search for: oversubscrib

Hi all, I am having some fun with traffic shaping, and have run into an interesting situation. Here is South Africa, most internet links are heavily oversubscribed, which means that in most cases the local link is _not_ the bottleneck, and shaping on the local link does not help that much... Does anybody have some tips on shaping such links? How can you get interractive traffic if you don''t know how much bandwidth to reserve for it? How can y...

Hopefully someone has a suggestion on how I might do this...as I can''t figure it out :( I need to be able to set up a group of seperate users who have a "bandwidth pool" they share, but also be able to limit their individual bandwidth as well. Example: I have 5 customers and would like to be able to provide them with a maximum of 256Kbit each, with a CIR of 33%. To do this,

...use contention for bandwidth is he number one cause of jitter, delay, and packet loss. Most consumer broadband systems do not fall into the undersubscribed category whereas most T1 and above commercial services are much closer to undersubscribed. I have seen cable systems and DSL networks that are oversubscribed at more than 100:1. (too much...). So the short answer to the question, 100ms or less is desired, but useless if accompanied by packet loss and jitter. There are programs you can use to analyze delay, jitter and packet loss. Search the web for a free one, tune the packet size and rate to match...

...arora at oracle.com> writes: > A KVM host (or another hypervisor) might advertise paravirtualized > features and optimization hints (ex KVM_HINTS_REALTIME) which might > become stale over the lifetime of the guest. For instance, the > host might go from being undersubscribed to being oversubscribed > (or the other way round) and it would make sense for the guest > switch pv-ops based on that. If your host changes his advertised behaviour then you want to fix the host setup or find a competent admin. > This lockorture splat that I saw on the guest while testing this is > indica...

All, Thank you for the prompt and useful answers to my questions. I had missed references in 5.7.6 which would have answered some of the points. As Bill pointed out a newer version of acrobat would help, but the Sun system here is still running 5.0. (An oversubscribed sysadmin). Then I could have searched and at at least avoided the most trivial. All three comments were different, and all three helped. Terry T. "I see" said the blind carpenter, as he picked up his hammer and saw. (A favorite phrase of my mother's when something becam...

...:57PM -0700, Ankur Arora wrote: > A KVM host (or another hypervisor) might advertise paravirtualized > features and optimization hints (ex KVM_HINTS_REALTIME) which might > become stale over the lifetime of the guest. For instance, the > host might go from being undersubscribed to being oversubscribed > (or the other way round) and it would make sense for the guest > switch pv-ops based on that. So what, the paravirt spinlock stuff works just fine when you're not oversubscribed. > We keep an interesting subset of pv-ops (pv_lock_ops only for now, > but PV-TLB ops are also goo...

...:57PM -0700, Ankur Arora wrote: > A KVM host (or another hypervisor) might advertise paravirtualized > features and optimization hints (ex KVM_HINTS_REALTIME) which might > become stale over the lifetime of the guest. For instance, the > host might go from being undersubscribed to being oversubscribed > (or the other way round) and it would make sense for the guest > switch pv-ops based on that. So what, the paravirt spinlock stuff works just fine when you're not oversubscribed. > We keep an interesting subset of pv-ops (pv_lock_ops only for now, > but PV-TLB ops are also goo...

I''ve been recently testing the Xendemo CD and I can say that Xen is awesome. I''d like to start deploying it initially in some development/testing servers. However the limitation of the max memory of 800MB or so per virtual machine is a show stopper for many applications. Are there plans to raise the limit to something higher (like 2GB or so)? How difficult would it be?

