Extreme slow samba speeds

    • OMV 0.5

    This site uses cookies. By continuing to browse this site, you are agreeing to our Cookie Policy.

    • Extreme slow samba speeds

      First up the build

      MSI k8n neo4-f
      Amd fx-60
      2gb ocz el platinum
      Tplink GB nic
      1 2tb WD green
      1 1tb WD blue
      1 500gb WD green
      2 250 GB ide drives

      Basically built out of spare parts, now the samba problem.

      During single file transfers from windows 7 machine to OMV I'm getting 40ish mb/sec via samba, one it becomes a multiple file transfer it drops to 2mb or lower per second, enough to make you want to drink.

      Transferring the same files in a batch over ftp gives 40+ mb/sec.

      Neither of the speeds is all that fantastic for full GB either net throughout the entire network. Needless to say the samba speed has to increase because I don't really want to go back to nas4free.

      Any help would be appreciated.
    • My speeds use to drop a while into the transfer, so I tried adding these options to the extra options (from this vornoff.wordpress.com/2012/02/…fer-rates-of-samba-shares )

      Source Code

      1. max protocol = SMB2
      2. max xmit = 65535
      3. socket options = TCP_NODELAY IPTOS_LOWDELAY SO_SNDBUF=65535 SO_RCVBUF=65535
      4. read raw = yes
      5. write raw = yes
      6. max connections = 65535
      7. max open files = 65535

      Transfering one file (size 2.7 GB) had the speed of 96MB/s. Transferring 3GB of music files ran at about 30-35MB/s and was declining in speed. Three files at a total of 5.7GB together was about 80-95MB/s. All these transfers were from OMV to my computer though.

      I would start with testing the network with iperf and see what speeds you get, it could be a bad router/switch or something else :) You should also check the performance of the drives so you know their limit.
    • Hi,

      I had the same problem i did test the lan connection and got speeds up to 80 to 90 mbs but the nic i had in the nas was not good so i got 2 more nic's from intell and and pared them up
      now a have no more problems with file transfer.
      gr. steel

      Cooler Master CM 690 III
      with 650 watt 80+ gold power supply
      AMD A8-5600k processor
      8 GB ddr 3 1333 ram
      crusial 120 ssd
      5 x 2 TB WesternDigital red harddrive in raid 5
      2 intel 1000mT nic's
      latest OMV stone burner

      lets get cooking .....
      don't be afraid of learning it can be fun
    • <update>
      I have tried all 3 nics, basically all have about the same response.

      I tried the above samba conf change, restarted samba service, seems to be the same situation.

      So to aid in diagnostic below is a rough network diagram. I know this may not be the right place for network diagnostics, but I'd really like to get to the bottom of this.



      If anybody would care to chime in with the next idea I would appreciate it.
    • You hop through three switches, alltough I doubt they could interfere, rule it out by going over just one switch instead.

      Greetings
      David
      "Well... lately this forum has become support for everything except omv" [...] "And is like someone is banning Google from their browsers"

      Only two things are infinite, the universe and human stupidity, and I'm not sure about the former.


      Upload Logfile via WebGUI/CLI
      #openmediavault on freenode IRC | German & English | GMT+1
      Absolutely no Support via PM!

      I host parts of the omv-extras.org Repository, the OpenMediaVault Live Demo and the pre-built PXE Images. If you want you can take part and help covering the costs by having a look at my profile page.
    • Are you copying small or big files?

      Greetings
      David
      "Well... lately this forum has become support for everything except omv" [...] "And is like someone is banning Google from their browsers"

      Only two things are infinite, the universe and human stupidity, and I'm not sure about the former.


      Upload Logfile via WebGUI/CLI
      #openmediavault on freenode IRC | German & English | GMT+1
      Absolutely no Support via PM!

      I host parts of the omv-extras.org Repository, the OpenMediaVault Live Demo and the pre-built PXE Images. If you want you can take part and help covering the costs by having a look at my profile page.
    • if your switch is smart enough to have a web interface check the ports for errors/crc errors.

