Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - pocock

Pages: 1 2 [3] 4 5 ... 19
31
There are some hints about multi-seat setups in other topics in the forum

Multi-seat can make the workstations more viable because the cost is shared between two or three users.

I had some discussions about this with a few people.  Most people are satisfied that POWER9 provides enough compute capacity but there were some practical concerns

The type of user who would benefit from this setup is typically a developer, system administrator or IT support worker who already works in Linux

By their nature, this type of user would like to tweak the system, for example, installing some kernel module, installing some non-standard version of some development header files or whatever.

What level of isolation can be achieved between users in such scenarios?

For example, using virtualization, people can have their own kernels and separate GPU ports.

Using LXC and cgroups, people can have their own root filesystem but they share a kernel

Has anybody tested these possibilities with POWER / Linux workstations or even on x86?

I found some links about the topic for some of the distributions that people are using

Hardware passthrough in LXC or running a desktop in a cgroup

two X servers one graphics card

Debian - Multi Seat

Fedora - Multi Seat

Arch - Multi Seat

FreeBSD - Multi Seat

32
The PCIe capabilities of these cards make them a very good match for Talos II at a hardware level so it is sad that nothing happened.

I suspect AMD would tell us that it is easier for us to buy their Ryzen processors and they might not make the effort on these drivers for non-x86 users

IBM, who make both the POWER9 and own Red Hat recently wasted a lot of money on an attempted reverse-domain-name-hijacking.  If they stopped giving the money to lawyers and gave it to real developers then some of us would probably spend the time to fix the GPU drivers.

33
There is one bug open against kernel 5.10.x, if anybody can try the card with a newer kernel like 5.15.x that would be helpful

34
Has anybody tried any of these cards with a recent kernel?

Does the kernel command line option mentioned on the wiki here make any difference?

Code: [Select]
amdgpu.aspm=0

35
I wouldn't care. Because the maintainers of Fedora (sharkcz is on this forum) are aware of the problem. If they don't feel the need to offer 4K kernels, so be it...

That's the blessing of open source, you can choose whatever you like.

Given the POWER eco-system is smaller compared to the overall eco-system, the choices are not so wide and the POWER development teams in each distribution are relatively limited in what they can do

The commit below doesn't credit people who spent time identifying the root cause of the problem, that is not a blessing at all.  It verges on plagiarism.

And it seems the problem is fixed?
Commit 5234de6c797565815ece9321b1dfe2e6732b5090
https://cdn.kernel.org/pub/linux/kernel/v5.x/ChangeLog-5.10.101

36

There is an update on the Fedora situation today

A legal panel has declared that rogue elements of Fedora committed harassment and abuse, this is what is effectively slowing down my work to help Fedora users on POWER

Here is my blog about it

Here is the verdict from the panel

It is interesting to note that when people immersed in the open source space make accusations of harassment, they are usually very biased and swayed by conflicts of interest and personal relationships.

The verdict on Fedora was made by an outside observer so it is more credible than a code of conduct.

37
Operating Systems and Porting / Re: [NEWS] Debian 11 is out
« on: November 29, 2021, 03:51:26 pm »

The person who wrote the character assassination claims that I am "purporting to be a Debian Developer"

If you look at his own Debian Developer profile, it says he is a non-uploading developer and he never created one package:

https://qa.debian.org/developer.php?login=donald@debian.org

https://nm.debian.org/person/donald/

I started programming microprocessors when I was about 10 years old and before Debian existed. They can not prevent me from creating and publishing Debian packages.  All they are doing is stopping other people like you from using them in the most convenient manner.  In other words, they are not hurting me, they are simply sabotaging Debian.

This rogue behavior deters other people from creating packages too.  If somebody spends a weekend creating a package, nobody is going to pay them for it but if they are unlucky they will be subject to defamation.  So there is no upside but there is a very big downside.  These vendettas stop people, especially women, from doing voluntary work in any free software project.  Everybody loses in situations like this.

38
Operating Systems and Porting / Re: [NEWS] Debian 11 is out
« on: November 18, 2021, 03:47:27 pm »
I'm not afraid to share those links but I prefer not to because if we look at that then we also need to look at the links about Debian Developers, Ubuntu employees, GSoC mentors and a Debian Project Leader having inappropriate interactions with the young female interns from developing countries.  I chose not to post any of that here.

The link about me does not contain any links to evidence.  It is pure defamation.

The real question is this: why would Donald Norwood write such a post about a volunteer?  Or to put that question in other words: if the attack on me is nonsense (a smokescreen), what are the real flaws in the Debian structure that they are trying to avoid discussion about?

39
Operating Systems and Porting / Re: [NEWS] Debian 11 is out
« on: November 18, 2021, 01:09:41 pm »
I received quite a few messages about Debian recently.

