p13

Members
  • Posts

    19
  • Joined

  • Last visited

Everything posted by p13

  1. 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...
  2. 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.
  3. 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: I really wish (hope) to hear something from developer...
  4. 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
  5. Hi, Any chance to see 28 (or more) storage devices in Pro version (not counting cash)? Cheers.
  6. 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
  7. Status floating bar sitll does not float on iPad Safari. Many thanks. Regards.
  8. @ speeding ant Yes, status bar scrolls up with the page and blocks content. That happens on iPad (safari) only. Regards.
  9. 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
  10. 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.
  11. 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