1What: /sys/fs/f2fs/<disk>/gc_max_sleep_time 2Date: July 2013 3Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 4Description: Controls the maximum sleep time for gc_thread. Time 5 is in milliseconds. 6 7What: /sys/fs/f2fs/<disk>/gc_min_sleep_time 8Date: July 2013 9Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 10Description: Controls the minimum sleep time for gc_thread. Time 11 is in milliseconds. 12 13What: /sys/fs/f2fs/<disk>/gc_no_gc_sleep_time 14Date: July 2013 15Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 16Description: Controls the default sleep time for gc_thread. Time 17 is in milliseconds. 18 19What: /sys/fs/f2fs/<disk>/gc_idle 20Date: July 2013 21Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 22Description: Controls the victim selection policy for garbage collection. 23 Setting gc_idle = 0(default) will disable this option. Setting: 24 25 =========== =============================================== 26 gc_idle = 1 will select the Cost Benefit approach & setting 27 gc_idle = 2 will select the greedy approach & setting 28 gc_idle = 3 will select the age-threshold based approach. 29 =========== =============================================== 30 31What: /sys/fs/f2fs/<disk>/reclaim_segments 32Date: October 2013 33Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 34Description: This parameter controls the number of prefree segments to be 35 reclaimed. If the number of prefree segments is larger than 36 the number of segments in the proportion to the percentage 37 over total volume size, f2fs tries to conduct checkpoint to 38 reclaim the prefree segments to free segments. 39 By default, 5% over total # of segments. 40 41What: /sys/fs/f2fs/<disk>/main_blkaddr 42Date: November 2019 43Contact: "Ramon Pantin" <pantin@google.com> 44Description: Shows first block address of MAIN area. 45 46What: /sys/fs/f2fs/<disk>/ipu_policy 47Date: November 2013 48Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 49Description: Controls the in-place-update policy. 50 updates in f2fs. User can set: 51 52 ==== ================= 53 0x01 F2FS_IPU_FORCE 54 0x02 F2FS_IPU_SSR 55 0x04 F2FS_IPU_UTIL 56 0x08 F2FS_IPU_SSR_UTIL 57 0x10 F2FS_IPU_FSYNC 58 0x20 F2FS_IPU_ASYNC 59 0x40 F2FS_IPU_NOCACHE 60 0x80 F2FS_IPU_HONOR_OPU_WRITE 61 ==== ================= 62 63 Refer segment.h for details. 64 65What: /sys/fs/f2fs/<disk>/min_ipu_util 66Date: November 2013 67Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 68Description: Controls the FS utilization condition for the in-place-update 69 policies. It is used by F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies. 70 71What: /sys/fs/f2fs/<disk>/min_fsync_blocks 72Date: September 2014 73Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 74Description: Controls the dirty page count condition for the in-place-update 75 policies. 76 77What: /sys/fs/f2fs/<disk>/min_seq_blocks 78Date: August 2018 79Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 80Description: Controls the dirty page count condition for batched sequential 81 writes in writepages. 82 83What: /sys/fs/f2fs/<disk>/min_hot_blocks 84Date: March 2017 85Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 86Description: Controls the dirty page count condition for redefining hot data. 87 88What: /sys/fs/f2fs/<disk>/min_ssr_sections 89Date: October 2017 90Contact: "Chao Yu" <yuchao0@huawei.com> 91Description: Controls the free section threshold to trigger SSR allocation. 92 If this is large, SSR mode will be enabled early. 93 94What: /sys/fs/f2fs/<disk>/max_small_discards 95Date: November 2013 96Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 97Description: Controls the issue rate of discard commands that consist of small 98 blocks less than 2MB. The candidates to be discarded are cached until 99 checkpoint is triggered, and issued during the checkpoint. 100 By default, it is disabled with 0. 101 102What: /sys/fs/f2fs/<disk>/max_ordered_discard 103Date: October 2022 104Contact: "Yangtao Li" <frank.li@vivo.com> 105Description: Controls the maximum ordered discard, the unit size is one block(4KB). 