- use_hierarchy is on by default and the cgroup file for the flag is
not created.
+- The original lower boundary, the soft limit, is defined as a limit
+ that is per default unset. As a result, the set of cgroups that
+ global reclaim prefers is opt-in, rather than opt-out. The costs
+ for optimizing these mostly negative lookups are so high that the
+ implementation, despite its enormous size, does not even provide the
+ basic desirable behavior. First off, the soft limit has no
+ hierarchical meaning. All configured groups are organized in a
+ global rbtree and treated like equal peers, regardless where they
+ are located in the hierarchy. This makes subtree delegation
+ impossible. Second, the soft limit reclaim pass is so aggressive
+ that it not just introduces high allocation latencies into the
+ system, but also impacts system performance due to overreclaim, to
+ the point where the feature becomes self-defeating.
+
+ The memory.low boundary on the other hand is a top-down allocated
+ reserve. A cgroup enjoys reclaim protection when it and all its
+ ancestors are below their low boundaries, which makes delegation of
+ subtrees possible. Secondly, new cgroups have no reserve per
+ default and in the common case most cgroups are eligible for the
+ preferred reclaim pass. This allows the new low boundary to be
+ efficiently implemented with just a minor addition to the generic
+ reclaim code, without the need for out-of-band data structures and
+ reclaim passes. Because the generic reclaim code considers all
+ cgroups except for the ones running low in the preferred first
+ reclaim pass, overreclaim of individual groups is eliminated as
+ well, resulting in much better overall workload performance.
+
+- The original high boundary, the hard limit, is defined as a strict
+ limit that can not budge, even if the OOM killer has to be called.
+ But this generally goes against the goal of making the most out of
+ the available memory. The memory consumption of workloads varies
+ during runtime, and that requires users to overcommit. But doing
+ that with a strict upper limit requires either a fairly accurate
+ prediction of the working set size or adding slack to the limit.
+ Since working set size estimation is hard and error prone, and
+ getting it wrong results in OOM kills, most users tend to err on the
+ side of a looser limit and end up wasting precious resources.
+
+ The memory.high boundary on the other hand can be set much more
+ conservatively. When hit, it throttles allocations by forcing them
+ into direct reclaim to work off the excess, but it never invokes the
+ OOM killer. As a result, a high boundary that is chosen too
+ aggressively will not terminate the processes, but instead it will
+ lead to gradual performance degradation. The user can monitor this
+ and make corrections until the minimal memory footprint that still
+ gives acceptable performance is found.
+
+ In extreme cases, with many concurrent allocations and a complete
+ breakdown of reclaim progress within the group, the high boundary
+ can be exceeded. But even then it's mostly better to satisfy the
+ allocation from the slack available in other groups or the rest of
+ the system than killing the group. Otherwise, memory.max is there
+ to limit this type of spillover and ultimately contain buggy or even
+ malicious applications.
+
+- The original control file names are unwieldy and inconsistent in
+ many different ways. For example, the upper boundary hit count is
+ exported in the memory.failcnt file, but an OOM event count has to
+ be manually counted by listening to memory.oom_control events, and
+ lower boundary / soft limit events have to be counted by first
+ setting a threshold for that value and then counting those events.
+ Also, usage and limit files encode their units in the filename.
+ That makes the filenames very long, even though this is not
+ information that a user needs to be reminded of every time they type
+ out those names.
+
+ To address these naming issues, as well as to signal clearly that
+ the new interface carries a new configuration model, the naming
+ conventions in it necessarily differ from the old interface.
+
+- The original limit files indicate the state of an unset limit with a
+ Very High Number, and a configured limit can be unset by echoing -1
+ into those files. But that very high number is implementation and
+ architecture dependent and not very descriptive. And while -1 can
+ be understood as an underflow into the highest possible value, -2 or
+ -10M etc. do not work, so it's not consistent.
+
+ memory.low, memory.high, and memory.max will use the string
+ "infinity" to indicate and set the highest possible value.
5. Planned Changes
"swap",
};
-enum mem_cgroup_events_index {
- MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
- MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
- MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */
- MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */
- MEM_CGROUP_EVENTS_NSTATS,
-};
-
static const char * const mem_cgroup_events_names[] = {
"pgpgin",
"pgpgout",
struct mem_cgroup_stat_cpu {
long count[MEM_CGROUP_STAT_NSTATS];
- unsigned long events[MEM_CGROUP_EVENTS_NSTATS];
+ unsigned long events[MEMCG_NR_EVENTS];
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
};
struct page_counter memsw;
struct page_counter kmem;
+ /* Normal memory consumption range */
+ unsigned long low;
+ unsigned long high;
+
unsigned long soft_limit;
/* vmpressure notifications */
if (!(gfp_mask & __GFP_WAIT))
goto nomem;
+ mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1);
+
nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
gfp_mask, may_swap);
if (fatal_signal_pending(current))
goto bypass;
+ mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1);
+
mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages));
nomem:
if (!(gfp_mask & __GFP_NOFAIL))
css_get_many(&memcg->css, batch);
if (batch > nr_pages)
refill_stock(memcg, batch - nr_pages);
+ /*
+ * If the hierarchy is above the normal consumption range,
+ * make the charging task trim their excess contribution.
