Changes in sysfs-block-zram

4127e13c - zram: remove max_comp_streams device attr

Mon, 03 Mar 2025 02:03:13 +0000

zram: remove max_comp_streams device attrmax_comp_streams device attribute has been defunct since May 2016 whenzram switched to per-CPU compression streams, remove it.Link: https://lkml.kernel.org/r/20250303022425.285971-5-senozhatsky@chromium.orgSigned-off-by: Sergey Senozhatsky Cc: Hillf Danton Cc: Kairui Song Cc: Minchan Kim Cc: Sebastian Andrzej Siewior Cc: Yosry Ahmed Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

4eac9321 - zram: introduce algorithm_params device attribute

Mon, 02 Sep 2024 10:56:03 +0000

zram: introduce algorithm_params device attributeThis attribute is used to setup compression algorithms' parameters, so wecan tweak algorithms' characteristics. At this point only 'level' issupported (to be extended in the future).Each call sets up parameters for one particular algorithm, which should bespecified either by the algorithm's priority or algo name. This isexpected to be called after corresponding algorithm is selected viacomp_algorithm or recomp_algorithm. echo "priority=0 level=1" > /sys/block/zram0/algorithm_paramsor echo "algo=zstd level=1" > /sys/block/zram0/algorithm_paramsLink: https://lkml.kernel.org/r/20240902105656.1383858-16-senozhatsky@chromium.orgSigned-off-by: Sergey Senozhatsky Cc: Minchan Kim Cc: Nick Terrell Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

c959a0e8 - Docs/ABI/zram: document zram recompress sysfs knobs

Tue, 15 Nov 2022 02:03:14 +0000

Docs/ABI/zram: document zram recompress sysfs knobsDocument zram re-compression sysfs knobs.Link: https://lkml.kernel.org/r/20221115020314.386235-1-senozhatsky@chromium.orgSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

1d69a3f8 - zram: idle writeback fixes and cleanup

Tue, 08 Jan 2019 23:22:53 +0000

zram: idle writeback fixes and cleanupThis patch includes some fixes and cleanup for idle-page writeback.1. writeback_limit interfaceNow writeback_limit interface is rather conusing. For example, oncewriteback limit budget is exausted, admin can see 0 from/sys/block/zramX/writeback_limit which is same semantic with disablewriteback_limit at this moment. IOW, admin cannot tell that zero camefrom disable writeback limit or exausted writeback limit.To make the interface clear, let's sepatate enable of writeback limit toanother knob - /sys/block/zram0/writeback_limit_enable* before: while true : # to re-enable writeback limit once previous one is used up echo 0 > /sys/block/zram0/writeback_limit echo $((200<<20)) > /sys/block/zram0/writeback_limit .. .. # used up the writeback limit budget* new # To enable writeback limit, from the beginning, admin should # enable it. echo $((200<<20)) > /sys/block/zram0/writeback_limit echo 1 > /sys/block/zram/0/writeback_limit_enable while true : echo $((200<<20)) > /sys/block/zram0/writeback_limit .. .. # used up the writeback limit budgetIt's much strightforward.2. fix condition check idle/huge writeback mode checkThe mode in writeback_store is not bit opeartion any more so no need touse bit operations. Furthermore, current condition check is broken inthat it does writeback every pages regardless of huge/idle.3. clean up idle_storeNo need to use goto.[minchan@kernel.org: missed spin_lock_init] Link: http://lkml.kernel.org/r/20190103001601.GA255139@google.comLink: http://lkml.kernel.org/r/20181224033529.19450-1-minchan@kernel.orgSigned-off-by: Minchan Kim Suggested-by: John Dias Cc: Sergey Senozhatsky Cc: John Dias Cc: Srinivas Paladugu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

