Hello!
I''ve got an interesting performance problem, I''m running Xen
3.1 on a
Dell with 2 x Quad-core 2.33Ghz CPUs, and 4GB RAM. Running UnixBench on
the system without Xen the performance is pretty good, but once running
Xen the performance drops by a large amount.
Any insight into why the score is so much lower with Xen would be
appreciated. (UnixBench scores at bottom)
Thanks,
John
CentOS 5 without Xen
INDEX VALUES
TEST BASELINE RESULT INDEX
Dhrystone 2 using register variables 376783.7 52116444.7 1383.2
Double-Precision Whetstone 83.1 2612.0 314.3
Execl Throughput 188.3 11429.1 607.0
File Copy 1024 bufsize 2000 maxblocks 2672.0 155443.0 581.7
File Copy 256 bufsize 500 maxblocks 1077.0 37493.0 348.1
File Read 4096 bufsize 8000 maxblocks 15382.0 1475439.0 959.2
Pipe-based Context Switching 15448.6 548465.7 355.0
Pipe Throughput 111814.6 3313637.0 296.4
Process Creation 569.3 34050.6 598.1
Shell Scripts (8 concurrent) 44.8 3566.8 796.2
System Call Overhead 114433.5 2756155.3 240.9
========
FINAL SCORE 510.9
CentOS 5 Dom0
INDEX VALUES
TEST BASELINE RESULT INDEX
Dhrystone 2 using register variables 376783.7 50864253.7 1350.0
Double-Precision Whetstone 83.1 2617.9 315.0
Execl Throughput 188.3 2786.5 148.0
File Copy 1024 bufsize 2000 maxblocks 2672.0 159749.0 597.9
File Copy 256 bufsize 500 maxblocks 1077.0 44884.0 416.8
File Read 4096 bufsize 8000 maxblocks 15382.0 1191772.0 774.8
Pipe-based Context Switching 15448.6 306121.8 198.2
Pipe Throughput 111814.6 1417645.2 126.8
Process Creation 569.3 4699.2 82.5
Shell Scripts (8 concurrent) 44.8 781.6 174.5
System Call Overhead 114433.5 1021813.7 89.3
========
FINAL SCORE 261.6
CentOS 5 DomU
INDEX VALUES
TEST BASELINE RESULT INDEX
Dhrystone 2 using register variables 376783.7 38015133.3 1008.9
Double-Precision Whetstone 83.1 2023.4 243.5
Execl Throughput 188.3 3877.4 205.9
File Copy 1024 bufsize 2000 maxblocks 2672.0 270737.0 1013.2
File Copy 256 bufsize 500 maxblocks 1077.0 78470.0 728.6
File Read 4096 bufsize 8000 maxblocks 15382.0 1227115.0 797.8
Pipe Throughput 111814.6 1383157.5 123.7
Pipe-based Context Switching 15448.6 310378.3 200.9
Process Creation 569.3 7534.8 132.4
Shell Scripts (8 concurrent) 44.8 1179.6 263.3
System Call Overhead 114433.5 1056362.3 92.3
========
FINAL SCORE 308.2
_______________________________________________
Xen-users mailing list
Xen-users@lists.xensource.com
http://lists.xensource.com/xen-users
The benchmark I used is called UnixBench. --John jian zhang wrote:> Hi: > I also want to measure the performance of Xenlinux, but I don''t know > which tools to use, would you please tell me which tool you used for the > following results. > Thank you very much!! > > 2007/7/31, John T. Yocum <john@fluidhosting.com > <mailto:john@fluidhosting.com>>: > > Hello! > > I''ve got an interesting performance problem, I''m running Xen 3.1 on a > Dell with 2 x Quad-core 2.33Ghz CPUs, and 4GB RAM. Running UnixBench on > the system without Xen the performance is pretty good, but once running > Xen the performance drops by a large amount. > > Any insight into why the score is so much lower with Xen would be > appreciated. (UnixBench scores at bottom) > > Thanks, > John > > CentOS 5 without Xen > > INDEX VALUES > TEST BASELINE > RESULT INDEX > > Dhrystone 2 using register variables 376783.7 52116444.7 > 1383.2 > Double-Precision Whetstone 83.1 > 2612.0 314.3 > Execl Throughput > 188.3 11429.1 607.0 > File Copy 1024 bufsize 2000 maxblocks 2672.0 > 155443.0 