> the silly rule of 2x size of RAM == swap space came from the old days > when memory was 10x the costs of disks or some silly cost performance > that it made sense when grandpa was floating around ram is currently about $.1/MB, and disk is about $.0004/MB, so there is still a good reason to put idle pages onto swap disks. > by todays ram and disk pricing ... and cpu speeds ...2x memory sorta > goes out the door no. the cpu-speed argument is based on the fact that disk latencies are improving quite slowly, compared to ram latency (which is itself falling drastically behind cpu speeds.) this assumes that the argument for swap depends on swap latency, which it doesn't: swap pages are, ideally, *NEVER*READ*! the whole point is to choose anonymous pages which are so idle that they won't practically ever be touched. you *could* argue that the fraction of pages which can be profitably swapped is decreasing because "hot" items in memory are larger. it would be interesting to find out if that's true. certainly if only a few percent of ram is being used by idle anonymous pages, swapping has become irrelevant. - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
