1 |
On Thursday 21 July 2011 21:08:49 Albert Hopkins did opine thusly: |
2 |
> > "When a linux machine hits swap, it does so very aggressively, |
3 |
> > there is nothing nice about it at all. The entire machine slows |
4 |
> > to a painstaking crawl for easily a minute at a time while the |
5 |
> > kernel writes pages out to disk, and disk is thousands of times |
6 |
> > slower than RAM. |
7 |
> > |
8 |
> > |
9 |
> |
10 |
> This is not entirely true. There's regular swapping and there is |
11 |
> "thrashing". |
12 |
|
13 |
Yes, thrashing is the correct word for what I described. |
14 |
|
15 |
I very seldom see swapping happen as one expects swap to be used, it |
16 |
almost always becomes thrashing shortly thereafter, and we do monitor |
17 |
our machines closely at work. |
18 |
|
19 |
That's what I've observed and it's not a large data set so I could be |
20 |
completely wrong. |
21 |
|
22 |
|
23 |
-- |
24 |
alan dot mckinnon at gmail dot com |