Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 

Quick Go »
No member browsing this thread
Thread Status: Active
Total posts in this thread: 17
Posts: 17   Pages: 2   [ Previous Page | 1 2 ]
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 13263 times and has 16 replies Next Thread
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

Write in on the CEP2 forum if you see a perceptible change, pretty plz. Already asked for testers on the Alpha list with focus on Linux. The nightlies processed on Windows(64 bit) did a final 99% efficiency... same as before.

--//--
[Feb 12, 2012 10:30:08 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Dark Angel
Veteran Cruncher
Australia
Joined: Nov 11, 2005
Post Count: 728
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

On what hardware? Most of my kit is running on old PATA drives so it's going to suffer straight away. The two I have now were run on an dual socket Xeon system with an old 40GB Seagate PATA drive that's also used as a desktop rig and the efficiency is predictably poor (sub 90%) while almost identical hardware running a server install (also running my network proxy, DNS forwarder, content filter and virus scanner to protect the wife's Windows laptop) and only one CEP2 unit got over 96%. If I had the money to put some decent SATA drives in them I would expect better. I'll stop communication on the two machines with SATA drives and see how they come out tomorrow.

I don't know what these machines were getting before.
----------------------------------------

Currently being moderated under false pretences
[Feb 12, 2012 11:52:15 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

SATA drive internal and an USB 3.0 external TB drive [measured throughput a ludicrous 5Gb... hard to believe that's right]. Anything on Linux hitting > 96-97% with spinning hardware is an appreciable improvement to me.

--//--
[Feb 12, 2012 12:01:13 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Dark Angel
Veteran Cruncher
Australia
Joined: Nov 11, 2005
Post Count: 728
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

Really?
My Q6600 rig (SATA II, Seagate Barracuda) got 96% on one and 96.5% on another overnight, the server install Xeon got a 96.5%, one desktop Xeon got two 97% returns while the other was still 89% (it has very slow old drives but got 99% for C4CW work). The other rig with a SATA drive didn't get to a CEP2 overnight.
----------------------------------------

Currently being moderated under false pretences
[Feb 12, 2012 8:45:36 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

Someone made the odd comment quite some time ago that slow drives was better. Beat me if I ever will comprehend that... data vacuum?

Yes, a Barracuda sits in that Linux [Q6600] box, which under Window 64 bit gives 99%, but no where near under Linux. If that's what you get with 7.0.15 alpha, then there's really no difference with 7.0.11 and before notwithstanding the async large file handling.

--//--
[Feb 12, 2012 8:59:12 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Dark Angel
Veteran Cruncher
Australia
Joined: Nov 11, 2005
Post Count: 728
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

I don't get the slow drive comment either. It doesn't make sense to me.
----------------------------------------

Currently being moderated under false pretences
[Feb 12, 2012 10:25:35 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Dark Angel
Veteran Cruncher
Australia
Joined: Nov 11, 2005
Post Count: 728
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Error from two HCMD2 wus

This might help:
http://blogs.technet.com/b/winserverperforman...performance-analysis.aspx

From point 5:
5. Processor power management (PPM) may cause CPU utilization to appear artificially high

Power management features introduce more complexity to CPU utilization percentages. Processor power management (PPM) matches the CPU performance to demand by scaling the frequency and voltage of CPU’s. During low-intensity computational tasks like word processing, a core that nominally runs at 2.4 GHz rarely requires all 2.4 billion potential cycles per second. When fewer cycles are needed, the frequency can be scaled back, sometimes significantly (as low as 28% of maximum). This is very prevalent in the market - PPM is present on nearly every commodity processor shipped today (with the exception of some “low-power” processor SKUs), and Windows ships with PPM enabled by default in Vista, Windows 7, and Server 2008 / R2.



In environments where CPU frequency is dynamically changing (reminder: this is more likely than not), be very careful when interpreting the CPU utilization counter reported by Performance Monitor or any other current Windows monitoring tool. Utilization values are calculated based on the instantaneous (or possibly mean) operating frequency, not the maximum rated frequency.



Example: In a situation where your CPU is lightly utilized, Windows might reduce the operating frequency down to 50% or 28% of its maximum. When CPU utilization is calculated, Windows is using this reference point as the “maximum” utilization. If a CPU nominally rated at 2.0 GHz is running at 500 MHz, and all 500 million cycles available are used, the CPU utilization would be shown as 100%. Extending the example, a CPU that is 50% utilized at 28% of its maximum frequency is using approximately 14% of the maximum possible cycles during the time interval measured, but CPU utilization would appear in the performance counter as 50%, not 14%.


As a comparison, my Linux boxes are configured with all power management features disabled both in the BIOS and the OS itself. If your Windows box sees the BIONC threads as low enough priority it may well throttle the CPUs (which I've seen happen before). Disabling Speedstep, Cool-n-Quiet, Frequency Scaling, setting Performance scheduling etc stops that and based on the above will report different CPU utilization.
----------------------------------------

Currently being moderated under false pretences
[Feb 12, 2012 10:41:44 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Posts: 17   Pages: 2   [ Previous Page | 1 2 ]
[ Jump to Last Post ]
Post new Thread