106 Set it to 16 by default. 107 108What: /sys/fs/f2fs/<disk>/max_discard_request 109Date: December 2021 110Contact: "Konstantin Vyshetsky" <vkon@google.com> 111Description: Controls the number of discards a thread will issue at a time. 112 Higher number will allow the discard thread to finish its work 113 faster, at the cost of higher latency for incomming I/O. 114 115What: /sys/fs/f2fs/<disk>/min_discard_issue_time 116Date: December 2021 117Contact: "Konstantin Vyshetsky" <vkon@google.com> 118Description: Controls the interval the discard thread will wait between 119 issuing discard requests when there are discards to be issued and 120 no I/O aware interruptions occur. 121 122What: /sys/fs/f2fs/<disk>/mid_discard_issue_time 123Date: December 2021 124Contact: "Konstantin Vyshetsky" <vkon@google.com> 125Description: Controls the interval the discard thread will wait between 126 issuing discard requests when there are discards to be issued and 127 an I/O aware interruption occurs. 128 129What: /sys/fs/f2fs/<disk>/max_discard_issue_time 130Date: December 2021 131Contact: "Konstantin Vyshetsky" <vkon@google.com> 132Description: Controls the interval the discard thread will wait when there are 133 no discard operations to be issued. 134 135What: /sys/fs/f2fs/<disk>/discard_granularity 136Date: July 2017 137Contact: "Chao Yu" <yuchao0@huawei.com> 138Description: Controls discard granularity of inner discard thread. Inner thread 139 will not issue discards with size that is smaller than granularity. 140 The unit size is one block(4KB), now only support configuring 141 in range of [1, 512]. Default value is 16. 142 For small devices, default value is 1. 143 144What: /sys/fs/f2fs/<disk>/umount_discard_timeout 145Date: January 2019 146Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 147Description: Set timeout to issue discard commands during umount. 148 Default: 5 secs 149 150What: /sys/fs/f2fs/<disk>/pending_discard 151Date: November 2021 152Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 153Description: Shows the number of pending discard commands in the queue. 154 155What: /sys/fs/f2fs/<disk>/max_victim_search 156Date: January 2014 157Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 158Description: Controls the number of trials to find a victim segment 159 when conducting SSR and cleaning operations. The default value 160 is 4096 which covers 8GB block address range. 161 162What: /sys/fs/f2fs/<disk>/migration_granularity 163Date: October 2018 164Contact: "Chao Yu" <yuchao0@huawei.com> 165Description: Controls migration granularity of garbage collection on large 166 section, it can let GC move partial segment{s} of one section 167 in one GC cycle, so that dispersing heavy overhead GC to 168 multiple lightweight one. 169 170What: /sys/fs/f2fs/<disk>/dir_level 171Date: March 2014 172Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 173Description: Controls the directory level for large directory. If a 174 directory has a number of files, it can reduce the file lookup 175 latency by increasing this dir_level value. Otherwise, it 176 needs to decrease this value to reduce the space overhead. 177 The default value is 0. 178 179What: /sys/fs/f2fs/<disk>/ram_thresh 180Date: March 2014 181Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 182Description: Controls the memory footprint used by free nids and cached 183 nat entries. By default, 1 is set, which indicates 184 10 MB / 1 GB RAM. 185 186What: /sys/fs/f2fs/<disk>/batched_trim_sections 187Date: February 2015 188Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 189Description: Controls the trimming rate in batch mode. 190 <deprecated> 191 192What: /sys/fs/f2fs/<disk>/cp_interval 193Date: October 2015 194Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 195Description: Controls the checkpoint timing, set to 60 seconds by default. 196 197What: /sys/fs/f2fs/<disk>/idle_interval 198Date: January 2016 199Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 200Description: Controls the idle timing of system, if there is no FS operation 201 during given interval. 