Re: Single cpu vp woe

Neil Truby schrieb: > 9.20 UC3 on Red Hat 7. > > This site is running the time series datablade in production on a 2-cpu box. > It's all working fine. > > For reasons we needn't go into they want to move to a single cpu box. > They've set up an identical test server. When we run the same programs with > the live setting (NUMCPUVPS=2) we get the same consistent results. However, > if we reduce NUMCPUVPS to 1 then (and regardless of whether there are 1 or 2 > physical cpus present in the test box) the tests run 15-20 times more > slowly. The reason isn't difficult to see: onstat -g rea shows the ready > queue with 3 or more entries, indicating a bottleneck on cpu vps. > > The one test I didn't try, through lack of time, is running with > MULTIPROCESSOR=1, NUMCPUVPS=2 with a single physical cpu. > > Anyway, I infer from all this that they need to run this version of IDS and > the TimeSeries datablade on a 2-way box. But the customer isn't happy with > this, and wants a decent and plausible explanation as to why this cannot be > made to work on a single cpu server. I don't know enought about the > datablade to give a more detailed opinion. > > Any comment gratefully received, as ever. > > thanks > Neil > > Hi Neal If your cutomers site can use a dual threaded CPU and can run it in multi threaded mode, you will lose only a small percentage of CPU power compared to a box having 2 CPUs running single threaded mode. I have done many tests on setups using one dual threaded CPU configured with 2 CPUVPs showing that what Madison calls a 'theoretical for instance' will NOT be a problem (all this tests on Linux using INTEL CPU on TYAN MoBo) You gonna have all pros, like 2 KIO threads sharing the I/O load and so on. Only when the application is CPU intensive (SPL code doing many casts or calculations, or if you have fragmented tables with long and calc intensive rules or if you do many re-optimizations of quries) then you will see, that only so many ALU and floating arith units are in one chip .... The disadvantages can be flattened out by investing into a MoBo which has 4 way memory attach lines and using fast memory chips. Going that route one can see upto 17K BUFFER attaches per second, which is top speed! dic_k -- Richard Kofler SOLID STATE EDV Dienstleistungen GmbH Vienna/Austria/Europe

"Richard Kofler" <richard.kofler@chello.at> wrote in message news:huERd.52484$2e4.20127@news.chello.at... > Neil Truby schrieb: >> 9.20 UC3 on Red Hat 7. > If your cutomers site can use a dual threaded CPU and can run it > in multi threaded mode, you will lose only a small percentage > of CPU power compared to a box having 2 CPUs running single > threaded mode. Thanks. Doesn't IBM have special rules about the licensing of "multithreaded" CPUs?

Neil Truby wrote: > "Richard Kofler" <richard.kofler@chello.at> wrote in message > news:huERd.52484$2e4.20127@news.chello.at... > >>Neil Truby schrieb: >> >>>9.20 UC3 on Red Hat 7. > > >>If your cutomers site can use a dual threaded CPU and can run it >>in multi threaded mode, you will lose only a small percentage >>of CPU power compared to a box having 2 CPUs running single >>threaded mode. > > > Thanks. > Doesn't IBM have special rules about the licensing of "multithreaded" CPUs? > > Dual core is classed as two CPUs I believe. However, hyperthreading on one CPU is still classed as a single CPU. Do not believe me, believe the pudding :)