581.7 > File Copy 256 bufsize 500 maxblocks > 1077.0 37493.0 348.1 > File Read 4096 bufsize 8000 > maxblocks 15382.0 1475439.0 959.2 > Pipe-based Context Switching 15448.6 > 548465.7 355.0 > Pipe Throughput > 111814.6 3313637.0 296.4 > Process Creation > 569.3 34050.6 598.1 > Shell Scripts (8 concurrent) 44.8 > 3566.8 796.2 > System Call Overhead > 114433.5 2756155.3 240.9 > ========> FINAL > SCORE 510.9 > > CentOS 5 Dom0 > > INDEX VALUES > TEST BASELINE > RESULT INDEX > > Dhrystone 2 using register variables 376783.7 50864253.7 > 1350.0 > Double-Precision Whetstone 83.1 > 2617.9 315.0 > Execl Throughput 188.3 > 2786.5 148.0 > File Copy 1024 bufsize 2000 maxblocks 2672.0 > 159749.0 597.9 > File Copy 256 bufsize 500 maxblocks > 1077.0 44884.0 416.8 > File Read 4096 bufsize 8000 > maxblocks 15382.0 1191772.0 774.8 > Pipe-based Context Switching 15448.6 > 306121.8 198.2 > Pipe Throughput > 111814.6 1417645.2 126.8 > Process Creation 569.3 > 4699.2 82.5 > Shell Scripts (8 > concurrent) 44.8 781.6 174.5 > System Call Overhead > 114433.5 1021813.7 89.3 > ========> FINAL > SCORE 261.6 > > CentOS 5 DomU > > INDEX VALUES > TEST BASELINE > RESULT INDEX > > Dhrystone 2 using register variables 376783.7 38015133.3 > 1008.9 > Double-Precision Whetstone 83.1 > 2023.4 243.5 > Execl Throughput 188.3 > 3877.4 205.9 > File Copy 1024 bufsize 2000 maxblocks 2672.0 270737.0 > 1013.2 > File Copy 256 bufsize 500 maxblocks > 1077.0 78470.0 728.6 > File Read 4096 bufsize 8000 > maxblocks 15382.0 1227115.0 797.8 > Pipe Throughput > 111814.6 1383157.5 123.7 > Pipe-based Context Switching 15448.6 > 310378.3 200.9 > Process Creation 569.3 > 7534.8 132.4 > Shell Scripts (8 concurrent) 44.8 > 1179.6 263.3 > System Call Overhead > 114433.5 1056362.3 92.3 > ========> FINAL > SCORE 308.2 > > _______________________________________________ > Xen-users mailing list > Xen-users@lists.xensource.com <mailto:Xen-users@lists.xensource.com> > http://lists.xensource.com/xen-users > >_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Any thoughts on this? Thanks, John John T. Yocum wrote:> Hello! > > I''ve got an interesting performance problem, I''m running Xen 3.1 on a > Dell with 2 x Quad-core 2.33Ghz CPUs, and 4GB RAM. Running UnixBench on > the system without Xen the performance is pretty good, but once running > Xen the performance drops by a large amount. > > Any insight into why the score is so much lower with Xen would be > appreciated. (UnixBench scores at bottom) > > Thanks, > John > > CentOS 5 without Xen > > INDEX VALUES > TEST BASELINE RESULT INDEX > > Dhrystone 2 using register variables 376783.7 52116444.7 1383.2 > Double-Precision Whetstone 83.1 2612.0 314.3 > Execl Throughput 188.3 11429.1 607.0 > File Copy 1024 bufsize 2000 maxblocks 2672.0 155443.0 581.7 > File Copy 256 bufsize 500 maxblocks 1077.0 37493.0 348.1 > File Read 4096 bufsize 8000 maxblocks 15382.0 1475439.0 959.2 > Pipe-based Context Switching 15448.6 548465.7 355.0 > Pipe Throughput 111814.6 3313637.0 296.4 > Process Creation 569.3 34050.6 598.1 > Shell Scripts (8 concurrent) 44.8 3566.8 796.2 > System Call Overhead 114433.5 2756155.3 240.9 > ========> FINAL SCORE 510.9 > > CentOS 5 Dom0 > > INDEX VALUES > TEST BASELINE RESULT INDEX > > Dhrystone 2 using register variables 376783.7 50864253.7 1350.0 > Double-Precision Whetstone 83.1 2617.9 315.0 > Execl Throughput 188.3 2786.5 148.0 > File Copy 1024 bufsize 2000 maxblocks 2672.0 159749.0 597.9 > File Copy 256 bufsize 