summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>2011-07-08 15:07:30 -0400
committerKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>2011-07-08 15:07:30 -0400
commit136d9ebff300044865693a57d68fe5905635992a (patch)
tree1a336de0e43c499c8b51475cca3afb52b8d1499d /drivers
parent149bb2fab547253e6359e76f1b86b95247110e68 (diff)
parenta50777c791031d7345ce95785ea6220f67339d90 (diff)
Merge branch 'xen-tmem-selfballoon-v8' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem into stable/drivers
* 'xen-tmem-selfballoon-v8' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem: xen: tmem: self-ballooning and frontswap-selfshrinking
Diffstat (limited to 'drivers')
-rw-r--r--drivers/xen/Kconfig17
-rw-r--r--drivers/xen/Makefile1
-rw-r--r--drivers/xen/xen-balloon.c2
-rw-r--r--drivers/xen/xen-selfballoon.c485
4 files changed, 505 insertions, 0 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index be8732c32185..5014c6dcbdfa 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -9,6 +9,23 @@ config XEN_BALLOON
the system to expand the domain's memory allocation, or alternatively
return unneeded memory to the system.
+config XEN_SELFBALLOONING
+ bool "Dynamically self-balloon kernel memory to target"
+ depends on XEN && XEN_BALLOON && CLEANCACHE && SWAP
+ default n
+ help
+ Self-ballooning dynamically balloons available kernel memory driven
+ by the current usage of anonymous memory ("committed AS") and
+ controlled by various sysfs-settable parameters. Configuring
+ FRONTSWAP is highly recommended; if it is not configured, self-
+ ballooning is disabled by default but can be enabled with the
+ 'selfballooning' kernel boot parameter. If FRONTSWAP is configured,
+ frontswap-selfshrinking is enabled by default but can be disabled
+ with the 'noselfshrink' kernel boot parameter; and self-ballooning
+ is enabled by default but can be disabled with the 'noselfballooning'
+ kernel boot parameter. Note that systems without a sufficiently
+ large swap device should not enable self-ballooning.
+
config XEN_SCRUB_PAGES
bool "Scrub pages before returning them to system"
depends on XEN_BALLOON
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 7c1bc0a4d9f4..bc3bf5679f6e 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_BLOCK) += biomerge.o
obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o
obj-$(CONFIG_XEN_XENCOMM) += xencomm.o
obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o
+obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o
obj-$(CONFIG_XEN_DEV_EVTCHN) += xen-evtchn.o
obj-$(CONFIG_XEN_GNTDEV) += xen-gntdev.o
obj-$(CONFIG_XEN_GRANT_DEV_ALLOC) += xen-gntalloc.o
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index a4ff225ee868..5c9dc43c1e94 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -98,6 +98,8 @@ static int __init balloon_init(void)
register_balloon(&balloon_sysdev);
+ register_xen_selfballooning(&balloon_sysdev);
+
target_watch.callback = watch_target;
xenstore_notifier.notifier_call = balloon_init_watcher;
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
new file mode 100644
index 000000000000..010937b5a7c9
--- /dev/null
+++ b/drivers/xen/xen-selfballoon.c
@@ -0,0 +1,485 @@
+/******************************************************************************
+ * Xen selfballoon driver (and optional frontswap self-shrinking driver)
+ *
+ * Copyright (c) 2009-2011, Dan Magenheimer, Oracle Corp.
+ *
+ * This code complements the cleancache and frontswap patchsets to optimize
+ * support for Xen Transcendent Memory ("tmem"). The policy it implements
+ * is rudimentary and will likely improve over time, but it does work well
+ * enough today.
+ *
+ * Two functionalities are implemented here which both use "control theory"
+ * (feedback) to optimize memory utilization. In a virtualized environment
+ * such as Xen, RAM is often a scarce resource and we would like to ensure
+ * that each of a possibly large number of virtual machines is using RAM
+ * efficiently, i.e. using as little as possible when under light load
+ * and obtaining as much as possible when memory demands are high.
+ * Since RAM needs vary highly dynamically and sometimes dramatically,
+ * "hysteresis" is used, that is, memory target is determined not just
+ * on current data but also on past data stored in the system.
+ *
+ * "Selfballooning" creates memory pressure by managing the Xen balloon
+ * driver to decrease and increase available kernel memory, driven
+ * largely by the target value of "Committed_AS" (see /proc/meminfo).
+ * Since Committed_AS does not account for clean mapped pages (i.e. pages
+ * in RAM that are identical to pages on disk), selfballooning has the
+ * affect of pushing less frequently used clean pagecache pages out of
+ * kernel RAM and, presumably using cleancache, into Xen tmem where
+ * Xen can more efficiently optimize RAM utilization for such pages.
