unsigned int flags;
+ /* are there any throtl rules between this group and td? */
+ bool has_rules[2];
+
/* bytes per second rate limits */
uint64_t bps[2];
{
struct throtl_grp *tg = blkg_to_tg(blkg);
struct throtl_data *td = blkg->q->td;
+ struct throtl_service_queue *parent_sq;
unsigned long flags;
int rw;
- throtl_service_queue_init(&tg->service_queue, &td->service_queue);
+ /*
+ * If sane_hierarchy is enabled, we switch to properly hierarchical
+ * behavior where limits on a given throtl_grp are applied to the
+ * whole subtree rather than just the group itself. e.g. If 16M
+ * read_bps limit is set on the root group, the whole system can't
+ * exceed 16M for the device.
+ *
+ * If sane_hierarchy is not enabled, the broken flat hierarchy
+ * behavior is retained where all throtl_grps are treated as if
+ * they're all separate root groups right below throtl_data.
+ * Limits of a group don't interact with limits of other groups
+ * regardless of the position of the group in the hierarchy.
+ */
+ parent_sq = &td->service_queue;
+
+ if (cgroup_sane_behavior(blkg->blkcg->css.cgroup) && blkg->parent)
+ parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
+
+ throtl_service_queue_init(&tg->service_queue, parent_sq);
+
for (rw = READ; rw <= WRITE; rw++) {
throtl_qnode_init(&tg->qnode_on_self[rw], tg);
throtl_qnode_init(&tg->qnode_on_parent[rw], tg);
spin_unlock_irqrestore(&tg_stats_alloc_lock, flags);
}
+/*
+ * Set has_rules[] if @tg or any of its parents have limits configured.
+ * This doesn't require walking up to the top of the hierarchy as the
+ * parent's has_rules[] is guaranteed to be correct.
+ */
+static void tg_update_has_rules(struct throtl_grp *tg)
+{
+ struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
+ int rw;
+
+ for (rw = READ; rw <= WRITE; rw++)
+ tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
+ (tg->bps[rw] != -1 || tg->iops[rw] != -1);
+}
+
+static void throtl_pd_online(struct blkcg_gq *blkg)
+{
+ /*
+ * We don't want new groups to escape the limits of its ancestors.
+ * Update has_rules[] after a new group is brought online.
+ */
+ tg_update_has_rules(blkg_to_tg(blkg));
+}
+
static void throtl_pd_exit(struct blkcg_gq *blkg)
{
struct throtl_grp *tg = blkg_to_tg(blkg);
return false;
}
+static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
+ bool rw, unsigned long start)
+{
+ tg->bytes_disp[rw] = 0;
+ tg->io_disp[rw] = 0;
+
+ /*
+ * Previous slice has expired. We must have trimmed it after last
+ * bio dispatch. That means since start of last slice, we never used
+ * that bandwidth. Do try to make use of that bandwidth while giving
+ * credit.
+ */
+ if (time_after_eq(start, tg->slice_start[rw]))
+ tg->slice_start[rw] = start;
+
+ tg->slice_end[rw] = jiffies + throtl_slice;
+ throtl_log(&tg->service_queue,
+ "[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
+ rw == READ ? 'R' : 'W', tg->slice_start[rw],
+ tg->slice_end[rw], jiffies);
+}
+
static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
{
tg->bytes_disp[rw] = 0;
return 0;
}
-static bool tg_no_rule_group(struct throtl_grp *tg, bool rw) {
- if (tg->bps[rw] == -1 && tg->iops[rw] == -1)
- return 1;
- return 0;
-}
-
/*
* Returns whether one can dispatch a bio or not. Also returns approx number
* of jiffies to wait before this bio is with-in IO rate and can be dispatched
tg->flags &= ~THROTL_TG_WAS_EMPTY;
}
+static void start_parent_slice_with_credit(struct throtl_grp *child_tg,
+ struct throtl_grp *parent_tg, bool rw)
+{
+ if (throtl_slice_used(parent_tg, rw)) {
+ throtl_start_new_slice_with_credit(parent_tg, rw,
+ child_tg->slice_start[rw]);
+ }
+
+}
+
static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw)
{
struct throtl_service_queue *sq = &tg->service_queue;
*/
if (parent_tg) {
throtl_add_bio_tg(bio, &tg->qnode_on_parent[rw], parent_tg);
+ start_parent_slice_with_credit(tg, parent_tg, rw);
} else {
throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw],
&parent_sq->queued[rw]);
struct blkg_conf_ctx ctx;
struct throtl_grp *tg;
struct throtl_service_queue *sq;
+ struct blkcg_gq *blkg;
+ struct cgroup *pos_cgrp;
int ret;
ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
tg->bps[READ], tg->bps[WRITE],
tg->iops[READ], tg->iops[WRITE]);
+ /*
+ * Update has_rules[] flags for the updated tg's subtree. A tg is
+ * considered to have rules if either the tg itself or any of its
+ * ancestors has rules. This identifies groups without any
+ * restrictions in the whole hierarchy and allows them to bypass
+ * blk-throttle.
+ */
+ tg_update_has_rules(tg);
+ blkg_for_each_descendant_pre(blkg, pos_cgrp, ctx.blkg)
+ tg_update_has_rules(blkg_to_tg(blkg));
+
/*
* We're already holding queue_lock and know @tg is valid. Let's
* apply the new config directly.
.cftypes = throtl_files,
.pd_init_fn = throtl_pd_init,
+ .pd_online_fn = throtl_pd_online,
.pd_exit_fn = throtl_pd_exit,
.pd_reset_stats_fn = throtl_pd_reset_stats,
};
blkcg = bio_blkcg(bio);
tg = throtl_lookup_tg(td, blkcg);
if (tg) {
- if (tg_no_rule_group(tg, rw)) {
+ if (!tg->has_rules[rw]) {
throtl_update_dispatch_stats(tg_to_blkg(tg),
bio->bi_size, bio->bi_rw);
goto out_unlock_rcu;