2009-09-22 04:56:53 +00:00
|
|
|
/*
|
2010-06-01 08:01:25 +00:00
|
|
|
* Compressed RAM block device
|
2009-09-22 04:56:53 +00:00
|
|
|
*
|
2010-01-28 15:51:35 +00:00
|
|
|
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
|
2014-01-30 23:45:55 +00:00
|
|
|
* 2012, 2013 Minchan Kim
|
2009-09-22 04:56:53 +00:00
|
|
|
*
|
|
|
|
|
* This code is released using a dual license strategy: BSD/GPL
|
|
|
|
|
* You can choose the licence that better fits your requirements.
|
|
|
|
|
*
|
|
|
|
|
* Released under the terms of 3-clause BSD License
|
|
|
|
|
* Released under the terms of GNU General Public License Version 2.0
|
|
|
|
|
*
|
|
|
|
|
*/
|
|
|
|
|
|
2010-06-01 08:01:25 +00:00
|
|
|
#ifndef _ZRAM_DRV_H_
|
|
|
|
|
#define _ZRAM_DRV_H_
|
2009-09-22 04:56:53 +00:00
|
|
|
|
zram: use crypto api to check alg availability
There is no way to get a string with all the crypto comp algorithms
supported by the crypto comp engine, so we need to maintain our own
backends list. At the same time we additionally need to use
crypto_has_comp() to make sure that the user has requested a compression
algorithm that is recognized by the crypto comp engine. Relying on
/proc/crypto is not an options here, because it does not show
not-yet-inserted compression modules.
Example:
modprobe zram
cat /proc/crypto | grep -i lz4
modprobe lz4
cat /proc/crypto | grep -i lz4
name : lz4
driver : lz4-generic
module : lz4
So the user can't tell exactly if the lz4 is really supported from
/proc/crypto output, unless someone or something has loaded it.
This patch also adds crypto_has_comp() to zcomp_available_show(). We
store all the compression algorithms names in zcomp's `backends' array,
regardless the CONFIG_CRYPTO_FOO configuration, but show only those that
are also supported by crypto engine. This helps user to know the exact
list of compression algorithms that can be used.
Example:
module lz4 is not loaded yet, but is supported by the crypto
engine. /proc/crypto has no information on this module, while
zram's `comp_algorithm' lists it:
cat /proc/crypto | grep -i lz4
cat /sys/block/zram0/comp_algorithm
[lzo] lz4 deflate lz4hc 842
We still use the `backends' array to determine if the requested
compression backend is known to crypto api. This array, however, may not
contain some entries, therefore as the last step we call crypto_has_comp()
function which attempts to insmod the requested compression algorithm to
determine if crypto api supports it. The advantage of this method is that
now we permit the usage of out-of-tree crypto compression modules
(implementing S/W or H/W compression).
[sergey.senozhatsky@gmail.com: zram-use-crypto-api-to-check-alg-availability-v3]
Link: http://lkml.kernel.org/r/20160604024902.11778-4-sergey.senozhatsky@gmail.com
Link: http://lkml.kernel.org/r/20160531122017.2878-5-sergey.senozhatsky@gmail.com
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:22:48 +00:00
|
|
|
#include <linux/rwsem.h>
|
2014-01-30 23:45:50 +00:00
|
|
|
#include <linux/zsmalloc.h>
|
zram: use crypto api to check alg availability
There is no way to get a string with all the crypto comp algorithms
supported by the crypto comp engine, so we need to maintain our own
backends list. At the same time we additionally need to use
crypto_has_comp() to make sure that the user has requested a compression
algorithm that is recognized by the crypto comp engine. Relying on
/proc/crypto is not an options here, because it does not show
not-yet-inserted compression modules.
Example:
modprobe zram
cat /proc/crypto | grep -i lz4
modprobe lz4
cat /proc/crypto | grep -i lz4
name : lz4
driver : lz4-generic
module : lz4
So the user can't tell exactly if the lz4 is really supported from
/proc/crypto output, unless someone or something has loaded it.
This patch also adds crypto_has_comp() to zcomp_available_show(). We
store all the compression algorithms names in zcomp's `backends' array,
regardless the CONFIG_CRYPTO_FOO configuration, but show only those that
are also supported by crypto engine. This helps user to know the exact
list of compression algorithms that can be used.
