The following message is a courtesy copy of an article that has been posted to bit.listserv.ibm-main,alt.folklore.computers as well.
[EMAIL PROTECTED] (R.S.) writes: > Parallel Sysplex has nothing to do with that. You're talking about > *banking system* which consist of many elements, optionally including > > PS. > Even if the PS is there and is really available, it doesn't mean the > system (banking system) will be available. I work under SLA which > allows me to have 8 hours of planned outage per year. No sysplex. I > have never reached the limit, because I easily "share" outages > demanded by other components. In such case PS adds almost no value, > and is not the factor of banking system availability. re: http://www.garlic.com/~lynn/2008i.html#97 We're losing the battle working on ha/cmp we looked at customer that required five-nines availability ... five minute outage (planned & unplanned) per year. on the other hand ... one of the large financial transaction networks has claimed 100% availability over extended number of years ... using triple redundant IMS hot-standby and multiple geographic locations. slight drift ... recent Information Security blog post http://www.garlic.com/~lynn/2008i.html#17 Does anyone have any IT data center disaster stories? made a passing reference in previous post with regard to contention with the communication division. the tcp/ip mainframe product had significant performance issues ... consuming nearly a full 3090 processor getting 44kbytes/sec thruput. I enhanced the product with RFC1044 support and in some tuning tests at Cray research got 1mbyte/sec (hardware limitation) sustained between a Cray and a 4341-clone (using only a modest amount of the 4341) ... aka nearly three orders of magnitude increase in the ratio of bytes transferred per instruction executed. another area of conflict ... as part of the hsdt project http://www.garlic.com/~lynn/subnetwork.html#hsdt the friday before we were to leave on trip to the other side of the pacific to discuss some custom built hardware for hsdt ... somebody (from the communication division) announced a new online conference in the area of high-speed communication ... and specified the following definitions: low-speed <9.6kbits medium-speed 19.2kbits high-speed 56kbits very high-speed 1.5mbits the following monday on the wall of conference room on the other side of the pacific were these definitions: low-speed <20mbits medium-speed 100mbits high-speed 200-300mbits very high-speed >600mbits ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
