p13
-
Posts
19 -
Joined
-
Last visited
Content Type
Profiles
Forums
Downloads
Store
Gallery
Bug Reports
Documentation
Landing
Posts posted by p13
-
-
This is more wide spread that it appears. Most people just won’t bother with checking why their Marvell controller connected disks don’t show up.
Also, this is not kernel, driver or firmware related. At least if it is the case, not the main cause. This is clearly UnRAID issue. I have done extensive tests, during which confirmed that the same 88SE9230 cards (yes, multiple) wold work just fine with OMV throughout 3 last versions, but would fail in UnRAID throughout 3 last versions.
The fix didn’t work in my case.It seems that the Linux distor under UnRAID or UnRAID itself initialises SATA controllers in some special way. Most often error output is “soft reset failed”.
Considering the number of Marvell controllers on the market, it would be reasonable to address this issue rather sooner than later.
-
Greate. Many thanks.
Regards.
-
Many thanks for your answer.
Which plugin that is you took as example, where can I get it please?
Cheers.
-
Hi,
Is there a place unRAID API Documentation is available?
Cheers.
-
Hi,
Have done some tests with latest unRaid and SSDs and got some surprising results. No meter how good SSDs are, write speed of unRaid never reaches network maximum. From the other hand, same hardware running under Windows 7 does. What's wrong?
Some details:
- used SATA3 SSDs on PCI-E2 add-on cards, which in Winows show >350 MB/s read and >250 MB/s write internal access speed (large sequential).
- Before each test (including unRaid), drives are forcely TRIMed (reset as new). So no SSD segmentation is occurring.
- unRaid is not even configured for parity at all (neither user shares enabled), just simple drives, so performance drop is not because of parity writing.
- when writing to shared drive under Windows 7 got read/write speed of 115 MB/s (which is 1 Gb network limit), means drives do function correctly to their full capacity.
- when writing to same shared drive under unRaid got 75 MB/s write only (that's on large sequential). Things getting even worth on small files. When doing the same with parity enabled (also SSD), performance drops down to 56 MB/s...
Frustrating...
Is there any special tuning/trick needed in order to make SSDs work to their full capacity under unRaid? Or such performance drop comparing to W7 is sort of "normal"?
Thanks for giving any ideas...
-
Still no input by developer?
-
When you say access, is that read or write?
In both cases, and it even seems that load is less when accessing user share. I know its weird, but that is what i see... maybe better CPU load tool needed.
-
Updated initial post with test method.
Also, some people are saying that this is low-end CPU issue. I disagree. First of all, I didn't notice higher CPU load when accessing to user shares comparing to disk shares. Secondly, my CPU was not even 100% loaded on either share access. I believe, problem lies somewhere else...
Besides, unRAID is advertised as "low hardware requirement". If to have same performance on user shares as on directly shared drives one needs a XEON E7 or something alike, this is not good for "home" server. Home server supposes to be low power, noiseless (read passive cooling), and that means low power/performance CPU.
As it was said:
... it flies in the face of years of unRAID recommendations.
I really wish (hope) to hear something from developer...
-
Updated initial post with hardware data
-
Hi,
After running multiple tests using SSDs on both client and server (7+1 disk), I can confirm that transfers to/from user Shares are more than 20% slower comparing to transfers to/from directly shared disks. All that on SMB network.
I think this is inherited issue from previous versions. User shares is a very important feature, but loosing >20% of transfer rate is pretty bad. Is there any chance to have that fixed in release?
Cheers.
Test setup
Server
- unRAID - Server Pro, Version 5.0-rc5
- Processor - Intel® AtomTM CPU N450 @ 1.66GHz
- Cache - L1 = 24 kB L2 = 512 kB
- Memory - 1 GB - DIMM0 = 667 MHz
- SSD - Verbatim 2SSD64 64GB * 8
Network
- Speed - 1000Mb/s Full Duplex
- Switch - Cisco SLM224P
Client
- OS - Windows7
- Processor - Intel Core I7 @3.40 GHz
- Memory - 16 GB
- SSD - M4-CT256M4SSD2
Testing method
- Software - NAS performance tester (http://www.808.dk/?code-csharp-nas-performance)
- File size - 4000 MB
- Loops -10
- Network mapped drive "Y" - directly shared empty SSD "drive 5"
- Network mapped drive "Z" - user share "test" with single included "drive 5" (same as directly shared)
- No cash drive
- unRAID - Server Pro, Version 5.0-rc5
-
-
Hi,
Any chance to see 28 (or more) storage devices in Pro version (not counting cash)?
Cheers.
-
Hi, Speeding_Ant
I would like to thank you one more time for this marvelous piece of software.
There is a minor bug I have noticed with the latest version. Have a look on attached screen print. Check out network graph. You will see that after a file transfer (spike in processor usage) the network usage graph didn't go down to zero activity at a due time, but rather was spread linearly from the time of transfer termination till the current time. This happens both in IE9 and Chrome.
Regards,
Eugene
-
Status floating bar sitll does not float on iPad Safari.
Many thanks. Regards.
-
Sorry just re-read your post. Do you mean it still scrolls up with the page, but blocks other content?
@ speeding ant
Yes, status bar scrolls up with the page and blocks content. That happens on iPad (safari) only.
Regards.
-
Hi,
Many thanks for excelet improvement to unRaid. Tom should seriously consider making this default feature.
I just wanted to report a little bug (or sort of). When using this GUI on iPad (safari), status line (one which says "array started" is not dynamically moved with page scroll, it actually keeps initial position (stays fixed on page) and scrolls with the page. I have noticed this misbehaviour on some other public Internet pages, so it might be not a bug of plugin, but general iPad/Safari problem.
Regards
-
Yeah, workaround ... works, thanks.
The same behaviour can be observed with user shares permissions change. For example, changing from "secure" to "public" requires array restart to make such change effective.
While this does not affect functionality directly, it would be quite nice to fix that, or at least, to make a notice or a pop-up saying that array restart is required for changes to be effective.
Any idea if Tom is planning something about that?
Regards.
-
Hi,
Problem - user stage available size not displayed correctly (not updated) after adding disk to array.
Here is how to reproduce the bug:
- create array with some (1P + 3D in my case) disks
- create user share wit "fill-up" option, split "1", empty for included and excluded disks
- Check available space in user shares list (3TB in my case)
- install additional (3 in my case) disks (pre clean and format), array size increases (to 6TB in my case)
- check available space for created earlier user share ---> free space displayed remained UNCHANGED (3TB in my case). I did not try to fill all that space with data to check if it's display only or real space problem.
I believe this is not intended behaviour and it would be quite nice to fix that.
Regards,
Eugene
Marvell disk controller chipsets and virtualization
in Defect Reports [DEPRECATED]
Posted
I meant 3 major version, e.g 4,5,6 (yes, that backwards).
Well, one way or another it works in OMV (Windows) and doesn’t in Unraid. A typical consumer business would “correct” the situation. Guess, UnRAID is still enthusiasts oriented.