+ *
+ * When kernel memory demand unexpectedly increases faster than Xen, via
+ * the selfballoon driver, is able to (or chooses to) provide usable RAM,
+ * the kernel may invoke swapping. In most cases, frontswap is able
+ * to absorb this swapping into Xen tmem. However, due to the fact
+ * that the kernel swap subsystem assumes swapping occurs to a disk,
+ * swapped pages may sit on the disk for a very long time; even if
+ * the kernel knows the page will never be used again. This is because
+ * the disk space costs very little and can be overwritten when
+ * necessary. When such stale pages are in frontswap, however, they
+ * are taking up valuable real estate. "Frontswap selfshrinking" works
+ * to resolve this: When frontswap activity is otherwise stable
+ * and the guest kernel is not under memory pressure, the "frontswap
+ * selfshrinking" accounts for this by providing pressure to remove some
+ * pages from frontswap and return them to kernel memory.
+ *
+ * For both "selfballooning" and "frontswap-selfshrinking", a worker
+ * thread is used and sysfs tunables are provided to adjust the frequency
+ * and rate of adjustments to achieve the goal, as well as to disable one
+ * or both functions independently.
+ *
+ * While some argue that this functionality can and should be implemented
+ * in userspace, it has been observed that bad things happen (e.g. OOMs).
+ *
+ * System configuration note: Selfballooning should not be enabled on
+ * systems without a sufficiently large swap device configured; for best
+ * results, it is recommended that total swap be increased by the size
+ * of the guest memory. Also, while technically not required to be
+ * configured, it is highly recommended that frontswap also be configured
+ * and enabled when selfballooning is running. So, selfballooning
+ * is disabled by default if frontswap is not configured and can only
+ * be enabled with the "selfballooning" kernel boot option; similarly
+ * selfballooning is enabled by default if frontswap is configured and
+ * can be disabled with the "noselfballooning" kernel boot option. Finally,
+ * when frontswap is configured, frontswap-selfshrinking can be disabled
+ * with the "noselfshrink" kernel boot option.
+ *
+ * Selfballooning is disallowed in domain0 and force-disabled.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+
+#include <xen/balloon.h>
+
+#include <xen/tmem.h>
+
+/* Enable/disable with sysfs. */
+static int xen_selfballooning_enabled __read_mostly;
+
+/*
+ * Controls rate at which memory target (this iteration) approaches
+ * ultimate goal when memory need is increasing (up-hysteresis) or
+ * decreasing (down-hysteresis). Higher values of hysteresis cause
+ * slower increases/decreases. The default values for the various
+ * parameters were deemed reasonable by experimentation, may be
+ * workload-dependent, and can all be adjusted via sysfs.
+ */
+static unsigned int selfballoon_downhysteresis __read_mostly = 8;
+static unsigned int selfballoon_uphysteresis __read_mostly = 1;
+
+/* In HZ, controls frequency of worker invocation. */
+static unsigned int selfballoon_interval __read_mostly = 5;
+
+static void selfballoon_process(struct work_struct *work);
+static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
+
+#ifdef CONFIG_FRONTSWAP
+#include <linux/frontswap.h>
+
+/* Enable/disable with sysfs. */
+static bool frontswap_selfshrinking __read_mostly;
+
+/* Enable/disable with kernel boot option. */
+static bool use_frontswap_selfshrink __initdata = true;
+
+/*
+ * The default values for the following parameters were deemed reasonable
+ * by experimentation, may be workload-dependent, and can all be
+ * adjusted via sysfs.
+ */
+
+/* Control rate for frontswap shrinking. Higher hysteresis is slower. */
+static unsigned int frontswap_hysteresis __read_mostly = 20;
+
+/*
+ * Number of selfballoon worker invocations to wait before observing that
+ * frontswap selfshrinking should commence. Note that selfshrinking does
+ * not use a separate worker thread.
+ */
+static unsigned int frontswap_inertia __read_mostly = 3;
+
+/* Countdown to next invocation of frontswap_shrink() */
+static unsigned long frontswap_inertia_counter;
+
+/*
+ * Invoked by the selfballoon worker thread, uses current number of pages
+ * in frontswap (frontswap_curr_pages()), previous status, and control
+ * values (hysteresis and inertia) to determine if frontswap should be
+ * shrunk and what the new frontswap size should be. Note that
+ * frontswap_shrink is essentially a partial swapoff that immediately
+ * transfers pages from the "swap device" (frontswap) back into kernel
+ * RAM; despite the name, frontswap "shrinking" is very different from
+ * the "shrinker" interface used by the kernel MM subsystem to reclaim
+ * memory.
