mm/damon/paddr: support the pageout scheme

Introduction
============

This patchset 1) makes the engine for general data access
pattern-oriented memory management (DAMOS) be more useful for production
environments, and 2) implements a static kernel module for lightweight
proactive reclamation using the engine.

Proactive Reclamation
---------------------

On general memory over-committed systems, proactively reclaiming cold
pages helps saving memory and reducing latency spikes that incurred by
the direct reclaim or the CPU consumption of kswapd, while incurring
only minimal performance degradation[2].

A Free Pages Reporting[8] based memory over-commit virtualization system
would be one more specific use case.  In the system, the guest VMs
reports their free memory to host, and the host reallocates the reported
memory to other guests.  As a result, the system's memory utilization
can be maximized.  However, the guests could be not so memory-frugal,
because some kernel subsystems and user-space applications are designed
to use as much memory as available.  Then, guests would report only
small amount of free memory to host, results in poor memory utilization.
Running the proactive reclamation in such guests could help mitigating
this problem.

Google has also implemented this idea and using it in their data center.
They further proposed upstreaming it in LSFMM'19, and "the general
consensus was that, while this sort of proactive reclaim would be useful
for a number of users, the cost of this particular solution was too high
to consider merging it upstream"[3].  The cost mainly comes from the
coldness tracking.  Roughly speaking, the implementation periodically
scans the 'Accessed' bit of each page.  For the reason, the overhead
linearly increases as the size of the memory and the scanning frequency
grows.  As a result, Google is known to dedicating one CPU for the work.
That's a reasonable option to someone like Google, but it wouldn't be so
to some others.

DAMON and DAMOS: An engine for data access pattern-oriented memory management
-----------------------------------------------------------------------------

DAMON[4] is a framework for general data access monitoring.  Its
adaptive monitoring overhead control feature minimizes its monitoring
overhead.  It also let the upper-bound of the overhead be configurable
by clients, regardless of the size of the monitoring target memory.
While monitoring 70 GiB memory of a production system every 5
milliseconds, it consumes less than 1% single CPU time.  For this, it
could sacrify some of the quality of the monitoring results.
Nevertheless, the lower-bound of the quality is configurable, and it
uses a best-effort algorithm for better quality.  Our test results[5]
show the quality is practical enough.  From the production system
monitoring, we were able to find a 4 KiB region in the 70 GiB memory
that shows highest access frequency.

We normally don't monitor the data access pattern just for fun but to
improve something like memory management.  Proactive reclamation is one
such usage.  For such general cases, DAMON provides a feature called
DAMon-based Operation Schemes (DAMOS)[6].  It makes DAMON an engine for
general data access pattern oriented memory management.  Using this,
clients can ask DAMON to find memory regions of specific data access
pattern and apply some memory management action (e.g., page out, move to
head of the LRU list, use huge page, ...).  We call the request
'scheme'.

Proactive Reclamation on top of DAMON/DAMOS
-------------------------------------------

Therefore, by using DAMON for the cold pages detection, the proactive
reclamation's monitoring overhead issue can be solved.  Actually, we
previously implemented a version of proactive reclamation using DAMOS
and achieved noticeable improvements with our evaluation setup[5].
Nevertheless, it more for a proof-of-concept, rather than production
uses.  It supports only virtual address spaces of processes, and require
additional tuning efforts for given workloads and the hardware.  For the
tuning, we introduced a simple auto-tuning user space tool[8].  Google
is also known to using a ML-based similar approach for their fleets[2].
But, making it just works with intuitive knobs in the kernel would be
helpful for general users.

To this end, this patchset improves DAMOS to be ready for such
production usages, and implements another version of the proactive
reclamation, namely DAMON_RECLAIM, on top of it.

DAMOS Improvements: Aggressiveness Control, Prioritization, and Watermarks
--------------------------------------------------------------------------

First of all, the current version of DAMOS supports only virtual address
spaces.  This patchset makes it supports the physical address space for
the page out action.

Next major problem of the current version of DAMOS is the lack of the
aggressiveness control, which can results in arbitrary overhead.  For
example, if huge memory regions having the data access pattern of
interest are found, applying the requested action to all of the regions
could incur significant overhead.  It can be controlled by tuning the
target data access pattern with manual or automated approaches[2,7].
But, some people would prefer the kernel to just work with only
intuitive tuning or default values.

