Search results

It's actually a very clever approach since the Ubuntu kernel used is the LTS branch providing 5 years of support. A kernel from Debian, at the time the decision was made (before Debian LTS), was only supported for the time a Debian stable was living plus 1 year. With current Debian LTS that...

Something that everybody was not mentioning. When using Debian you are guarantied to always only use FOSS software which is not the case with Ubuntu.

Opteron:;-) Spectre and Meltdown mitigation detection tool v0.27 Checking for vulnerabilities against live running kernel Linux 4.4.98-3-pve #1 SMP PVE 4.4.98-102 (Sun, 7 Jan 2018 13:15:19 +0100) x86_64 CVE-2017-5753 [bounds check bypass] aka 'Spectre Variant 1' * Checking count of LFENCE...

It is a lot easier to simply do: sudo apt install intel-microcode, on every proxmox node since microcode patches must be applied on every reboot and not all patches can be applied to a booted system, eg. a boot is required. See https://wiki.debian.org/Microcode

Hi all, The following is a mixture of facts and speculations but never the less in my opinion means a paradigm shift for the virtualization industry! First the facts: 1) Virtualization as a driving factor first began in this decade 2) According to Intel any CPU before 2011 (Westmere) is not...

Since your disks in the RAID are all SSD I would remove the log and cache. In your setup it could easily reduce your performance. As a general rule of thump: Unless your log device is given at least 4-5 times the random performance over your disks in the array it often only reduces the overall...

Which host CPU, Intel, ARM or AMD?

Come on, ZFS is a filesystem!

Without this boot time option: pti=on?

I am running with AMD Opteron processors so the newly released kernel are almost useless unless changing boot settings. This information might have come handy in the release notes! Now I will have to rescheduled a new reboot :-(

I you consider your customers data of just modest value you would behave professionally and upgrade your hardware instead of gambling with the validity of there data!

This must by far be one of the worst advices ever given! disable sync: Do not honour sync requests from applications and instead give applications the impression that data is safely persisted. I hope no database server is running on this disk disable checksum: Effectively break ZFS' self healing...

I have been in the same situation at work with our new HCI SAN where each node contains 1 TB of RAM and since each node contains 25 TB storage it requires a large part of the storage to make the test;-)

It is important for the validity of the benchmark to choose a file size which is at least twice the size of the RAM or you may otherwise test your RAM

# prtdiag System Configuration: Supermicro X10SLL-F BIOS Configuration: American Megatrends Inc. 3.0 04/24/2015 BMC Configuration: IPMI 2.0 (KCS: Keyboard Controller Style) ==== Processor Sockets ==================================== Version Location Tag...

Another comparison: SuperMicro MB, 2 mirrors striped 4xWD red 1TB (RAID 10) and Intel DC s3510 as SLOG on OmniosCE omnios-r151022 $ sudo zfs create vMotion/test $ sudo pveperf /vMotion/test/ CPU BOGOMIPS: Not available REGEX/SECOND: 1148085 HD SIZE: 510.56 GB (vMotion)...

Since fall 2015 the default compression algorithm in ZOL is LZ4 and since choosing compression=on means activate compression using default algorithm then your pools are using LZ4 -> http://open-zfs.org/wiki/Performance_tuning#Compression