      To rule that out connect your workstation (set up with static ip) directly with the omv box (also with static ip)

      edit: try out iperf to check your network speed

      client: iperf -c <ipaddressofserve>
      server: iperf -s

      iperf.fr
      Tom

      ----

      HP N54L, 6GB, 5disc Raid5, SSD Boot with OMV Stone Burner
      HP N54L, 16GB, 4disc Raid5, SSD Boot with OMV Stone Burner
    • Ok, so I tried tonigh and my down speed seemed reasonable (40MB/sec) upload was about 30MB/sec on single 1.5 GB files

      Now on a lot of smaller files, it starts off at around 1.5MB/sec, goes up to 14MB/sec, mow 5 minutes in its down to 2.1MB/sec and slowing down.

      iperf gave me the following

      Brainfuck Source Code

      1. ------------------------------------------------------------
      2. Client connecting to 192.168.1.250, TCP port 5001
      3. TCP window size: 64.0 KByte (default)
      4. ------------------------------------------------------------
      5. [ 3] local 192.168.1.173 port 56778 connected with 192.168.1.250 port 5001
      6. [ ID] Interval Transfer Bandwidth
      7. [ 3] 0.0-10.0 sec 783 MBytes 656 Mbits/sec
      8. C:\iperf>iperf -c 192.168.1.250
      9. ------------------------------------------------------------
      10. Client connecting to 192.168.1.250, TCP port 5001
      11. TCP window size: 64.0 KByte (default)
      12. ------------------------------------------------------------
      13. [ 3] local 192.168.1.173 port 56779 connected with 192.168.1.250 port 5001
      14. [ ID] Interval Transfer Bandwidth
      15. [ 3] 0.0-10.0 sec 784 MBytes 657 Mbits/sec
      Display All


      Processes as as follows

      Source Code

      1. PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
      2. 1 root 20 0 8356 768 636 S 0 0.0 0:01.97 init
      3. 2 root 20 0 0 0 0 S 0 0.0 0:00.00 kthreadd
      4. 3 root RT 0 0 0 0 S 0 0.0 0:00.06 migration/0
      5. 4 root 20 0 0 0 0 S 0 0.0 0:00.60 ksoftirqd/0
      6. 5 root RT 0 0 0 0 S 0 0.0 0:00.00 watchdog/0
      7. 6 root RT 0 0 0 0 S 0 0.0 0:00.06 migration/1
      8. 7 root 20 0 0 0 0 S 0 0.0 0:06.49 ksoftirqd/1
      9. 8 root RT 0 0 0 0 S 0 0.0 0:00.00 watchdog/1
      10. 9 root 20 0 0 0 0 S 0 0.0 0:02.07 events/0
      11. 10 root 20 0 0 0 0 S 0 0.0 0:01.16 events/1
      12. 11 root 20 0 0 0 0 S 0 0.0 0:00.00 cpuset
      13. 12 root 20 0 0 0 0 S 0 0.0 0:00.00 khelper
      14. 13 root 20 0 0 0 0 S 0 0.0 0:00.00 netns
      15. 14 root 20 0 0 0 0 S 0 0.0 0:00.00 async/mgr
      16. 15 root 20 0 0 0 0 S 0 0.0 0:00.00 pm
      17. 16 root 20 0 0 0 0 S 0 0.0 0:00.18 sync_supers
      18. 17 root 20 0 0 0 0 S 0 0.0 0:00.24 bdi-default
      19. 18 root 20 0 0 0 0 S 0 0.0 0:00.00 kintegrityd/0
      20. 19 root 20 0 0 0 0 S 0 0.0 0:00.00 kintegrityd/1
      21. 20 root 20 0 0 0 0 S 0 0.0 0:00.10 kblockd/0
      22. 21 root 20 0 0 0 0 S 0 0.0 0:00.15 kblockd/1
      23. 22 root 20 0 0 0 0 S 0 0.0 0:00.00 kacpid
      24. 23 root 20 0 0 0 0 S 0 0.0 0:00.00 kacpi_notify
      25. 24 root 20 0 0 0 0 S 0 0.0 0:00.00 kacpi_hotplug
      26. 25 root 20 0 0 0 0 S 0 0.0 0:00.00 kseriod
      27. 26 root 20 0 0 0 0 S 0 0.0 0:00.00 kondemand/0
      28. 27 root 20 0 0 0 0 S 0 0.0 0:00.00 kondemand/1
      29. 53 root 20 0 0 0 0 S 0 0.0 0:00.06 khungtaskd
      30. 54 root 20 0 0 0 0 S 0 0.0 0:25.41 kswapd0
      31. 55 root 25 5 0 0 0 S 0 0.0 0:00.00 ksmd
      32. 56 root 20 0 0 0 0 S 0 0.0 0:00.00 aio/0
      33. 57 root 20 0 0 0 0 S 0 0.0 0:00.00 aio/1
      34. 58 root 20 0 0 0 0 S 0 0.0 0:00.00 crypto/0
      35. 59 root 20 0 0 0 0 S 0 0.0 0:00.00 crypto/1
      36. 257 root 20 0 0 0 0 S 0 0.0 0:00.00 ksuspend_usbd
      37. 258 root 20 0 0 0 0 S 0 0.0 0:00.00 khubd
      38. 260 root 20 0 0 0 0 S 0 0.0 0:00.00 ata/0
      39. 261 root 20 0 0 0 0 S 0 0.0 0:00.02 ata/1
      40. 262 root 20 0 0 0 0 S 0 0.0 0:00.00 ata_aux
      41. 265 root 20 0 0 0 0 S 0 0.0 0:00.00 scsi_eh_0
      42. 266 root 20 0 0 0 0 S 0 0.0 0:00.00 scsi_eh_1
      Display All