500 maxblocks 1077.0 44884.0 416.8 > File Read 4096 bufsize 8000 maxblocks 15382.0 1191772.0 774.8 > Pipe-based Context Switching 15448.6 306121.8 198.2 > Pipe Throughput 111814.6 1417645.2 126.8 > Process Creation 569.3 4699.2 82.5 > Shell Scripts (8 concurrent) 44.8 781.6 174.5 > System Call Overhead 114433.5 1021813.7 89.3 > ========> FINAL SCORE 261.6 > > CentOS 5 DomU > > INDEX VALUES > TEST BASELINE RESULT INDEX > > Dhrystone 2 using register variables 376783.7 38015133.3 1008.9 > Double-Precision Whetstone 83.1 2023.4 243.5 > Execl Throughput 188.3 3877.4 205.9 > File Copy 1024 bufsize 2000 maxblocks 2672.0 270737.0 1013.2 > File Copy 256 bufsize 500 maxblocks 1077.0 78470.0 728.6 > File Read 4096 bufsize 8000 maxblocks 15382.0 1227115.0 797.8 > Pipe Throughput 111814.6 1383157.5 123.7 > Pipe-based Context Switching 15448.6 310378.3 200.9 > Process Creation 569.3 7534.8 132.4 > Shell Scripts (8 concurrent) 44.8 1179.6 263.3 > System Call Overhead 114433.5 1056362.3 92.3 > ========> FINAL SCORE 308.2 > > _______________________________________________ > Xen-users mailing list > Xen-users@lists.xensource.com > http://lists.xensource.com/xen-users_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Hi Jian, I am running CentOS 5, and didn''t have any problems with my network connection so I just downloaded UnixBench to it directly. You could try mounting the image file in Dom0, and copy over UnixBench. --John jian zhang wrote:> Hi John, > I think this results are not so exact, because the first time I run > unbixbench on my machine, the performance with xen is better that > without xen. So, you can run it again, and DO NOT do other things while > run unixbench. > What kind DomainU you installed on your machine? I used Unixbench to > measure the performance, my results are: > Fedora 6 without xen: > > INDEX VALUES > TEST BASELINE RESULT INDEX > > Dhrystone 2 using register variables 116700.0 4149904.9 355.6 > Double-Precision? Whetstone 55.0 1024.7 186.3 > Execl Throughput 43.0 2331.1 542.1 > File Copy 1024 bufsize 2000 maxblocks 3960.0 236222.0 596.5 > File Copy 256 bufsize 500 maxblocks 1655.0 71599.0 432.6 > File Copy 4096 bufsize 8000 maxblocks 5800.0 550196.0 948.6 > Pipe Throughput 12440.0 501010.4 402.7 > Process Creation 126.0 7753.6 615.4 > Shell Scripts (8 concurrent) 6.0 1012.3 1687.2 > System Call Overhead 15000.0 558716.2 372.5 > =====> FINAL SCORE 517.2 > > Fedora with xen: > > INDEX VALUES > TEST BASELINE RESULT INDEX > > Dhrystone 2 using register variables 116700.0 4441113.2 380.6 > Double-Precision? Whetstone 55.0 1039.3 189.0 > Execl Throughput 43.0 1798.8 418.3 > File Copy 1024 bufsize 2000 maxblocks 3960.0 376698.0 951.3 > File Copy 256 bufsize 500 maxblocks 1655.0 130982.0 791.4 > File Copy 4096 bufsize 8000 maxblocks 5800.0 429981.0 741.3 > Pipe Throughput 12440.0 658735.5 529.5 > Process Creation 126.0 3831.6 304.1 > Shell Scripts (8 concurrent) 6.0 226.0 376.7 > System Call Overhead 15000.0 683112.7 455.4 > ========> FINAL SCORE 464.1 > > > > It seems the difference between my results is much smaller than you. > BTW, I installed domainU in xen by img files, however, my ether net > interface card doesn''t work with DomainU, so I can not run benchmark in > domainU. Can you suggest any other way to run it or tell me how you > installed domainU? > > > > > > 2007/7/31, John T. Yocum <john@fluidhosting.com > <mailto:john@fluidhosting.com>>: > > The benchmark I used is called