Example:
module lz4 is not loaded yet, but is supported by the crypto
engine. /proc/crypto has no information on this module, while
zram's `comp_algorithm' lists it:
cat /proc/crypto | grep -i lz4
cat /sys/block/zram0/comp_algorithm
[lzo] lz4 deflate lz4hc 842
We still use the `backends' array to determine if the requested
compression backend is known to crypto api. This array, however, may not
contain some entries, therefore as the last step we call crypto_has_comp()
function which attempts to insmod the requested compression algorithm to
determine if crypto api supports it. The advantage of this method is that
now we permit the usage of out-of-tree crypto compression modules
(implementing S/W or H/W compression).
[sergey.senozhatsky@gmail.com: zram-use-crypto-api-to-check-alg-availability-v3]
Link: http://lkml.kernel.org/r/20160604024902.11778-4-sergey.senozhatsky@gmail.com
Link: http://lkml.kernel.org/r/20160531122017.2878-5-sergey.senozhatsky@gmail.com
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-26 22:22:48 +00:00
|
|
|
#include <linux/crypto.h>
|
2009-09-22 04:56:53 +00:00
|
|
|
|
2014-04-07 22:38:12 +00:00
|
|
|
#include "zcomp.h"
|
|
|
|
|
|
2009-09-22 04:56:53 +00:00
|
|
|
#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
|
|
|
|
|
#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
|
2011-06-10 13:28:48 +00:00
|
|
|
#define ZRAM_LOGICAL_BLOCK_SHIFT 12
|
|
|
|
|
#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
|
|
|
|
|
#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
|
|
|
|
|
(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
|
2009-09-22 04:56:53 +00:00
|
|
|
|
zram: replace global tb_lock with fine grain lock
Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.
The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.
With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:
Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.
iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166
To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.
fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471
All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.
On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.
This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.
On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:08:31 +00:00
|
|
|
|
|
|
|
|
/*
|
2022-09-12 15:27:44 +00:00
|
|
|
* ZRAM is mainly used for memory efficiency so we want to keep memory
|
|
|
|
|
* footprint small and thus squeeze size and zram pageflags into a flags
|
|
|
|
|
* member. The lower ZRAM_FLAG_SHIFT bits is for object size (excluding
|
|
|
|
|
* header), which cannot be larger than PAGE_SIZE (requiring PAGE_SHIFT
|
|
|
|
|
* bits), the higher bits are for zram_pageflags.
|
zram: replace global tb_lock with fine grain lock
Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.
The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.
With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:
Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.
iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166
To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.
fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471
All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.
On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.
This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.
On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:08:31 +00:00
|
|
|
*
|
2022-09-12 15:27:44 +00:00
|
|
|
* We use BUILD_BUG_ON() to make sure that zram pageflags don't overflow.
|
zram: replace global tb_lock with fine grain lock
Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.
The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.
With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:
Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.
iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166
To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.
fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471
All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.
On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.
This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.
On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:08:31 +00:00
|
|
|
*/
|
2022-09-12 15:27:44 +00:00
|
|
|
#define ZRAM_FLAG_SHIFT (PAGE_SHIFT + 1)
|
zram: replace global tb_lock with fine grain lock
Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.
The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.
With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:
Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.
iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166
To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.
fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471
All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.
On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.
This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.
On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:08:31 +00:00
|
|
|
|
2022-11-09 11:50:38 +00:00
|
|
|
/* Only 2 bits are allowed for comp priority index */
|
|
|
|
|
#define ZRAM_COMP_PRIORITY_MASK 0x3
|
|
|
|
|
|
2018-12-28 08:36:40 +00:00
|
|
|
/* Flags for zram pages (table[page_no].flags) */
|
2010-06-01 08:01:25 +00:00
|
|
|
enum zram_pageflags {
|
2018-06-08 00:05:39 +00:00
|
|
|
/* zram slot is locked */
|
|
|
|
|
ZRAM_LOCK = ZRAM_FLAG_SHIFT,
|
|
|
|
|
ZRAM_SAME, /* Page consists the same element */
|
2017-09-06 23:20:03 +00:00
|
|
|
ZRAM_WB, /* page is stored on backing_device */
|
zram: support idle/huge page writeback
Add a new feature "zram idle/huge page writeback". In the zram-swap use
case, zram usually has many idle/huge swap pages. It's pointless to keep
them in memory (ie, zram).
