple of unnecessary assertion panics with error messages. Signed-off-by: David Teigland --- fs/dlm/recoverd.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'fs/dlm/recoverd.c') diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 11351b57c781..f1a9073c0835 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -84,6 +84,8 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } + ls->ls_recover_locks_in = 0; + dlm_set_recover_status(ls, DLM_RS_NODES); error = dlm_recover_members_wait(ls); @@ -130,7 +132,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) * Clear lkb's for departed nodes. */ - dlm_purge_locks(ls); + dlm_recover_purge(ls); /* * Get new master nodeid's for rsb's that were mastered on @@ -161,6 +163,9 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } + log_debug(ls, "dlm_recover_locks %u in", + ls->ls_recover_locks_in); + /* * Finalize state in master rsb's now that all locks can be * checked. This includes conversion resolution and lvb @@ -225,7 +230,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } - dlm_grant_after_purge(ls); + dlm_recover_grant(ls); log_debug(ls, "dlm_recover %llu generation %u done: %u ms", (unsigned long long)rv->seq, ls->ls_generation, -- cgit v1.2.3-58-ga151