bb416d18 - zram: writeback throttle

Fri, 28 Dec 2018 08:36:54 +0000

zram: writeback throttleIf there are lots of write IO with flash device, it could have awearout problem of storage. To overcome the problem, admin needsto design write limitation to guarantee flash healthfor entire product life.This patch creates a new knob "writeback_limit" for zram.writeback_limit's default value is 0 so that it doesn't limitany writeback. If admin want to measure writeback count in acertain period, he could know it via /sys/block/zram0/bd_stat's3rd column.If admin want to limit writeback as per-day 400M, he could do itlike below. MB_SHIFT=20 4K_SHIFT=12 echo $((400<>4K_SHIFT)) > \ /sys/block/zram0/writeback_limit.If admin want to allow further write again, he could do it like below echo 0 > /sys/block/zram0/writeback_limitIf admin want to see remaining writeback budget, cat /sys/block/zram0/writeback_limitThe writeback_limit count will reset whenever you reset zram (e.g., systemreboot, echo 1 > /sys/block/zramX/reset) so keeping how many of writebackhappened until you reset the zram to allocate extra writeback budget innext setting is user's job.[minchan@kernel.org: v4] Link: http://lkml.kernel.org/r/20181203024045.153534-8-minchan@kernel.orgLink: http://lkml.kernel.org/r/20181127055429.251614-8-minchan@kernel.orgSigned-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

23eddf39 - zram: add bd_stat statistics

Fri, 28 Dec 2018 08:36:51 +0000

zram: add bd_stat statisticsbd_stat represents things that happened in the backing device. Currentlyit supports bd_counts, bd_reads and bd_writes which are helpful tounderstand wearout of flash and memory saving.[minchan@kernel.org: v4] Link: http://lkml.kernel.org/r/20181203024045.153534-7-minchan@kernel.orgLink: http://lkml.kernel.org/r/20181127055429.251614-7-minchan@kernel.orgSigned-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

a939888e - zram: support idle/huge page writeback

Fri, 28 Dec 2018 08:36:47 +0000

zram: support idle/huge page writebackAdd a new feature "zram idle/huge page writeback". In the zram-swap usecase, zram usually has many idle/huge swap pages. It's pointless to keepthem in memory (ie, zram).To solve this problem, this feature introduces idle/huge page writeback tothe backing device so the goal is to save more memory space on embeddedsystems.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 athttps://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 "IDLEwriteback" 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 "IDLEwriteback" path; but a much more reasonable one, based on a page idlingperiod.I understand that you want to keep "direct incompressible writeback"around. ZRAM is especially popular on devices which do suffer from flashwearout, so I can see "incompressible writeback" path becoming a deadcode, 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 toenable only idlepage writeback so we need to introduce turn on/off knobfor hugepage or new CONFIG_ZRAM_IDLEPAGE_WRITEBACK for those usecase. Idon't want to make it complicated *if possible*.Long term, I imagine we need to make VM aware of new swap hierarchy alittle bit different with as-is. For example, first high priority swapcan return -EIO or -ENOCOMP, swap try to fallback to next lower priorityswap device. With that, hugepage writeback will work tranparently.So we could regard it as regression because incompressible pages doesn'tgo to backing storage automatically. Instead, user should do it via "echohuge" > /sys/block/zram/writeback" manually.== &< ==Link: http://lkml.kernel.org/r/20181127055429.251614-6-minchan@kernel.orgSigned-off-by: Minchan Kim Reviewed-by: Joey Pabalinas Reviewed-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

e82592c4 - zram: introduce ZRAM_IDLE flag

Fri, 28 Dec 2018 08:36:44 +0000

zram: introduce ZRAM_IDLE flagTo support idle page writeback with upcoming patches, this patchintroduces a new ZRAM_IDLE flag.Userspace can mark zram slots as "idle" via "echo all > /sys/block/zramX/idle"which marks every allocated zram slot as ZRAM_IDLE.User could see it by /sys/kernel/debug/zram/zram0/block_state. 300 75.033841 ...i 301 63.806904 s..i 302 63.806919 ..hiOnce there is IO for the slot, the mark will be disappeared. 300 75.033841 ... 301 63.806904 s..i 302 63.806919 ..hiTherefore, 300th block is idle zpage. With this feature,user can how many zram has idle pages which are waste of memory.Link: http://lkml.kernel.org/r/20181127055429.251614-5-minchan@kernel.orgSigned-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Reviewed-by: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

