Time is used for timing. dd is used for copying, reading from if, and writing to. If =/dev/zero does not produce IO, so it can be used to test the pure write speed. Similarly, of =/dev/null does not generate IO and can be used to test the pure read speed. Bs indicates the size of each read or write, that is, the size of a block. count indicates the number of read/write blocks. 1. the pure write speed of the disk where the test/directory is located: [root @ yunvi/] # timeddif =/dev/zerobs = 1024 time has a timing effect. dd is used for replication and read from if, write to. If =/dev/zero does not produce IO, so it can be used to test the pure write speed. Similarly, of =/dev/null does not generate IO and can be used to test the pure read speed. Bs indicates the size of each read or write, that is, the size of a block. count indicates the number of read/write blocks.
1. test/directory disk's pure write speed:
[Root @ yunvi/] # time dd if =/dev/zero bs = 1024 count = 1000000 of =/1 GB. file
2. test/directory disk's pure read speed:
Dd if =/kvm/ftp/other/1Gb. file bs = 64 k | dd of =/dev/null
3. test the read/write speed (what is this ):
Dd if =/vat/test of =/oradata/test1 bs = 64 k
Theoretically, the larger the replication volume, the more accurate the test.