+ */
+ do {
+ if (page_counter_read(&memcg->memory) <= memcg->high)
+ continue;
+ mem_cgroup_events(memcg, MEMCG_HIGH, 1);
+ try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+ } while ((memcg = parent_mem_cgroup(memcg)));
done:
return ret;
}
return ret;
}
-static struct cftype mem_cgroup_files[] = {
+static struct cftype mem_cgroup_legacy_files[] = {
{
.name = "usage_in_bytes",
.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
if (parent_css == NULL) {
root_mem_cgroup = memcg;
page_counter_init(&memcg->memory, NULL);
+ memcg->high = PAGE_COUNTER_MAX;
memcg->soft_limit = PAGE_COUNTER_MAX;
page_counter_init(&memcg->memsw, NULL);
page_counter_init(&memcg->kmem, NULL);
if (parent->use_hierarchy) {
page_counter_init(&memcg->memory, &parent->memory);
+ memcg->high = PAGE_COUNTER_MAX;
memcg->soft_limit = PAGE_COUNTER_MAX;
page_counter_init(&memcg->memsw, &parent->memsw);
page_counter_init(&memcg->kmem, &parent->kmem);
*/
} else {
page_counter_init(&memcg->memory, NULL);
+ memcg->high = PAGE_COUNTER_MAX;
memcg->soft_limit = PAGE_COUNTER_MAX;
page_counter_init(&memcg->memsw, NULL);
page_counter_init(&memcg->kmem, NULL);
mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
+ memcg->low = 0;
+ memcg->high = PAGE_COUNTER_MAX;
memcg->soft_limit = PAGE_COUNTER_MAX;
}
mem_cgroup_from_css(root_css)->use_hierarchy = true;
}
+static u64 memory_current_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
+{
+ return mem_cgroup_usage(mem_cgroup_from_css(css), false);
+}
+
+static int memory_low_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ unsigned long low = ACCESS_ONCE(memcg->low);
+
+ if (low == PAGE_COUNTER_MAX)
+ seq_puts(m, "infinity\n");
+ else
+ seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE);
+
+ return 0;
+}
+
+static ssize_t memory_low_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ unsigned long low;
+ int err;
+
+ buf = strstrip(buf);
+ err = page_counter_memparse(buf, "infinity", &low);
+ if (err)
+ return err;
+
+ memcg->low = low;
+
+ return nbytes;
+}
+
+static int memory_high_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ unsigned long high = ACCESS_ONCE(memcg->high);
+
+ if (high == PAGE_COUNTER_MAX)
+ seq_puts(m, "infinity\n");
+ else
+ seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE);
+
+ return 0;
+}
+
+static ssize_t memory_high_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ unsigned long high;
+ int err;
+
+ buf = strstrip(buf);
+ err = page_counter_memparse(buf, "infinity", &high);
+ if (err)
+ return err;
+
+ memcg->high = high;
+
+ return nbytes;
+}
+
+static int memory_max_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ unsigned long max = ACCESS_ONCE(memcg->memory.limit);
+
+ if (max == PAGE_COUNTER_MAX)
+ seq_puts(m, "infinity\n");
+ else
+ seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
+
+ return 0;
+}
+
+static ssize_t memory_max_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ unsigned long max;
+ int err;
+
+ buf = strstrip(buf);
+ err = page_counter_memparse(buf, "infinity", &max);
+ if (err)
+ return err;
+
+ err = mem_cgroup_resize_limit(memcg, max);
+ if (err)
+ return err;
+
+ return nbytes;
+}
+
+static int memory_events_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+ seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW));
+ seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH));
+ seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX));
+ seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM));
+
+ return 0;
+}
+
+static struct cftype memory_files[] = {
+ {
+ .name = "current",
+ .read_u64 = memory_current_read,
+ },
+ {
+ .name = "low",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = memory_low_show,
+ .write = memory_low_write,
+ },
+ {
+ .name = "high",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = memory_high_show,
+ .write = memory_high_write,
+ },
+ {
+ .name = "max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = memory_max_show,
+ .write = memory_max_write,
+ },
+ {
+ .name = "events",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = memory_events_show,
+ },
+ { } /* terminate */
+};
+
struct cgroup_subsys memory_cgrp_subsys = {
.css_alloc = mem_cgroup_css_alloc,
.css_online = mem_cgroup_css_online,
.cancel_attach = mem_cgroup_cancel_attach,
.attach = mem_cgroup_move_task,
.bind = mem_cgroup_bind,
- .legacy_cftypes = mem_cgroup_files,
+ .dfl_cftypes = memory_files,
+ .legacy_cftypes = mem_cgroup_legacy_files,
.early_init = 0,
};
}
#endif
+/**
+ * mem_cgroup_events - count memory events against a cgroup
+ * @memcg: the memory cgroup
+ * @idx: the event index
+ * @nr: the number of events to account for
+ */
+void mem_cgroup_events(struct mem_cgroup *memcg,
+ enum mem_cgroup_events_index idx,
+ unsigned int nr)
+{
+ this_cpu_add(memcg->stat->events[idx], nr);
+}
+
+/**
+ * mem_cgroup_low - check if memory consumption is below the normal range
+ * @root: the highest ancestor to consider
+ * @memcg: the memory cgroup to check
+ *
+ * Returns %true if memory consumption of @memcg, and that of all
+ * configurable ancestors up to @root, is below the normal range.
+ */
+bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
+{
+ if (mem_cgroup_disabled())
+ return false;
+
+ /*
+ * The toplevel group doesn't have a configurable range, so
+ * it's never low when looked at directly, and it is not
+ * considered an ancestor when assessing the hierarchy.
+ */
+
+ if (memcg == root_mem_cgroup)
+ return false;
+
+ if (page_counter_read(&memcg->memory) > memcg->low)
+ return false;
+
+ while (memcg != root) {
+ memcg = parent_mem_cgroup(memcg);
+
+ if (memcg == root_mem_cgroup)
+ break;
+
+ if (page_counter_read(&memcg->memory) > memcg->low)
+ return false;
+ }
+ return true;
+}
+
#ifdef CONFIG_MEMCG_SWAP
/**
* mem_cgroup_swapout - transfer a memsw charge to swap
projects / users / willy / linux.git / commitdiff