=== zz_bigbash is now known as bigbash | ||
bigbash | ping h00k | 00:10 |
---|---|---|
=== bigbash is now known as zz_bigbash | ||
=== zz_bigbash is now known as bigbash | ||
=== bigbash is now known as zz_bigbash | ||
=== zz_bigbash is now known as bigbash | ||
bigbash | h00k, what processor do you use in your vSphere setup? | 14:09 |
Cheesehead | The EMEA Membership board is meeting at 2000 UTC today (five hours from now) in #ubuntu-meeting. Anyone who wants to support (or oppsose) my Ubuntu Membership application is welcome! | 15:09 |
bigbash | Cheesehead, at 2CT or 3CT? | 15:53 |
Cheesehead | bigbash: 2PM CST | 16:53 |
bigbash | ok sounds good | 16:54 |
h00k | bigbash: oh hi | 20:23 |
bigbash | hi | 20:23 |
h00k | shooot, I was late. | 20:24 |
h00k | I don't think there'll be any issues | 20:24 |
bigbash | I don't think so | 20:25 |
bigbash | lots to vouch for him | 20:25 |
bigbash | Congrats Cheesehead!! | 20:25 |
h00k | Cheesehead: congrats! | 20:25 |
Cheesehead | Thanks everybody! | 20:25 |
Cheesehead | Wait...I said that in the other channel. | 20:25 |
Cheesehead | Thanks FOR TAKING THE TIME TO COME BY! | 20:26 |
Cheesehead | Thanks for your testimonials and efforts. | 20:26 |
h00k | I'm working from home today | 20:29 |
h00k | bigbash: coincidentally, vmware vcp test tomorrow. | 20:29 |
bigbash | h00k, nice | 20:29 |
h00k | bigbash: we have a pretty nice environment set up, although I wouldn't recommend the Cisco UCS 250's yet | 20:39 |
h00k | there's some firmware issues that need to get fixed. It's first-round hardware :( | 20:40 |
bigbash | ah | 20:44 |
bigbash | sorry helping someone in another channel | 20:44 |
h00k | no prob | 20:45 |
bigbash | you think that 1 host could run 10-20 vm? | 20:45 |
h00k | what are the VMs doing? | 20:45 |
h00k | That's the biggest part, really. | 20:45 |
bigbash | I'm just being super cautious because I have 1 vendor we've worked with forever saying Xeon and the other with the HP engineers saying AMD | 20:45 |
h00k | I am personally an Intel fan, but I really don't have any solid evidence towards one or the other | 20:47 |
bigbash | Webserver, DC/File/Print, Payroll, Accounting, Exchange, and old SNA server to corporate, and a reporting server that has 10 ppl RDP | 20:47 |
h00k | Memory is the biggest thing, really. | 20:47 |
bigbash | that's what it really sounds like | 20:47 |
h00k | bigbash: cool, with that license, you can do HA for things. That's nice | 20:47 |
bigbash | the combined amount of RAM all 7 have is like 40GB | 20:48 |
bigbash | yea the HA is what I was after | 20:48 |
h00k | bigbash: cool. One thing you can do too, to estimate how much 'stuff' you'll need, is turn on PerfMon for a week on your servers and collect data on IOPS | 20:49 |
bigbash | hmmm thats a good idea | 20:49 |
bigbash | EgyParadox, you there? | 20:50 |
EgyParadox | yes | 20:50 |
bigbash | aren't you supposed to be in #ubuntu-meeting? | 20:50 |
EgyParadox | for? | 20:51 |
bigbash | https://wiki.ubuntu.com/Membership/RegionalBoards/EMEA | 20:51 |
h00k | bigbash: and they have guided consolition | 20:52 |
bigbash | nice, I've been plowing through videos and readings getting ready | 20:53 |
h00k | bigbash: http://goo.gl/2sgBg | 20:54 |
bigbash | I've been waiting to change over to virtual | 20:54 |
h00k | :D | 20:54 |
bigbash | down the road we are going to test thin clients but we'll add more hosts at that point | 20:55 |
h00k | bigbash: what are you using for storage? | 20:57 |
h00k | bigbash: also: http://whughgriffin.wordpress.com/2009/10/16/vmware-vsphere-4-guided-consolidation/ | 20:57 |
bigbash | we are using the HP P4300 Starter SAN http://h10010.www1.hp.com/wwpc/us/en/sm/WF06b/12169-304616-3930449-3930449-3930449-4118659-4118705-4118707.html | 21:05 |
bigbash | it's pretty much a full replacment of infrastructure | 21:05 |
h00k | bigbash: cool, we just spec'd out a P2000 G3 for a client | 21:07 |
bigbash | doubt we need the whole 7.2TB | 21:08 |
bigbash | I think we are using about 1.5-2Tb currently | 21:08 |
bigbash | I saw that VMWare Standard Acceleration comes with SLES | 21:09 |
h00k | bigbash: oh, interesting. | 21:10 |
h00k | bigbash: are you doing ESX or ESXi | 21:10 |
h00k | bigbash: also beware that the more virtual processors that you give a virtual machine, it won't necessarily speed it up | 21:11 |
bigbash | if it doesn't speed it up what does it do? | 21:12 |
bigbash | ESXi is the only hypervisor available in vSphere 5 | 21:12 |
h00k | phew, good. | 21:13 |
bigbash | so I guess that is what we are going with | 21:13 |
h00k | I thought so. | 21:13 |
h00k | So, if you give it >1 processor, it can actually slow it down if it wants access to both cores. If you have machines wanting more cores, you can create contention because they're going to want them open at the same time | 21:13 |
h00k | If that makes sense | 21:14 |
bigbash | not exactly but I can read up that part more, so more cores is better for processor then? | 21:15 |
h00k | http://lonesysadmin.net/2008/04/22/why-my-two-vcpu-vm-is-slow/ | 21:15 |
h00k | each core, and if you have hyperthreading, a core will show up as 2 processors | 21:15 |
h00k | for instance, our dual hex cores with hyperthreading show as 2x6x2 = 24 processors available to VMs | 21:15 |
h00k | A two-vCPU virtual machine has to wait for two physical processors to free up, but the hypervisor doesn’t like to have idle CPUs, so it runs a single vCPU virtual machine instead. It ends up being a long time before two physical CPUs free up simultaneously, and the two vCPU virtual machine seems really slow as a result. By “seems really slow” I mean it doesn’t perform very well, but none of the performance graphs show any problems at all. | 21:16 |
h00k | that explains it pretty well. At first it's counterintuitive, but it does make sense | 21:16 |
bigbash | the opterons we are looking at are 12-core, and there will be 2 procs per host | 21:16 |
h00k | I mean, with something your scale, you may not have issues running each VM with 2 cores | 21:18 |
h00k | but if you may grow, know it can/will actually slow things down if they're waiting for 2 cores to be open at the same time | 21:18 |
bigbash | good to know | 21:19 |
h00k | bigbash: I'ma cruise and study, let me know if you have anything I can try to help with | 21:34 |
bigbash | I'm sure I can think of more things :) | 21:34 |
bigbash | So much to learn and play with | 21:35 |
EgyParadox | bigbash: Thank you for notifying me | 22:25 |
bigbash | EgyParadox, sorry I was too late notifying you | 22:26 |
EgyParadox | no its ok :) I didnt know the new date was today | 22:27 |
Generated by irclog2html.py 2.7 by Marius Gedminas - find it at mg.pov.lt!