To solve this problem, this feature introduces idle/huge page writeback to
the backing device so the goal is to save more memory space on embedded
systems.
Normal sequence to use idle/huge page writeback feature is as follows,
while (1) {
# mark allocated zram slot to idle
echo all > /sys/block/zram0/idle
# leave system working for several hours
# Unless there is no access for some blocks on zram,
# they are still IDLE marked pages.
echo "idle" > /sys/block/zram0/writeback
or/and
echo "huge" > /sys/block/zram0/writeback
# write the IDLE or/and huge marked slot into backing device
# and free the memory.
}
Per the discussion at
https://lore.kernel.org/lkml/20181122065926.GG3441@jagdpanzerIV/T/#u,
This patch removes direct incommpressibe page writeback feature
(d2afd25114f4 ("zram: write incompressible pages to backing device")).
Below concerns from Sergey:
== &< ==
"IDLE writeback" is superior to "incompressible writeback".
"incompressible writeback" is completely unpredictable and uncontrollable;
it depens on data patterns and compression algorithms. While "IDLE
writeback" is predictable.
I even suspect, that, *ideally*, we can remove "incompressible writeback".
"IDLE pages" is a super set which also includes "incompressible" pages.
So, technically, we still can do "incompressible writeback" from "IDLE
writeback" path; but a much more reasonable one, based on a page idling
period.
I understand that you want to keep "direct incompressible writeback"
around. ZRAM is especially popular on devices which do suffer from flash
wearout, so I can see "incompressible writeback" path becoming a dead
code, long term.
== &< ==
Below concerns from Minchan:
== &< ==
My concern is if we enable CONFIG_ZRAM_WRITEBACK in this implementation,
both hugepage/idlepage writeck will turn on. However someuser want to
enable only idlepage writeback so we need to introduce turn on/off knob
for hugepage or new CONFIG_ZRAM_IDLEPAGE_WRITEBACK for those usecase. I
don't want to make it complicated *if possible*.
Long term, I imagine we need to make VM aware of new swap hierarchy a
little bit different with as-is. For example, first high priority swap
can return -EIO or -ENOCOMP, swap try to fallback to next lower priority
swap device. With that, hugepage writeback will work tranparently.
So we could regard it as regression because incompressible pages doesn't
go to backing storage automatically. Instead, user should do it via "echo
huge" > /sys/block/zram/writeback" manually.
== &< ==
Link: http://lkml.kernel.org/r/20181127055429.251614-6-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Joey Pabalinas <joeypabalinas@gmail.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:47 +00:00
|
|
|
ZRAM_UNDER_WB, /* page is under writeback */
|
2018-06-08 00:05:42 +00:00
|
|
|
ZRAM_HUGE, /* Incompressible page */
|
2018-12-28 08:36:44 +00:00
|
|
|
ZRAM_IDLE, /* not accessed page since last idle marking */
|
2022-11-09 11:50:38 +00:00
|
|
|
ZRAM_INCOMPRESSIBLE, /* none of the algorithms could compress it */
|
|
|
|
|
|
|
|
|
|
ZRAM_COMP_PRIORITY_BIT1, /* First bit of comp priority index */
|
|
|
|
|
ZRAM_COMP_PRIORITY_BIT2, /* Second bit of comp priority index */
|
2009-09-22 04:56:53 +00:00
|
|
|
|
2010-06-01 08:01:25 +00:00
|
|
|
__NR_ZRAM_PAGEFLAGS,
|
2009-09-22 04:56:53 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*-- Data structures */
|
|
|
|
|
|
2010-06-01 08:01:25 +00:00
|
|
|
/* Allocated for each disk page */
|
2014-08-06 23:08:25 +00:00
|
|
|
struct zram_table_entry {
|
2017-02-24 22:59:27 +00:00
|
|
|
union {
|
|
|
|
|
unsigned long handle;
|
|
|
|
|
unsigned long element;
|
|
|
|
|
};
|
2018-12-28 08:36:40 +00:00
|
|
|
unsigned long flags;
|
2018-06-08 00:05:49 +00:00
|
|
|
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
|
|
|
|
|
ktime_t ac_time;
|
|
|
|
|
#endif
|
zram: replace global tb_lock with fine grain lock
Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table. However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.
The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.
