General :: How To Mitigate The Multi-core "performance Penalty"
Aug 20, 2010
I've been doing some computations at home and at work and have noticed some unexpected performance issues. The work machine is quite a bit more "serious" than the home machine, but sometimes the home machine outperforms the work machine. I'm curious what the dynamic is -- why this should be, and if I can tweak it at all.
Ultimately on both machines the computations are just a lot of very large arbitrary-precision integer linear algebra computations (based on the GNU multi-precision library). Reducing a lot of sparse but "large" integer matrices, finding the vertices on the boundary of high-dimensional polyhedra, and so on.
On my home computer (which has two cores), if I run a standard computation on only one core (the 2nd core near-idle), it takes 282s.
On the home computer running two identical parallel computations (the same computation as above), it takes approx 320s on each core.
On my office computer, with all cores essentially idle except for one core running this computation, it takes 196s.
On my office computer, if I have all 8 cores running full-out, and one of the cores is doing the computation above, it takes 356s on the one core that's running the computation.
Here are the details on my home computer:
View 2 Replies
ADVERTISEMENT
Nov 11, 2010
I have installed OpenSuse 11.3 32 Bit in a virtual machine on an older computer on a Windows XP host and on a new computer with AMD Phenom II X4 965 processor.
With sysbench I tested the performance of mutex and on the new computer it is 3 - 4 times slower than on the virtual machine. Other performance tests with sysbench for CPU, memory and threads are faster on new computer like expected. I tested this, because I have a slower performance of table creation in MySql tested with sql-bench, where creation of 10000 tables lasts 45 seconds on the virtual machine but over 400 seconds on the new computer.
I have tested with kernel-desktop and kernel-default but there are not large differences. File creation was tested with bonnie++ and is on newer computer faster as expected.
My questions are:
- Why is the mutex handling on the multi core CPU slower than in the virtual machine and how to speed up this?
- Or is there another reason why table creation of MySql is so much slower on multi core CPU?
View 7 Replies
View Related
Mar 27, 2011
I have a command line OCR program called OCR Shop XTR (Vividata corp) that I am using on a system with a 6-core AMD chip. I changed the bios so that the 6-cores were activated, but htop shows me that while the program is running, I am only getting activity on one core (the program maxes out the one core with consistent usage between 97% and 100%).
I have read that many programs are not written to take advantage of multiple core cpu's. However, I am just hoping that there is some way to get this program to take advantage of the extra cores. Does anyone know of a way to invoke programs from the command line which would spread the workload out among additional cores?
Here is the output of uname -a:Linux linux 2.6.37.1-1.2-desktop #1 SMP PREEMPT 2011-02-21 10:34:10 +0100 i686 athlon i386 GNU/LinuxAnd here is the output for one of the cores from cat /proc/cpuinfo:processor : 5
vendor_id : AuthenticAMD
cpu family : 16
model : 10
model name : AMD Phenom(tm) II X6 1100T Processor
stepping : 0
[Code].....
View 5 Replies
View Related
Oct 31, 2010
Is there any Linux API that will let me control on what core will a thread run? If not, do I have to use assembly language?
View 2 Replies
View Related
Sep 12, 2011
Im running 64bit centos 5.6 and using virt-manager.On one of my guest OS's, Windows 7, The max Physical CPUs is 2, you can have unlimited CPU Cores however. (like my machine i use for work has 1, 4 core processor).The issue im having is xen only allows you to set the vcpu arguemnet in your xen config file. How can i set it so that 1 CPU has several Cores just as windows would recognize this machine if i were installing directly to the hardware vs via a VM.Ive searched for 2 days staright trying to address this issue, very little progress, Does anyone know where a XEN support forum is? all i get is the citrix xen support forums.
here is the best info i have found on this, but i dont know how to change this for my CPU to work, when i enter this in my xen config it essentially ignores it and just takes the value of vcpu= so windows shows 2 CPUs each with ONLY one core. Id like 1 or 2 CPUS showing Several cores.The physical Hardware is 2x Xeon 5300 Quad Core CPUs.
> # Expose to the guest multi-core cpu instead of multiple processors
> # Example for intel, expose a 8-core processor :
> #cpuid=['1:edx=xxx1xxxxxxxxxxxxxxxxxxxxxxxxxxxx,[code]........
View 3 Replies
View Related
Sep 9, 2011
I need to set the CR4.MCE bit for all the cores on my system (4). I'd like to write a linux kernel module for that, but I am not sure how to proceed: How do you sequentially access all of the CR4 registers? I have read the Intel manuals and they describe a way to initialize each core, but this is done in the bios.