5a47074f - zram: add config and doc file for writeback feature

Wed, 06 Sep 2017 23:20:10 +0000

zram: add config and doc file for writeback featureThis patch adds document and kconfig for using of writeback feature.Link: http://lkml.kernel.org/r/1498459987-24562-10-git-send-email-minchan@kernel.orgSigned-off-by: Minchan Kim Cc: Juneho Choi Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

c87d1655 - zram: remove obsolete sysfs attrs

Wed, 22 Feb 2017 23:46:45 +0000

zram: remove obsolete sysfs attrsWe had a deprecated_attr_warn() warning for 2 years and now the time hascome and we finally can do the cleanup.The plan was as follows:: per-stat sysfs attributes are considered to be deprecated.: The basic strategy is:: -- the existing RW nodes will be downgraded to WO nodes (in linux 4.11): -- deprecated RO sysfs nodes will eventually be removed (in linux 4.11):: The list of deprecated attributes can be found here:: Documentation/ABI/obsolete/sysfs-block-zram:: Basically, every attribute that has its own read accessible sysfs: node (e.g. num_reads) *AND* is accessible via one of the stat files: (zram/stat or zram/io_stat or zram/mm_stat) is considered: to be deprecated.The patch also removes `obsolete/sysfs-block-zram', clean ups`testing/sysfs-block-zram' and tweaks zram.txt files.Link: http://lkml.kernel.org/r/20170118035838.11090-1-sergey.senozhatsky@gmail.comSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

623e47fc - zram: introduce per-device debug_stat sysfs node

Sat, 21 May 2016 00:00:02 +0000

zram: introduce per-device debug_stat sysfs nodedebug_stat sysfs is read-only and represents various debugging data thatzram developers may need. This file is not meant to be used by anyoneelse: its content is not documented and will change any time w/o anynotice. Therefore, the output of debug_stat file contains a versionstring. To avoid any confusion, we will increase the version numberevery time we modify the output.At the moment this file exports only one value -- the number ofre-compressions, IOW, the number of times compression fast path hasfailed. This stat is temporary any will be useful in case if anyper-cpu compression streams regressions will be reported.Link: http://lkml.kernel.org/r/20160513230834.GB26763@bboxLink: http://lkml.kernel.org/r/20160511134553.12655-1-sergey.senozhatsky@gmail.comSigned-off-by: Sergey Senozhatsky Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

4f2109f6 - zram: export new 'mm_stat' sysfs attrs

Wed, 15 Apr 2015 23:16:06 +0000

zram: export new 'mm_stat' sysfs attrsPer-device `zram/mm_stat' file provides mm statistics of a particularzram device in a format similar to block layer statistics. The fileconsists of a single line and represents the following stats (separated bywhitespace): orig_data_size compr_data_size mem_used_total mem_limit mem_used_max zero_pages num_migratedSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

2f6a3bed - zram: export new 'io_stat' sysfs attrs

Wed, 15 Apr 2015 23:16:03 +0000

zram: export new 'io_stat' sysfs attrsPer-device `zram/io_stat' file provides accumulated I/O statistics ofparticular zram device in a format similar to block layer statistics. Thefile consists of a single line and represents the following stats(separated by whitespace): failed_reads failed_writes invalid_io notify_freeSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

10447b60 - zram: remove `num_migrated' device attr

Wed, 15 Apr 2015 23:15:52 +0000

zram: remove `num_migrated' device attrThis patch introduces rework to zram stats. We have per-stat sysfs nodes,and it makes things a bit hard to use in user space: it doesn't give animmediate stats 'snapshot', it requires user space to use more syscalls -open, read, close for every stat file, with appropriate error checks onevery step, etc.First, zram now accounts block layer statistics, available in/sys/block/zram/stat and /proc/diskstats files. So some new stats areavailable (see Documentation/block/stat.txt), besides, zram's activitiesnow can be monitored by sysstat's iostat or similar tools.Example:cat /sys/block/zram0/stat248 0 1984 0 251029 0 2008232 5120 0 5116 5116Second, group currently exported on per-stat basis nodes into twocategories (files):-- zram/io_stataccumulates device's IO stats, that are not accounted by block layer,and contains: failed_reads failed_writes invalid_io notify_freeExample:cat /sys/block/zram0/io_stat0 0 0 652572-- zram/mm_stataccumulates zram mm stats and contains: orig_data_size compr_data_size mem_used_total mem_limit mem_used_max zero_pages num_migratedExample:cat /sys/block/zram0/mm_stat434634752 270288572 279158784 0 579895296 15060 0per-stat sysfs nodes are now considered to be deprecated and we plan toremove them (and clean up some of the existing stat code) in two years (asof now, there is no warning printed to syslog about deprecated stats beingused). User space is advised to use the above mentioned 3 files.This patch (of 7):Remove sysfs `num_migrated' attribute. We are moving away from per-statdevice attrs towards 3 stat files that will accumulate io and mm stats ina format similar to block layer statistics in /sys/block//stat. Thatwill be easier to use in user space, and reduce the number of syscallsneeded to read zram device statistics.`num_migrated' will return back in zram/mm_stat file.Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

