Hello Herbert,

08 Dec 99 18:13, Herbert Rosenau wrote to Eddy Thilleman:

ET>> 9 lazy write workers? I haven't seen mentioned that high before.

HR> Why not?

I haven't seen that before.

HR> The optimasion was done at a time this computer was used as
HR> - 3 lines node with mostly ISDN throughput
HR> - developement mashine (edit/compile/debug...) with all lines running
HR> - some other aktive tasks

so that number of lazy write workers maximize the write performance to disk
with a lowest possible CPU usage, so maximizing transfer speed?

HR> The optimasion was at least done with help another node to become the
HR> highest possible transfer rate during an connect on both lines and
HR> running tosser in background.

OK.

HR> I'd found that throwing on the cache parameters has the most
HR> incredible effect on the transfer rates. I'd found values that are
HR> commonly nearst the physical maximum (7950/15500 cps as sender and
HR> 7850/14500 as receiver of *.bmp)

HR> Exchange of large *.bmp can kill the telko's convey station if both
HR> sides can send with maximum speed on direct CAPI. :-)

Don't tell your telco (Deutsche Telekom) that, or they will limit the highest
possible transfer speed to 7000 cps. ;-)

HR> Without the excessive optimasision step my transfer rate where more
HR> than 200 cps less.

HR> Yes. But not this extensive testing to find the best parameters.

OK.

HR> After that playing with the cache parameters can speed up the lines
HR> more.

I am just looking for more information about the number of lazy write workers.

HR> Changes can be made without reboot. call cache.exe with the
HR> propper parameters.

I know. :)

  Greetings   -=Eddy=-        email: eddy.thilleman@net.hcc.nl

... "Pieces of Nine! Pieces of Nine!"  Another parroty error!
--- GoldED/2 3.0.1