tag:blogger.com,1999:blog-3155908228127841862.post7539787298480977530..comments2023-06-28T10:04:44.463-06:00Comments on The Perils of Parallel: How Hardware Virtualization Works (Part 1)Greg Pfisterhttp://www.blogger.com/profile/12651996181651540140noreply@blogger.comBlogger16125tag:blogger.com,1999:blog-3155908228127841862.post-3887630445041477332012-01-03T02:35:18.900-07:002012-01-03T02:35:18.900-07:00My name is Matt and I work for Dell. There are a l...My name is Matt and I work for Dell. There are a lot of great comments happening on this blog. Thank you so much for the information.server virtualizationhttp://content.dell.com/uk/en/enterprise/virtualization.aspxnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-26455424215928921072010-07-16T10:06:49.861-06:002010-07-16T10:06:49.861-06:00The Intel comparison looks as if it probably invol...The Intel comparison looks as if it probably involved very little disk I/O. The machines had 128 GB of RAM, and the database size was only 27 GB.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-17720951029389212062010-07-14T20:21:41.657-06:002010-07-14T20:21:41.657-06:00And, speak of the devil, we now have SPECvirt_sc20...And, speak of the devil, we now have SPECvirt_sc2010. It takes an interesting approach.<br /><br />http://www.spec.org/virt_sc2010/docs/SPECvirt_FAQ.htmlGreg Pfisterhttps://www.blogger.com/profile/12651996181651540140noreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-56587572033599522062010-07-13T22:36:11.212-06:002010-07-13T22:36:11.212-06:00Raj,
FYI, Intel just published a comparison of na...Raj,<br /><br />FYI, Intel just published a comparison of native & virtual servers running SQL stress tests in the most recent issue of their "Intel Software Dispatch" mag. Here's the URL I end up at. Not sure if it will work for you, but you can Google the mag:<br /><br />http://a676.g.akamaitech.net/f/676/773/1d/images.delivery.net/cm50content/intel/software/e-alert2/Insight21.pdfGreg Pfisterhttps://www.blogger.com/profile/12651996181651540140noreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-74899934743619815532010-07-13T16:38:48.219-06:002010-07-13T16:38:48.219-06:00Ah, yes; I'd thought about wanting to use a si...Ah, yes; I'd thought about wanting to use a single VM on a host just for the management side of things, but couldn't think offhand of any particular management things that would be helpful.<br /><br />As for trying to get as many hosts as possible on a server (i.e., to optimize as much as possible your resource utilisation), well, "clown" computing is a good term for it. There are two issues there, of course. The first is that the extra savings in going from twenty machines to three machines instead of twenty machines to four machines is a pretty minimal saving. The second is that I've dealt with situations where you're trying to run "near the edge" of maximum performance and doing that is usually rather insane because in most cases the failure modes are catastrophic rather than gradual. As you know, it's like delaying one train by a minute on a busy subway: everything behind it backs up, and recovery can take hours. (The classic situation I've seen is having a service run so close to maximum memory utilization that a burst in the offered load drives the host into swap, often "wedging" the host for tens of minutes.)Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-37599751875808710102010-07-12T20:38:18.051-06:002010-07-12T20:38:18.051-06:00Good to hear about your experiences, Curt.
I'...Good to hear about your experiences, Curt.<br /><br />I'd point to two cases where virtual IO efficiency does matter, though --<br /><br />- Clown computing. That's where you pack so many virtual machines in a single physical server that... you get the idea. People will do that.<br /><br />- Database servers on the back end. You might do that native, but: <br /> (a) doing it virtual will present a more uniform management interface, given that everything else is likely virtual;<br /> (b) it may be convenient to be able to use VMotion, moving the VM to another machine, to avoid planned outages (one of the most frequent kinds of outage).<br /><br />GregGreg Pfisterhttps://www.blogger.com/profile/12651996181651540140noreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-11929315826086742132010-07-12T17:42:54.385-06:002010-07-12T17:42:54.385-06:00I've done a few rough performance checks of di...I've done a few rough performance checks of disk and network I/O from time to time on some of my virtual machines. Xen disk I/O and KVM's network and disk virtio run at something close enough to native speed that it's not been worth checking it further. Surprisingly (to me, anyway), even KVM's emulated IDE disk I/O was very fast. (Virtio for disks under KVM is unfortunately not yet stable, and can lead to data loss--see the Ubuntu and KVM bug databases for details.) Note that my tests were going through a lot of OS code (e.g., filesystems and so on), and so that overhead was quite possibly drowning out any differences. <br /><br />However: I suspect that in most uses of virtualization, performance makes very little difference, so long as it's not truly awful. In the corporate world, at least, servers tend to be quite under-utilized.<br /><br />If you are running an application pushing a server to its limits, you might just as well use native mode anyway, since moving more stuff on to an already fully-loaded server doesn't make much sense.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-67461101869375685842010-07-12T12:12:06.716-06:002010-07-12T12:12:06.716-06:00Hi, Raj.
