From: David Teigland <teigland@redhat.com> Subject: [RHEL5.1 PATCH] dlm: schedule during recovery loops Date: Tue, 25 Sep 2007 11:06:05 -0500 Bugzilla: 250464 Message-Id: <20070925160605.GD15893@redhat.com> Changelog: [GFS2] dlm: schedule during recovery loops bz 250464 Call schedule() in a bunch of places where the recovery code loops through lists of locks. The theory is that these lists become so long that looping through them triggers the softlockup watchdog (usually on ia64, doesn't seem to happen often on other arch's). Will send the same patch upstream. Index: linux-rhel51-2007-08-20/fs/dlm/lock.c =================================================================== --- linux-rhel51-2007-08-20.orig/fs/dlm/lock.c +++ linux-rhel51-2007-08-20/fs/dlm/lock.c @@ -3997,6 +3997,7 @@ int dlm_recover_waiters_post(struct dlm_ unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); + schedule(); } return error; Index: linux-rhel51-2007-08-20/fs/dlm/recover.c =================================================================== --- linux-rhel51-2007-08-20.orig/fs/dlm/recover.c +++ linux-rhel51-2007-08-20/fs/dlm/recover.c @@ -533,6 +533,7 @@ int dlm_recover_locks(struct dlm_ls *ls) } count += r->res_recover_locks_count; + schedule(); } up_read(&ls->ls_root_sem); @@ -705,6 +706,7 @@ void dlm_recover_rsbs(struct dlm_ls *ls) rsb_clear_flag(r, RSB_RECOVER_CONVERT); rsb_clear_flag(r, RSB_NEW_MASTER2); unlock_rsb(r); + schedule(); } up_read(&ls->ls_root_sem); @@ -732,6 +734,7 @@ int dlm_create_root_list(struct dlm_ls * dlm_hold_rsb(r); } read_unlock(&ls->ls_rsbtbl[i].lock); + schedule(); } out: up_write(&ls->ls_root_sem); @@ -741,11 +744,15 @@ int dlm_create_root_list(struct dlm_ls * void dlm_release_root_list(struct dlm_ls *ls) { struct dlm_rsb *r, *safe; + unsigned int count = 0; down_write(&ls->ls_root_sem); list_for_each_entry_safe(r, safe, &ls->ls_root_list, res_root_list) { list_del_init(&r->res_root_list); dlm_put_rsb(r); + + if (!(++count % 100)) + schedule(); } up_write(&ls->ls_root_sem); } @@ -763,6 +770,7 @@ void dlm_clear_toss_list(struct dlm_ls * free_rsb(r); } write_unlock(&ls->ls_rsbtbl[i].lock); + schedule(); } } Index: linux-rhel51-2007-08-20/fs/dlm/requestqueue.c =================================================================== --- linux-rhel51-2007-08-20.orig/fs/dlm/requestqueue.c +++ linux-rhel51-2007-08-20/fs/dlm/requestqueue.c @@ -192,6 +192,7 @@ void dlm_purge_requestqueue(struct dlm_l list_del(&e->list); kfree(e); } + schedule(); } mutex_unlock(&ls->ls_requestqueue_mutex); }