202 Set to 5 seconds by default. 203 204What: /sys/fs/f2fs/<disk>/discard_idle_interval 205Date: September 2018 206Contact: "Chao Yu" <yuchao0@huawei.com> 207Contact: "Sahitya Tummala" <stummala@codeaurora.org> 208Description: Controls the idle timing of discard thread given 209 this time interval. 210 Default is 5 secs. 211 212What: /sys/fs/f2fs/<disk>/gc_idle_interval 213Date: September 2018 214Contact: "Chao Yu" <yuchao0@huawei.com> 215Contact: "Sahitya Tummala" <stummala@codeaurora.org> 216Description: Controls the idle timing for gc path. Set to 5 seconds by default. 217 218What: /sys/fs/f2fs/<disk>/iostat_enable 219Date: August 2017 220Contact: "Chao Yu" <yuchao0@huawei.com> 221Description: Controls to enable/disable IO stat. 222 223What: /sys/fs/f2fs/<disk>/ra_nid_pages 224Date: October 2015 225Contact: "Chao Yu" <chao2.yu@samsung.com> 226Description: Controls the count of nid pages to be readaheaded. 227 When building free nids, F2FS reads NAT blocks ahead for 228 speed up. Default is 0. 229 230What: /sys/fs/f2fs/<disk>/dirty_nats_ratio 231Date: January 2016 232Contact: "Chao Yu" <chao2.yu@samsung.com> 233Description: Controls dirty nat entries ratio threshold, if current 234 ratio exceeds configured threshold, checkpoint will 235 be triggered for flushing dirty nat entries. 236 237What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes 238Date: January 2016 239Contact: "Shuoran Liu" <liushuoran@huawei.com> 240Description: Shows total written kbytes issued to disk. 241 242What: /sys/fs/f2fs/<disk>/features 243Date: July 2017 244Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 245Description: <deprecated: should use /sys/fs/f2fs/<disk>/feature_list/> 246 Shows all enabled features in current device. 247 Supported features: 248 encryption, blkzoned, extra_attr, projquota, inode_checksum, 249 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 250 verity, sb_checksum, casefold, readonly, compression, pin_file. 251 252What: /sys/fs/f2fs/<disk>/feature_list/ 253Date: June 2021 254Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 255Description: Expand /sys/fs/f2fs/<disk>/features to meet sysfs rule. 256 Supported on-disk features: 257 encryption, block_zoned (aka blkzoned), extra_attr, 258 project_quota (aka projquota), inode_checksum, 259 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 260 verity, sb_checksum, casefold, readonly, compression. 261 Note that, pin_file is moved into /sys/fs/f2fs/features/. 262 263What: /sys/fs/f2fs/features/ 264Date: July 2017 265Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 266Description: Shows all enabled kernel features. 267 Supported features: 268 encryption, block_zoned, extra_attr, project_quota, 269 inode_checksum, flexible_inline_xattr, quota_ino, 270 inode_crtime, lost_found, verity, sb_checksum, 271 casefold, readonly, compression, test_dummy_encryption_v2, 272 atomic_write, pin_file, encrypted_casefold. 273 274What: /sys/fs/f2fs/<disk>/inject_rate 275Date: May 2016 276Contact: "Sheng Yong" <shengyong1@huawei.com> 277Description: Controls the injection rate of arbitrary faults. 278 279What: /sys/fs/f2fs/<disk>/inject_type 280Date: May 2016 281Contact: "Sheng Yong" <shengyong1@huawei.com> 282Description: Controls the injection type of arbitrary faults. 283 284What: /sys/fs/f2fs/<disk>/dirty_segments 285Date: October 2017 286Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 287Description: Shows the number of dirty segments. 288 289What: /sys/fs/f2fs/<disk>/reserved_blocks 290Date: June 2017 291Contact: "Chao Yu" <yuchao0@huawei.com> 292Description: Controls target reserved blocks in system, the threshold 293 is soft, it could exceed current available user space. 294 295What: /sys/fs/f2fs/<disk>/current_reserved_blocks 296Date: October 2017 297Contact: "Yunlong Song" <yunlong.song@huawei.com> 298Contact: "Chao Yu" <yuchao0@huawei.com> 299Description: Shows current reserved blocks in system, it may be temporarily 300 smaller than target_reserved_blocks, but will gradually 301 increase to target_reserved_blocks when more free blocks are 302 freed by user later. 