UnixBench. > > --John > > jian zhang wrote: > > Hi: > > I also want to measure the performance of Xenlinux, but I don''t know > > which tools to use, would you please tell me which tool you used > for the > > following results. > > Thank you very much!! > > > > 2007/7/31, John T. Yocum < john@fluidhosting.com > <mailto:john@fluidhosting.com> > > <mailto:john@fluidhosting.com <mailto:john@fluidhosting.com>>>: > > > > Hello! > > > > I''ve got an interesting performance problem, I''m running Xen > 3.1 on a > > Dell with 2 x Quad-core 2.33Ghz CPUs, and 4GB RAM. Running > UnixBench on > > the system without Xen the performance is pretty good, but > once running > > Xen the performance drops by a large amount. > > > > Any insight into why the score is so much lower with Xen would be > > appreciated. (UnixBench scores at bottom) > > > > Thanks, > > John > > > > CentOS 5 without Xen > > > > INDEX VALUES > > TEST BASELINE > > RESULT INDEX > > > > Dhrystone 2 using register variables 376783.7 52116444.7 > > 1383.2 > > Double-Precision Whetstone 83.1 > > 2612.0 314.3 > > Execl Throughput > > 188.3 11429.1 607.0 > > File Copy 1024 bufsize 2000 maxblocks 2672.0 > > 155443.0 581.7 > > File Copy 256 bufsize 500 maxblocks > > 1077.0 37493.0 348.1 > > File Read 4096 bufsize 8000 > > maxblocks 15382.0 1475439.0 959.2 > > Pipe-based Context Switching 15448.6 > > 548465.7 355.0 > > Pipe Throughput > > 111814.6 3313637.0 296.4 > > Process Creation > > 569.3 34050.6 598.1 > > Shell Scripts (8 concurrent) 44.8 > > 3566.8 796.2 > > System Call Overhead > > 114433.5 2756155.3 240.9 > > > ========> > FINAL > > SCORE 510.9 > > > > CentOS 5 Dom0 > > > > INDEX VALUES > > TEST BASELINE > > RESULT INDEX > > > > Dhrystone 2 using register variables 376783.7 50864253.7 > > 1350.0 > > Double-Precision Whetstone 83.1 > > 2617.9 315.0 > > Execl Throughput 188.3 > > 2786.5 148.0 > > File Copy 1024 bufsize 2000 maxblocks 2672.0 > > 159749.0 597.9 > > File Copy 256 bufsize 500 maxblocks > > 1077.0 44884.0 416.8 > > File Read 4096 bufsize 8000 > > maxblocks 15382.0 1191772.0 774.8 > > Pipe-based Context Switching 15448.6 > > 306121.8 198.2 > > Pipe Throughput > > 111814.6 1417645.2 126.8 > > Process Creation 569.3 > > 4699.2 82.5 > > Shell Scripts (8 > > concurrent) 44.8 781.6 174.5 > > System Call Overhead > > 114433.5 1021813.7 89.3 > > > ========> > FINAL > > SCORE 261.6 > > > > CentOS 5 DomU > > > > INDEX VALUES > > TEST BASELINE > > RESULT INDEX > > > > Dhrystone 2 using register variables 376783.7 38015133.3 > > 1008.9 > > Double-Precision Whetstone 83.1 > > 2023.4 243.5 > > Execl Throughput 188.3 > > 3877.4 205.9 > > File Copy 1024 bufsize 2000 maxblocks 2672.0 270737.0 > > 1013.2 > > File Copy 256 bufsize 500 maxblocks > > 1077.0 78470.0 728.6 > > File Read 4096 bufsize 8000 > > maxblocks 15382.0 1227115.0 797.8 > > Pipe Throughput > > 111814.6 1383157.5 123.7 > > Pipe-based Context Switching 15448.6 > > 310378.3 200.9 > > Process Creation 569.3 > > 7534.8 132.4 > > Shell Scripts (8 concurrent) 44.8 > > 1179.6 263.3 > > System Call Overhead > > 114433.5 1056362.3 92.3 > > > ========> > FINAL > > SCORE 308.2 > > > > _______________________________________________ > > Xen-users mailing list > > Xen-users@lists.xensource.com > <mailto:Xen-users@lists.xensource.com> <mailto: > Xen-users@lists.xensource.com <mailto:Xen-users@lists.xensource.com>> > > http://lists.xensource.com/xen-users > > > > > >_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users