Did you check if your firmware was updated on the DTU?
You probably did but I noticed much better performance after updating
the firmware.
Ivar
C. Daniel Mojoli B. schreef:
Marty Sholes described <SRSS 4.2, OSol 124-6> performance *_exactly_*
as I would describe <SRSS 4.2, Sol 10u8>:
/I would add to that list switching virtual screens,
loggin in, output scrolling in gnome-terminal, scrolling
in firefox, scrolling in evince, scrolling in OpenOffice,
or scrollin in anything plus anything flash.
Also add in another OS via virtualbox and pretty
much anything else reasonable office worker would
do outside of xterm with compression mode and
the response screams that this is slow and you
are better off using a local box./
I would like to add a couple bits:
1. <SRSS 4.0, Sol 10u4>'s performance was satisfactory; there was a
exasperating performance loss after upgrading to <SRSS 4.2, Sol
10u8>. (NB: 18GB of RAM for 10 DTUs, 4 Opteron cores, well
suited for its load.)
2. The performance loss remains even during a test where *_I
eliminated network components_* and connected a straight through
cable between the DTU and our x2200m2.
3. A different deployment, 40 DTU against <SRSS 4.1, Sol 10u7, Sun
x4400> performs well.
4. I tried using old Xsun instead of Xnewt with no impact.
5. I tried renice -n -10 of X server processes with no impact.
6. The clearest demonstration of the performance difference is
watching a regular size YouTube video.
We will try rolling back to SRSS 4.1 (or 4.0) and will report on its
effects.
--
C. Daniel Mojoli Boggino
Presidente
Taller de Ideas S.A.
http://tdi.com.py
------------------------------------------------------------------------
_______________________________________________
SunRay-Users mailing list
[email protected]
http://www.filibeto.org/mailman/listinfo/sunray-users
_______________________________________________
SunRay-Users mailing list
[email protected]
http://www.filibeto.org/mailman/listinfo/sunray-users
