Quantcast
Channel: VMware Communities : Popular Discussions - VMware Server Archives
Viewing all articles
Browse latest Browse all 69891

I/O performance, HT, and other matters

$
0
0

Hi

 

I have a hyperthreading capable P4 (2.8), though HT was disabled in the BIOS for the tests below.  This is a 3 GB RAM system running Ubuntu Linux (6.06.1, clean and minimum install) and VMware server (downloaded yesterday).

 

I also have 4 x SATA disks, though I should say that all disks are on the same PCI bus (33MHz, 32 bit).  The hardware is a Dell Optiplex gx270, for the test below I used the onbaord sata controller.

 

Using LVM I have created various metadevices

 

raid0 over 2 disks (md0) mounted as /raid0

raid1 over 2 disks (md1) mounted as /raid1

single disk partition (sda7) mounted as /noraid

 

On each metadevice I created an ext3 file system, and mounted.  Under each of these mount points I installed another copy of Ubuntu (so 3 VMs in total), each using a 5 GB virtual disk, all pre-allocated and NOT split into 2GB chunks. each VM with 768 MB RAM (kickstart is great for this!).

 

I also enabled the option to disable page trimming, and set useNamedFile=FALSE as suggested by some searching of these forums and elsewhere.  Since everything was "clean" installed I don't expect any fragmentation issues come into play?

 

This is the performance I get on the host, using bonnie++ with following options

 

bonnie++ -r 1024 -s 6g -u root -n0 -f -d /raid0/

bonnie++ -r 1024 -s 6g -u root -n0 -f -d /raid1/

bonnie++ -r 1024 -s 6g -u root -n0 -f -d /noraid/

 

Version  1.03       -


Sequential Output------ --Sequential Input- --Random-

                    -Per Chr- \--Block-- -Rewrite- -Per Chr- \--Block-- \--Seeks--

Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP

host-r0           6G           128192  33 50419  13           138371  16 282.7   0

host-r1           6G           69504  19 32539  10           87986  10 210.7   0

host-noR        6G           65631  17 28854   7           66487   6 199.5   0

 

That performance is about what I expected, the host being able to provide decent I/O throughput.  BUT on the VMs the story was different:

 

bonnie++ -r 1024 -s 2g -u root -n0 -f -d /test

bonnie++ -r 1024 -s 2g -u root -n0 -f -d /test

bonnie++ -r 1024 -s 2g -u root -n0 -f -d /test

 

(of course on each VM /test is actually a virtual disk sitting on top of the underlying host-side metadevices)

 

Version  1.03       -


Sequential Output------ --Sequential Input- --Random-

                    -Per Chr- \--Block-- -Rewrite- -Per Chr- \--Block-- \--Seeks--

Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP  /sec %CP

guest-r0          2G           44231  55 25321  44           72603  69 288.2   3

guest-r1          2G           26306  56  6203  15           23551  19 280.6   3

guest-noR       2G           34266  42 19942  35           57773  49 385.3   3

 

In all cases the performance is significantly poorer (30%-70% poorer), in particular the raid-1 case (the one I actually want to use!) the I/O performance is very poor.

 

Is there anything I can/should do here?  The test scenario seems to fairly accurately match my planned real deployment (1 VM for apache/wiki, one for small scale e-mail server, and one for a samba server), so I'm hopeful to get the best I/O performance I can get from the hardware/software.  Does VMware virtual disks layer introduce such a significant bottleneck into the I/O?

 

Ideas/comments?  As an aside, I'm not sure whether to enable HT or not - might the fact that Linux will "see" 2 CPUs confuse VMware at all?  I did not yet find a definitive recommendation on that.

 

Kevin

 

PS: For the real systems I had planned to use a hardware raid card, and raid5 over all 4 drives (which would be connected to the LSI megaraid card).  But in that case, so far, I have not been able to persuade decent (host-side, nothing to do with VMware) raid5 performance out of the raid card yet ...  I might end up using software raid after all ....


Viewing all articles
Browse latest Browse all 69891

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>