      cpu usage now shows 100% while transferring which seems strange for a FX-60, the old P4 2.8 could handle it all day long, but the mobo was getting sketchy.

      In searching a little more I found this is the syslog

      Source Code

      1. Sep 8 22:02:31 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228151; last cache update = 1410228151;
      2. Sep 8 22:02:31 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      3. Sep 8 22:03:05 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228185; last cache update = 1410228185;
      4. Sep 8 22:03:05 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      5. Sep 8 22:03:36 xxxxxxxxx monit[2023]: 'localhost' cpu wait usage of 97.6% matches resource limit [cpu wait usage>95.0%]
      6. Sep 8 22:03:36 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228216; last cache update = 1410228216;
      7. Sep 8 22:03:36 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      8. Sep 8 22:04:00 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228240; last cache update = 1410228240;
      9. Sep 8 22:04:00 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      10. Sep 8 22:04:33 xxxxxxxxx monit[2023]: 'localhost' 'localhost' cpu wait usage check succeeded [current cpu wait usage=66.2%]#012
      11. Sep 8 22:04:33 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228273; last cache update = 1410228273;
      12. Sep 8 22:04:33 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      13. Sep 8 22:05:25 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228325; last cache update = 1410228325;
      14. Sep 8 22:05:25 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      15. Sep 8 22:05:53 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228353; last cache update = 1410228353;
      16. Sep 8 22:05:53 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      17. Sep 8 22:06:26 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228386; last cache update = 1410228386;
      18. Sep 8 22:06:26 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      19. Sep 8 22:06:56 xxxxxxxxx collectd[3113]: uc_update: Value too old: name = localhost/df/df-media-CE5E2E0A5E2DEC41; value time = 1410228416; last cache update = 1410228416;
      20. Sep 8 22:06:56 xxxxxxxxx collectd[3113]: Filter subsystem: Built-in target `write': Dispatching value to all write plugins failed with status -1.
      Display All


      The post was edited 2 times, last by roeulogy ().