303 304What: /sys/fs/f2fs/<disk>/gc_urgent 305Date: August 2017 306Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 307Description: Do background GC aggressively when set. Set to 0 by default. 308 gc urgent high(1): does GC forcibly in a period of given 309 gc_urgent_sleep_time and ignores I/O idling check. uses greedy 310 GC approach and turns SSR mode on. 311 gc urgent low(2): lowers the bar of checking I/O idling in 312 order to process outstanding discard commands and GC a 313 little bit aggressively. uses cost benefit GC approach. 314 gc urgent mid(3): does GC forcibly in a period of given 315 gc_urgent_sleep_time and executes a mid level of I/O idling check. 316 uses cost benefit GC approach. 317 318What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time 319Date: August 2017 320Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 321Description: Controls sleep time of GC urgent mode. Set to 500ms by default. 322 323What: /sys/fs/f2fs/<disk>/readdir_ra 324Date: November 2017 325Contact: "Sheng Yong" <shengyong1@huawei.com> 326Description: Controls readahead inode block in readdir. Enabled by default. 327 328What: /sys/fs/f2fs/<disk>/gc_pin_file_thresh 329Date: January 2018 330Contact: Jaegeuk Kim <jaegeuk@kernel.org> 331Description: This indicates how many GC can be failed for the pinned 332 file. If it exceeds this, F2FS doesn't guarantee its pinning 333 state. 2048 trials is set by default. 334 335What: /sys/fs/f2fs/<disk>/extension_list 336Date: Feburary 2018 337Contact: "Chao Yu" <yuchao0@huawei.com> 338Description: Used to control configure extension list: 339 - Query: cat /sys/fs/f2fs/<disk>/extension_list 340 - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list 341 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list 342 - [h] means add/del hot file extension 343 - [c] means add/del cold file extension 344 345What: /sys/fs/f2fs/<disk>/unusable 346Date April 2019 347Contact: "Daniel Rosenberg" <drosen@google.com> 348Description: If checkpoint=disable, it displays the number of blocks that 349 are unusable. 350 If checkpoint=enable it displays the number of blocks that 351 would be unusable if checkpoint=disable were to be set. 352 353What: /sys/fs/f2fs/<disk>/encoding 354Date July 2019 355Contact: "Daniel Rosenberg" <drosen@google.com> 356Description: Displays name and version of the encoding set for the filesystem. 357 If no encoding is set, displays (none) 358 359What: /sys/fs/f2fs/<disk>/free_segments 360Date: September 2019 361Contact: "Hridya Valsaraju" <hridya@google.com> 362Description: Number of free segments in disk. 363 364What: /sys/fs/f2fs/<disk>/cp_foreground_calls 365Date: September 2019 366Contact: "Hridya Valsaraju" <hridya@google.com> 367Description: Number of checkpoint operations performed on demand. Available when 368 CONFIG_F2FS_STAT_FS=y. 369 370What: /sys/fs/f2fs/<disk>/cp_background_calls 371Date: September 2019 372Contact: "Hridya Valsaraju" <hridya@google.com> 373Description: Number of checkpoint operations performed in the background to 374 free segments. Available when CONFIG_F2FS_STAT_FS=y. 375 376What: /sys/fs/f2fs/<disk>/gc_foreground_calls 377Date: September 2019 378Contact: "Hridya Valsaraju" <hridya@google.com> 379Description: Number of garbage collection operations performed on demand. 380 Available when CONFIG_F2FS_STAT_FS=y. 381 382What: /sys/fs/f2fs/<disk>/gc_background_calls 383Date: September 2019 384Contact: "Hridya Valsaraju" <hridya@google.com> 385Description: Number of garbage collection operations triggered in background. 386 Available when CONFIG_F2FS_STAT_FS=y. 387 388What: /sys/fs/f2fs/<disk>/moved_blocks_foreground 389Date: September 2019 390Contact: "Hridya Valsaraju" <hridya@google.com> 391Description: Number of blocks moved by garbage collection in foreground. 