On Mon, 2009-11-16 at 03:49 +0000, Bishop, Peter wrote: > With zLinux named pipes I think there will be more than one read for > each record, viz one for the cat command and one for the pipe itself > (perhaps two if the program then has to issue another read to get the > data from the pipe). Assuming an extra two milliseconds for each I/O, > for every million I/Os you get about another 30 minutes' time (a bit > more). So an extra ten or twenty million I/Os adds about 5 to 10 > extra hours of processing time.
As I said Peter, I don't think there'll extra (physical) I/O. There will be multiple read and write calls - but they should be resolved from the page cache. In micro/pico-, not milli- seconds. The code seems to support this assumption. I see about 5% elapsed elongation on (most of) my tests - probably consistent with the writer to the pipe being put to sleep while the reader catches up. However I did see some really odd numbers on occasion - I'm going to see if I can set some probes in the pipe code to see what's happening. Shane ... (All my testing was done on an x86 non-virtualized server) ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to lists...@vm.marist.edu with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
