That's what I'm thinking about. I have two harddrives. One I use for large data and one for Windows and everything else. Was thinking about making smaller clusters for the Windows drive and larger clusters for the other drive witch just holds lots of large data.defakto said:It's going to depend on the data you're reading. Larger clusters work better with large files usually, and smaller ones typically work better with smaller files. Perfomance impact can be minimal, but the main thing is effective use of space. 128k clusters means every tiny 1k file would use 128k of disc space. This wouldn't be much of a big deal if the smallest files you ahve are like 128k or larger.
drizzt81 said:Are you sure that in NTFS the 1K file wouldn't be included in the MFT? I remember from a couple of years ago that NTFS' master file table is used to house the first 4KB of every file, which means that all sub 4K files are completed within the MFT. Since the MFT is treated as a large file, it elemininates cluster waste.
see more here
Let me send you over to http://en.wikipedia.org/wiki/NTFSTalonz said:This is news to me. Are you sure that this is true? The MFT is supposed to act as an index, it does not differentiate between contents. I'm not trying to sound like a smartass, but what you're saying makes no sense to me.
Every allocated sector on an NTFS volume belongs to a file. Even the file system metadata is part of a file. NTFS views each file (or folder) as a set of file attributes. File elements such as its name, its security information, and even its data are file attributes. Each attribute is identified by an attribute type code and an optional attribute name.
File and folder records are 1 KB each and are stored in the MFT, the attributes of which are written to the allocated space in the MFT. Besides file attributes, each file record contains information about the position of the file record in the MFT.
When a files attributes can fit within the MFT file record for that file, they are called resident attributes. Attributes such as file name and time stamp are always resident. When the amount of information for a file does not fit in its MFT file record, some file attributes become nonresident. Nonresident attributes are allocated one or more clusters of disk space. A portion of the nonresident attribute remains in the MFT and points to the external clusters. NTFS creates the Attribute List attribute to describe the location of all attribute records. The table NTFS File Attribute Types lists the file attributes currently defined by NTFS.
Bad idea. Any third-party tools are very likely to assume the default cluster size, and break horribly if you use them. And you probably won't be able to detect the difference.DukenukemX said:Anyone have a link to benchmarks showing the performance of NTFS when you change the cluster size? I wanna see if reducing or increasing the cluster size has any real benefits.