Recent content by guerby

No more network issue with our intel E810XXVDA4 on HPE DL385 since the rmmod irdma/ib_core/ib_uverbs

Next version of Alpine Linux will blacklist irdma by default : https://github.com/alpinelinux/aports/commit/313096cd1f8f6ec031437eddcad49595c7a7eb7f

Hi, Same happening once every few day on one of our 6 HPE DL385 E810-XXVDA4 with plugged 4x25G DAC running proxmox VE 9.0 kernel 6.14.11-2-pve, it's the box with the most traffic, I added comments on the intel ICE github issue...

[32029.460800] Kernel panic - not syncing: Host injected async #PF in kernel mode [32029.472728] CPU: 2 UID: 0 PID: 136167 Comm: pvestatd Tainted: P O 6.14.8-2-pve #1 [32029.476915] Tainted: [P]=PROPRIETARY_MODULE, [O]=OOT_MODULE [32029.481049] Hardware name: QEMU Standard PC...

For the record on a debian 13 host (kernel 6.12.38) I ran a kvm (10.0.2) with PVE9 qemu-system-x86_64 -machine type=pc,accel=kvm -cpu host -m 8192 -drive file=vm1.qcow2,format=qcow2,if=virtio -k fr -netdev user,id=net0,hostfwd=tcp:127.0.0.1:8066-:8006,hostfwd=tcp:127.0.0.1:8022-:22 -device...

Hi, I did a GC on one of our repo with the strace which gaves lines like [pid 1181406] utimensat(-1, "/mnt/datastore/datastore1/.chunks/bb9f/bb9f8df61474d25e71fa00722318cd387396ca1736605e1248821cc0de3d3af8", [UTIME_NOW, UTIME_OMIT], AT_SYMLINK_NOFOLLOW) = 0 After processing the output by...

On this first GC I have a proxy measure as I was running iostat -xmt 10 during the GC. Measures varied from 10 MB/s to 70 MB/s write with a ballpark average of 20 MB/s. That means 27 minutes * 20 MB/s equals around 32 Gbyte of writes, and so 1300 bytes written per chunk on average through our...

Hi, I upgraded our PBS from 3.3 to 3.4 and added the following tuning to our datastores GC : tuning chunk-order=none,gc-atime-cutoff=30,gc-atime-safety-check=1,gc-cache-capacity=8388608 I'm happy to report that our GC time went from 1h30-2h to 27mn on our SSD PBS and from 45-50mn to 15mn on...

l already opened a bug report : https://bugzilla.proxmox.com/show_bug.cgi?id=3290

Hi, I will first open a bug report. I and @spirit have signed the proxmox source code contributor agreement in case we need to propose a patch

There's a bugzilla request open for remote-migrate with shared storage: https://bugzilla.proxmox.com/show_bug.cgi?id=4928 Both ceph and NFS could be of interest as shared storage. I assume technically it would be simpler since there's nothing to be done disk-wise during migration for shared...

Done : https://bugzilla.proxmox.com/show_bug.cgi?id=5493

Yes that's another way when you're able to match the set of disks you want the installer to choose. May be copying the disk_list syntax for filter.xxx would be a nice addition to the tool: filter.ID_SERIAL= ["*194K","*191V"] I don't think I'm alone wanting to do a RAID1 for system install and...

Hi, I have a machine with 8 disks from the same model (pretty common situation for a new server), I'm trying to match 2 of the disks for a ZFS RAID1 install by using their ID_SERIAL as follows: [disk-setup] filesystem = "zfs" zfs.raid = "raid1" filter.ID_SERIAL="*194K" filter.ID_SERIAL="*191V"...

Hi, In order to work on https://bugzilla.proxmox.com/show_bug.cgi?id=2370#c17 starting with a PVE 8.2 system I was able to rebuild proxmox-firewall program as follows: echo "deb http://download.proxmox.com/debian/devel bookworm main" >> /etc/apt/sources.list apt-get update apt-get dist-upgrade...