On 23 Jan 2002, Momchil Velikov wrote: > William> Q1: what takes the most time during boot? > William> A1: inefficient userspace initialization > William> but worse yet, firmware stuff > > We don't (re)boot :) I think you both have different target systems in mind here, i can see William's concern for it especially for embedded devices. > William> Q2: what takes the most time during application startup? > William> A2: disk accesses I wouldn't really blame disk access for that one, unless your program requires a great amount of it's core in memory, loading at page fault saves us a lot here. Now if only we had page fault readahead... > William> A1 and A2 have some impact on what could perhaps be considered > William> important (to some people) aspects of performance. For instance, > William> boot times contribute to some rather large latencies important > William> to clustering folk. I don't see how boottimes will help you here, unless the box takes aeons to boot, 1minute and 5minutes are essentially the same thing. > "Using a cluster to hide the fact that the underlying systems crash > regularly is an extremely dangerous way to manage a computing > environment." > > -- Matt Dillon Was this by any chance in reference to Microsoft's clustering software? > Defragmentation may result as a side effect of online logical volume > resizing effort. Once again, this is more for the enterprise market. Cheers, Zwane Mwaikambo -- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ IRC Channel: irc.openprojects.net / #kernelnewbies Web Page: http://www.kernelnewbies.org/
