Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

When Solid State Drives Are Not That Solid

blog.algolia.com

Post reply on HN
Print view View original

81–90 of 123 posts

Re: When Solid State Drives Are Not That Solid

#81

Post by madez »

simoncion wrote: post #41
madez wrote: post #32

Earlier quoted context omitted.

That remains to be seen. I really hope not. With Samsungs finished-forms walling the company already tells Linux users to not expect any support, at all. So, that is consisting with the testbed-theory.

> With Samsungs finished-forms walling the company already tells Linux users to not expect any support, at all. I'm sorry. I'm too dumb to parse this. :( Would you kindly rephrase it? Thanks much. :)

    I'm sorry. I'm too dumb to parse this. :(
I am sorry. I was too dumb to phrase it understandibly, so the shame is on me. The sentence smelled problematic to me but after several times rereading it I concluded it is understandable. I should have gone with my guts…

Here is another try: Samsung's support walls with prewritten answers that say Linux is open and thus Linux is unsupported, and this action of Samsung is consisting with the testbed-theory.

Re: When Solid State Drives Are Not That Solid

#82

Post by madez »

adamsurak wrote: post #49
madez wrote: post #25

It feels like Samsung used the Linux community here as a free testbed. Samsung knew that only Linux supported queued trim, so releasing it without proper testing is just externalizing the disproportionately increased cost of testing to the Linux community.

In this case it was un-queued TRIM (I forgot to mention it in the blogpost). We have reached to Samsung and although it looked good at the beginning now they are silent for more than a month without any progress.

I was refering to the Native Command Queued trim (hence "queued trim"), not the traditional trim command.

Re: When Solid State Drives Are Not That Solid

#83

Post by cabirum »

Strange, Samsung 840/850 evo/pro are considered [1][2] among the best consumer SSDs. The issues article mentions do not exist on Windows, the SSDs are very reliable there. I suspect it's not only Samsung fault. Are we sure Linux handling of TRIM operations is absolutely correct?

[1] http://techreport.com/review/27062/the-ssd-endurance-experim...

[2] http://www.anandtech.com/show/8216/samsung-ssd-850-pro-128gb...

Re: When Solid State Drives Are Not That Solid

#84

Post by mrmondo »

u02sgb wrote: post #72
mrmondo wrote: post #48

I've worked on some interesting SSD deployments / experiments a lot over the past 12 months. Quite honestly - I wouldn't go anywhere near Samsung products regardless of their 'PRO' labelling or otherwise. We have had great success with both Sandisk Extreme Pro SATA and Intel DC NVMe series drives, we've also recently deployed a number of Crucial 'Micron' M600 1TB SATA drives that are performing very well and so far h…

I've done similar over the last three years and had good luck with the Crucial drives. However if you take a look at the Linux Kernel patch they link to (search for "don't properly handle queued TRIM"): https://github.com/torvalds/linux/blob/e64f638483a21105c7ce3... There are Crucial SSDs on the list. I'm going to be keeping a closer eye on them now.

Yeah I saw that - although that's the older, now discontinued series that has a different controller and doesn't show the same consistent performance as the newer M600 drives.

Re: When Solid State Drives Are Not That Solid

#85

Post by sfilipov »

cabirum wrote: post #83

Strange, Samsung 840/850 evo/pro are considered [1][2] among the best consumer SSDs. The issues article mentions do not exist on Windows, the SSDs are very reliable there. I suspect it's not only Samsung fault. Are we sure Linux handling of TRIM operations is absolutely correct? [1] http://techreport.com/review/27062/the-ssd-endurance-experim... [2] http://www.anandtech.com/show/8216/samsung-ssd-850-pro-128gb...

Windows doesn't do queued TRIM (yet).

Re: When Solid State Drives Are Not That Solid

#86

Post by buffportion »

madez wrote: post #81
simoncion wrote: post #41

Earlier quoted context omitted.

> With Samsungs finished-forms walling the company already tells Linux users to not expect any support, at all. I'm sorry. I'm too dumb to parse this. :( Would you kindly rephrase it? Thanks much. :)

I'm sorry. I'm too dumb to parse this. :( I am sorry. I was too dumb to phrase it understandibly, so the shame is on me. The sentence smelled problematic to me but after several times rereading it I concluded it is understandable. I should have gone with my guts… Here is another try: Samsung's support walls with prewritten answers that say Linux is open and thus Linux is unsupported, and this action of Samsung is con…

I think the confusion stems from your verbing of "wall".

Re: When Solid State Drives Are Not That Solid

#87

Post by simoncion »

madez wrote: post #81
simoncion wrote: post #41

Earlier quoted context omitted.

> With Samsungs finished-forms walling the company already tells Linux users to not expect any support, at all. I'm sorry. I'm too dumb to parse this. :( Would you kindly rephrase it? Thanks much. :)

I'm sorry. I'm too dumb to parse this. :( I am sorry. I was too dumb to phrase it understandibly, so the shame is on me. The sentence smelled problematic to me but after several times rereading it I concluded it is understandable. I should have gone with my guts… Here is another try: Samsung's support walls with prewritten answers that say Linux is open and thus Linux is unsupported, and this action of Samsung is con…

Don't sweat it, I'm the king of less-than-comprehensible statements. :)

Anyway, I get your statement now. Maybe instead of saying "walls" you should say "stonewalls" (derived from "stonewalling")?

Re: When Solid State Drives Are Not That Solid

#88

Post by userbinator »

Aardwolf wrote: post #73

I'm so sick of this TRIM. Constant configurations needed because of it, constant care like "this thing you better don't do on SSDs". And then problems like this. Do you think there'll ever be SSDs that don't need it?

They never "needed" TRIM, it was mainly introduced as a performance optimisation.

I have an old Intel SSD that doesn't even support TRIM, and it still works fine. As do all the other USB flash drives I have...

Re: When Solid State Drives Are Not That Solid

#89

Post by notacoward »

jjawssd wrote: post #50
_yosefk wrote: post #43

Earlier quoted context omitted.

The thing is, almost all hardware accessed through drivers has tons of bugs, at least it's nowhere near as close to "bug-free" as are things like CPUs or DRAMs which cannot hide their bugs behind drivers. The thing that one can hope to work reasonably is a piece of hardware plus an accompanying driver which knows to hide that hardware's issues. So another way of putting what you said would be "on Linux there's no wor…

If you think CPUs do not come with a shit-ton of hardware bugs YOU ARE GRAVELY MISTAKEN. Google up the Intel errata for the i7 The list goes on and on.

FWIW, memory has plenty of bugs too. With respect to the original point, these are usually not visible to drivers (unless you count EDAC) because they're handled at the chipset level. However, for certain kinds of systems - especially embedded - that don't have chipsets these issues can become painfully visible. My own exposure to this was at SiCortex, where the memory logic was directly on the same single die as everything else that comprised a node.

Re: When Solid State Drives Are Not That Solid

#90

Post by PythonicAlpha »

caf wrote: post #31
madez wrote: post #25

It feels like Samsung used the Linux community here as a free testbed. Samsung knew that only Linux supported queued trim, so releasing it without proper testing is just externalizing the disproportionately increased cost of testing to the Linux community.

Is the loss of reputation really worth less than the value of the externalised testing?

I once was a huge fan of Samsung. But with the EVO disaster and this one, I really regret to have bought one of these.
Post reply on HN