The pickings are quite lean, I'm afr...Hi, Raj.<br /><br />The pickings are quite lean, I'm afraid. I know of no standard benchmarks, and in fact very few public measurements at all at this point. Mostly there are statements in white papers about "near native" performance for SR-IOV (see last part of the sequence of posts). This may well be true, and I think it certainly can be, but the proof's not there.<br /><br />But here are a couple of links to one-off trials that show about 2X performance between SR-IOV on vs. off:<br /><br />http://bit.ly/cFjuHG<br />http://bit.ly/9PpCCv<br /><br />And here's one with more cases, but since it's about IBM System i SAN volume controllers, it's pretty much a niche:<br /><br />http://bit.ly/acEjj5<br /><br />If anybody else knows of others, I'd be obliged for links, myself!<br /><br />Thanks for commenting,<br /><br />GregGreg Pfisterhttps://www.blogger.com/profile/12651996181651540140noreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-59533482110494863432010-07-12T01:50:19.970-06:002010-07-12T01:50:19.970-06:00Hi Greg,
Is there some study done from a I/O thro...Hi Greg,<br /><br />Is there some study done from a I/O throughput or Network latency perspective on a standard set of applications running in multiple servers as against running in multiple guest operating systems on a VM ? Can you please share some details on this ?Rajnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-34425601619901866852010-07-01T01:36:48.198-06:002010-07-01T01:36:48.198-06:00Perhaps one of the things that's not entirely ...Perhaps one of the things that's not entirely clear here to those without a lot of sysadmin experience is that in larger installations servers are typically partitioned as much or more based on role (in relation to various administrative [both engineering and administrative] and security concerns) as they are server load.<br /><br />"A new project gets its own server" is a pretty typical procedure in many organizations, for example, even if a dozen of the smaller projects could be run off just one server. This can be due to ownership and budget issues, compartmentalization between projects, or many other reasons.<br /><br />I personally run five hosts on my home Internet connection, since it helps greatly in dealing with security issues. (I don't have to worry about having other shell users on my mail server, for example, and I can split applications based on whether they have a greater need to come up unattended or be resident on an encrypted filesystem.) Being able to do this on one box instead of five saves me a considerable amount in hardware and power costs.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-25658922794454337692010-06-28T18:39:09.065-06:002010-06-28T18:39:09.065-06:00Thanks!
To answer your question:
One virtual mac...Thanks!<br /><br />To answer your question:<br /><br />One virtual machine will not better utilize a single processor (or system).<br /><br />The idea is that you consolidate several virtual machines onto one physical machine. <br /><br />Typical commercial server utilization is around 12%, so 4 virtual servers, for example, will together use around 48% of a physical machine (plus small virtualization overhead).<br /><br />This works even if each of those has no parallelism in the app or the OS. The parallelism is across the multiple virtual machines that were consolidated together on one physical system.Greg Pfisterhttps://www.blogger.com/profile/12651996181651540140noreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-85955085534671038222010-06-28T18:15:42.912-06:002010-06-28T18:15:42.912-06:00Like your blog! New to virtualization. Could you e...Like your blog! New to virtualization. Could you explain how it is that a virtualized machine is more efficient in using the processing power of the microprocessor if there is no parallelism and the operating system or hypervisor can still only send one instruction at a time? I guess I am trying to figure out how a virtualized environment is able to utilize more capacity of the processor than a non-virtualized processor. Thanks!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-91927244859643184932010-05-26T16:41:23.144-06:002010-05-26T16:41:23.144-06:00Good Article.
Looking forward to Part 2.Good Article.<br />Looking forward to Part 2.Irfanhttp://www.linkedin.comnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-47777852149356001202010-05-26T11:38:01.899-06:002010-05-26T11:38:01.899-06:00I'm not disputing that hardware virtualisation...I'm not disputing that hardware virtualisation has virtually no cost. However, I wonder how much of the low usage on conventional machines is due to the way OS's have been designed for historical usage (ie, licencing mechanisms that are assume they are whole machine rather than per user group, difficulty in checkpointing/migrating a subset of the OS, lack of rigorous QoS at OS level, etc)? The vague reason for wondering about this is that I don't want to administer every aspect of an OS, what I want is to be able to select a different "component" to the standard configuration in those few cases where it matters to me.<br /><br />This is orthogonal to however hardware may facilitate things.banenoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-60124839602119242312010-05-25T02:26:17.156-06:002010-05-25T02:26:17.156-06:00Nice blog. Virtualization + elasticity + automatio...Nice blog. Virtualization + elasticity + automation are the core aspects of cloud computing. This is a good introduction to virtualization in the context of cloud computing. I look forward to the next part in the post.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3155908228127841862.post-81665781611226574462010-05-25T02:24:35.112-06:002010-05-25T02:24:35.112-06:00This comment has been removed by the author.PChttps://www.blogger.com/profile/14490167742314676078noreply@blogger.com