How to mount ext4 fs with block size of 65536?

I am benchmarking EXT4 performance on Compact Flash media.

I have created an ext4 fs with block size of 65536. However I cannot mount it on ubuntu-10.10-netbook-i386 (it is already mounting ext4 fs with 4096 bytes of block sizes)

According to my readings on ext4 it should allow such big block sized fs. I want to hear your comments.

root@ubuntu:~# mkfs.ext4 -b 65536 /dev/sda3 Warning: blocksize 65536 not usable on most systems. mke2fs 1.41.12 (17-May-2010) mkfs.ext4: 65536-byte blocks too big for system (max 4096) Proceed anyway? (y,n) y Warning: 65536-byte blocks too big for system (max 4096), forced to continue Filesystem label= OS type: Linux Block size=65536 (log=6) Fragment size=65536 (log=6) Stride=0 blocks, Stripe width=0 blocks 19968 inodes, 19830 blocks 991 blocks (5.00%) reserved for the super user First data block=0 1 block group 65528 blocks per group, 65528 fragments per group 19968 inodes per group Writing inode tables: done Creating journal (1024 blocks): done Writing superblocks and filesystem accounting information: done This filesystem will be automatically checked every 37 mounts or 180 days, whichever comes first. Use tune2fs -c or -i to override. root@ubuntu:~# tune2fs -l /dev/sda3 tune2fs 1.41.12 (17-May-2010) Filesystem volume name: <none> Last mounted on: <not available> Filesystem UUID: 4cf3f507-e7b4-463c-be11-5b408097099b Filesystem magic number: 0xEF53 Filesystem revision #: 1 (dynamic) Filesystem features: has_journal ext_attr resize_inode dir_index filetype extent flex_bg sparse_super large_file huge_file uninit_bg dir_nlink extra_isize Filesystem flags: signed_directory_hash Default mount options: (none) Filesystem state: clean Errors behavior: Continue Filesystem OS type: Linux Inode count: 19968 Block count: 19830 Reserved block count: 991 Free blocks: 18720 Free inodes: 19957 First block: 0 Block size: 65536 Fragment size: 65536 Blocks per group: 65528 Fragments per group: 65528 Inodes per group: 19968 Inode blocks per group: 78 Flex block group size: 16 Filesystem created: Sat Feb 5 14:39:55 2011 Last mount time: n/a Last write time: Sat Feb 5 14:40:02 2011 Mount count: 0 Maximum mount count: 37 Last checked: Sat Feb 5 14:39:55 2011 Check interval: 15552000 (6 months) Next check after: Thu Aug 4 14:39:55 2011 Lifetime writes: 70 MB Reserved blocks uid: 0 (user root) Reserved blocks gid: 0 (group root) First inode: 11 Inode size: 256 Required extra isize: 28 Desired extra isize: 28 Journal inode: 8 Default directory hash: half_md4 Directory Hash Seed: afb5b570-9d47-4786-bad2-4aacb3b73516 Journal backup: inode blocks root@ubuntu:~# mount -t ext4 /dev/sda3 /mnt/ mount: wrong fs type, bad option, bad superblock on /dev/sda3, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so 

3 Answers

AFAIK ext2/3/4 is based on the generic Linux VFS framework which requires block size to be less than or equal to page size

You may experience mounting problems if block size is greater than page size (i.e. 64KiB blocks on a i386 which only has 4KiB memory pages).

There were some talks regarding solving the big block issue

• Large pages, large blocks, and large problems
• Design for Large Allocation Blocks
• RFC: CONFIG_PAGE_SHIFT (aka software PAGE_SIZE)

Unfortunately there's almost no great progress yet

However since you just want to test the speed, I suggest to use bigalloc which allocates in big clusters instead of big blocks. For example to create an ext4 partition with 64KB cluster

dd if=/dev/zero of=ext4.bigalloc bs=1M count=256 mkfs.ext4 -C 65535 -O bigalloc ext4.bigalloc sudo mount -o loop ext4.bigalloc /mnt 

This option is new in Linux 3.2 kernel and you must specify that option when calling mkfs.ext4 as seen above

• -C cluster-size
  • Specify the size of cluster in bytes for filesystems using the bigalloc feature. Valid cluster-size values are from 2048 to 256M bytes per cluster. This can only be specified if the bigalloc feature is enabled. (See the ext4 (5) man page for more details about bigalloc.) The default cluster size if bigalloc is enabled is 16 times the block size.

This feature is still in development so use it with care. But since you typically don't care about file corruption while benchmarking, it's probably the best option

That said, the limit is just in the in-kernel driver and you can still mount the partition with the FUSE driver. Some examples:

• Fuse-ext2

  Fuse-ext2 is an EXT2/EXT3/EXT4 filesystem for FUSE, and is built to work with osxfuse.

  Usage: fuse-ext2 <device|image_file> <mount_point> [-o option[,...]] Options: ro, rw+, force, allow_other Please see details in the manual. Example: fuse-ext2 /dev/sda1 /mnt/sda1 

  Just run sudo apt install fuseext2 to install if it's not available. Tested on my system and it works perfectly

• guestmount. See how to use it in Possible to mount an ext4 partition image via FUSE?

If you just want to copy the data then you can use debugfs but it's not quite useful for benchmarking. Even the performance of FUSE may be not good enough for measuring the device speed

The max ext4 block size is still limited by the page size of the kernel/CPU. Your page size is 4K and so the max ext4 block size is 4K.

I'd say use 4KB blocks for compatibility and use extents and stripe stride-width options on create/mount to get block allocations in accordance with the erase block size of your flash media.

Make sure also that the partition is aligned to this erase block size too!