Weird Upload Performance for FreeNAS

[chungcf2006]

I have installed FreeNAS 11.2 on a Dell PowerEdge R510 server and hosted it on a data centre.

Now if I download some files from the FreeNAS server to my Desktop (via Internet), the performance is very poor.

So I am using speedtest-cli, which is using the servers used by speedtest.net. The following are the results obtained by testing from the servers hosted by 3 famous ISPs in Hong Kong on both FreeNAS and a Linux machine which has the identical network environment with the FreeNAS machine. The Upload and Download speed for the ISP we are using on Data Centre are 100 Mbps.

Show : FreeNAS

Hosted by HGC Global Communications Limited (Shatin) [10.08 km]: 27.98 ms Download: 90.91 Mbit/s Upload: 3.81 Mbit/s Hosted by CSL (Tai Po) [10.77 km]: 26.892 ms Download: 91.09 Mbit/s Upload: 3.87 Mbit/s Hosted by SmarTone (Hong Kong) [14.68 km]: 26.976 ms Download: 91.75 Mbit/s Upload: 82.72 Mbit/s

Show : Linux

Hosted by HGC Global Communications Limited (Shatin) [10.08 km]: 25.677 ms Download: 91.63 Mbit/s Upload: 88.48 Mbit/s Hosted by CSL (Tai Po) [10.77 km]: 28.326 ms Download: 91.61 Mbit/s Upload: 87.37 Mbit/s Hosted by SmarTone (Hong Kong) [14.68 km]: 32.798 ms Download: 86.57 Mbit/s Upload: 85.95 Mbit/s

As we can see, the upload speed for FreeNAS is generally very slow (only 3 Mb on a 100 Mb line) but the performance on Linux machine is normal.

However the performance on some servers are normal on both machine (SmarTone server in this case, I've tested for other Hong Kong servers which are normal also but I didn't post the result here).

I think the FreeNAS OS is the culprit since I've tested the speedtest script also on a Debian Live CD on this machine and the result is similar to that of the Linux server mentioned above.

Anyone has idea on this weird symptom?

 

[dlavigne]

What is the full output of ifconfig ?

 

[chungcf2006]

What is the full output of ifconfig ?

Code:

bce0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
        options=c01bb<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,TSO4,VLAN_HWTSO,LINKSTATE>
        ether 78:2b:cb:6c:32:86
        hwaddr 78:2b:cb:6c:32:86
        nd6 options=9<PERFORMNUD,IFDISABLED>
        media: Ethernet autoselect (1000baseT <full-duplex>)
        status: active
bce1: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
        options=c01bb<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,TSO4,VLAN_HWTSO,LINKSTATE>
        ether 78:2b:cb:6c:32:86
        hwaddr 78:2b:cb:6c:32:87
        nd6 options=9<PERFORMNUD,IFDISABLED>
        media: Ethernet autoselect (1000baseT <full-duplex>)
        status: active
lo0: flags=8049<UP,LOOPBACK,RUNNING,MULTICAST> metric 0 mtu 16384
        options=600003<RXCSUM,TXCSUM,RXCSUM_IPV6,TXCSUM_IPV6>
        inet6 ::1 prefixlen 128
        inet6 fe80::1%lo0 prefixlen 64 scopeid 0x3
        inet 127.0.0.1 netmask 0xff000000
        nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>
        groups: lo
lagg0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
        options=c01bb<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,TSO4,VLAN_HWTSO,LINKSTATE>
        ether 78:2b:cb:6c:32:86
        inet xxx.xxx.xxx.xxx netmask 0xffffffc0 broadcast xxx.xxx.xxx.xxx
        nd6 options=9<PERFORMNUD,IFDISABLED>
        media: Ethernet autoselect
        status: active
        groups: lagg
        laggproto loadbalance lagghash l2,l3,l4
        laggport: bce0 flags=4<ACTIVE>
        laggport: bce1 flags=4<ACTIVE>

 

[dlavigne]

Did you ever figure out the bottleneck? If not, it may be worth reporting at bugs.freenas.org.