View 2 Replies
View Related
May 18, 2011
So I have built a program that takes a picture from two cameras every second and converts them both to jpeg format. The problem is that currently it takes ~2 seconds to convert a single raw photo to jpeg format, thus every second I add another raw photo (30 MB) to ram waiting to be converted to jpeg. So, theoretically the conversion to jpeg is running on a single core with hyperthreading, would I see better performance running the exact same process (a program pulling from a queue and converting to jpeg) running as a single process, or two concurrent processes? (both processes running on the same core, (so 1 thread on one clock cycle, the other on the other... (or one thread running on 1 core and the other on another core. What other steps would you take to improve the performance so there would no longer be a race condition?
-Currently using QT
View 5 Replies
View Related
Jun 30, 2011
I have a multi-threaded app using pThreads that runs great under Windows on my 4 core machine - all four cores get maxed out processing parts of a large file. I recompiled the same code to run on Red Hat linux on a 64 CPU machine - but from I can tell when it runs - it gets stuck on one core. "mpstat -P ALL" shows the cores are barely loaded. I have tried sched_affinity, sched_priority and SCHED_FIFO - nothing has helped. Any ideas on getting more performance?
View 14 Replies
View Related
Mar 13, 2009
Many people have multi-core cpus supporting frequency scaling now, if you want to see if the workload is being evenly distributed then add as many CPU Frequency Scaling Monitor applets to the Gnome panel as you have cores/cpus. Then right-click each one and select preferences and choose which cpu to monitor.
Now compile a large program or run a cpu intensive game and watch how the workload dances around between the two (hopefully)
Some clever apps like gnome chess will multi-thread and make max use of both cores, sadly many others won't.
View 9 Replies
View Related
Sep 14, 2009
I've tried searching the forums / google and haven't been able to come up with anything... in Debian-based distros there's an option that can be set to allow boot concurrency so that multiple processor cores can be used for the boot process. Windows also has an option similar to this to specify how many processor cores to use for boot.
Is there an option for multi-core booting in Fedora?
View 1 Replies
View Related
Apr 11, 2011
I have written a simple script which has to find required patterns from a bunch of files ( where each file is around 2 GB each,which contain the output of seq 1 10000000000000) on an 8 core machine.I am current forking 6 child processes which run simultaneously on 6 cores of the processor & have to search for the required pattern in 6 different files & inform the parent process when a pattern is found using a PIPE.
The problem is,when a child process is done reading a text file looking for a pattern,it is becoming a zombie process.It exits cleanly when i put a $SIG{CHLD} = "IGNORE"; in the script.Can any one tell me whats going on & how do i improve the communication between child and parent processes?
Code:
#!/bin/perl
use strict;
[code]...
View 3 Replies
View Related
Feb 19, 2010
In my Open-Suse server I have a script, where makepasswd output(by default it generates similar passwords: cGyTbqpr, tpJ1LA, 33EXdo) is redirected to mkpasswd(which uses DES by default) in order to generate salted hash of this previously generated password. I would like to test the strength of this system. I have a quad core CPU, and if I start John The Ripper like this(I want to use -incremental:all flag):
john -incremental:all passwd
..only one core is utilized at 100%. Is there a possibility to make all four cores to crack this password? Or is this possible only after reprogramming John The Ripper? Or what is the algorithm for generating passwords with with -incremental:all flag? I mean if John generates passwords randomly in brute-force mode, then it's smart to start four different John processes simultaneously because then one of those four will find the password firs
View 2 Replies
View Related
Jun 17, 2011
Is there any performance penalty from running the service cpuspeed? On my desktop FC 15 machine, /proc/cpuinfo shows the Athlon dual core processors running at 1000 MHZ when cpuspeed is running and 2000 MHZ when the service is stopped. Does the processor automatically "know" when it needs to speed up?
View 1 Replies
View Related
Mar 14, 2011
I recently read in a forum that by default the Linux kernel only activates one of two cores in a dual core processor. Searching online gave one option to find out and that was the mpstat command. I therefore ran the command and got the following output.As the result says, it shows only 1 cpu. I was wondering what I could do to activate both cores in my machine, and whether doing so was going to cause me any problems.
View 14 Replies
View Related
Jan 25, 2011
I will be relocating to a permanent residence sometime in the next year or two. I've recently begun thinking about the best way to implement a home-based network. It occurred to me that the most elegant solution might be the use of VM technology to eliminate as much hardware and wiring as possible.My thinking is this: Install a multi-core system and configure it to run several VMs, one each for a firewall, a caching proxy server, a mail server, a web server. Additionally, I would like to run 2-4 VMs as remote (RDP)workstations, using diskless workstations to boot the VMs over powerline ethernet.The latest powerline technology (available later this year) will allow multiple devices on a residential circuit operating at near gigabit speed, just like legacy wired networks.
