sysfs-fs-f2fs (23472B)
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_discard_request 103Date: December 2021 104Contact: "Konstantin Vyshetsky" <vkon@google.com> 105Description: Controls the number of discards a thread will issue at a time. 106 Higher number will allow the discard thread to finish its work 107 faster, at the cost of higher latency for incomming I/O. 108 109What: /sys/fs/f2fs/<disk>/min_discard_issue_time 110Date: December 2021 111Contact: "Konstantin Vyshetsky" <vkon@google.com> 112Description: Controls the interval the discard thread will wait between 113 issuing discard requests when there are discards to be issued and 114 no I/O aware interruptions occur. 115 116What: /sys/fs/f2fs/<disk>/mid_discard_issue_time 117Date: December 2021 118Contact: "Konstantin Vyshetsky" <vkon@google.com> 119Description: Controls the interval the discard thread will wait between 120 issuing discard requests when there are discards to be issued and 121 an I/O aware interruption occurs. 122 123What: /sys/fs/f2fs/<disk>/max_discard_issue_time 124Date: December 2021 125Contact: "Konstantin Vyshetsky" <vkon@google.com> 126Description: Controls the interval the discard thread will wait when there are 127 no discard operations to be issued. 128 129What: /sys/fs/f2fs/<disk>/discard_granularity 130Date: July 2017 131Contact: "Chao Yu" <yuchao0@huawei.com> 132Description: Controls discard granularity of inner discard thread. Inner thread 133 will not issue discards with size that is smaller than granularity. 134 The unit size is one block(4KB), now only support configuring 135 in range of [1, 512]. Default value is 4(=16KB). 136 137What: /sys/fs/f2fs/<disk>/umount_discard_timeout 138Date: January 2019 139Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 140Description: Set timeout to issue discard commands during umount. 141 Default: 5 secs 142 143What: /sys/fs/f2fs/<disk>/pending_discard 144Date: November 2021 145Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 146Description: Shows the number of pending discard commands in the queue. 147 148What: /sys/fs/f2fs/<disk>/max_victim_search 149Date: January 2014 150Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 151Description: Controls the number of trials to find a victim segment 152 when conducting SSR and cleaning operations. The default value 153 is 4096 which covers 8GB block address range. 154 155What: /sys/fs/f2fs/<disk>/migration_granularity 156Date: October 2018 157Contact: "Chao Yu" <yuchao0@huawei.com> 158Description: Controls migration granularity of garbage collection on large 159 section, it can let GC move partial segment{s} of one section 160 in one GC cycle, so that dispersing heavy overhead GC to 161 multiple lightweight one. 162 163What: /sys/fs/f2fs/<disk>/dir_level 164Date: March 2014 165Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 166Description: Controls the directory level for large directory. If a 167 directory has a number of files, it can reduce the file lookup 168 latency by increasing this dir_level value. Otherwise, it 169 needs to decrease this value to reduce the space overhead. 170 The default value is 0. 171 172What: /sys/fs/f2fs/<disk>/ram_thresh 173Date: March 2014 174Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 175Description: Controls the memory footprint used by free nids and cached 176 nat entries. By default, 1 is set, which indicates 177 10 MB / 1 GB RAM. 178 179What: /sys/fs/f2fs/<disk>/batched_trim_sections 180Date: February 2015 181Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 182Description: Controls the trimming rate in batch mode. 183 <deprecated> 184 185What: /sys/fs/f2fs/<disk>/cp_interval 186Date: October 2015 187Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 188Description: Controls the checkpoint timing, set to 60 seconds by default. 189 190What: /sys/fs/f2fs/<disk>/idle_interval 191Date: January 2016 192Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 193Description: Controls the idle timing of system, if there is no FS operation 194 during given interval. 195 Set to 5 seconds by default. 