Lecture 3

File System Parameterization

• The old file system operated completely independent of any processor- or disk-specific parameters.

• The new file system customizes its behavior based on the values of the following parameters:
  • Processor speed.
  • Hardware support for mass storage transfer
  • Mass storage device characteristics (may differ for each file system on a given machine)

• The new file system was designed based on the disk technology of the mid 1980s. At that time, most disks had very little on-board processing and their device drivers had relatively transparent access to their physical layout.

• The new file system tries to allocate further blocks for a file in the same cylinder as the previous block for a file.

  Why?

• The alocation routines consider the number of blocks per track, the disk rotational speed, and the expected time for the processor to service an interrupt and schedule a new disk transfer. When a block is allocatd to a file, the filesystem calculates the location of the block that will be under the head when the next disk transfer operation starts.

  What disk operations will benefit from such a strategy?

• The cylinder group summary block contains the number of available blocks in 8 different rotational positions. The superblock contains a rotational layout table, identifying the position in the block map for each of the rotational positions. When a write happens, the appropriate index in the rotational layout table is consulted so the search for a new block will occur in the best rotational block group.

• The parameter defining the delay between end of one data transfer and beginning of another can be changed at any time. This accomodates the moving of a disk from one system to another slower or faster system.

Layout Policies

• Two levels of policy:
  • Global: uses file-system-wide summary information to decide the placement of new inodes and data.
  • Local: Use locally optimal schemes to lay out data blocks.

• Improve file system performance by increasing locality of reference and improving layout to make larger transfers possible.

• Layout policy tries to place all inodes corresponding to files in a given directory in the same cylinder group.

  Can you think of any properties of the Unix file system that make this goal impossible?

• The policies attempt to place all data blocks for a file in the same cylinder group at rotationally optimal positions in that cylinder. Unfortunately, a few large files can use up all the space in a cylinder group. Block allocation is forced to another cylinder group whenever a file will require an indirect block. and whenever a file has used up 25% of the space in the current cylinder group.

  The cylinder group chosen for new blocks is chosen from those having a larger than average number of free blocks.

• The local allocation routines are exercised by the global allocation routines. Whenever possible, they return the exact block being asked for. Where not possible, they will allocate a free block that is rotationally closest to the one requested. The local allocator uses this four-level allocation strategy:
  1. Use the next free block rotationally closest to the requested block in the same cylinder.
  2. If no blocaks are available on the same cylinder, use one in the same cylinder group.
  3. If the cylinder group is entirely filled, choose another cylinder group using a quadratic hash to yeild the new cylinder group.
  4. If the hash fails, search all cylinder groups for one that can accomodate a new block.
  File systems keeping 10% free space rarely need to use the hashing mechanism.

Performance

• Reading rates:

  FS Type	Processor/Bus	Speed KB/s	Read bandwidth %	%CPU
  Old 1024	750/UNIBUS	29	29/983 3	11
  New 4096/1024	750/UNIBUS	221	221/983 22	43
  New 8192/1024	750/UNIBUS	233	233/983 24	29
  New 4096/1024	750/MASSBUS	466	466/983 47	73
  New 8192/1024	750/MASSBUS	466	466/983 47	54

• Writing rates:

  FS Type	Processor/Bus	Speed KB/s	Write bandwidth %	%CPU
  Old 1024	750/UNIBUS	48	48/983 5	29
  New 4096/1024	750/UNIBUS	142	142/983 14	43
  New 8192/1024	750/UNIBUS	215	215/983 22	46
  New 4096/1024	750/MASSBUS	323	323/983 33	94
  New 8192/1024	750/MASSBUS	466	466/983 47	95

• Observations:
  • Disks used were configured with 10% free space.

  • The number of disk operations to access inodes in a large directory ls is 1/2 the number on the old file system.

  • Transfer rates for the new system do not change over time.

  • Upper bound for bandwidth is calculated by multiplying the number of bytes per track by the number of revolutions per second.

  • Slower write rates vs. read rates in the 4096 system result from having to do twice as many disk allocations per second, prohibiting the processor from keeping up with the transfer rate.

    The old system, on the other hand, was faster at writing than reading because it was essentially optimized to make writing and block allocation easy. When reading, however, the poor placement of blocks causes delay.

File System Functional Enhanacements

• Long file names. Limit: 255 characters.

• File locking. In the old system, the only way to lock a files was to create a separate lock file. (File creation was certain to be sequential, so only one process could create the lock file successfully at any given time.)

  The new file system supports advisory locks.

• Symbolic links. Relative pathnames are evaluated relative to the directory in which the link is contained (not the directory in which the creating process was running).

• Rename. This was added to avoid a situation in which three system calls had to be made (possibly leaving the target file with a temporary name).

• Quotas. Quotas involving both soft and hard limits were introduced in the new file system.