119 lines · plain
1What: /sys/fs/ext4/<disk>/mb_stats2Date: March 20083Contact: "Theodore Ts'o" <tytso@mit.edu>4Description:5 Controls whether the multiblock allocator should6 collect statistics, which are shown during the unmount.7 1 means to collect statistics, 0 means not to collect8 statistics9 10What: /sys/fs/ext4/<disk>/mb_group_prealloc11Date: March 200812Contact: "Theodore Ts'o" <tytso@mit.edu>13Description:14 The multiblock allocator will round up allocation15 requests to a multiple of this tuning parameter if the16 stripe size is not set in the ext4 superblock17 18What: /sys/fs/ext4/<disk>/mb_max_to_scan19Date: March 200820Contact: "Theodore Ts'o" <tytso@mit.edu>21Description:22 The maximum number of extents the multiblock allocator23 will search to find the best extent24 25What: /sys/fs/ext4/<disk>/mb_min_to_scan26Date: March 200827Contact: "Theodore Ts'o" <tytso@mit.edu>28Description:29 The minimum number of extents the multiblock allocator30 will search to find the best extent31 32What: /sys/fs/ext4/<disk>/mb_order2_req33Date: March 200834Contact: "Theodore Ts'o" <tytso@mit.edu>35Description:36 Tuning parameter which controls the minimum size for37 requests (as a power of 2) where the buddy cache is38 used39 40What: /sys/fs/ext4/<disk>/mb_stream_req41Date: March 200842Contact: "Theodore Ts'o" <tytso@mit.edu>43Description:44 Files which have fewer blocks than this tunable45 parameter will have their blocks allocated out of a46 block group specific preallocation pool, so that small47 files are packed closely together. Each large file48 will have its blocks allocated out of its own unique49 preallocation pool.50 51What: /sys/fs/ext4/<disk>/inode_readahead_blks52Date: March 200853Contact: "Theodore Ts'o" <tytso@mit.edu>54Description:55 Tuning parameter which controls the maximum number of56 inode table blocks that ext4's inode table readahead57 algorithm will pre-read into the buffer cache58 59What: /sys/fs/ext4/<disk>/delayed_allocation_blocks60Date: March 200861Contact: "Theodore Ts'o" <tytso@mit.edu>62Description:63 This file is read-only and shows the number of blocks64 that are dirty in the page cache, but which do not65 have their location in the filesystem allocated yet.66 67What: /sys/fs/ext4/<disk>/lifetime_write_kbytes68Date: March 200869Contact: "Theodore Ts'o" <tytso@mit.edu>70Description:71 This file is read-only and shows the number of kilobytes72 of data that have been written to this filesystem since it was73 created.74 75What: /sys/fs/ext4/<disk>/session_write_kbytes76Date: March 200877Contact: "Theodore Ts'o" <tytso@mit.edu>78Description:79 This file is read-only and shows the number of80 kilobytes of data that have been written to this81 filesystem since it was mounted.82 83What: /sys/fs/ext4/<disk>/inode_goal84Date: June 200885Contact: "Theodore Ts'o" <tytso@mit.edu>86Description:87 Tuning parameter which (if non-zero) controls the goal88 inode used by the inode allocator in preference to89 all other allocation heuristics. This is intended for90 debugging use only, and should be 0 on production91 systems.92 93What: /sys/fs/ext4/<disk>/max_writeback_mb_bump94Date: September 200995Contact: "Theodore Ts'o" <tytso@mit.edu>96Description:97 The maximum number of megabytes the writeback code will98 try to write out before move on to another inode.99 100What: /sys/fs/ext4/<disk>/extent_max_zeroout_kb101Date: August 2012102Contact: "Theodore Ts'o" <tytso@mit.edu>103Description:104 The maximum number of kilobytes which will be zeroed105 out in preference to creating a new uninitialized106 extent when manipulating an inode's extent tree. Note107 that using a larger value will increase the108 variability of time necessary to complete a random109 write operation (since a 4k random write might turn110 into a much larger write due to the zeroout111 operation).112 113What: /sys/fs/ext4/<disk>/journal_task114Date: February 2019115Contact: "Theodore Ts'o" <tytso@mit.edu>116Description:117 This file is read-only and shows the pid of journal thread in118 current pid-namespace or 0 if task is unreachable.119