196 197What: /sys/fs/f2fs/<disk>/discard_idle_interval 198Date: September 2018 199Contact: "Chao Yu" <yuchao0@huawei.com> 200Contact: "Sahitya Tummala" <stummala@codeaurora.org> 201Description: Controls the idle timing of discard thread given 202 this time interval. 203 Default is 5 secs. 204 205What: /sys/fs/f2fs/<disk>/gc_idle_interval 206Date: September 2018 207Contact: "Chao Yu" <yuchao0@huawei.com> 208Contact: "Sahitya Tummala" <stummala@codeaurora.org> 209Description: Controls the idle timing for gc path. Set to 5 seconds by default. 210 211What: /sys/fs/f2fs/<disk>/iostat_enable 212Date: August 2017 213Contact: "Chao Yu" <yuchao0@huawei.com> 214Description: Controls to enable/disable IO stat. 215 216What: /sys/fs/f2fs/<disk>/ra_nid_pages 217Date: October 2015 218Contact: "Chao Yu" <chao2.yu@samsung.com> 219Description: Controls the count of nid pages to be readaheaded. 220 When building free nids, F2FS reads NAT blocks ahead for 221 speed up. Default is 0. 222 223What: /sys/fs/f2fs/<disk>/dirty_nats_ratio 224Date: January 2016 225Contact: "Chao Yu" <chao2.yu@samsung.com> 226Description: Controls dirty nat entries ratio threshold, if current 227 ratio exceeds configured threshold, checkpoint will 228 be triggered for flushing dirty nat entries. 229 230What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes 231Date: January 2016 232Contact: "Shuoran Liu" <liushuoran@huawei.com> 233Description: Shows total written kbytes issued to disk. 234 235What: /sys/fs/f2fs/<disk>/features 236Date: July 2017 237Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 238Description: <deprecated: should use /sys/fs/f2fs/<disk>/feature_list/ 239 Shows all enabled features in current device. 240 Supported features: 241 encryption, blkzoned, extra_attr, projquota, inode_checksum, 242 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 243 verity, sb_checksum, casefold, readonly, compression, pin_file. 244 245What: /sys/fs/f2fs/<disk>/feature_list/ 246Date: June 2021 247Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 248Description: Expand /sys/fs/f2fs/<disk>/features to meet sysfs rule. 249 Supported on-disk features: 250 encryption, block_zoned (aka blkzoned), extra_attr, 251 project_quota (aka projquota), inode_checksum, 252 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 253 verity, sb_checksum, casefold, readonly, compression. 254 Note that, pin_file is moved into /sys/fs/f2fs/features/. 255 256What: /sys/fs/f2fs/features/ 257Date: July 2017 258Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 259Description: Shows all enabled kernel features. 260 Supported features: 261 encryption, block_zoned, extra_attr, project_quota, 262 inode_checksum, flexible_inline_xattr, quota_ino, 263 inode_crtime, lost_found, verity, sb_checksum, 264 casefold, readonly, compression, test_dummy_encryption_v2, 265 atomic_write, pin_file, encrypted_casefold. 266 267What: /sys/fs/f2fs/<disk>/inject_rate 268Date: May 2016 269Contact: "Sheng Yong" <shengyong1@huawei.com> 270Description: Controls the injection rate of arbitrary faults. 271 272What: /sys/fs/f2fs/<disk>/inject_type 273Date: May 2016 274Contact: "Sheng Yong" <shengyong1@huawei.com> 275Description: Controls the injection type of arbitrary faults. 276 277What: /sys/fs/f2fs/<disk>/dirty_segments 278Date: October 2017 279Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 280Description: Shows the number of dirty segments. 281 282What: /sys/fs/f2fs/<disk>/reserved_blocks 283Date: June 2017 284Contact: "Chao Yu" <yuchao0@huawei.com> 285Description: Controls target reserved blocks in system, the threshold 286 is soft, it could exceed current available user space. 287 288What: /sys/fs/f2fs/<disk>/current_reserved_blocks 289Date: October 2017 290Contact: "Yunlong Song" <yunlong.song@huawei.com> 291Contact: "Chao Yu" <yuchao0@huawei.com> 292Description: Shows current reserved blocks in system, it may be temporarily 293 smaller than target_reserved_blocks, but will gradually 294 increase to target_reserved_blocks when more free blocks are 295 freed by user later. 296 297What: /sys/fs/f2fs/<disk>/gc_urgent 298Date: August 2017 299Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 300Description: Do background GC aggressively when set. Set to 0 by default. 