    • Hi,

      It sounds like you have traffic problems is it possible to test out the connection to the OMV box as a stand alone connected to ONLY your work computer ?
      gr. steel

      Cooler Master CM 690 III
      with 650 watt 80+ gold power supply
      AMD A8-5600k processor
      8 GB ddr 3 1333 ram
      crusial 120 ssd
      5 x 2 TB WesternDigital red harddrive in raid 5
      2 intel 1000mT nic's
      latest OMV stone burner

      lets get cooking .....
      don't be afraid of learning it can be fun
    • Sorry about the delayed response, I'm currently reinstalling on another machine to take its place, its a higher powered machine as it is, but still has the same hard drives and 1 of the same nics, so in a few hours (after some formatting and configuration) I will test again and see if it is a network issue, software issue, or hardware issue.
    • Also had slow speeds

      set it up a while ago with an RC i believe. didnt think about it too much until now when i also had really slow speeds using CIFS/SAMBA.

      turns out i changed my local dns while ago, changed in OMV and bam i got fast speeds again.

      can it be something like that?
    • Guys,

      I'm using max protocol = SMB2 for Windows 10, and my read speed increased a little bit.
      I wonder if OMV 2.0 supports max protocol = SMB3 or not.

      Thanks.


      Source Code

      1. ii libwbclient0:amd64 2:3.6.6-6+deb7u5 amd64 Samba winbind client library
      2. ii samba 2:3.6.6-6+deb7u5 amd64 SMB/CIFS file, print, and login server for Unix
      3. ii samba-common 2:3.6.6-6+deb7u5 all common files used by both the Samba server and client
      4. ii samba-common-bin 2:3.6.6-6+deb7u5 amd64 common files used by both the Samba server and client


      Display Spoiler

      Source: wiki.samba.org/index.php/Samba3/SMB2
      IntroductionThis page describes the plan, design and work in progress of the efforts to implement SMB2 in Samba3.

      SMB 2.0 (SMB2.02 dialect) was introduced with Windows Vista/2008.Samba 3.6 added basic support for SMB2.0. This support was essentially complete except for one big item:durable file handles (Added in Samba 4.0.0)

      SMB 2.1 was introduced with Windows 7/Windows 2008R2.Basic support for SMB 2.1 was added in Samba 4.0.0
      Features done:multi credit/large MTU (Added in Samba 4.0.0)
      dynamic reauthentication (Added in Samba 4.0.0)
      writethrough (Added in Samba 4.0.0)
      leases (Added in Samba 4.2.0)

      Features TODO:resilient file handles
      branch cache

      SMB 3 (previously known as SMB2.2 dialect) was introduced with Windows 8 and Windows Server 2012. SMB3 dialect defines the following features:Basic support for SMB3 is included in Samba 4.0.0 and later.
      security improvements (Added in 4.0.0)improved faster more secure packet signing
      secure negotiate protection against downgrade attacks
      share level encryption

      directory leases
      persistent file handles
      multi channel
      witness notification protocol (a new RPC service)
      interface discovery (a new FSCTL)
      SMB direct (SMB 3 over RDMA)
      Support for a misc. set of loosely related storage features for virtualization (new fsctls, T10 block copy offload, TRIM etc.)
      remote shadow copy support
      branch cache v2

      SMB3.02 was introduced in Windows 8.1 (Windows 'Blue') and Windows Server 2012 R2. Among the new protocol features are those particularly useful for virtualization (HyperV):SMB3.02 dialect is not yet negotiated by Samba servers
      SMB3.02 dialect can be requested by the Linux cifs client ("vers=3.02" on mount) but the new optional features, unique to SMB3.02, are not requested.
      Unbuffered I/O flags (ie a 'no cache flag' which may be sent on read or write)
      New RDMA remote invalidate flag
      MS-RSVD (a set of remoteable FSCTLs that improve "SCSI over SMB3")
      Asymmetric Shares (extensions to Witness protocol to allow moving users of one share to a different server, eg for load balancing or maintenance - previously witness protocol could only do this on a per server rather than per-share basis).

      SMB3.11 is expected to be introduced in Windows 10. Among the new features defined so far are:Improvements to security negotiation ("negotiate contexts") and dynamically selectable Cipher and Hash Algorithms. Implemented in the Samba client libraries (in master branch) but not in Samba server yet.
      New FSCTL for server side copying of file ranges (implementation waiting on Windows server to test against)

      OMV v3.0
      Asus Z97-A/3.1; i3-4370
      32GB RAM Corsair Vengeance Pro
      4x3TB RAID10