cvs commit: src/sys/kern imgact_elf.c init_main.c kern_checkpoint.c kern_descrip.c kern_event.c sys_generic.c sys_pipe.c uipc_syscalls.c uipc_usrreq.c vfs_aio.c vfs_syscalls.c src/sys/sys filedesc.h src/sys/dev/misc/streams streams.c ...

[Matthew Dillon]

:    Lets quantify slower.
:
:    Bytes per entry (before):	9	(three separate arrays)
:    Bytes per entry (after):	16	(one array of fdnodes)
:
:    Linear copy rate:	1 gigabyte sec
:
:    Do I need to continue and calculate how many nanoseconds longer
:    it takes to do something that isn't in the critical path?
:

    Sorry, I meant:  before = 9 bytes, after = 12 bytes.

    The assembly generated is actually fairly optimal, so I don't think
    I need to pad it 16 bytes.  The index is converted with two instructions
    and does not use a multiply.

					-Matt
					Matthew Dillon 
					<dillon at xxxxxxxxxxxxx>