301 gc urgent high(1): does GC forcibly in a period of given 302 gc_urgent_sleep_time and ignores I/O idling check. uses greedy 303 GC approach and turns SSR mode on. 304 gc urgent low(2): lowers the bar of checking I/O idling in 305 order to process outstanding discard commands and GC a 306 little bit aggressively. uses cost benefit GC approach. 307 gc urgent mid(3): does GC forcibly in a period of given 308 gc_urgent_sleep_time and executes a mid level of I/O idling check. 309 uses cost benefit GC approach. 310 311What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time 312Date: August 2017 313Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 314Description: Controls sleep time of GC urgent mode. Set to 500ms by default. 315 316What: /sys/fs/f2fs/<disk>/readdir_ra 317Date: November 2017 318Contact: "Sheng Yong" <shengyong1@huawei.com> 319Description: Controls readahead inode block in readdir. Enabled by default. 320 321What: /sys/fs/f2fs/<disk>/gc_pin_file_thresh 322Date: January 2018 323Contact: Jaegeuk Kim <jaegeuk@kernel.org> 324Description: This indicates how many GC can be failed for the pinned 325 file. If it exceeds this, F2FS doesn't guarantee its pinning 326 state. 2048 trials is set by default. 327 328What: /sys/fs/f2fs/<disk>/extension_list 329Date: Feburary 2018 330Contact: "Chao Yu" <yuchao0@huawei.com> 331Description: Used to control configure extension list: 332 - Query: cat /sys/fs/f2fs/<disk>/extension_list 333 - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list 334 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list 335 - [h] means add/del hot file extension 336 - [c] means add/del cold file extension 337 338What: /sys/fs/f2fs/<disk>/unusable 339Date April 2019 340Contact: "Daniel Rosenberg" <drosen@google.com> 341Description: If checkpoint=disable, it displays the number of blocks that 342 are unusable. 343 If checkpoint=enable it displays the number of blocks that 344 would be unusable if checkpoint=disable were to be set. 345 346What: /sys/fs/f2fs/<disk>/encoding 347Date July 2019 348Contact: "Daniel Rosenberg" <drosen@google.com> 349Description: Displays name and version of the encoding set for the filesystem. 350 If no encoding is set, displays (none) 351 352What: /sys/fs/f2fs/<disk>/free_segments 353Date: September 2019 354Contact: "Hridya Valsaraju" <hridya@google.com> 355Description: Number of free segments in disk. 356 357What: /sys/fs/f2fs/<disk>/cp_foreground_calls 358Date: September 2019 359Contact: "Hridya Valsaraju" <hridya@google.com> 360Description: Number of checkpoint operations performed on demand. Available when 361 CONFIG_F2FS_STAT_FS=y. 362 363What: /sys/fs/f2fs/<disk>/cp_background_calls 364Date: September 2019 365Contact: "Hridya Valsaraju" <hridya@google.com> 366Description: Number of checkpoint operations performed in the background to 367 free segments. Available when CONFIG_F2FS_STAT_FS=y. 368 369What: /sys/fs/f2fs/<disk>/gc_foreground_calls 370Date: September 2019 371Contact: "Hridya Valsaraju" <hridya@google.com> 372Description: Number of garbage collection operations performed on demand. 373 Available when CONFIG_F2FS_STAT_FS=y. 374 375What: /sys/fs/f2fs/<disk>/gc_background_calls 376Date: September 2019 377Contact: "Hridya Valsaraju" <hridya@google.com> 378Description: Number of garbage collection operations triggered in background. 379 Available when CONFIG_F2FS_STAT_FS=y. 380 381What: /sys/fs/f2fs/<disk>/moved_blocks_foreground 382Date: September 2019 383Contact: "Hridya Valsaraju" <hridya@google.com> 384Description: Number of blocks moved by garbage collection in foreground. 385 Available when CONFIG_F2FS_STAT_FS=y. 386 387What: /sys/fs/f2fs/<disk>/moved_blocks_background 388Date: September 2019 389Contact: "Hridya Valsaraju" <hridya@google.com> 390Description: Number of blocks moved by garbage collection in background. 391 Available when CONFIG_F2FS_STAT_FS=y. 392 393What: /sys/fs/f2fs/<disk>/avg_vblocks 394Date: September 2019 395Contact: "Hridya Valsaraju" <hridya@google.com> 396Description: Average number of valid blocks. 