In theory, the above would allow me to consolidate everything but the disklessworkstations on a single server and eliminate all wired (and wireless) connections except the broadband connection to the Internet and the cabling to the nearest power outlets. It appears technically possible, but I'm not sure about the various virtual connections among VMs. In theory, each VM should be able to communicate with the other as if it was on the same network via the server data bus, but what about setting up firewall zones? Any internal I/O bandwidth bottlenecks? Any other potential "gotchas", caveats, issues? (Other than the obvious requirement of having enough CPU and RAM).Any thoughts or observations welcome, especially if they are from real world experience in a VM environment. BTW--in case you're wondering why I'm posting here, it's because I run Debian on all my workstations/servers (running VirtualBox as a VM for Windows XP on one workstation).
View 14 Replies
View Related
Mar 26, 2011
I've a program that launches new processes, and wait for them to die before it exits. So, for example, my program is a process, and it launches 3 more processes, and when the 3 child processes end, it will exit.
As you see, at end of the example, the program used a total number of 4 processes.
1 - Now, I'm running this program in a CPU with 4 cores. This means that the program used each core for each process?
2 - How can I know which core the program used?
View 1 Replies
View Related
Jun 24, 2011
I have an ATI Radeon HD 3300 on-board video chipset, and an ATI Radeon HD 4350 PCI card. What I want is to have both displays available from one mouse/keyboard. I want to play media on one and have the other as my main desktop.The problem is that with Xinerama enabled, KDE desktop effects do not work (KDE says XComposite and XDamage are not available, even though I explicitly enabled them as extensions in the xorg.conf file), and performance is quite bad. Without Xinerama enabled, performance is great, desktop effects work great, but there's a lot of trouble with full-screen video, and the KWin window manager does not apply in the second display (although I can run a second instance of KWin on :0.1).
View 2 Replies
View Related
Mar 21, 2011
Anyone successfully using VNC client on a Mac to control a Debian server?I have the vncserver setup on the Debian machine properly. But I'm having problems connecting to it from both a PowerMac running Tiger and a MacBookPro running leopard.I can connect no problem from a machine running Slack12.2, have not setup port forwarding on my router to connect remotely yet.My Debian machine is running the latest stable release of squeeze with KDE4.I originally tried this with RealVNC Enterprise for OSX but I'm not gonna buy it so I need another alternative after the 30 day trial ends as they have no free version for OSX.
The situation is that I do freelance graphic design on the PowerMac with Cinema4D and Photoshop so I spend most of my time on that machine which is located in my home studio in my attic. Aside from the MacBook and a Dell desktop(family machine)all my other machines and network hardware are in the basement. So to go from the attic to the basement everytime I need to do something on another machine is not practical, and the only other machine I need to access on a regular basis is the Debian box in the basement, this makes the most sense.
I also have a 14 year old living in the house and he's fascinated by all this and will meddle in anything he gets the chance to so all the Linux machines and network hardware need to be behind lock and key.
View 6 Replies
View Related
Jul 31, 2010
I just wanted to know if having my laptop set to ondemand, will this affect performance in any way? I realize it increases the clock speed to performance when the CPU is under load, but does the time it take to go from ondemand to performance affect speed? Will there be any noticeable difference between the two setups? I have a dual core intel at 2.2GHz when in performance. When ondemand is set with no load it downclocks to 800Mhz.
View 7 Replies
View Related
Sep 17, 2010
Now that Ubuntu 10.04 has multi-touch capabilities built-in, if I do not have a multi-touch screen or surface device, can I get 2 USB mice and get 2 pointers on the screen? One for the right hand and one for the left hand as I am ambidextrous, and would find it very convenient to have 2 mice.
View 4 Replies
View Related
Apr 1, 2011
i am running gigabyte GA-M68M-S2P and AMD sempron 2.7. the problem is when i try to run dual core. it will boot and run for 2mins then it crashes. single core runs perfect.
View 6 Replies
View Related
Nov 3, 2010
I just loaded F14 on an old Dell Dimension 3000 with a dual core processor but only one is showing. Here's the output from top:
processor: 0
vendor_id: GenuineIntel
cpu family: 15
model: 4
[Code]....
View 2 Replies
View Related
Feb 14, 2010
Just a quick question. Does Kubuntu Karmic support core 2 E8500 out of the box or do you need the SMP kernel?
View 3 Replies
View Related
Jan 12, 2011
I am in school for my CIS degree and the book I am using this session covers Windows XP and Fedora Core 4. I am having trouble finding & downloading Fedora Core 4. My question is: Is there a big enough difference between Fedora Core 4 and Fedora Core 14 that I would not be able to use 14 instead of 4?