Seeing as IPV4 is near it's end of life (http://www.internetnews.com/infra/article.php/3915471/IPv4+Nearing+Final+Days.htm), I'm curios as who know whether everyone is ready for the changeover to IPV6? Is anyone using it in production already, and what are your experiences with it? -- Kind Regards Rudi Ahlers SoftDux Website: http://www.SoftDux.com Technical Blog:

Hello everyone, Excuse the title. I'm trying to do something very specific that goes against some common assumptions. I am aware of how Linux uses available memory to cache. This, in almost all cases, is desirable. I've spent years explaining to users how to properly read the free output. I'm now trying to increase VM density on host systems (by host, I mean the physical system, not

Hi All, I started a 501c3 (not-for-profit) organization back in February 2011 to deal with information archival. A long vision here, I wont bore you with the details (if you really want to know, e-mail me privately) but the gist is I need to build an infrastructure to accommodate about 2PB of data that is database stuff, stored video, crawl data, static data sets, etc. Right now in my testing of

...-DBUILD_SHARED_LIBS=OFF. BUILD_SHARED_LIBS is a non-sense from a performance point of view. It is really not advised to use this. > > FYI, -DLLVM_PARALLEL_LINK_JOBS=1 didn't seem to make any difference, > seeing how each LD stop was using all available cores. It only helps limiting oversubscribing the number of cores, and reduces the peak memory for the link. — Mehdi

...; loss. > > > > Most consumer broadband systems do not fall into the > > undersubscribed > > category whereas most T1 and above commercial > > services are much closer > > to undersubscribed. I have seen cable systems and > > DSL networks that are > > oversubscribed at more than 100:1. (too much...). > > > > So the short answer to the question, 100ms or less > > is desired, but > > useless if accompanied by packet loss and jitter. > > > > There are programs you can use to analyze delay, > > jitter and packet loss. &g...

Hello guys, Does anyone has an Asterisk server hosted off-site ? Like in those data centers that do web hosting in dedicated servers ? Is there a hosting company that has a special plan to host voip services like this, or usually is hosted in those dedicated servers like the ones I asked above ? What about QoS ? I know that most (if not all) are connected to their switch through a

Am Do., 1. Nov. 2018 um 16:56 Uhr schrieb David Greene <dag at cray.com>: > Ok. I would like to start posting patches for review without > speculating too much on fancy/exotic things that may come later. We > shouldn't do anything that precludes extensions but I don't want to get > bogged down in a lot of details on things related to a small number of > targets.

...pass is taking metadata to avoid un-optimizing? Not yet, but it would be valid. > Loop fusion can make it worse if you have strong locality (two > completely separate big memory access) in terms of cache miss in > small-memory platforms. Agreed. And it can compound register pressure and oversubscribe other execution resources. A general-purpose loop fusion pass should consider such things. > So, would be good if the front-end could pass > on some information down the codegen? Perhaps, although most front-ends don't have the kind of information that a loop fusion pass would need, un...

...scription risks running out of RAM, if all of the guests decide to try and use all the RAM the host told them it gave. All of the guests end up being forced to deflate their balloons until there is no more balloon memory left. > The increase in vm density is an acceptable tradeoff. Instead of oversubscribing the real RAM of the system, consider starting and stopping VMs at need, so that only a subset of them are running at a given time. That lets you host more VMs underneath a given hypervisor than would run simultaneously, as long as you don?t need too many of the VMs at once. This patterns works...

HI. Got a question. When I assign a number of vcpus to a DomU, Are they dedicated to that VM? For example: If I have 16 vcpus available and 8 DomUs, should I assign 2 vcpus for each one? or could I assign more vcpus (i.e. 6) and the hypervisor takes care of it? Thanks -- ---------------------------------------------------------- Luis R. Romano Estudiante de Ingeniería en Computación. FCEFyN -

To get MeetMe working properly, I know some sort of timing device provided by the zaptel package is required (even if it means the zt_dummy). But, on a virtual machine I know that the Linux timing won't work as expected. Is it possible to then dedicate a physical device like a USB port or something to the virtual machine to use for the timing interrupts? Thanks.

Hi, Can someone tell us what is the usual number of guests on a typical host in a production environment ? Has someone tested this ? What number does it scale to ? We have around 150 per host running fine. Regards, Navin