With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:
Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.
iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------------
Initial write 1381094 1425435 1422860 1423075 1421521
Rewrite 1529479 1641199 1668762 1672855 1654910
Read 8468009 11324979 11305569 11117273 10997202
Re-read 8467476 11260914 11248059 11145336 10906486
Reverse Read 6821393 8106334 8282174 8279195 8109186
Stride read 7191093 8994306 9153982 8961224 9004434
Random read 7156353 8957932 9167098 8980465 8940476
Mixed workload 4172747 5680814 5927825 5489578 5972253
Random write 1483044 1605588 1594329 1600453 1596010
Pwrite 1276644 1303108 1311612 1314228 1300960
Pread 4324337 4632869 4618386 4457870 4500166
To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.
fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)
Test base CAS spinlock rwlock bit_spinlock
-------------------------------------------------------------
seq-write 933789 999357 1003298 995961 1001958
seq-read 5634130 6577930 6380861 6243912 6230006
seq-rw 1405687 1638117 1640256 1633903 1634459
rand-rw 1386119 1614664 1617211 1609267 1612471
All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.
On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.
This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.
On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly. So we can ignore the different performances
among locks.
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 23:08:31 +00:00
|
|
|
};
|
2009-09-22 04:56:53 +00:00
|
|
|
|
2010-06-01 08:01:25 +00:00
|
|
|
struct zram_stats {
|
2014-04-07 22:38:03 +00:00
|
|
|
atomic64_t compr_data_size; /* compressed size of pages stored */
|
2014-08-29 22:18:37 +00:00
|
|
|
atomic64_t failed_reads; /* can happen when memory is too low */
|
2013-06-06 16:07:31 +00:00
|
|
|
atomic64_t failed_writes; /* can happen when memory is too low */
|
|
|
|
|
atomic64_t notify_free; /* no. of swap slot free notifications */
|
2017-02-24 22:59:27 +00:00
|
|
|
atomic64_t same_pages; /* no. of same element filled pages */
|
2018-06-08 00:05:42 +00:00
|
|
|
atomic64_t huge_pages; /* no. of huge pages */
|
2020-12-15 03:14:32 +00:00
|
|
|
atomic64_t huge_pages_since; /* no. of huge pages since zram set up */
|
2014-04-07 22:38:03 +00:00
|
|
|
atomic64_t pages_stored; /* no. of pages currently stored */
|
2014-10-09 22:29:55 +00:00
|
|
|
atomic_long_t max_used_pages; /* no. of maximum pages stored */
|
Revert "zram: remove double compression logic"
This reverts commit e7be8d1dd983156b ("zram: remove double compression
logic") as it causes zram failures. It does not revert cleanly, PTR_ERR
handling was introduced in the meantime. This is handled by appropriate
IS_ERR.
When under memory pressure, zs_malloc() can fail. Before the above
commit, the allocation was retried with direct reclaim enabled (GFP_NOIO).
After the commit, it is not -- only __GFP_KSWAPD_RECLAIM is tried.
So when the failure occurs under memory pressure, the overlaying
filesystem such as ext2 (mounted by ext4 module in this case) can emit
failures, making the (file)system unusable:
EXT4-fs warning (device zram0): ext4_end_bio:343: I/O error 10 writing to inode 16386 starting block 159744)
Buffer I/O error on device zram0, logical block 159744
With direct reclaim, memory is really reclaimed and allocation succeeds,
eventually. In the worst case, the oom killer is invoked, which is proper
outcome if user sets up zram too large (in comparison to available RAM).
This very diff doesn't apply to 5.19 (stable) cleanly (see PTR_ERR note
above). Use revert of e7be8d1dd983 directly.
Link: https://bugzilla.suse.com/show_bug.cgi?id=1202203
Link: https://lkml.kernel.org/r/20220810070609.14402-1-jslaby@suse.cz
Fixes: e7be8d1dd983 ("zram: remove double compression logic")
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Alexey Romanov <avromanov@sberdevices.ru>
Cc: Dmitry Rokosov <ddrokosov@sberdevices.ru>
Cc: Lukas Czerner <lczerner@redhat.com>
Cc: <stable@vger.kernel.org> [5.19]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-10 07:06:09 +00:00
|
|
|
atomic64_t writestall; /* no. of write slow paths */
|
zram: fix lockdep warning of free block handling
Patch series "zram idle page writeback", v3.
Inherently, swap device has many idle pages which are rare touched since
it was allocated. It is never problem if we use storage device as swap.