4e3ba878 - zram: support compaction

Wed, 15 Apr 2015 23:15:36 +0000

zram: support compactionNow that zsmalloc supports compaction, zram can use it. For the firststep, this patch exports compact knob via sysfs so user can do compactionvia "echo 1 > /sys/block/zram0/compact".Signed-off-by: Minchan Kim Cc: Juneho Choi Cc: Gunho Lee Cc: Luigi Semenzato Cc: Dan Streetman Cc: Seth Jennings Cc: Nitin Gupta Cc: Jerome Marchand Cc: Sergey Senozhatsky Cc: Joonsoo Kim Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

015254da - zram: use notify_free to account all free notifications

Thu, 09 Oct 2014 22:29:57 +0000

zram: use notify_free to account all free notifications`notify_free' device attribute accounts the number of slot freenotifications and internally represents the number of zram_free_page()calls. Slot free notifications are sent only when device is used as aswap device, hence `notify_free' is used only for swap devices. Sincef4659d8e620d08 (zram: support REQ_DISCARD) ZRAM handles yet another onefree notification (also via zram_free_page() call) -- REQ_DISCARDrequests, which are sent by a filesystem, whenever some data blocks arediscarded. However, there is no way to know the number of notificationsin the latter case.Use `notify_free' to account the number of pages freed byzram_bio_discard() and zram_slot_free_notify(). Depending on usagescenario `notify_free' represents: a) the number of pages freed because of slot free notifications, which is equal to the number of swap_slot_free_notify() calls, so there is no behaviour change b) the number of pages freed because of REQ_DISCARD notificationsSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Acked-by: Jerome Marchand Cc: Nitin Gupta Cc: Chao Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

461a8eee - zram: report maximum used memory

Thu, 09 Oct 2014 22:29:55 +0000

zram: report maximum used memoryNormally, zram user could get maximum memory usage zram consumed viapolling mem_used_total with sysfs in userspace.But it has a critical problem because user can miss peak memory usageduring update inverval of polling. For avoiding that, user should poll itwith shorter interval(ie, 0.0000000001s) with mlocking to avoid page faultdelay when memory pressure is heavy. It would be troublesome.This patch adds new knob "mem_used_max" so user could see the maximummemory usage easily via reading the knob and reset it via "echo 0 >/sys/block/zram0/mem_used_max".Signed-off-by: Minchan Kim Reviewed-by: Dan Streetman Cc: Sergey Senozhatsky Cc: Jerome Marchand Cc: Cc: Cc: Luigi Semenzato Cc: Nitin Gupta Cc: Seth Jennings Reviewed-by: David Horner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

9ada9da9 - zram: zram memory size limitation

Thu, 09 Oct 2014 22:29:53 +0000

zram: zram memory size limitationSince zram has no control feature to limit memory usage, it makes hard tomanage system memrory.This patch adds new knob "mem_limit" via sysfs to set up the a limit sothat zram could fail allocation once it reaches the limit.In addition, user could change the limit in runtime so that he couldmanage the memory more dynamically.Initial state is no limit so it doesn't break old behavior.[akpm@linux-foundation.org: fix typo, per Sergey]Signed-off-by: Minchan Kim Cc: Dan Streetman Cc: Sergey Senozhatsky Cc: Jerome Marchand Cc: Cc: Cc: Luigi Semenzato Cc: Nitin Gupta Cc: Seth Jennings Cc: David Horner Cc: Joonsoo Kim Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

e46b8a03 - zram: make compression algorithm selection possible

Mon, 07 Apr 2014 22:38:17 +0000

zram: make compression algorithm selection possibleAdd and document `comp_algorithm' device attribute. This attribute allowsto show supported compression and currently selected compressionalgorithms: cat /sys/block/zram0/comp_algorithm [lzo] lz4and change selected compression algorithm: echo lzo > /sys/block/zram0/comp_algorithmSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jerome Marchand Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram

