Home Original page

hppa build broken

John David Anglin dave@hiauly1.hia.nrc.ca
Wed Jun 15 03:30:00 GMT 2005 
> You might like to see whether increasing the buffer size at write.c:1146
> helps poor HPUX file I/O.  4k would probably be a better size.

Doesn't help:

4k:
real    16m13.524s
user    0m1.250s
sys     0m21.310s

64k:
real    16m18.884s
user    0m0.230s
sys     0m21.430s

vmstat indicates ~ 300 xfer/sec for the drive.  At 4k per transfer,
that's about 1000s or 16m.  Why linux would be so much faster isn't
clear although the drive and interface used is faster.

I'd also previously tried changing pa_block to output 8MB blocks
followed by the residual (i.e., using the old way but limiting
memory usage to 8MB).  While the user and sys times went down, the
real time actually got worse.  The old code suffers from the same
problem.

Dave
-- 
J. David Anglin                                  dave.anglin@nrc-cnrc.gc.ca
National Research Council of Canada              (613) 990-0752 (FAX: 952-6602)
More information about the Binutils mailing list