Re: Informix on Raid 5

In article <32FF4E1D.468D@mail.delcoelect.com>, Matt Reprogle <mcreprog@mail.delcoelect.com> writes >Murray Oldfield wrote: >> >> > >Actually, the performance hit is not because it must read the parity disk. >In RAID >5, parity is spread across every disk. RAID 3 has a dedicated parity disk for a >rank of data disks. In RAID 5, the write performance problem comes from having >to >read parity, calculate new parity, then write data+parity. So every write >becomes a >read-write, which results in a performance penaly of 10-40% depending on whom >you >believe. > Thanks for the correction - I was not awake when writing that bit. For a larger discussion talk to :- Baydel Ltd Baydel North America Inc. Brook Way 2370 Bering Drive Leatherhead or San Jose Surrey California 95131 KT22 7NA USA United Kingdom Telephone 44 (0)1372 378811 Telephone 1 (408) 383 7474 FAX 44 (0)1372 386960 FAX 1 (408) 383 9501 And ask for the document "Informix and RAID A Discussion Document" It talks about the problems with RAID 5 array and how they resolve them. This is the only document that I have come across. It mentions the internal study done by Informix (that my OnLine Performance Tuning tutor mentioned) which dicovered that RAID 5 was slow. > >For a good article on this subject go to: >http://www.compumedia.com/~kkirk/raid.html > -- David Williams