summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/cgroups/blkio-controller.txt29
-rw-r--r--block/blk-cgroup.c8
-rw-r--r--block/blk-throttle.c22
-rw-r--r--include/linux/cgroup.h2
4 files changed, 38 insertions, 23 deletions
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index da272c8f44e7..cd556b914786 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -94,11 +94,13 @@ Throttling/Upper Limit policy
Hierarchical Cgroups
====================
-- Currently only CFQ supports hierarchical groups. For throttling,
- cgroup interface does allow creation of hierarchical cgroups and
- internally it treats them as flat hierarchy.
- If somebody created a hierarchy like as follows.
+Both CFQ and throttling implement hierarchy support; however,
+throttling's hierarchy support is enabled iff "sane_behavior" is
+enabled from cgroup side, which currently is a development option and
+not publicly available.
+
+If somebody created a hierarchy like as follows.
root
/ \
@@ -106,21 +108,20 @@ Hierarchical Cgroups
|
test3
- CFQ will handle the hierarchy correctly but and throttling will
- practically treat all groups at same level. For details on CFQ
- hierarchy support, refer to Documentation/block/cfq-iosched.txt.
- Throttling will treat the hierarchy as if it looks like the
- following.
+CFQ by default and throttling with "sane_behavior" will handle the
+hierarchy correctly. For details on CFQ hierarchy support, refer to
+Documentation/block/cfq-iosched.txt. For throttling, all limits apply
+to the whole subtree while all statistics are local to the IOs
+directly generated by tasks in that cgroup.
+
+Throttling without "sane_behavior" enabled from cgroup side will
+practically treat all groups at same level as if it looks like the
+following.
pivot
/ / \ \
root test1 test2 test3
- Nesting cgroups, while allowed, isn't officially supported and blkio
- genereates warning when cgroups nest. Once throttling implements
- hierarchy support, hierarchy will be supported and the warning will
- be removed.
-
Various user visible config options
===================================
CONFIG_BLK_CGROUP
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d0747605f56c..290792a13e3c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -911,14 +911,6 @@ struct cgroup_subsys blkio_subsys = {
.subsys_id = blkio_subsys_id,
.base_cftypes = blkcg_files,
.module = THIS_MODULE,
-
- /*
- * blkio subsystem is utterly broken in terms of hierarchy support.
- * It treats all cgroups equally regardless of where they're
- * located in the hierarchy - all cgroups are treated as if they're
- * right below the root. Fix it and remove the following.
- */
- .broken_hierarchy = true,
};
EXPORT_SYMBOL_GPL(blkio_subsys);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 27f006bb363b..08a32dfd3844 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -397,10 +397,30 @@ static void throtl_pd_init(struct blkcg_gq *blkg)
{
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);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5047355b9a0f..09f1a1408ae0 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -272,6 +272,8 @@ enum {
* - memcg: use_hierarchy is on by default and the cgroup file for
* the flag is not created.
*
+ * - blkcg: blk-throttle becomes properly hierarchical.
+ *
* The followings are planned changes.
*
* - release_agent will be disallowed once replacement notification