beca3ec7 - zram: add multi stream functionality

Mon, 07 Apr 2014 22:38:14 +0000

zram: add multi stream functionalityExisting zram (zcomp) implementation has only one compression stream(buffer and algorithm private part), so in order to prevent datacorruption only one write (compress operation) can use this compressionstream, forcing all concurrent write operations to wait for stream lockto be released. This patch changes zcomp to keep a compression streamslist of user-defined size (via sysfs device attr). Each write operationstill exclusively holds compression stream, the difference is that wecan have N write operations (depending on size of streams list)executing in parallel. See TEST section later in commit message forperformance data.Introduce struct zcomp_strm_multi and a set of functions to managezcomp_strm stream access. zcomp_strm_multi has a list of idlezcomp_strm structs, spinlock to protect idle list and wait queue, makingit possible to perform parallel compressions.The following set of functions added:- zcomp_strm_multi_find()/zcomp_strm_multi_release() find and release a compression stream, implement required locking- zcomp_strm_multi_create()/zcomp_strm_multi_destroy() create and destroy zcomp_strm_multizcomp ->strm_find() and ->strm_release() callbacks are set duringinitialisation to zcomp_strm_multi_find()/zcomp_strm_multi_release()correspondingly.Each time zcomp issues a zcomp_strm_multi_find() call, the following setof operations performed:- spin lock strm_lock- if idle list is not empty, remove zcomp_strm from idle list, spin unlock and return zcomp stream pointer to caller- if idle list is empty, current adds itself to wait queue. it will be awaken by zcomp_strm_multi_release() caller.zcomp_strm_multi_release():- spin lock strm_lock- add zcomp stream to idle list- spin unlock, wake up sleeperMinchan Kim reported that spinlock-based locking scheme has demonstrateda severe perfomance regression for single compression stream case,comparing to mutex-based (see https://lkml.org/lkml/2014/2/18/16)base spinlock mutex==Initial write ==Initial write ==Initial writerecords: 5 records: 5 records: 5avg: 1642424.35 avg: 699610.40 avg: 1655583.71std: 39890.95(2.43%) std: 232014.19(33.16%) std: 52293.96max: 1690170.94 max: 1163473.45 max: 1697164.75min: 1568669.52 min: 573429.88 min: 1553410.23==Rewrite ==Rewrite ==Rewriterecords: 5 records: 5 records: 5avg: 1611775.39 avg: 501406.64 avg: 1684419.11std: 17144.58(1.06%) std: 15354.41(3.06%) std: 18367.42max: 1641800.95 max: 531356.78 max: 1706445.84min: 1593515.27 min: 488817.78 min: 1655335.73When only one compression stream available, mutex with spin on ownertends to perform much better than frequent wait_event()/wake_up(). Thisis why single stream implemented as a special case with mutex locking.Introduce and document zram device attribute max_comp_streams. Thisattr shows and stores current zcomp's max number of zcomp streams(max_strm). Extend zcomp's zcomp_create() with `max_strm' parameter.`max_strm' limits the number of zcomp_strm structs in compressionbackend's idle list (max_comp_streams).max_comp_streams used during initialisation as follows:-- passing to zcomp_create() max_strm equals to 1 will initialise zcompusing single compression stream zcomp_strm_single (mutex-based locking).-- passing to zcomp_create() max_strm greater than 1 will initialise zcompusing multi compression stream zcomp_strm_multi (spinlock-based locking).default max_comp_streams value is 1, meaning that zram with single streamwill be initialised.Later patch will introduce configuration knob to change max_comp_streamson already initialised and used zcomp.TESTiozone -t 3 -R -r 16K -s 60M -I +Z test base 1 strm (mutex) 3 strm (spinlock)----------------------------------------------------------------------- Initial write 589286.78 583518.39 718011.05 Rewrite 604837.97 596776.38 1515125.72 Random write 584120.11 595714.58 1388850.25 Pwrite 535731.17 541117.38 739295.27 Fwrite 1418083.88 1478612.72 1484927.06Usage example:set max_comp_streams to 4 echo 4 > /sys/block/zram0/max_comp_streamsshow current max_comp_streams (default value is 1). cat /sys/block/zram0/max_comp_streamsSigned-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jerome Marchand Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds List of files: /linux-6.15/Documentation/ABI/testing/sysfs-block-zram