xref: /linux/Documentation/admin-guide/mm/zswap.rst (revision 68a052239fc4b351e961f698b824f7654a346091)
1=====
2zswap
3=====
4
5Overview
6========
7
8Zswap is a lightweight compressed cache for swap pages. It takes pages that are
9in the process of being swapped out and attempts to compress them into a
10dynamically allocated RAM-based memory pool.  zswap basically trades CPU cycles
11for potentially reduced swap I/O.  This trade-off can also result in a
12significant performance improvement if reads from the compressed cache are
13faster than reads from a swap device.
14
15Some potential benefits:
16
17* Desktop/laptop users with limited RAM capacities can mitigate the
18  performance impact of swapping.
19* Overcommitted guests that share a common I/O resource can
20  dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
21  throttling by the hypervisor. This allows more work to get done with less
22  impact to the guest workload and guests sharing the I/O subsystem
23* Users with SSDs as swap devices can extend the life of the device by
24  drastically reducing life-shortening writes.
25
26Zswap evicts pages from compressed cache on an LRU basis to the backing swap
27device when the compressed pool reaches its size limit.  This requirement had
28been identified in prior community discussions.
29
30Whether Zswap is enabled at the boot time depends on whether
31the ``CONFIG_ZSWAP_DEFAULT_ON`` Kconfig option is enabled or not.
32This setting can then be overridden by providing the kernel command line
33``zswap.enabled=`` option, for example ``zswap.enabled=0``.
34Zswap can also be enabled and disabled at runtime using the sysfs interface.
35An example command to enable zswap at runtime, assuming sysfs is mounted
36at ``/sys``, is::
37
38	echo 1 > /sys/module/zswap/parameters/enabled
39
40When zswap is disabled at runtime it will stop storing pages that are
41being swapped out.  However, it will _not_ immediately write out or fault
42back into memory all of the pages stored in the compressed pool.  The
43pages stored in zswap will remain in the compressed pool until they are
44either invalidated or faulted back into memory.  In order to force all
45pages out of the compressed pool, a swapoff on the swap device(s) will
46fault back into memory all swapped out pages, including those in the
47compressed pool.
48
49Design
50======
51
52Zswap receives pages for compression from the swap subsystem and is able to
53evict pages from its own compressed pool on an LRU basis and write them back to
54the backing swap device in the case that the compressed pool is full.
55
56Zswap makes use of zsmalloc for the managing the compressed memory pool.  Each
57allocation in zsmalloc is not directly accessible by address.  Rather, a handle is
58returned by the allocation routine and that handle must be mapped before being
59accessed.  The compressed memory pool grows on demand and shrinks as compressed
60pages are freed.  The pool is not preallocated.
61
62When a swap page is passed from swapout to zswap, zswap maintains a mapping
63of the swap entry, a combination of the swap type and swap offset, to the
64zsmalloc handle that references that compressed swap page.  This mapping is
65achieved with a red-black tree per swap type.  The swap offset is the search
66key for the tree nodes.
67
68During a page fault on a PTE that is a swap entry, the swapin code calls the
69zswap load function to decompress the page into the page allocated by the page
70fault handler.
71
72Once there are no PTEs referencing a swap page stored in zswap (i.e. the count
73in the swap_map goes to 0) the swap code calls the zswap invalidate function
74to free the compressed entry.
75
76Zswap seeks to be simple in its policies.  Sysfs attributes allow for one user
77controlled policy:
78
79* max_pool_percent - The maximum percentage of memory that the compressed
80  pool can occupy.
81
82The default compressor is selected in ``CONFIG_ZSWAP_COMPRESSOR_DEFAULT``
83Kconfig option, but it can be overridden at boot time by setting the
84``compressor`` attribute, e.g. ``zswap.compressor=lzo``.
85It can also be changed at runtime using the sysfs "compressor"
86attribute, e.g.::
87
88	echo lzo > /sys/module/zswap/parameters/compressor
89
90When the compressor parameter is changed at runtime, any existing compressed
91pages are not modified; they are left in their own pool.  When a request is
92made for a page in an old pool, it is uncompressed using its original
93compressor.  Once all pages are removed from an old pool, the pool and its
94compressor are freed.
95
96Some of the pages in zswap are same-value filled pages (i.e. contents of the
97page have same value or repetitive pattern). These pages include zero-filled
98pages and they are handled differently. During store operation, a page is
99checked if it is a same-value filled page before compressing it. If true, the
100compressed length of the page is set to zero and the pattern or same-filled
101value is stored.
102
103To prevent zswap from shrinking pool when zswap is full and there's a high
104pressure on swap (this will result in flipping pages in and out zswap pool
105without any real benefit but with a performance drop for the system), a
106special parameter has been introduced to implement a sort of hysteresis to
107refuse taking pages into zswap pool until it has sufficient space if the limit
108has been hit. To set the threshold at which zswap would start accepting pages
109again after it became full, use the sysfs ``accept_threshold_percent``
110attribute, e. g.::
111
112	echo 80 > /sys/module/zswap/parameters/accept_threshold_percent
113
114Setting this parameter to 100 will disable the hysteresis.
115
116Some users cannot tolerate the swapping that comes with zswap store failures
117and zswap writebacks. Swapping can be disabled entirely (without disabling
118zswap itself) on a cgroup-basis as follows::
119
120	echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
121
122Note that if the store failures are recurring (for e.g if the pages are
123incompressible), users can observe reclaim inefficiency after disabling
124writeback (because the same pages might be rejected again and again).
125
126When there is a sizable amount of cold memory residing in the zswap pool, it
127can be advantageous to proactively write these cold pages to swap and reclaim
128the memory for other use cases. By default, the zswap shrinker is disabled.
129User can enable it as follows::
130
131  echo Y > /sys/module/zswap/parameters/shrinker_enabled
132
133This can be enabled at the boot time if ``CONFIG_ZSWAP_SHRINKER_DEFAULT_ON`` is
134selected.
135
136A debugfs interface is provided for various statistic about pool size, number
137of pages stored, same-value filled pages and various counters for the reasons
138pages are rejected.
139