Adding 16GB RAM - Measuring performance increase?

[cube]

But it is the instant rate, and more accessible for most people.

I agree that the instant rate is theoretically more important, but who has the time to watch it all day and know when/what is causing page outs? Mostly when I look at instant rate it is zero.

If you restart the computer (reset page outs)...use it....and next day have a few Gb of page outs, then you need more RAM, though you may not know what app or usage was causing it.

No, you start your test workload and watch at the instant rate while running it.

The sampling of top, you can parameterise.

Pages are easier to read than MB/s.

No one here ever mentioned the instant rate regarding Activity Monitor usage.

 

[talmy]

top shows the number of pages in the sampling period, not MB/s.

Can't find what the sampling period is. If it is 1 second and the page size is 4096 bytes (which it appears to be) then the value would be in units of 4KB/s. Still analogous to and needlessly complicated from the display of Activity Monitor. I only use top when checking up on a remote system via ssh. For a command line program it is nicer than using vm_stat and ps. But none are as friendly as Activity Monitor.

 

[cube]

Can't find what the sampling period is. If it is 1 second and the page size is 4096 bytes (which it appears to be) then the value would be in units of 4KB/s. Still analogous to and needlessly complicated from the display of Activity Monitor. I only use top when checking up on a remote system via ssh. For a command line program it is nicer than using vm_stat and ps. But none are as friendly as Activity Monitor.

Well, I think I never noticed that MB/s display because it is always 0.

top, on the other hand, I can see pages passing by.

 

[talmy]

Well, I think I never noticed that MB/s display because it is always 0.

top, on the other hand, I can see pages passing by.

Probably because it is 250x more sensitive? But you won't feel the burden of such small amounts of paging. Even 1 MB/s might hurt performance by 1%.

 

[Mike Boreham]

No, you start your test workload and watch at the instant rate while running it.

The sampling of top, you can parameterise.

Pages are easier to read than MB/s.

No one here ever mentioned the instant rate regarding Activity Monitor usage.

I can see that Top provides much more capability to really analyse and understand what is happening, by people who are sufficiently expert to set it up use it and understand the results (not me). Just launching Top in Terminal doesn't seem to tell you much more than Activity Monitor.

As a simpler check...do I need more RAM?....a high number cumulative pageouts in a known (short) period is pretty good indicator.

BTW I mentioned instant rate in Activity Monitor in post # 48.

 

[cube]

BTW I mentioned instant rate in Activity Monitor in post # 48.

That is very rare here in MacRumors.

 

[Big Stevie]

My previous screenshot photos arent displaying as ive exceeded my photobucket bandwidth.

But ive just installed the 16GB RAM and heres how its looking..


With previous 4GB RAM...

With current 16GB RAM..