Hot answers tagged

3

i've seen this on lenovos. try upgrading the bios as a starter. If you have an SSD, make sure the bios is set to SSD to reflect it, and upgrade firmware for SSD


2

It looks like your motherboard only supports SATA 3Gb/s and so the max transfer rate is about 250MB/s.


2

Your faster stick will downclock to the speed of the slower stick. As the stick you'd be adding is faster than your current one, you won't notice any drawback from this. My usual advice would be to just try it. It won't do any harm and if you did feel it was in any way slower it's a simple job to reverse it.


2

FSB and Northbridge are obsolete technologies. All modern systems work on the basis of a point-to-point interconnect (Intel's QuickPath Interconnect, AMD's HyperTransport etc.) which doesn't have a 'hub' like a Northbridge or a bus with limited global bandwidth as was the case with FSB. This alone reduces the burden on system resources, but the fact that a ...


2

Well all you can get is the list of running processes (Task Manager). All other tools use the same data. Generally you can track processes and check how much CPU time they require, but: 1) Slow response can have a plethora of reasons 2) The fan spiking has not a lot to do with CPU usage I assume it's not a U series i7 but an M, so this is a pretty ...


2

You have it backwards. The most important thing is having the same amount of RAM on each channel.


1

There is no one single good answer to this. It depends a lot on how you use a VM and on which programs. E.g. using VMWare (a type 2 hypervisor) and a purely CPU bound program yielded almost full CPU speed. If I used the same hypervisor an a program with a lot of system calls I would get a serious slowdown. And things alos change when you use a type 1 ...


1

For number-crunching programs (very CPU-bound), there should be almost zero performance hit for the VM. The instructions run directly on the CPU, which is the same for host and VM. Even for serious compilation tasks, the performance difference is hardly noticeable. We run CentOS VMs in VMware on Windows. Since you're running Linux on the host, you might ...


1

On older chipsets (P4 era, some core2duo's) you are right. These are bandwidth starved and integrating a GPU on the same die as the CPU will reduce CPU performance. On more modern systems there no longer is a FSB (see @Lunatik's answer which is very good in that regard) and CPU performance decrease due to shared bandwidth to the memory should be minimal. ...


1

It should come out to ~1 minute and 21 seconds (+- 1 second). to do this: 500 / 8 //calculate the MBps. 8Mbps to a MBps. = 62.5 5 * 1024 //calculate what 5GB is in MB = 5120 5120 / 62.5 //calculate the final seconds amount = 81.92


1

How many minutes should it take to transmit 5GB over a USB2.0 (assume 500 Mbps) Using the Bandwidth Calculator: 90,071,992.5 ns nanoseconds 87,960.9 ms milliseconds 85.9 s seconds (default) 1.4 m minutes


1

Recording the network traffic data takes some time, which results in a slowdown of the page load. Though normally this slowdown isn't that big. Note that the 20ms you measured only refers to the time needed to generate the page script. It doesn't take all the other requests into account involved into the page load, e.g. CSS, JavaScripts, images, etc. I ...


1

The temperature 90° C might be the limit for your GPU where it starts "throttling", i.e. halts for a bit to cool down. Or maybe the CPU using the same heatpipes/sink hits its limit. How high does the CPU temp go? (CPU-Z) and what specific CPU model does that MacBook have? Put something small under the laptop to prod it up giving it more room to breathe or ...


1

About JBOD moosefs.com website says as follows (in "Best practices"): (https://moosefs.com/documentation/best-practices.html#jbod) JBOD and XFS for Chunkservers We recommend to connect to Chunkserver(s) JBODs. Just format the drive as XFS and mount on e.g. /mnt/chunk01, /mnt/chunk02, ... and put these paths into /etc/mfs/mfschunkserver.cfg. ...


1

you would need to reformat the hard disk with the new block size, and then reinstall the OS. The new install is then always slightly different from the current one, so it would be hard to even measurable if there was any gain, in performance as well as in disk space. Any effect would be minimal if at all. If you are really sweating for 1 or 2% space ...


1

You've clearly stated yourself your application is single-threaded and limited by single-core CPU performance. By definition, multi-core processors and hyperthreading won't help. Adding a million cores won't make a program run faster when it can only use one core. The only way to improve single-core application performance is to get a CPU with faster cores. ...


1

You should plug both monitors into the graphics card, as your graphics card is substantially more powerful than the built-in GPU. If they are displaying the same image, this takes almost no additional processing power. It's not remotely clear this is your intention, though, as you say you want to use the monitors for different things. If you aren't ...


1

Assuming there is no hardware failures, then it is most likely software. Two things come to mind. First, go to the manufacturer's website and download all the drivers for the motherboard, chipset, etc. It could be that Windows is using a generic driver that might be slowing it down. Secondly, and less likely, is the CMOS battery has died and the BIOS has ...



Only top voted, non community-wiki answers of a minimum length are eligible