[Ocfs2-devel] [PATCH 2/2] ocfs2/dlm: Migrate lockres with no locks if it has a reference
Joel Becker
Joel.Becker at oracle.com
Thu Dec 9 17:44:51 PST 2010
On Fri, Nov 19, 2010 at 03:06:50PM -0800, Sunil Mushran wrote:
> o2dlm was not migrating resources with zero locks because it assumed that that
> resource would get purged by dlm_thread. However, some usage patterns involve
> creating and dropping locks at a high rate leading to the migrate thread seeing
> zero locks but the purge thread seeing an active reference. When this happens,
> the dlm_thread cannot purge the resource and the migrate thread sees no reason
> to migrate that resource. The spell is broken when the migrate thread catches
> the resource with a lock.
>
> The fix is to make the migrate thread also consider the reference map.
>
> This usage pattern can be triggered by userspace on userdlm locks and flocks.
>
> Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
This patch is now in the 'fixes' branch of ocfs2.git.
Joel
> ---
> fs/ocfs2/dlm/dlmmaster.c | 40 +++++++++++++++++++++++++++-------------
> 1 files changed, 27 insertions(+), 13 deletions(-)
>
> diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
> index f564b0e..59f0f6b 100644
> --- a/fs/ocfs2/dlm/dlmmaster.c
> +++ b/fs/ocfs2/dlm/dlmmaster.c
> @@ -2346,7 +2346,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
> */
> static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
> struct dlm_lock_resource *res,
> - int *numlocks)
> + int *numlocks,
> + int *hasrefs)
> {
> int ret;
> int i;
> @@ -2356,6 +2357,9 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
>
> assert_spin_locked(&res->spinlock);
>
> + *numlocks = 0;
> + *hasrefs = 0;
> +
> ret = -EINVAL;
> if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
> mlog(0, "cannot migrate lockres with unknown owner!\n");
> @@ -2386,7 +2390,13 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
> }
>
> *numlocks = count;
> - mlog(0, "migrateable lockres having %d locks\n", *numlocks);
> +
> + count = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
> + if (count < O2NM_MAX_NODES)
> + *hasrefs = 1;
> +
> + mlog(0, "%s: res %.*s, Migrateable, locks %d, refs %d\n", dlm->name,
> + res->lockname.len, res->lockname.name, *numlocks, *hasrefs);
>
> leave:
> return ret;
> @@ -2408,7 +2418,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
> const char *name;
> unsigned int namelen;
> int mle_added = 0;
> - int numlocks;
> + int numlocks, hasrefs;
> int wake = 0;
>
> if (!dlm_grab(dlm))
> @@ -2417,13 +2427,13 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
> name = res->lockname.name;
> namelen = res->lockname.len;
>
> - mlog(0, "migrating %.*s to %u\n", namelen, name, target);
> + mlog(0, "%s: Migrating %.*s to %u\n", dlm->name, namelen, name, target);
>
> /*
> * ensure this lockres is a proper candidate for migration
> */
> spin_lock(&res->spinlock);
> - ret = dlm_is_lockres_migrateable(dlm, res, &numlocks);
> + ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
> if (ret < 0) {
> spin_unlock(&res->spinlock);
> goto leave;
> @@ -2431,10 +2441,8 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
> spin_unlock(&res->spinlock);
>
> /* no work to do */
> - if (numlocks == 0) {
> - mlog(0, "no locks were found on this lockres! done!\n");
> + if (numlocks == 0 && !hasrefs)
> goto leave;
> - }
>
> /*
> * preallocate up front
> @@ -2459,14 +2467,14 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
> * find a node to migrate the lockres to
> */
>
> - mlog(0, "picking a migration node\n");
> spin_lock(&dlm->spinlock);
> /* pick a new node */
> if (!test_bit(target, dlm->domain_map) ||
> target >= O2NM_MAX_NODES) {
> target = dlm_pick_migration_target(dlm, res);
> }
> - mlog(0, "node %u chosen for migration\n", target);
> + mlog(0, "%s: res %.*s, Node %u chosen for migration\n", dlm->name,
> + namelen, name, target);
>
> if (target >= O2NM_MAX_NODES ||
> !test_bit(target, dlm->domain_map)) {
> @@ -2667,7 +2675,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
> {
> int ret;
> int lock_dropped = 0;
> - int numlocks;
> + int numlocks, hasrefs;
>
> spin_lock(&res->spinlock);
> if (res->owner != dlm->node_num) {
> @@ -2681,8 +2689,8 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
> }
>
> /* No need to migrate a lockres having no locks */
> - ret = dlm_is_lockres_migrateable(dlm, res, &numlocks);
> - if (ret >= 0 && numlocks == 0) {
> + ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
> + if (ret >= 0 && numlocks == 0 && !hasrefs) {
> spin_unlock(&res->spinlock);
> goto leave;
> }
> @@ -2915,6 +2923,12 @@ static u8 dlm_pick_migration_target(struct dlm_ctxt *dlm,
> }
> queue++;
> }
> +
> + nodenum = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
> + if (nodenum < O2NM_MAX_NODES) {
> + spin_unlock(&res->spinlock);
> + return nodenum;
> + }
> spin_unlock(&res->spinlock);
> mlog(0, "have not found a suitable target yet! checking domain map\n");
>
> --
> 1.5.6.5
>
--
"Sometimes one pays most for the things one gets for nothing."
- Albert Einstein
Joel Becker
Senior Development Manager
Oracle
E-mail: joel.becker at oracle.com
Phone: (650) 506-8127
More information about the Ocfs2-devel
mailing list