397 Available when CONFIG_F2FS_STAT_FS=y. 398 399What: /sys/fs/f2fs/<disk>/mounted_time_sec 400Date: February 2020 401Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 402Description: Show the mounted time in secs of this partition. 403 404What: /sys/fs/f2fs/<disk>/data_io_flag 405Date: April 2020 406Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 407Description: Give a way to attach REQ_META|FUA to data writes 408 given temperature-based bits. Now the bits indicate: 409 410 +-------------------+-------------------+ 411 | REQ_META | REQ_FUA | 412 +------+------+-----+------+------+-----+ 413 | 5 | 4 | 3 | 2 | 1 | 0 | 414 +------+------+-----+------+------+-----+ 415 | Cold | Warm | Hot | Cold | Warm | Hot | 416 +------+------+-----+------+------+-----+ 417 418What: /sys/fs/f2fs/<disk>/node_io_flag 419Date: June 2020 420Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 421Description: Give a way to attach REQ_META|FUA to node writes 422 given temperature-based bits. Now the bits indicate: 423 424 +-------------------+-------------------+ 425 | REQ_META | REQ_FUA | 426 +------+------+-----+------+------+-----+ 427 | 5 | 4 | 3 | 2 | 1 | 0 | 428 +------+------+-----+------+------+-----+ 429 | Cold | Warm | Hot | Cold | Warm | Hot | 430 +------+------+-----+------+------+-----+ 431 432What: /sys/fs/f2fs/<disk>/iostat_period_ms 433Date: April 2020 434Contact: "Daeho Jeong" <daehojeong@google.com> 435Description: Give a way to change iostat_period time. 3secs by default. 436 The new iostat trace gives stats gap given the period. 437What: /sys/fs/f2fs/<disk>/max_io_bytes 438Date: December 2020 439Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 440Description: This gives a control to limit the bio size in f2fs. 441 Default is zero, which will follow underlying block layer limit, 442 whereas, if it has a certain bytes value, f2fs won't submit a 443 bio larger than that size. 444 445What: /sys/fs/f2fs/<disk>/stat/sb_status 446Date: December 2020 447Contact: "Chao Yu" <yuchao0@huawei.com> 448Description: Show status of f2fs superblock in real time. 449 450 ====== ===================== ================================= 451 value sb status macro description 452 0x1 SBI_IS_DIRTY dirty flag for checkpoint 453 0x2 SBI_IS_CLOSE specify unmounting 454 0x4 SBI_NEED_FSCK need fsck.f2fs to fix 455 0x8 SBI_POR_DOING recovery is doing or not 456 0x10 SBI_NEED_SB_WRITE need to recover superblock 457 0x20 SBI_NEED_CP need to checkpoint 458 0x40 SBI_IS_SHUTDOWN shutdown by ioctl 459 0x80 SBI_IS_RECOVERED recovered orphan/data 460 0x100 SBI_CP_DISABLED CP was disabled last mount 461 0x200 SBI_CP_DISABLED_QUICK CP was disabled quickly 462 0x400 SBI_QUOTA_NEED_FLUSH need to flush quota info in CP 463 0x800 SBI_QUOTA_SKIP_FLUSH skip flushing quota in current CP 464 0x1000 SBI_QUOTA_NEED_REPAIR quota file may be corrupted 465 0x2000 SBI_IS_RESIZEFS resizefs is in process 466 0x4000 SBI_IS_FREEZING freefs is in process 467 ====== ===================== ================================= 468 469What: /sys/fs/f2fs/<disk>/ckpt_thread_ioprio 470Date: January 2021 471Contact: "Daeho Jeong" <daehojeong@google.com> 472Description: Give a way to change checkpoint merge daemon's io priority. 473 Its default value is "be,3", which means "BE" I/O class and 474 I/O priority "3". We can select the class between "rt" and "be", 475 and set the I/O priority within valid range of it. "," delimiter 476 is necessary in between I/O class and priority number. 477 478What: /sys/fs/f2fs/<disk>/ovp_segments 479Date: March 2021 480Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 481Description: Shows the number of overprovision segments. 482 483What: /sys/fs/f2fs/<disk>/compr_written_block 484Date: March 2021 485Contact: "Daeho Jeong" <daehojeong@google.com> 486Description: Show the block count written after compression since mount. Note 487 that when the compressed blocks are deleted, this count doesn't 488 decrease. If you write "0" here, you can initialize 489 compr_written_block and compr_saved_block to "0". 490 491What: /sys/fs/f2fs/<disk>/compr_saved_block 492Date: March 2021 493Contact: "Daeho Jeong" <daehojeong@google.com> 494Description: Show the saved block count with compression since mount. Note 495 that when the compressed blocks are deleted, this count doesn't 496 decrease. If you write "0" here, you can initialize 497 compr_written_block and compr_saved_block to "0". 