- oom-killer disable knob and oom-notifier
- Root cgroup has no limit controls.
- Kernel memory and Hugepages are not under control yet. We just manage
- pages on LRU. To add more controls, we have to take care of performance.
+ Hugepages is not under control yet. We just manage pages on LRU. To add more
+ controls, we have to take care of performance. Kernel memory support is work
+ in progress, and the current version provides basically functionality.
Brief summary of control files.
(See 5.5 for details)
memory.memsw.usage_in_bytes # show current res_counter usage for memory+Swap
(See 5.5 for details)
+ memory.kmem.usage_in_bytes # show current res_counter usage for kmem only.
+ (See 2.7 for details)
memory.limit_in_bytes # set/show limit of memory usage
memory.memsw.limit_in_bytes # set/show limit of memory+Swap usage
+ memory.kmem.limit_in_bytes # if allowed, set/show limit of kernel memory
memory.failcnt # show the number of memory usage hits limits
memory.memsw.failcnt # show the number of memory+Swap hits limits
memory.max_usage_in_bytes # show max memory usage recorded
memory.oom_control # set/show oom controls.
memory.numa_stat # show the number of memory usage per numa node
+ memory.independent_kmem_limit # select whether or not kernel memory limits are
+ independent of user limits
+
1. History
The memory controller has a long history. A request for comments for the memory
per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
zone->lru_lock, it has no lock of its own.
+2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+
+With the Kernel memory extension, the Memory Controller is able to limit
+the amount of kernel memory used by the system. Kernel memory is fundamentally
+different than user memory, since it can't be swapped out, which makes it
+possible to DoS the system by consuming too much of this precious resource.
+
+Some kernel memory resources may be accounted and limited separately from the
+main "kmem" resource. For instance, a slab cache that is considered important
+enough to be limited separately may have its own knobs.
+
+Kernel memory limits are not imposed for the root cgroup. Usage for the root
+cgroup may or may not be accounted.
+
+Memory limits as specified by the standard Memory Controller may or may not
+take kernel memory into consideration. This is achieved through the file
+memory.independent_kmem_limit. A Value different than 0 will allow for kernel
+memory to be controlled separately.
+
+When kernel memory limits are not independent, the limit values set in
+memory.kmem files are ignored.
+
+Currently no soft limit is implemented for kernel memory. It is future work
+to trigger slab reclaim when those limits are reached.
+
+2.7.1 Current Kernel Memory resources accounted
+
+None
+
3. User Interface
0. Configuration
For those who want to have the feature enabled by default should
select this option (if, for some reason, they need to disable it
then swapaccount=0 does the trick).
+config CGROUP_MEM_RES_CTLR_KMEM
+ bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
+ depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL
+ default n
+ help
+ The Kernel Memory extension for Memory Resource Controller can limit
+ the amount of memory used by kernel objects in the system. Those are
+ fundamentally different from the entities handled by the standard
+ Memory Controller, which are page-based, and can be swapped. Users of
+ the kmem extension can use it to guarantee that no group of processes
+ will ever exhaust kernel resources alone.
config CGROUP_PERF
bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
* the counter to account for mem+swap usage.
*/
struct res_counter memsw;
+ /*
+ * the counter to account for kmem usage.
+ */
+ struct res_counter kmem;
/*
* Per cgroup active and inactive list, similar to the
* per zone LRU lists.
* mem_cgroup ? And what type of charges should we move ?
*/
unsigned long move_charge_at_immigrate;
+ /*
+ * Should kernel memory limits be stabilished independently
+ * from user memory ?
+ */
+ int kmem_independent_accounting;
/*
* percpu counter.
*/
};
/* for encoding cft->private value on file */
-#define _MEM (0)
-#define _MEMSWAP (1)
-#define _OOM_TYPE (2)
+
+enum mem_type {
+ _MEM = 0,
+ _MEMSWAP,
+ _OOM_TYPE,
+ _KMEM,
+};
+
#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val))
#define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val) ((val) & 0xffff)
u64 val;
if (!mem_cgroup_is_root(memcg)) {
+ val = 0;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ if (!memcg->kmem_independent_accounting)
+ val = res_counter_read_u64(&memcg->kmem, RES_USAGE);
+#endif
if (!swap)
- return res_counter_read_u64(&memcg->res, RES_USAGE);
+ val += res_counter_read_u64(&memcg->res, RES_USAGE);
else
- return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+ val += res_counter_read_u64(&memcg->memsw, RES_USAGE);
+
+ return val;
}
val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
else
val = res_counter_read_u64(&memcg->memsw, name);
break;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ case _KMEM:
+ val = res_counter_read_u64(&memcg->kmem, name);
+ break;
+#endif
default:
BUG();
break;
}
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static u64 kmem_limit_independent_read(struct cgroup *cgroup, struct cftype *cft)
+{
+ return mem_cgroup_from_cont(cgroup)->kmem_independent_accounting;
+}
+
+static int kmem_limit_independent_write(struct cgroup *cgroup, struct cftype *cft,
+ u64 val)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+ struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+
+ val = !!val;
+
+ /*
+ * This follows the same hierarchy restrictions than
+ * mem_cgroup_hierarchy_write()
+ */
+ if (!parent || !parent->use_hierarchy) {
+ if (list_empty(&cgroup->children))
+ memcg->kmem_independent_accounting = val;
+ else
+ return -EBUSY;
+ }
+ else
+ return -EINVAL;
+
+ return 0;
+}
+static struct cftype kmem_cgroup_files[] = {
+ {
+ .name = "independent_kmem_limit",
+ .read_u64 = kmem_limit_independent_read,
+ .write_u64 = kmem_limit_independent_write,
+ },
+ {
+ .name = "kmem.usage_in_bytes",
+ .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
+ .read_u64 = mem_cgroup_read,
+ },
+ {
+ .name = "kmem.limit_in_bytes",
+ .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+ .read_u64 = mem_cgroup_read,
+ },
+};
+
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ int ret = 0;
+
+ ret = cgroup_add_files(cont, ss, kmem_cgroup_files,
+ ARRAY_SIZE(kmem_cgroup_files));
+ return ret;
+};
+
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ return 0;
+}
+#endif
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
if (parent && parent->use_hierarchy) {
res_counter_init(&memcg->res, &parent->res);
res_counter_init(&memcg->memsw, &parent->memsw);
+ res_counter_init(&memcg->kmem, &parent->kmem);
/*
* We increment refcnt of the parent to ensure that we can
* safely access it on res_counter_charge/uncharge.
} else {
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
+ res_counter_init(&memcg->kmem, NULL);
}
memcg->last_scanned_child = 0;
memcg->last_scanned_node = MAX_NUMNODES;
if (!ret)
ret = register_memsw_files(cont, ss);
+
+ if (!ret)
+ ret = register_kmem_files(cont, ss);
+
return ret;
}
projects / openwrt / staging / blogic.git / commitdiff