Search results

I see it made its way into pvetest - thanks a lot, I just installed it. Will report back if I find any issues with it.

In theory, it's also possible to add a drive to a running system ("drive_add" in KVM monitor). Unfortunately, I was not able to add a drive (with "drive_add") so that it's visible in the guest.

Yes, that's problematic here - there is just no easy way to reproduce it with a simple script like: # ./cause-slowness-with-virtio_net.sh running for 5 minutes ;) In practice, it usually takes a couple of days until I hit it. It first happens for guests which do lots of IO and use CPU a bit...

The bug is still there (guest slow when using virtio_net). Please, do not apply fairsched patch to KVM as it is simply broken with it - or provide an option to disable cpuunits/fairsched for KVM guests. As discussed on the mailing list and privately ("CPU units" breaks virtio - in June), the...

No, the "slowness" for guests using virtio_net is not solved in Proxmox VE 1.3 (and the problem is still there in the latest beta of 1.4, too).

IET is really unstable and I would discourage using it. SCST is fine as a iSCSI target, although its setup is slightly complicated. There is also tgt (http://stgt.berlios.de), but the Debian's package is really antique, and you should use an upstream version (tgt-0.9.9, or newer, if such is...

I haven't heard of any. I can imagine one (which doesn't require the binaries to be modified) using existing kernel infrastructure though: use in-kernel binfmt_misc to execute every binary in the guest with a special "interpreter". It would use additional system resources though and would need...

Not really, for the following reasons: 1) OpenVZ would have to support 2.6.32 or newer kernel - long term, fixable, but rather not in foreseeable future, 2) application using KSM has to support "madvise" (MADV_MERGEABLE, MADV_UNMERGEABLE...) system call. Here, kvm is one process and supports...

2.6.32 kernel will support KSM - Kernel Samepage Merging feature. For example, when running lots of similar guests, memory pages with identical contents will be "merged", thus saving the memory. This feature can possibly make KVM use even less memory than OpenVZ (although some tests would be...

AFAIK, only some bits of LXC are in the upstream kernel. Correct me if I'm wrong.

BTW - will this release give possibility to not use "fairsched" for KVM, as we discussed on the mailing list once? In the line of: '-cpuunits=0' (0 == ignore) I'm not sure if the issue I'm describing here does not come from this one as well (in addition to problems it gives to guests running...

BTW, I didn't see tg3 mentioned in the changelog... So I'll try building 2.6.31.1 myself.

The patch was the problem. The slowness didn't return.

No, I did not test it yet. Is it the same as here (pve-kernel-2.6.24-8-pve_2.6.24-14_amd64.deb)? http://download.proxmox.com/debian/dists/lenny/pvetest/binary-amd64/

I know that it's not supported, but I was wondering if someone is using Proxmox VE with a newer kernel (for KVM only, no OpenVZ). I have some strange network connectivity problems relating to tg3 module (host not reachable, tcpdump on the host shows absolutely no traffic, bringing down the...

Also, kqemu will be removed from Qemu soon (or maybe it's removed now) - as it is "unmaintainable" (nee kvm/qemu-devel lists for details).

virtio network is currently broken in Proxmox - due to patches to kvm which add "fair scheduler" functionality, KVM guests will get "slow" after a couple of days (may depend on the number of guests running and the load they have). So it's best to use e1000 network driver until it's fixed. For...

There are more downsides of OpenVZ than just not functioning iptables and inability to use most kernel functions/modules: i.e. lack of VPN. With most hosting providers offering OpenVZ, you will also have a severe problem with the amount of inodes available on your system. No problem for a small...

It works, but current implementation only allows you to lower guest memory. For example, if you started a guest with 1 GB RAM, you won't be able to balloon out this guest's memory to 2 GB. You will be able to decrease guest's memory to i.e. 512 MB, then increase it to 1 GB etc. - but never...

My types to make Proxmox VE a truly professional product: - shared storage - already in works, - resource monitoring (mainly bandwidth used, but if possible - on block devices - also IO - see iostat); some actions would be nice here: allow only 1 Mbit up; 2 Mbit down; after exceeding 100 GB...