However, it's just waste for zram-swap.
This patchset supports zram idle page writeback feature.
* Admin can define what is idle page "no access since X time ago"
* Admin can define when zram should writeback them
* Admin can define when zram should stop writeback to prevent wearout
Details are in each patch's description.
This patch (of 7):
================================
WARNING: inconsistent lock state
4.19.0+ #390 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
zram_verify/2095 [HC0[0]:SC1[1]:HE1:SE0] takes:
00000000b1828693 (&(&zram->bitmap_lock)->rlock){+.?.}, at: put_entry_bdev+0x1e/0x50
{SOFTIRQ-ON-W} state was registered at:
_raw_spin_lock+0x2c/0x40
zram_make_request+0x755/0xdc9
generic_make_request+0x373/0x6a0
submit_bio+0x6c/0x140
__swap_writepage+0x3a8/0x480
shrink_page_list+0x1102/0x1a60
shrink_inactive_list+0x21b/0x3f0
shrink_node_memcg.constprop.99+0x4f8/0x7e0
shrink_node+0x7d/0x2f0
do_try_to_free_pages+0xe0/0x300
try_to_free_pages+0x116/0x2b0
__alloc_pages_slowpath+0x3f4/0xf80
__alloc_pages_nodemask+0x2a2/0x2f0
__handle_mm_fault+0x42e/0xb50
handle_mm_fault+0x55/0xb0
__do_page_fault+0x235/0x4b0
page_fault+0x1e/0x30
irq event stamp: 228412
hardirqs last enabled at (228412): [<ffffffff98245846>] __slab_free+0x3e6/0x600
hardirqs last disabled at (228411): [<ffffffff98245625>] __slab_free+0x1c5/0x600
softirqs last enabled at (228396): [<ffffffff98e0031e>] __do_softirq+0x31e/0x427
softirqs last disabled at (228403): [<ffffffff98072051>] irq_exit+0xd1/0xe0
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&(&zram->bitmap_lock)->rlock);
<Interrupt>
lock(&(&zram->bitmap_lock)->rlock);
*** DEADLOCK ***
no locks held by zram_verify/2095.
stack backtrace:
CPU: 5 PID: 2095 Comm: zram_verify Not tainted 4.19.0+ #390
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
Call Trace:
<IRQ>
dump_stack+0x67/0x9b
print_usage_bug+0x1bd/0x1d3
mark_lock+0x4aa/0x540
__lock_acquire+0x51d/0x1300
lock_acquire+0x90/0x180
_raw_spin_lock+0x2c/0x40
put_entry_bdev+0x1e/0x50
zram_free_page+0xf6/0x110
zram_slot_free_notify+0x42/0xa0
end_swap_bio_read+0x5b/0x170
blk_update_request+0x8f/0x340
scsi_end_request+0x2c/0x1e0
scsi_io_completion+0x98/0x650
blk_done_softirq+0x9e/0xd0
__do_softirq+0xcc/0x427
irq_exit+0xd1/0xe0
do_IRQ+0x93/0x120
common_interrupt+0xf/0xf
</IRQ>
With writeback feature, zram_slot_free_notify could be called in softirq
context by end_swap_bio_read. However, bitmap_lock is not aware of that
so lockdep yell out:
get_entry_bdev
spin_lock(bitmap->lock);
irq
softirq
end_swap_bio_read
zram_slot_free_notify
zram_slot_lock <-- deadlock prone
zram_free_page
put_entry_bdev
spin_lock(bitmap->lock); <-- deadlock prone
With akpm's suggestion (i.e. bitmap operation is already atomic), we
could remove bitmap lock. It might fail to find a empty slot if serious
contention happens. However, it's not severe problem because huge page
writeback has already possiblity to fail if there is severe memory
pressure. Worst case is just keeping the incompressible in memory, not
storage.
The other problem is zram_slot_lock in zram_slot_slot_free_notify. To
make it safe is this patch introduces zram_slot_trylock where
zram_slot_free_notify uses it. Although it's rare to be contented, this
patch adds new debug stat "miss_free" to keep monitoring how often it
happens.