498 499What: /sys/fs/f2fs/<disk>/compr_new_inode 500Date: March 2021 501Contact: "Daeho Jeong" <daehojeong@google.com> 502Description: Show the count of inode newly enabled for compression since mount. 503 Note that when the compression is disabled for the files, this count 504 doesn't decrease. If you write "0" here, you can initialize 505 compr_new_inode to "0". 506 507What: /sys/fs/f2fs/<disk>/atgc_candidate_ratio 508Date: May 2021 509Contact: "Chao Yu" <yuchao0@huawei.com> 510Description: When ATGC is on, it controls candidate ratio in order to limit total 511 number of potential victim in all candidates, the value should be in 512 range of [0, 100], by default it was initialized as 20(%). 513 514What: /sys/fs/f2fs/<disk>/atgc_candidate_count 515Date: May 2021 516Contact: "Chao Yu" <yuchao0@huawei.com> 517Description: When ATGC is on, it controls candidate count in order to limit total 518 number of potential victim in all candidates, by default it was 519 initialized as 10 (sections). 520 521What: /sys/fs/f2fs/<disk>/atgc_age_weight 522Date: May 2021 523Contact: "Chao Yu" <yuchao0@huawei.com> 524Description: When ATGC is on, it controls age weight to balance weight proportion 525 in between aging and valid blocks, the value should be in range of 526 [0, 100], by default it was initialized as 60(%). 527 528What: /sys/fs/f2fs/<disk>/atgc_age_threshold 529Date: May 2021 530Contact: "Chao Yu" <yuchao0@huawei.com> 531Description: When ATGC is on, it controls age threshold to bypass GCing young 532 candidates whose age is not beyond the threshold, by default it was 533 initialized as 604800 seconds (equals to 7 days). 534 535What: /sys/fs/f2fs/<disk>/gc_reclaimed_segments 536Date: July 2021 537Contact: "Daeho Jeong" <daehojeong@google.com> 538Description: Show how many segments have been reclaimed by GC during a specific 539 GC mode (0: GC normal, 1: GC idle CB, 2: GC idle greedy, 540 3: GC idle AT, 4: GC urgent high, 5: GC urgent low 6: GC urgent mid) 541 You can re-initialize this value to "0". 542 543What: /sys/fs/f2fs/<disk>/gc_segment_mode 544Date: July 2021 545Contact: "Daeho Jeong" <daehojeong@google.com> 546Description: You can control for which gc mode the "gc_reclaimed_segments" node shows. 547 Refer to the description of the modes in "gc_reclaimed_segments". 548 549What: /sys/fs/f2fs/<disk>/seq_file_ra_mul 550Date: July 2021 551Contact: "Daeho Jeong" <daehojeong@google.com> 552Description: You can control the multiplier value of bdi device readahead window size 553 between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option. 554 555What: /sys/fs/f2fs/<disk>/max_fragment_chunk 556Date: August 2021 557Contact: "Daeho Jeong" <daehojeong@google.com> 558Description: With "mode=fragment:block" mount options, we can scatter block allocation. 559 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 560 in the length of 1..<max_fragment_hole> by turns. This value can be set 561 between 1..512 and the default value is 4. 562 563What: /sys/fs/f2fs/<disk>/max_fragment_hole 564Date: August 2021 565Contact: "Daeho Jeong" <daehojeong@google.com> 566Description: With "mode=fragment:block" mount options, we can scatter block allocation. 567 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 568 in the length of 1..<max_fragment_hole> by turns. This value can be set 569 between 1..512 and the default value is 4. 570 571What: /sys/fs/f2fs/<disk>/gc_urgent_high_remaining 572Date: December 2021 573Contact: "Daeho Jeong" <daehojeong@google.com> 574Description: You can set the trial count limit for GC urgent high mode with this value. 575 If GC thread gets to the limit, the mode will turn back to GC normal mode. 576 By default, the value is zero, which means there is no limit like before. 577 578What: /sys/fs/f2fs/<disk>/max_roll_forward_node_blocks 579Date: January 2022 580Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 581Description: Controls max # of node block writes to be used for roll forward 582 recovery. This can limit the roll forward recovery time.