2016-03-15

Moronix

I don't post about Linux too much, mostly because it's arcane, and my particular expertise is highly specialized, and thus not relevant to most casual Linux users.

It is sad though, since slashdot (no link) has devolved into a festering malebolge of anti-sjw butthurt, there is really only one other site that focuses on Linux related news: phoronix.

This is problematic for two reasons.  First, the misogynistic cancer unfortunately infects much of the open source community, has metastasized and spread there as well.  First ESR has some very controversial beliefs, and second, Breitbart is hardly a reputable enterprise.  It's a mind-boggling lack of judgment on the part of the phoronix proprietor, Michael Larabel.

The second reason is that a great deal of the time, ML has absolutely  no clue what he's even reporting about.  I mean stopped clocks finding the occasional nut and all that.  But the important information isn't in his incestuously interlinked postings, but in the source material (often simply summarized) that's usually, but not always, the final link in any particular "article."

Basically, the problem is the what is this, and why should we care questions go unanswered.   Specifically, with VMD, there is precious little information out in the wild about what it is for, and what hardware supports it.  In cases like these, it would be better not to report something, than to pretend to know what it is.

Basically, it seems to be specific to PCI-E attached storage devices in the md driver, but I'm not sure of that.  

Anyway, despite the well earned criticism, phoronix manages--accidentally, one would presume--to perform one good function (see the post by Sander_Marechal):

 Uh, yes they do. Phoronix isn't just running benchmarks. They have built a large testing framework and computerfarm capable of running many different benchmarks over many distributions and configurations automatically. It's even integrated with the Linux kernel's git repository. When there's a large performance drop (or increase) in a specific benchmark, the framework can automatically git bisect and rerun the benchmarks until it fins the exact commit that caused it. That's a huge contribution to development. It's been used quite succesfully in finding and killing performance regressions.


No comments:

Post a Comment

Note: Only a member of this blog may post a comment.