.TH HP 4 .SH NAME hp \- RH-11/RM02, RP04, RP05, RP06 moving-head disk \- RH-70/RM03, RP04, RP05, RP06 moving-head disk \- RH-11/ML11 solid state disk \- RH-70/ML11 solid state disk .SH DESCRIPTION The octal representation of the minor device number is encoded .IR idp , where .I i is an interleave flag, .I d is a physical drive number, and .I p is a pseudodrive (subsection) within a physical unit. If .I i is 0, the origins and sizes of the pseudodisks on each drive, counted in cylinders of 418 512-byte blocks, for the RP04/5/6 are: .nf .PP disk start length 0 0 23 1 23 21 2 44 21 3 65 345 4 65 749 5 411 403 6 0 410 7 0 814 .fi .PP The pseudodisks for the RM02/3 are: .nf .PP disk start length 0 0 60 1 60 55 2 115 50 3 165 657 4 0 0 5 0 0 6 0 0 7 0 822 .fi .PP If .I i is 1, the minor device consists of the specified pseudodisk on drives numbered 0 through the designated drive number. Successively numbered blocks are distributed across the drives in rotation. .PP Systems distributed for these devices use disk 0 for the root, disk 1 for swapping, disk 2 for the system souces, and disk 3 (rp04/5 & rm02/3), or disk 4 (rp06) for a mounted user file system. .PP The ML11 solid state disk may be connected to the RH11 or RH70 massbus disk controller in conjunction with RM and RP disks. The ML11 may be used for the swap device or perhaps mounted on /tmp. The ML11 has switch-selectable transfer rates of 0.25 mb, 0.5 mb, 1.0 mb, and 2.0 mb per second. The following transfer rate restrictions apply: .br .nf 0.25 mb all CPU's 0.5 mb all CPU's 1.0 mb PDP 11/70 with RH70 only 2.0 mb NO PDP11 CPU's .fi .PP The RM02/3, RP04/5/6, and ML11 disks may be attached to a second RH11 or RH70 massbus disk controller at the alternate address and vector. In this case these disks are referenced as .IR hm? . . .PP The block files access the disk via the system's normal buffering mechanism and may be read and written without regard to physical disk records. .PP A `raw' interface provides for direct transmission between the disk and the user's read or write buffer. A single read or write call results in exactly one I/O operation and therefore raw I/O is considerably more efficient when many words are transmitted. The names of the raw files conventionally begin with an extra `r.' In raw I/O the buffer must begin on a word boundary, and raw I/O to an interleaved device is likely to have disappointing results. .SH FILES /dev/rp?, /dev/rrp? .br /dev/hp?, /dev/rhp? .br /dev/hm?, /dev/rhm? .SH SEE ALSO /usr/doc/hpsizes .SH BUGS In raw I/O .I read and .IR write (2) truncate file offsets to 512-byte block boundaries, and .I write scribbles on the tail of incomplete blocks. Thus, in programs that are likely to access raw devices, .I read, write and .IR lseek (2) should always deal in 512-byte multiples. .PP Raw device drivers don't work on interleaved devices.