392 Available when CONFIG_F2FS_STAT_FS=y. 393 394What: /sys/fs/f2fs/<disk>/moved_blocks_background 395Date: September 2019 396Contact: "Hridya Valsaraju" <hridya@google.com> 397Description: Number of blocks moved by garbage collection in background. 398 Available when CONFIG_F2FS_STAT_FS=y. 399 400What: /sys/fs/f2fs/<disk>/avg_vblocks 401Date: September 2019 402Contact: "Hridya Valsaraju" <hridya@google.com> 403Description: Average number of valid blocks. 404 Available when CONFIG_F2FS_STAT_FS=y. 405 406What: /sys/fs/f2fs/<disk>/mounted_time_sec 407Date: February 2020 408Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 409Description: Show the mounted time in secs of this partition. 410 411What: /sys/fs/f2fs/<disk>/data_io_flag 412Date: April 2020 413Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 414Description: Give a way to attach REQ_META|FUA to data writes 415 given temperature-based bits. Now the bits indicate: 416 417 +-------------------+-------------------+ 418 | REQ_META | REQ_FUA | 419 +------+------+-----+------+------+-----+ 420 | 5 | 4 | 3 | 2 | 1 | 0 | 421 +------+------+-----+------+------+-----+ 422 | Cold | Warm | Hot | Cold | Warm | Hot | 423 +------+------+-----+------+------+-----+ 424 425What: /sys/fs/f2fs/<disk>/node_io_flag 426Date: June 2020 427Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 428Description: Give a way to attach REQ_META|FUA to node writes 429 given temperature-based bits. Now the bits indicate: 430 431 +-------------------+-------------------+ 432 | REQ_META | REQ_FUA | 433 +------+------+-----+------+------+-----+ 434 | 5 | 4 | 3 | 2 | 1 | 0 | 435 +------+------+-----+------+------+-----+ 436 | Cold | Warm | Hot | Cold | Warm | Hot | 437 +------+------+-----+------+------+-----+ 438 439What: /sys/fs/f2fs/<disk>/iostat_period_ms 440Date: April 2020 441Contact: "Daeho Jeong" <daehojeong@google.com> 442Description: Give a way to change iostat_period time. 3secs by default. 443 The new iostat trace gives stats gap given the period. 444What: /sys/fs/f2fs/<disk>/max_io_bytes 445Date: December 2020 446Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 447Description: This gives a control to limit the bio size in f2fs. 448 Default is zero, which will follow underlying block layer limit, 449 whereas, if it has a certain bytes value, f2fs won't submit a 450 bio larger than that size. 451 452What: /sys/fs/f2fs/<disk>/stat/sb_status 453Date: December 2020 454Contact: "Chao Yu" <yuchao0@huawei.com> 455Description: Show status of f2fs superblock in real time. 456 457 ====== ===================== ================================= 458 value sb status macro description 459 0x1 SBI_IS_DIRTY dirty flag for checkpoint 460 0x2 SBI_IS_CLOSE specify unmounting 461 0x4 SBI_NEED_FSCK need fsck.f2fs to fix 462 0x8 SBI_POR_DOING recovery is doing or not 463 0x10 SBI_NEED_SB_WRITE need to recover superblock 464 0x20 SBI_NEED_CP need to checkpoint 465 0x40 SBI_IS_SHUTDOWN shutdown by ioctl 466 0x80 SBI_IS_RECOVERED recovered orphan/data 467 0x100 SBI_CP_DISABLED CP was disabled last mount 468 0x200 SBI_CP_DISABLED_QUICK CP was disabled quickly 469 0x400 SBI_QUOTA_NEED_FLUSH need to flush quota info in CP 470 0x800 SBI_QUOTA_SKIP_FLUSH skip flushing quota in current CP 471 0x1000 SBI_QUOTA_NEED_REPAIR quota file may be corrupted 472 0x2000 SBI_IS_RESIZEFS resizefs is in process 473 0x4000 SBI_IS_FREEZING freefs is in process 474 ====== ===================== ================================= 475 476What: /sys/fs/f2fs/<disk>/stat/cp_status 477Date: September 2022 478Contact: "Chao Yu" <chao.yu@oppo.com> 479Description: Show status of f2fs checkpoint in real time. 480 481 =============================== ============================== 482 cp flag value 483 CP_UMOUNT_FLAG 0x00000001 484 CP_ORPHAN_PRESENT_FLAG 0x00000002 485 CP_COMPACT_SUM_FLAG 0x00000004 486 CP_ERROR_FLAG 0x00000008 487 CP_FSCK_FLAG 0x00000010 488 CP_FASTBOOT_FLAG 0x00000020 489 CP_CRC_RECOVERY_FLAG 0x00000040 490 CP_NAT_BITS_FLAG 0x00000080 491 CP_TRIMMED_FLAG 0x00000100 492 CP_NOCRC_RECOVERY_FLAG 0x00000200 493 CP_LARGE_NAT_BITMAP_FLAG 0x00000400 494 CP_QUOTA_NEED_FSCK_FLAG 0x00000800 495 CP_DISABLED_FLAG 0x00001000 496 CP_DISABLED_QUICK_FLAG 0x00002000 497 CP_RESIZEFS_FLAG 0x00004000 498 =============================== ============================== 499 500What: /sys/fs/f2fs/<disk>/ckpt_thread_ioprio 501Date: January 2021 502Contact: "Daeho Jeong" <daehojeong@google.com> 503Description: Give a way to change checkpoint merge daemon's io priority. 