I bet the original bit of mail has caused some ripples! Let me add my 2 cents worth here...
First of all the account teams need to attend the "Top Gun" course run in IBM. Then they can form proposals that addressed the problems of a customer rather than layer solutions with extra layers like z/OS just to run WLM (because they're comfortable with that approach). That way they wouldn't get well into a proposal before they discover they're in trouble. I don't know if this is the case for this particular customer but there seems to be a trend emerging. Also, they need to understand "server consolidation doesn't always = a few pSeries boxes". They could ask the right questions of the vast pool of resources at their disposal (but work in areas of IBM quite foreign to them) and do some sizing runs using their resources in Poughkeepsie. You have a heap of resources to answer Samba questions: - Large z900 systems to run things on - Sufficient network bandwidth to put clients on or simulate via a heap of virtual machines doing Samba client stuff - Performance tools to measure things accurately: - ESALPS which has an SNMP interface to acquire the data from the Samba server - ESAMON/ESAMAP which can interpret the monitor data - RMFPMS written by your German(?) colleagues - A pool of people in Endicott who know the internals of z/VM and can ensure you extract every last drop from the processor - A team of people in Boeblingen who know the internals of Linux and glibc to help you optimize your configuration - Enough people on lists like this who are focused on getting this stuff to work properly - An ITSO that can create a redbook team who'd examine all the issues you're worried about and create a document the rest of the IBM world could use P.S. My commiserations to the poor SOB who aired this publicly. You have done your company a service but I doubt they'll react that way. It sounds to me IBM needs to form a team who can spring into action before any proposals are made not before they're about to go "boom". > -----Original Message----- > Hi gang, > > I am right now canvasing interested parties trying to find an > answer to a > philosophical issue. One of the plays we are looking at is Server > Consolidation onto Linux, across brands. When I look at > Samba though, I > don't have a defined group to interface with (internal, > another company, > whatever). At best I have samba.org and some IBMers on the > Samba Team who > are making best effort to help. > > My problem is that there is no place to go for scaling > numbers. How many > print queues can I configure under Linux and at what rate can > I spool to > them? (There appears to be no answer to this.) Given any > disk array, how > much data can I push out through the pipe? (There are some > very limited > answers using a tool called smbtorture.) How do file serving > and print > serving interact when run at capacity? And what about when > we virtualize > this load, either using z/VM or VMware. > > I know the immediate answer, those are great questions and > unfortunately we > don't know the answers. So how should we go about getting them? In a > perfect world, I could look at a chart that would answer them > for both the > z800 and the x360. From what I can see & verify, we don't > even have the > tools to go about answering these questions.