+ */
+static void frontswap_selfshrink(void)
+{
+ static unsigned long cur_frontswap_pages;
+ static unsigned long last_frontswap_pages;
+ static unsigned long tgt_frontswap_pages;
+
+ last_frontswap_pages = cur_frontswap_pages;
+ cur_frontswap_pages = frontswap_curr_pages();
+ if (!cur_frontswap_pages ||
+ (cur_frontswap_pages > last_frontswap_pages)) {
+ frontswap_inertia_counter = frontswap_inertia;
+ return;
+ }
+ if (frontswap_inertia_counter && --frontswap_inertia_counter)
+ return;
+ if (cur_frontswap_pages <= frontswap_hysteresis)
+ tgt_frontswap_pages = 0;
+ else
+ tgt_frontswap_pages = cur_frontswap_pages -
+ (cur_frontswap_pages / frontswap_hysteresis);
+ frontswap_shrink(tgt_frontswap_pages);
+}
+
+static int __init xen_nofrontswap_selfshrink_setup(char *s)
+{
+ use_frontswap_selfshrink = false;
+ return 1;
+}
+
+__setup("noselfshrink", xen_nofrontswap_selfshrink_setup);
+
+/* Disable with kernel boot option. */
+static bool use_selfballooning __initdata = true;
+
+static int __init xen_noselfballooning_setup(char *s)
+{
+ use_selfballooning = false;
+ return 1;
+}
+
+__setup("noselfballooning", xen_noselfballooning_setup);
+#else /* !CONFIG_FRONTSWAP */
+/* Enable with kernel boot option. */
+static bool use_selfballooning __initdata = false;
+
+static int __init xen_selfballooning_setup(char *s)
+{
+ use_selfballooning = true;
+ return 1;
+}
+
+__setup("selfballooning", xen_selfballooning_setup);
+#endif /* CONFIG_FRONTSWAP */
+
+/*
+ * Use current balloon size, the goal (vm_committed_as), and hysteresis
+ * parameters to set a new target balloon size
+ */
+static void selfballoon_process(struct work_struct *work)
+{
+ unsigned long cur_pages, goal_pages, tgt_pages;
+ bool reset_timer = false;
+
+ if (xen_selfballooning_enabled) {
+ cur_pages = balloon_stats.current_pages;
+ tgt_pages = cur_pages; /* default is no change */
+ goal_pages = percpu_counter_read_positive(&vm_committed_as) +
+ balloon_stats.current_pages - totalram_pages;
+#ifdef CONFIG_FRONTSWAP
+ /* allow space for frontswap pages to be repatriated */
+ if (frontswap_selfshrinking && frontswap_enabled)
+ goal_pages += frontswap_curr_pages();
+#endif
+ if (cur_pages > goal_pages)
+ tgt_pages = cur_pages -
+ ((cur_pages - goal_pages) /
+ selfballoon_downhysteresis);
+ else if (cur_pages < goal_pages)
+ tgt_pages = cur_pages +
+ ((goal_pages - cur_pages) /
+ selfballoon_uphysteresis);
+ /* else if cur_pages == goal_pages, no change */
+ balloon_set_new_target(tgt_pages);
+ reset_timer = true;
+ }
+#ifdef CONFIG_FRONTSWAP
+ if (frontswap_selfshrinking && frontswap_enabled) {
+ frontswap_selfshrink();
+ reset_timer = true;
+ }
+#endif
+ if (reset_timer)
+ schedule_delayed_work(&selfballoon_worker,
+ selfballoon_interval * HZ);
+}
+
+#ifdef CONFIG_SYSFS
+
+#include <linux/sysdev.h>
+#include <linux/capability.h>
+
+#define SELFBALLOON_SHOW(name, format, args...) \
+ static ssize_t show_##name(struct sys_device *dev, \
+ struct sysdev_attribute *attr, \
+ char *buf) \
+ { \
+ return sprintf(buf, format, ##args); \
+ }
+
+SELFBALLOON_SHOW(selfballooning, "%d\n", xen_selfballooning_enabled);
+
+static ssize_t store_selfballooning(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ bool was_enabled = xen_selfballooning_enabled;
+ unsigned long tmp;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = strict_strtoul(buf, 10, &tmp);
+ if (err || ((tmp != 0) && (tmp != 1)))
+ return -EINVAL;
+
+ xen_selfballooning_enabled = !!tmp;
+ if (!was_enabled && xen_selfballooning_enabled)
+ schedule_delayed_work(&selfballoon_worker,
+ selfballoon_interval * HZ);
+
+ return count;
+}
+
+static SYSDEV_ATTR(selfballooning, S_IRUGO | S_IWUSR,
+ show_selfballooning, store_selfballooning);
+
+SELFBALLOON_SHOW(selfballoon_interval, "%d\n", selfballoon_interval);
+
+static ssize_t store_selfballoon_interval(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ selfballoon_interval = val;
+ return count;