504 Its default value is "be,3", which means "BE" I/O class and 505 I/O priority "3". We can select the class between "rt" and "be", 506 and set the I/O priority within valid range of it. "," delimiter 507 is necessary in between I/O class and priority number. 508 509What: /sys/fs/f2fs/<disk>/ovp_segments 510Date: March 2021 511Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 512Description: Shows the number of overprovision segments. 513 514What: /sys/fs/f2fs/<disk>/compr_written_block 515Date: March 2021 516Contact: "Daeho Jeong" <daehojeong@google.com> 517Description: Show the block count written after compression since mount. Note 518 that when the compressed blocks are deleted, this count doesn't 519 decrease. If you write "0" here, you can initialize 520 compr_written_block and compr_saved_block to "0". 521 522What: /sys/fs/f2fs/<disk>/compr_saved_block 523Date: March 2021 524Contact: "Daeho Jeong" <daehojeong@google.com> 525Description: Show the saved block count with compression since mount. Note 526 that when the compressed blocks are deleted, this count doesn't 527 decrease. If you write "0" here, you can initialize 528 compr_written_block and compr_saved_block to "0". 529 530What: /sys/fs/f2fs/<disk>/compr_new_inode 531Date: March 2021 532Contact: "Daeho Jeong" <daehojeong@google.com> 533Description: Show the count of inode newly enabled for compression since mount. 534 Note that when the compression is disabled for the files, this count 535 doesn't decrease. If you write "0" here, you can initialize 536 compr_new_inode to "0". 537 538What: /sys/fs/f2fs/<disk>/atgc_candidate_ratio 539Date: May 2021 540Contact: "Chao Yu" <yuchao0@huawei.com> 541Description: When ATGC is on, it controls candidate ratio in order to limit total 542 number of potential victim in all candidates, the value should be in 543 range of [0, 100], by default it was initialized as 20(%). 544 545What: /sys/fs/f2fs/<disk>/atgc_candidate_count 546Date: May 2021 547Contact: "Chao Yu" <yuchao0@huawei.com> 548Description: When ATGC is on, it controls candidate count in order to limit total 549 number of potential victim in all candidates, by default it was 550 initialized as 10 (sections). 551 552What: /sys/fs/f2fs/<disk>/atgc_age_weight 553Date: May 2021 554Contact: "Chao Yu" <yuchao0@huawei.com> 555Description: When ATGC is on, it controls age weight to balance weight proportion 556 in between aging and valid blocks, the value should be in range of 557 [0, 100], by default it was initialized as 60(%). 558 559What: /sys/fs/f2fs/<disk>/atgc_age_threshold 560Date: May 2021 561Contact: "Chao Yu" <yuchao0@huawei.com> 562Description: When ATGC is on, it controls age threshold to bypass GCing young 563 candidates whose age is not beyond the threshold, by default it was 564 initialized as 604800 seconds (equals to 7 days). 565 566What: /sys/fs/f2fs/<disk>/gc_reclaimed_segments 567Date: July 2021 568Contact: "Daeho Jeong" <daehojeong@google.com> 569Description: Show how many segments have been reclaimed by GC during a specific 570 GC mode (0: GC normal, 1: GC idle CB, 2: GC idle greedy, 571 3: GC idle AT, 4: GC urgent high, 5: GC urgent low 6: GC urgent mid) 572 You can re-initialize this value to "0". 573 574What: /sys/fs/f2fs/<disk>/gc_segment_mode 575Date: July 2021 576Contact: "Daeho Jeong" <daehojeong@google.com> 577Description: You can control for which gc mode the "gc_reclaimed_segments" node shows. 578 Refer to the description of the modes in "gc_reclaimed_segments". 579 580What: /sys/fs/f2fs/<disk>/seq_file_ra_mul 581Date: July 2021 582Contact: "Daeho Jeong" <daehojeong@google.com> 583Description: You can control the multiplier value of bdi device readahead window size 584 between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option. 