July 29, 201411 yr Running the following with no cache drive on Gigabit LAN. Tested copying files across Win8.1 systems and at "gigabit" speeds. When copy to Unraid server performance is usually 12mb/sec or less. Also when accessing the UNRAID GUI I have to refresh the browser 4-5 times before I'm prompted with the login. Recently installed Dynamix GUI and plugins for troubleshooting purposes however issue persisted before the GUI replacement. Array is configured as "highwater" Wondering if possible IRQ conflict with NIC - system has added SATA card. Total of 10 drives (1 parity, 9 storage). Attached syslog. Appreciate any help, Thanks unRAID Version: unRAID Server Pro, Version 5.0.5 Motherboard: BIOSTAR Group - A760G M2+ Processor: AMD Athlon II X2 250 - 3 GHz Cache: L1-Cache = 256 kB (max. 256 kB) L2-Cache = 2048 kB (max. 2048 kB) Memory: 4096 Module (max. 8 GB) BANK0 = 2048 MB, 400 MHz BANK1 = 2048 MB, 400 MHz BANK2 = No Module Installed, Unknown BANK3 = No Module Installed, Unknown Network: eth0: 1000Mb/s - Full Duplex Also drive specs: [disks] => Array ( [parity] => Array ( [idx] => 0 [name] => parity [device] => sdg [id] => WDC_WD30EFRX-68EUZN0_WD-WMC4N2008469 => 2930266532 [status] => DISK_OK [temp] => 26 [numReads] => 717 [numWrites] => 1177 [numErrors] => 0 [format] => GPT: 4K-aligned => green-on [fsStatus] => - [spindownDelay] => -1 [spinupGroup] => host2 [deviceSb] => [idSb] => WDC_WD30EFRX-68EUZN0_WD-WMC4N2008469 [sizeSb] => 2930266532 ) [disk1] => Array ( [idx] => 1 [name] => disk1 [device] => hda [id] => WDC_WD15EARS-00Z5B1_WD-WMAVU1318286 => 1465138552 [status] => DISK_OK [temp] => 27 [numReads] => 37 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host1 [deviceSb] => md1 [idSb] => WDC_WD15EARS-00Z5B1_WD-WMAVU1318286 [sizeSb] => 1465138552 [fsFree] => 733249036 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk2] => Array ( [idx] => 2 [name] => disk2 [device] => sdh [id] => ST31000528AS_9VP439BY => 976762552 [status] => DISK_OK [temp] => 27 [numReads] => 28 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host3 [deviceSb] => md2 [idSb] => ST31000528AS_9VP439BY [sizeSb] => 976762552 [fsFree] => 739706672 [fsSize] => 976732736 [fsType] => reiserfs ) [disk3] => Array ( [idx] => 3 [name] => disk3 [device] => sdf [id] => WDC_WD30EFRX-68EUZN0_WD-WMC4N2110389 => 2930266532 [status] => DISK_OK [temp] => 26 [numReads] => 718 [numWrites] => 1079 [numErrors] => 0 [format] => GPT: 4K-aligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host4 [deviceSb] => md3 [idSb] => WDC_WD30EFRX-68EUZN0_WD-WMC4N2110389 [sizeSb] => 2930266532 [fsFree] => 1958625488 [fsSize] => 2930177100 [fsType] => reiserfs ) [disk4] => Array ( [idx] => 4 [name] => disk4 [device] => sdi [id] => Hitachi_HDS5C3015ALA632_ML0B20F30UMH2D => 1465138552 [status] => DISK_OK [temp] => 27 [numReads] => 44 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host4 [deviceSb] => md4 [idSb] => Hitachi_HDS5C3015ALA632_ML0B20F30UMH2D [sizeSb] => 1465138552 [fsFree] => 812927120 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk5] => Array ( [idx] => 5 [name] => disk5 [device] => sdd [id] => ST31500341AS_9VS0A5NT => 1465138552 [status] => DISK_OK [temp] => 29 [numReads] => 35 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host5 [deviceSb] => md5 [idSb] => ST31500341AS_9VS0A5NT [sizeSb] => 1465138552 [fsFree] => 827305340 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk6] => Array ( [idx] => 6 [name] => disk6 [device] => sdc [id] => ST31500341AS_9VS44BYS => 1465138552 [status] => DISK_OK [temp] => 29 [numReads] => 32 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host6 [deviceSb] => md6 [idSb] => ST31500341AS_9VS44BYS [sizeSb] => 1465138552 [fsFree] => 861018272 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk7] => Array ( [idx] => 7 [name] => disk7 [device] => sdb [id] => WDC_WD15EADS-00R6B0_WD-WCAVY6602470 => 1465138552 [status] => DISK_OK [temp] => 29 [numReads] => 24 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => host7 [deviceSb] => md7 [idSb] => WDC_WD15EADS-00R6B0_WD-WCAVY6602470 [sizeSb] => 1465138552 [fsFree] => 1116471868 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk8] => Array ( [idx] => 8 [name] => disk8 [device] => hdb [id] => SAMSUNG_HD154UI_S1XWJ1CZ201663 => 1465138552 [status] => DISK_OK [temp] => 20 [numReads] => 21 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => ide0 [deviceSb] => md8 [idSb] => SAMSUNG_HD154UI_S1XWJ1CZ201663 [sizeSb] => 1465138552 [fsFree] => 1419948728 [fsSize] => 1465093832 [fsType] => reiserfs ) [disk9] => Array ( [idx] => 9 [name] => disk9 [device] => sde [id] => ST1500DM003-9YN16G_S2406LHS => 1465138552 [status] => DISK_OK [temp] => 33 [numReads] => 11 [numWrites] => 10 [numErrors] => 0 [format] => MBR: unaligned => green-on [fsStatus] => Mounted [spindownDelay] => -1 [spinupGroup] => [deviceSb] => md9 [idSb] => ST1500DM003-9YN16G_S2406LHS [sizeSb] => 1465138552 [fsFree] => 1465060992 [fsSize] => 1465093832 [fsType] => reiserfs ) => Array ( [idx] => 25 [name] => flash [device] => sda [id] => DataTraveler_R => 2031072 [status] => DISK_OK [temp] => * [numReads] => 251 [numWrites] => 22 [numErrors] => 0 [format] => unknown => green-on [fsStatus] => Mounted [fsFree] => 1984608 [fsSize] => 2030784 [fsType] => vfat ) ) syslog.txt
July 30, 201411 yr check smart reports. I had a similar issue (writing/reading) from a cache drive. turned out errors causing by a bad sata cable were slowing it all down to a crawl.
July 30, 201411 yr This sounds suspiciously like 100MB network speeds. Are you sure your network hasn't degraded in some way? What does ethtool eth0 show?
July 30, 201411 yr Author Thanks for responding. Kat Icarus login: root Password: Linux 3.9.11p-unRAID. root@Icarus:~# ethtool eth0 Settings for eth0: Supported ports: [ TP ] Supported link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Supports auto-negotiation: Yes Advertised link modes: 10baseT/Half 10baseT/Full 100baseT/Half 100baseT/Full 1000baseT/Full Advertised pause frame use: Symmetric Receive-only Advertised auto-negotiation: Yes Speed: 1000Mb/s Duplex: Full Port: Twisted Pair PHYAD: 0 Transceiver: internal Auto-negotiation: on MDI-X: Unknown Supports Wake-on: pumbg Wake-on: g Current message level: 0x00000033 (51) Link detected: yes root@Icarus:~#
July 30, 201411 yr This sounds suspiciously like 100MB network speeds. Are you sure your network hasn't degraded in some way? What does ethtool eth0 show? How about the connection on the windows machine? Do you have other clients you can test with? What exactly is your network topology? Have you power cycled your gigabit switch recently? Do you have any wireless clients connected?