Link: http://lkml.kernel.org/r/20181127055429.251614-2-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Joey Pabalinas <joeypabalinas@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:36:33 +00:00
|
|
|
atomic64_t miss_free; /* no. of missed free */
|
2018-12-28 08:36:51 +00:00
|
|
|
#ifdef CONFIG_ZRAM_WRITEBACK
|
|
|
|
|
atomic64_t bd_count; /* no. of pages in backing device */
|
|
|
|
|
atomic64_t bd_reads; /* no. of reads from backing device */
|
|
|
|
|
atomic64_t bd_writes; /* no. of writes from backing device */
|
|
|
|
|
#endif
|
2009-09-22 04:56:53 +00:00
|
|
|
};
|
|
|
|
|
|
2022-11-09 11:50:35 +00:00
|
|
|
#ifdef CONFIG_ZRAM_MULTI_COMP
|
|
|
|
|
#define ZRAM_PRIMARY_COMP 0U
|
|
|
|
|
#define ZRAM_SECONDARY_COMP 1U
|
|
|
|
|
#define ZRAM_MAX_COMPS 4U
|
|
|
|
|
#else
|
|
|
|
|
#define ZRAM_PRIMARY_COMP 0U
|
|
|
|
|
#define ZRAM_SECONDARY_COMP 0U
|
|
|
|
|
#define ZRAM_MAX_COMPS 1U
|
|
|
|
|
#endif
|
|
|
|
|
|
2017-05-03 21:55:47 +00:00
|
|
|
struct zram {
|
2014-08-06 23:08:25 +00:00
|
|
|
struct zram_table_entry *table;
|
2013-02-05 23:48:53 +00:00
|
|
|
struct zs_pool *mem_pool;
|
2022-11-09 11:50:35 +00:00
|
|
|
struct zcomp *comps[ZRAM_MAX_COMPS];
|
2009-09-22 04:56:53 +00:00
|
|
|
struct gendisk *disk;
|
2015-02-12 23:00:45 +00:00
|
|
|
/* Prevent concurrent execution of device init */
|
2011-09-06 13:02:11 +00:00
|
|
|
struct rw_semaphore init_lock;
|
2009-09-22 04:56:53 +00:00
|
|
|
/*
|
2015-02-12 23:00:45 +00:00
|
|
|
* the number of pages zram can consume for storing compressed data
|
2009-09-22 04:56:53 +00:00
|
|
|
*/
|
2015-02-12 23:00:45 +00:00
|
|
|
unsigned long limit_pages;
|
|
|
|
|
|
2010-06-01 08:01:25 +00:00
|
|
|
struct zram_stats stats;
|
2014-10-09 22:29:53 +00:00
|
|
|
/*
|
2015-02-12 23:00:45 +00:00
|
|
|
* This is the limit on amount of *uncompressed* worth of data
|
|
|
|
|
* we can store in a disk.
|
2014-10-09 22:29:53 +00:00
|
|
|
*/
|
2015-02-12 23:00:45 +00:00
|
|
|
u64 disksize; /* bytes */
|
2022-11-09 11:50:35 +00:00
|
|
|
const char *comp_algs[ZRAM_MAX_COMPS];
|
2022-11-09 11:50:44 +00:00
|
|
|
s8 num_active_comps;
|
2015-06-25 22:00:21 +00:00
|
|
|
/*
|
|
|
|
|
* zram is claimed so open request will be failed
|
|
|
|
|
*/
|
2021-05-25 06:12:56 +00:00
|
|
|
bool claim; /* Protected by disk->open_mutex */
|
2018-12-28 08:36:40 +00:00
|
|
|
#ifdef CONFIG_ZRAM_WRITEBACK
|
2021-07-01 01:53:07 +00:00
|
|
|
struct file *backing_dev;
|
2019-01-08 23:22:53 +00:00
|
|
|
spinlock_t wb_limit_lock;
|
|
|
|
|
bool wb_limit_enable;
|
|
|
|
|
u64 bd_wb_limit;
|
2023-09-27 09:34:14 +00:00
|
|
|
struct bdev_handle *bdev_handle;
|
2017-09-06 23:19:57 +00:00
|
|
|
unsigned long *bitmap;
|
|
|
|
|
unsigned long nr_pages;
|
2017-09-06 23:19:54 +00:00
|
|
|
#endif
|
2018-06-08 00:05:49 +00:00
|
|
|
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
|
|
|
|
|
struct dentry *debugfs_dir;
|
|
|
|
|
#endif
|
2009-09-22 04:56:53 +00:00
|
|
|
};
|
2010-01-28 15:43:37 +00:00
|
|
|
#endif
|