View 14 Replies
View Related
Sep 7, 2011
I have now installed Wheezy on two different hard drives and in each case it seems only one CPU of my dual core CPU computer is recognized. System Monitor, Gkrellm and lscpu show just one when prior to the new install the old Wheezy showed both CPU's. I have put the hard drive into two other computers with dual core CPU's and all show just one CPU.
Interestingly System Profiler and Benchmark (hardinfo?) > Devices > Processors now show a large amount of processor infomation when with the old Wheezy I would only see both CPU's listed and nothing else.
View 14 Replies
View Related
May 15, 2010
I've a Compaq CQ61 laptop, and i noticed that one of the cores is always at 100%.
I didn't check the duration of the battery but surely it will "eat" my battery in a hurry
View 1 Replies
View Related
Apr 27, 2010
Assume someone bind a particular process to a particular CPU core(In multi core machine) by using sched_setaffinity() like functions. Then how we can get that process running core id and CPU core utilisation of that process on that running CPU core(Pragmatically or by a Linux command)?.
View 5 Replies
View Related
May 20, 2009
I have created a virtual machine of a system running Fedora Core 4 and I need to upgrade it to Fedora Core 10. Based on what I have read, it iis possible so I started theupgrade process. I get an error message saying that /dev/hda6 (my root paritition does not exist) even though it does.
Does the installer need to read a label from /etc/fstab? I executed tune2fs -L / /dev/hda6 amd ,and added LABEL=/ for the corresponding entry for fstab. but the FEDORA CORE 10 is still giving the same problems for the installation process. Should I upgrade to an intermediate verson like Fedora Core 7 first?
View 14 Replies
View Related
Oct 7, 2009
I want to generate core dump files from my program when it crashes. Its a pretty big process and has about 10-11 threads in it.I have followed the documentation to enable core dump by setting ulimit to unlimited etc. I quickly tried "A demo program creating a core dump" from the following webpage, which succeeds in Segfault and dumping a core file in the directory that I configured.However, I tried running my original program and caused it to crash. I did this by making calls to kill(), raise() or the same null pointer access as shown in the webpage above. In each case, my program crashed but did not generate a core dump file. Am I missing something?My program is in C++ and my environment is Redhat 9.0 (kernel 2.4.20)
Going through the "Why do I NOT get a core dump?" section on the same webpage as above, I can see two potential problems. One - there are issues with the suid/sgid (bullet # 6). I am not able to change any settings with suid because my system does not contain either /proc/sys/fs/suid_dumpable or /proc/sys/kernel/suid_dumpableTwo, my program has threads in it and the bullet # 8 is the problem.
View 1 Replies
View Related
Jan 27, 2010
We have a small cluster of 20 HP systems, all running CentOS 5.3 in an NFS-root environment. Half are quad-socket, quad-core Xeon E7340 @ 2.40GHz (total 16 cores), the other half are 8-socket, quad-core Opteron 8354 (total 32 cores). All systems have a Mellanox Infiniband adapter ("Mellanox Technologies MT25418 [ConnectX VPI PCIe 2.0 2.5GT/s - IB DDR / 10GigE] (rev a0)")
With kernel 2.6.18-128.1.6.el5, infiniband works fine on all systems.
With the update to kernel 2.6.18-164.11.1.el5 (and both types of node running the same NFS-root image), the 16-core Xeons still work fine. Infiniband no longer works on the 32-core Opterons. Specifically, either the ib0 interface fails to appear, or it does appear but when configured with an IP address, doesn't actually work. In either case, loading the IB kernel modules takes a long time, but I haven't instrumented the load script yet to see which module, if any, is at fault. More errors listed below.
However, if I tweak the BIOS of the 32-core systems to reduce the per-socket core count to 2 (so effectively 8-socket, dual-core, down to a total of 16 available cores), Infiniband starts working again. Putting it back to 32-cores makes it fail. Booting the older kernel makes it work again. In summary: old kernel, IB works on all systems. Newer kernel, IB only works on 16-core systems.
Updating the IB firmware from 2.5.0 to 2.7.0 (latest available) doesn't help. I also did a full 'yum update' to make sure that libmlx4, openibd all other associated packages were up-to-date. Doesn't help either.
Some errors that appear on 32-core nodes:
ib_query_port failed (-16) for mlx4_0
ib_query_port failed (-16) for mlx4_0
mlx4_core 0000:04:00.0: SW2HW_MPT failed (-16)
mlx4_core 0000:04:00.0: SW2HW_MPT failed (-16)
[Code]....
View 5 Replies
View Related