For such cases, this patchset implements a safeguard, namely time/size
quota.  Using this, the clients can specify up to how much time can be
used for applying the action, and/or up to how much memory regions the
action can be applied within a user-specified time duration.  A followup
question is, to which memory regions should the action applied within
the limits? We implement a simple regions prioritization mechanism for
each action and make DAMOS to apply the action to high priority regions
first.  It also allows clients tune the prioritization mechanism to use
different weights for size, access frequency, and age of memory regions.
This means we could use not only LRU but also LFU or some fancy
algorithms like CAR[9] with lightweight overhead.

Though DAMON is lightweight, someone would want to remove even the cold
pages monitoring overhead when it is unnecessary.  Currently, it should
manually turned on and off by clients, but some clients would simply
want to turn it on and off based on some metrics like free memory ratio
or memory fragmentation.  For such cases, this patchset implements a
watermarks-based automatic activation feature.  It allows the clients
configure the metric of their interest, and three watermarks of the
metric.  If the metric is higher than the high watermark or lower than
the low watermark, the scheme is deactivated.  If the metric is lower
than the mid watermark but higher than the low watermark, the scheme is
activated.

DAMON-based Reclaim
-------------------

Using the improved version of DAMOS, this patchset implements a static
kernel module called 'damon_reclaim'.  It finds memory regions that
didn't accessed for specific time duration and page out.  Consuming too
much CPU for the paging out operations, or doing pageout too frequently
can be critical for systems configuring their swap devices with
software-defined in-memory block devices like zram/zswap or total number
of writes limited devices like SSDs, respectively.  To avoid the
problems, the time/size quotas can be configured.  Under the quotas, it
pages out memory regions that didn't accessed longer first.  Also, to
remove the monitoring overhead under peaceful situation, and to fall
back to the LRU-list based page granularity reclamation when it doesn't
make progress, the three watermarks based activation mechanism is used,
with the free memory ratio as the watermark metric.

For convenient configurations, it provides several module parameters.
Using these, sysadmins can enable/disable it, and tune its parameters
including the coldness identification time threshold, the time/size
quotas and the three watermarks.

Evaluation
==========

In short, DAMON_RECLAIM with 50ms/s time quota and regions
prioritization on v5.15-rc5 Linux kernel with ZRAM swap device achieves
38.58% memory saving with only 1.94% runtime overhead.  For this,
DAMON_RECLAIM consumes only 4.97% of single CPU time.

Setup
-----

We evaluate DAMON_RECLAIM to show how each of the DAMOS improvements
make effect.  For this, we measure DAMON_RECLAIM's CPU consumption,
entire system memory footprint, total number of major page faults, and
runtime of 24 realistic workloads in PARSEC3 and SPLASH-2X benchmark
suites on my QEMU/KVM based virtual machine.  The virtual machine runs
on an i3.metal AWS instance, has 130GiB memory, and runs a linux kernel
built on latest -mm tree[1] plus this patchset.  It also utilizes a 4
GiB ZRAM swap device.  We repeats the measurement 5 times and use
averages.

[1] https://github.com/hnaz/linux-mm/tree/v5.15-rc5-mmots-2021-10-13-19-55

Detailed Results
----------------

The results are summarized in the below table.

With coldness identification threshold of 5 seconds, DAMON_RECLAIM
without the time quota-based speed limit achieves 47.21% memory saving,
but incur 4.59% runtime slowdown to the workloads on average.  For this,
DAMON_RECLAIM consumes about 11.28% single CPU time.

Applying time quotas of 200ms/s, 50ms/s, and 10ms/s without the regions
prioritization reduces the slowdown to 4.89%, 2.65%, and 1.5%,
respectively.  Time quota of 200ms/s (20%) makes no real change compared
to the quota unapplied version, because the quota unapplied version
consumes only 11.28% CPU time.  DAMON_RECLAIM's CPU utilization also
similarly reduced: 11.24%, 5.51%, and 2.01% of single CPU time.  That
is, the overhead is proportional to the speed limit.  Nevertheless, it
also reduces the memory saving because it becomes less aggressive.  In
detail, the three variants show 48.76%, 37.83%, and 7.85% memory saving,
respectively.

Applying the regions prioritization (page out regions that not accessed
longer first within the time quota) further reduces the performance
degradation.  Runtime slowdowns and total number of major page faults
increase has been 4.89%/218,690% -> 4.39%/166,136% (200ms/s),
2.65%/111,886% -> 1.94%/59,053% (50ms/s), and 1.5%/34,973.40% ->
2.08%/8,781.75% (10ms/s).  The runtime under 10ms/s time quota has
increased with prioritization, but apparently that's under the margin of
error.