July 30, 201411 yr Author The connection to the Windows machine are all on the same switch. I've tried another switch to the same results. Have 5 computers in the house including two laptops which all report average around anywhere from 90-100mb/sec which is what I expect. Did hard wire the two laptops to test. Replaced the Ethernet cable to make sure on the unraid server with CAT-6 certified 3 foot cable with no improvements. I seemed to recall running Unraid 4.5 or maybe even earlier I did not have this performance issue but have since added more drives included a PCI SATA card and thought maybe there was an IRQ conflict with the NIC. Appreciate the help, Kat
July 30, 201411 yr Author check smart reports. I had a similar issue (writing/reading) from a cache drive. turned out errors causing by a bad sata cable were slowing it all down to a crawl. Let me Google this...not familiar with smart reports - suspect reference to S.M.A.R.T. Update - http://lime-technology.com/wiki/index.php/Troubleshooting#Obtaining_a_SMART_report However wouldn't the performance be sporadic then? I would suspect when Unraid is writing to a drive which does not have a defective SATA cable then performance would resume to normal expected speeds. No cache drive on my system at this time. Thanks - Kat
July 30, 201411 yr Author Adding network.cfg file for reference: # Generated settings: USE_DHCP="no" IPADDR="192.168.1.69" NETMASK="255.255.255.0" GATEWAY="192.168.1.1" DHCP_KEEPRESOLV="no" DNS_SERVER1="192.168.1.1" DNS_SERVER2="" DNS_SERVER3="" BONDING="no" BONDING_MODE="1"
July 31, 201411 yr Author What does "ifconfig" output? root@Icarus:/dev/disk# ifconfig eth0 Link encap:Ethernet HWaddr 00:30:67:0c:03:d9 inet addr:192.168.1.69 Bcast:192.168.1.255 Mask:255.255.255.0 UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:5182283 errors:0 dropped:16 overruns:0 frame:0 TX packets:3760403 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:2205073164 (2.0 GiB) TX bytes:2377213121 (2.2 GiB) Interrupt:41 lo Link encap:Local Loopback inet addr:127.0.0.1 Mask:255.0.0.0 UP LOOPBACK RUNNING MTU:65536 Metric:1 RX packets:9 errors:0 dropped:0 overruns:0 frame:0 TX packets:9 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:0 RX bytes:661 (661.0 B) TX bytes:661 (661.0 B) root@Icarus:/dev/disk#
July 31, 201411 yr Author Start in SAFE-Mode and check the speed. I see in your sig outlining safe mode. Not finding anything in the Wiki outlining more detail. Can you provide a link on implementation of "safe mode"? Appreciate your time. Kat
July 31, 201411 yr Start in SAFE-Mode and check the speed. I see in your sig outlining safe mode. Not finding anything in the Wiki outlining more detail. Can you provide a link on implementation of "safe mode"? Appreciate your time. Kat Safe Mode is in the boot menu. It starts unRAID but skips installation of addons. It was added during the v5 betas. You had to copy the new syslinux to get it. If you didn't, then you can accomplish the same thing by following the instructions in dgaschk's sig, which disables your addons by changing their location (renaming their folders) so the unRAID startup code doesn't use them when it boots. "Reverting to stock" is a good first step in debugging because it eliminates a lot of possible unknowns.
July 31, 201411 yr Author Start in SAFE-Mode and check the speed. I see in your sig outlining safe mode. Not finding anything in the Wiki outlining more detail. Can you provide a link on implementation of "safe mode"? Appreciate your time. Kat Safe Mode is in the boot menu. It starts unRAID but skips installation of addons. It was added during the v5 betas. You had to copy the new syslinux to get it. If you didn't, then you can accomplish the same thing by following the instructions in dgaschk's sig, which disables your addons by changing their location (renaming their folders) so the unRAID startup code doesn't use them when it boots. "Reverting to stock" is a good first step in debugging because it eliminates a lot of possible unknowns. Super thanks - will try this later this evening. I don't remember the last time I had a monitor hooked up to the Unraid box -Kat
August 1, 201411 yr Author Found out the problem - bad Ethernet cable between the Unraid server and the Windows boxes. Cable that sits in the switch cabinet I didn't think to check. Swapped it out and now I'm getting 65MB/sec transfer rates Thank you everyone for your assistance, -Kat
August 1, 201411 yr Not at all surprising. Note that anytime your network speed drops to 100Mb speeds (~ 12MB/s) it's almost certainly a bad pair in the cable. This can impact both directions ... or just one direction (which is often more perplexing). But I've never seen a case where a drop to this speed range wasn't either a bad cable or a bad switch port. As you've just noted, you have to consider EVERY cable in the topology. I've seen a short (12") cable between a UPS and the server have this issue ... probably caused by a slight movement of the server chassis when I was blowing out the dust.
Archived
This topic is now archived and is closed to further replies.