585 586What: /sys/fs/f2fs/<disk>/max_fragment_chunk 587Date: August 2021 588Contact: "Daeho Jeong" <daehojeong@google.com> 589Description: With "mode=fragment:block" mount options, we can scatter block allocation. 590 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 591 in the length of 1..<max_fragment_hole> by turns. This value can be set 592 between 1..512 and the default value is 4. 593 594What: /sys/fs/f2fs/<disk>/max_fragment_hole 595Date: August 2021 596Contact: "Daeho Jeong" <daehojeong@google.com> 597Description: With "mode=fragment:block" mount options, we can scatter block allocation. 598 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 599 in the length of 1..<max_fragment_hole> by turns. This value can be set 600 between 1..512 and the default value is 4. 601 602What: /sys/fs/f2fs/<disk>/gc_remaining_trials 603Date: October 2022 604Contact: "Yangtao Li" <frank.li@vivo.com> 605Description: You can set the trial count limit for GC urgent and idle mode with this value. 606 If GC thread gets to the limit, the mode will turn back to GC normal mode. 607 By default, the value is zero, which means there is no limit like before. 608 609What: /sys/fs/f2fs/<disk>/max_roll_forward_node_blocks 610Date: January 2022 611Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 612Description: Controls max # of node block writes to be used for roll forward 613 recovery. This can limit the roll forward recovery time. 614 615What: /sys/fs/f2fs/<disk>/unusable_blocks_per_sec 616Date: June 2022 617Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 618Description: Shows the number of unusable blocks in a section which was defined by 619 the zone capacity reported by underlying zoned device. 620 621What: /sys/fs/f2fs/<disk>/current_atomic_write 622Date: July 2022 623Contact: "Daeho Jeong" <daehojeong@google.com> 624Description: Show the total current atomic write block count, which is not committed yet. 625 This is a read-only entry. 626 627What: /sys/fs/f2fs/<disk>/peak_atomic_write 628Date: July 2022 629Contact: "Daeho Jeong" <daehojeong@google.com> 630Description: Show the peak value of total current atomic write block count after boot. 631 If you write "0" here, you can initialize to "0". 632 633What: /sys/fs/f2fs/<disk>/committed_atomic_block 634Date: July 2022 635Contact: "Daeho Jeong" <daehojeong@google.com> 636Description: Show the accumulated total committed atomic write block count after boot. 637 If you write "0" here, you can initialize to "0". 638 639What: /sys/fs/f2fs/<disk>/revoked_atomic_block 640Date: July 2022 641Contact: "Daeho Jeong" <daehojeong@google.com> 642Description: Show the accumulated total revoked atomic write block count after boot. 643 If you write "0" here, you can initialize to "0". 644 645What: /sys/fs/f2fs/<disk>/gc_mode 646Date: October 2022 647Contact: "Yangtao Li" <frank.li@vivo.com> 648Description: Show the current gc_mode as a string. 649 This is a read-only entry. 650 651What: /sys/fs/f2fs/<disk>/discard_urgent_util 652Date: November 2022 653Contact: "Yangtao Li" <frank.li@vivo.com> 654Description: When space utilization exceeds this, do background DISCARD aggressively. 655 Does DISCARD forcibly in a period of given min_discard_issue_time when the number 656 of discards is not 0 and set discard granularity to 1. 657 Default: 80 658 659What: /sys/fs/f2fs/<disk>/hot_data_age_threshold 660Date: November 2022 661Contact: "Ping Xiong" <xiongping1@xiaomi.com> 662Description: When DATA SEPARATION is on, it controls the age threshold to indicate 663 the data blocks as hot. By default it was initialized as 262144 blocks 664 (equals to 1GB). 665 666What: /sys/fs/f2fs/<disk>/warm_data_age_threshold 667Date: November 2022 668Contact: "Ping Xiong" <xiongping1@xiaomi.com> 669Description: When DATA SEPARATION is on, it controls the age threshold to indicate 670 the data blocks as warm. By default it was initialized as 2621440 blocks 671 (equals to 10GB). 672