    time quota   prioritization  memory_saving  cpu_util  slowdown  pgmajfaults overhead
    N            N               47.21%         11.28%    4.59%     194,802%
    200ms/s      N               48.76%         11.24%    4.89%     218,690%
    50ms/s       N               37.83%         5.51%     2.65%     111,886%
    10ms/s       N               7.85%          2.01%     1.5%      34,793.40%
    200ms/s      Y               50.08%         10.38%    4.39%     166,136%
    50ms/s       Y               38.58%         4.97%     1.94%     59,053%
    10ms/s       Y               3.63%          1.73%     2.08%     8,781.75%

Baseline and Complete Git Trees
===============================

The patches are based on the latest -mm tree
(v5.15-rc5-mmots-2021-10-13-19-55).  You can also clone the complete git tree
from:

    $ git clone git://github.com/sjp38/linux -b damon_reclaim/patches/v1

The web is also available:
https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/tag/?h=damon_reclaim/patches/v1

Sequence Of Patches
===================

The first patch makes DAMOS support the physical address space for the
page out action.  Following five patches (patches 2-6) implement the
time/size quotas.  Next four patches (patches 7-10) implement the memory
regions prioritization within the limit.  Then, three following patches
(patches 11-13) implement the watermarks-based schemes activation.

Finally, the last two patches (patches 14-15) implement and document the
DAMON-based reclamation using the advanced DAMOS.

[1] https://www.kernel.org/doc/html/v5.15-rc1/vm/damon/index.html
[2] https://research.google/pubs/pub48551/
[3] https://lwn.net/Articles/787611/
[4] https://damonitor.github.io
[5] https://damonitor.github.io/doc/html/latest/vm/damon/eval.html
[6] https://lore.kernel.org/linux-mm/20211001125604.29660-1-sj@kernel.org/
[7] https://github.com/awslabs/damoos
[8] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html
[9] https://www.usenix.org/conference/fast-04/car-clock-adaptive-replacement

This patch (of 15):

This makes the DAMON primitives for physical address space support the
pageout action for DAMON-based Operation Schemes.  With this commit,
hence, users can easily implement system-level data access-aware
reclamations using DAMOS.

[sj@kernel.org: fix missing-prototype build warning]
  Link: https://lkml.kernel.org/r/20211025064220.13904-1-sj@kernel.org

Link: https://lkml.kernel.org/r/20211019150731.16699-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20211019150731.16699-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Amit Shah <amit@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Woodhouse <dwmw@amazon.com>
Cc: Marco Elver <elver@google.com>
Cc: Leonard Foerster <foersleo@amazon.de>
Cc: Greg Thelen <gthelen@google.com>
Cc: Markus Boehme <markubo@amazon.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/damon.h

@@ -357,6 +357,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx);
 void damon_pa_prepare_access_checks(struct damon_ctx *ctx);
 unsigned int damon_pa_check_accesses(struct damon_ctx *ctx);
 bool damon_pa_target_valid(void *t);
+int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t,
+		struct damon_region *r, struct damos *scheme);
 void damon_pa_set_primitives(struct damon_ctx *ctx);
 
 #endif	/* CONFIG_DAMON_PADDR */

mm/damon/paddr.c

@@ -11,7 +11,9 @@
 #include <linux/page_idle.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
+#include <linux/swap.h>
 
+#include "../internal.h"
 #include "prmtv-common.h"
 
 static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma,
@@ -211,6 +213,39 @@ bool damon_pa_target_valid(void *t)
 	return true;
 }
 
+int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
+		struct damon_region *r, struct damos *scheme)
+{
+	unsigned long addr;
+	LIST_HEAD(page_list);
+
+	if (scheme->action != DAMOS_PAGEOUT)
+		return -EINVAL;
+
+	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+		struct page *page = damon_get_page(PHYS_PFN(addr));
+
+		if (!page)
+			continue;
+
+		ClearPageReferenced(page);
+		test_and_clear_page_young(page);
+		if (isolate_lru_page(page)) {
+			put_page(page);
+			continue;
+		}
+		if (PageUnevictable(page)) {
+			putback_lru_page(page);
+		} else {
+			list_add(&page->lru, &page_list);
+			put_page(page);
+		}
+	}
+	reclaim_pages(&page_list);
+	cond_resched();
+	return 0;
+}
+
 void damon_pa_set_primitives(struct damon_ctx *ctx)
 {
 	ctx->primitive.init = NULL;
@@ -220,5 +255,5 @@ void damon_pa_set_primitives(struct damon_ctx *ctx)
 	ctx->primitive.reset_aggregated = NULL;
 	ctx->primitive.target_valid = damon_pa_target_valid;
 	ctx->primitive.cleanup = NULL;
-	ctx->primitive.apply_scheme = NULL;
+	ctx->primitive.apply_scheme = damon_pa_apply_scheme;
 }