> given a swap in-swap out value, an average amount of dirty memory
> pages, is there a formula to calculate the effective page fault
> service time?

> It certainly seemed, even at the time, that HP's management were great
> believers in silver bullets for software problems. A few years earlier
> HP's then-president John Young had commented that though software
> advances had not kept up with hardware evolution lately, they expected
> the software problem would be "largely solved" in the next few years.

> By the way,the first I disk on which I stored data, held If I remember
> correctly about 35 megabytes on multiple (perhaps 10) 14 inch diameter
> platters packaged into a single removable disk pack. This was used in a
> drive that was about the size of a top loading clothes washer. By the
> time I got into the storage industry, we were supplying drives with 300
> MB capacity on the same sized disk packs. I think we paid about $15,000
> for the disk drive, to which we added our designed controller. A
> typical system supplied to the end user customer might be 10 drives and
> two controllers. This was long before SCSI, etc.

> This is not from IBM or about mainframes. But I think it will be of
> interest to the readers here. It is from Sun about "Transactional
> Memory" and how that it can be used to more easily implement
> threadsafeness and multiprocessors.
>
>
> Transactional memory appears to be the key to unlocking the full
> potential of next-generation chip multiprocessing (CMP) technologies and
> accelerating both their performance and their adoption. It could also be
> a core enabling technology for the massively powerful terascale and
> petascale computing systems now on the drawing boards of advanced
> research labs and government agencies. Why? Because transactional memory
> can solve a very serious problem in software engineering-a problem...