+}
+
+static SYSDEV_ATTR(selfballoon_interval, S_IRUGO | S_IWUSR,
+ show_selfballoon_interval, store_selfballoon_interval);
+
+SELFBALLOON_SHOW(selfballoon_downhys, "%d\n", selfballoon_downhysteresis);
+
+static ssize_t store_selfballoon_downhys(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ selfballoon_downhysteresis = val;
+ return count;
+}
+
+static SYSDEV_ATTR(selfballoon_downhysteresis, S_IRUGO | S_IWUSR,
+ show_selfballoon_downhys, store_selfballoon_downhys);
+
+
+SELFBALLOON_SHOW(selfballoon_uphys, "%d\n", selfballoon_uphysteresis);
+
+static ssize_t store_selfballoon_uphys(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ selfballoon_uphysteresis = val;
+ return count;
+}
+
+static SYSDEV_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
+ show_selfballoon_uphys, store_selfballoon_uphys);
+
+#ifdef CONFIG_FRONTSWAP
+SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
+
+static ssize_t store_frontswap_selfshrinking(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ bool was_enabled = frontswap_selfshrinking;
+ unsigned long tmp;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &tmp);
+ if (err || ((tmp != 0) && (tmp != 1)))
+ return -EINVAL;
+ frontswap_selfshrinking = !!tmp;
+ if (!was_enabled && !xen_selfballooning_enabled &&
+ frontswap_selfshrinking)
+ schedule_delayed_work(&selfballoon_worker,
+ selfballoon_interval * HZ);
+
+ return count;
+}
+
+static SYSDEV_ATTR(frontswap_selfshrinking, S_IRUGO | S_IWUSR,
+ show_frontswap_selfshrinking, store_frontswap_selfshrinking);
+
+SELFBALLOON_SHOW(frontswap_inertia, "%d\n", frontswap_inertia);
+
+static ssize_t store_frontswap_inertia(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ frontswap_inertia = val;
+ frontswap_inertia_counter = val;
+ return count;
+}
+
+static SYSDEV_ATTR(frontswap_inertia, S_IRUGO | S_IWUSR,
+ show_frontswap_inertia, store_frontswap_inertia);
+
+SELFBALLOON_SHOW(frontswap_hysteresis, "%d\n", frontswap_hysteresis);
+
+static ssize_t store_frontswap_hysteresis(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ err = strict_strtoul(buf, 10, &val);
+ if (err || val == 0)
+ return -EINVAL;
+ frontswap_hysteresis = val;
+ return count;
+}
+
+static SYSDEV_ATTR(frontswap_hysteresis, S_IRUGO | S_IWUSR,
+ show_frontswap_hysteresis, store_frontswap_hysteresis);
+
+#endif /* CONFIG_FRONTSWAP */
+
+static struct attribute *selfballoon_attrs[] = {
+ &attr_selfballooning.attr,
+ &attr_selfballoon_interval.attr,
+ &attr_selfballoon_downhysteresis.attr,
+ &attr_selfballoon_uphysteresis.attr,
+#ifdef CONFIG_FRONTSWAP
+ &attr_frontswap_selfshrinking.attr,
+ &attr_frontswap_hysteresis.attr,
+ &attr_frontswap_inertia.attr,
+#endif
+ NULL
+};
+
+static struct attribute_group selfballoon_group = {
+ .name = "selfballoon",
+ .attrs = selfballoon_attrs
+};
+#endif
+
+int register_xen_selfballooning(struct sys_device *sysdev)
+{
+ int error = -1;
+
+#ifdef CONFIG_SYSFS
+ error = sysfs_create_group(&sysdev->kobj, &selfballoon_group);
+#endif
+ return error;
+}
+EXPORT_SYMBOL(register_xen_selfballooning);
+
+static int __init xen_selfballoon_init(void)
+{
+ bool enable = false;
+
+ if (!xen_domain())
+ return -ENODEV;
+
+ if (xen_initial_domain()) {
+ pr_info("xen/balloon: Xen selfballooning driver "
+ "disabled for domain0.\n");
+ return -ENODEV;
+ }
+
+ xen_selfballooning_enabled = tmem_enabled && use_selfballooning;
+ if (xen_selfballooning_enabled) {
+ pr_info("xen/balloon: Initializing Xen "
+ "selfballooning driver.\n");
+ enable = true;
+ }
+#ifdef CONFIG_FRONTSWAP
+ frontswap_selfshrinking = tmem_enabled && use_frontswap_selfshrink;
+ if (frontswap_selfshrinking) {
+ pr_info("xen/balloon: Initializing frontswap "
+ "selfshrinking driver.\n");
+ enable = true;
+ }
+#endif
+ if (!enable)
+ return -ENODEV;
+
+ schedule_delayed_work(&selfballoon_worker, selfballoon_interval * HZ);
+
+ return 0;
+}
+
+subsys_initcall(xen_selfballoon_init);
+
+MODULE_LICENSE("GPL");