I won't go into the details.  As a professional, I simply want to focus on what this means for people who invested in the OpenPOWER platform.

There are not so many people doing OpenPOWER development for Debian.  The current politics will prevent important technical work and patches.

For example, my patch for the 4k page size can very easily be integrated into the official Debian releases.  I designed the patch to follow Debian's kernel packaging structure.  Unfortunately, in a period when I lost two family members, I experienced some extraordinary rudeness from the more difficult people in the Debian ecosystem.  I feel that they put politics ahead of the users, people like you.

From my perspective, if anybody wants to discuss the technical merits of the work I do as a Debian Developer, I remain happy to have those discussions and simply publish my packages using more reliable repositories and Gitlab.

After all, the Debian Social Contract, point 4 asserts "Our priorities are our users and free software".  Anybody who comes here to help users and provide them with solutions, such as the 4k patch for the Debian kernel packages and the installer ISO based on that patch, is free to call themselves a Debian Developer.

40
Any work on this topic in Fedora has now been undermined by the politics that is gripping large free software organizations.  This initiative is completely frozen and I can't say when it would resume.

During the Fedora 35 release cycle, many Red Hat employees joined the attacks on Dr Richard Stallman.  I wrote a blog about the human rights issues involved in these online mobs and subsequently received a number of malicious communications that undermine my voluntary work as a Fedora developer.

I would not expect Raptor to be keen on taking sides in these issues, after all, they made a big effort to attain the FSF RYF certification but the OpenPOWER hardware is coming from Red Hat's parent, IBM.  On that basis, I won't say a lot more about this but I feel that people who invested in this platform have a right to know that politics is getting ahead of important development issues.

41
Talos II / Re: Using the ╬╝PCIe connector (J10108)
« on: October 17, 2021, 06:20:27 am »
I notice the micro PCIe socket is right under one of the PCIe cards.  This means it may be better to use a cable with right angle (RA) connector like this:

Supermicro CBL-SAST-0955

42
General Discussion / Areca Tri-mode HBA NVMe / SAS / SATA controllers
« on: October 17, 2021, 05:41:43 am »

Online store / catalog

These are not cheap but they look like interesting HBAs for people who have a lot of disks and want to link them all into their workstation or server through a single x16 slot.

Has anybody tried any of them?

How do they compare to other brands offering a Tri-mode solution?

43

Quattro 400 web page

Has anybody tried it?

It is not really fast enough for somebody who wants the newest SSDs like the Samsung Pro 980, each of those can do 7GB/s.

For previous generation SSDs operating up to 4GB/s this looks like an interesting HBA for software RAID, Btrfs or ZFS in a x8 slot.

44
Talos II / Re: Using the ╬╝PCIe connector (J10108)
« on: October 17, 2021, 05:29:37 am »
The manual suggests it is 4 lanes (PCIe 4.0 x4)

The errata states it is an Oculink SFF-8621 physical connector but it is not completely wired for Oculink

Nonetheless, do the PCIe lanes work sufficiently for an SFF-8621 to U.2 NVMe cable?

Here is an example of the cable CBL-SAST-0956 from Supermicro

The cable is not very expensive, I might simply buy one to try it.

45
General Discussion / Re: Samsung PRO 980 1TB NVMe is working flawlessly
« on: October 17, 2021, 05:18:45 am »

https://www.tomshardware.com/news/samsung-launches-pm9a1-ssd-cheap-980proThere is also the OEM version, Samsung PM9A1, equivalent to the Pro 980 but at OEM price (cheaper)[/url]

In terms of performance and the previous comment about using dedicated slots for each of these drives, here are some details:

- the fastest sequential read from these new Samsung devices is 7000 MB/s

- a PCIe 4.0 (Gen4) slot, with one lane (x1) carries 2GB/s

- the Talos II motherboard has a mysterious x4 micro PCIe connector, it appears to be x4 lanes, that could carry 4 * 2GB/s = 8GB/s for one of these SSDs or two of the previous generation SSDs without congestion

- the PCIe 4.0 slots, x8 can carry 8 * 2GB/s = 16 GB/s, that is enough for two of these new Samsung devices + some spare capacity for legacy SATA all running simultaneously on a single Tri-mode HBA

- the PCIe 4.0 slots, x16 can carry 16 * 2GB/s = 32 GB/s, that is enough for four of these new Samsung devices + some spare capacity for legacy SATA all running simultaneously on a single Tri-mode HBA

For people building workstations based on Blackbird or Talos II Lite it is probably desirable and feasible to have an x8 HBA for SSDs and use the x16 for a GPU

Pages: 1 2 [3] 4 5 ... 19