Another data point:
HP BL-20 blade, two 'HYPErthreading' Intel Xeon CPUs
(looks like 4 CPUs to O/S)
Sort ~3.8GB distributed file with ~1.6M records by @ID
(@ID is multi-character alphanumeric value, e.g.
"Z996894|13787")
(File has four parts: 1.0GB, 1.2GB, 1.5GB & 100MB is
size
partitioned on 2nd part of @ID)
Only user on system
Two runs in each pass, reboot between passes
Pass 1
UVTSORT = 0
1st run 10:15
2nd run 09:45
Pass 2
Re-boot, then
UVTSORT = 1
1st run 10:02 (2.3% faster)
2nd run 09:48 (0.5% slower)
Thanks again to Andy Mack for actually doing the work!
On this hardware and O/S, multi-threading sort is neither significantly
faster nor significantly slower than non-multi-threading?
Mike
The information contained in this Internet Email message is intended
for the addressee only and may contain privileged information, but not
necessarily the official views or opinions of the New Zealand Defence Force.
If you are not the intended recipient you must not use, disclose, copy or
distribute this message or the information in it.
If you have received this message in error, please Email or telephone
the sender immediately.
-------
u2-users mailing list
[email protected]
To unsubscribe please visit http://listserver.u2ug.org/
