Packet Loss exclusive to FreeNas software

[cyberjock]

Yes, still trying the broadcom. But I'll try an intel just to double check things as soon as I can. It's just sad that something which desires to be free and open would limit itself to such proprietary limitations (Don't take that the wrong way - I know it's not FreeNas' fault for lack of driver support).

Yeah, it's the NIC manufacturer's fault. ;)

 

[c32767a]

Yes, still trying the broadcom. But I'll try an intel just to double check things as soon as I can. It's just sad that something which desires to be free and open would limit itself to such proprietary limitations (Don't take that the wrong way - I know it's not FreeNas' fault for lack of driver support).

just out of curiosity, can you log into the freenas and run ifconfig -a and post the results here? You can wrap it in "code" tags to make it more readable.

 

[Curtipus]

Here's ifconfig -a

Code:

bce0: flags=8943<UP,BROADCAST,RUNNING,PROMISC,SIMPLEX,MULTICAST> metric 0 mtu 1500
    options=c00b9<RXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,VLAN_HWTSO,LINKSTATE>
    ether bc:30:5b:e4:32:7e
    inet 192.168.14.220 netmask 0xffffff00 broadcast 192.168.14.255
    inet6 fe80::be30:5bff:fee4:327e%bce0 prefixlen 64 scopeid 0x2 
    nd6 options=29<PERFORMNUD,IFDISABLED,AUTO_LINKLOCAL>
    media: Ethernet autoselect (1000baseT <full-duplex>)
    status: active
bce1: flags=8802<BROADCAST,SIMPLEX,MULTICAST> metric 0 mtu 1500
    options=c01bb<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,TSO4,VLAN_HWTSO,LINKSTATE>
    ether bc:30:5b:e4:32:7f
    nd6 options=29<PERFORMNUD,IFDISABLED,AUTO_LINKLOCAL>
    media: Ethernet autoselect
ipfw0: flags=8801<UP,SIMPLEX,MULTICAST> metric 0 mtu 65536
    nd6 options=29<PERFORMNUD,IFDISABLED,AUTO_LINKLOCAL>
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 0x6 
    inet 127.0.0.1 netmask 0xff000000 
    nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>
bridge0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
    ether 02:f3:32:cc:fc:00
    nd6 options=1<PERFORMNUD>
    id 00:00:00:00:00:00 priority 32768 hellotime 2 fwddelay 15
    maxage 20 holdcnt 6 proto rstp maxaddr 2000 timeout 1200
    root id 00:00:00:00:00:00 priority 32768 ifcost 0 port 0
    member: epair0a flags=143<LEARNING,DISCOVER,AUTOEDGE,AUTOPTP>
           ifmaxaddr 0 port 8 priority 128 path cost 2000
    member: bce0 flags=143<LEARNING,DISCOVER,AUTOEDGE,AUTOPTP>
           ifmaxaddr 0 port 2 priority 128 path cost 20000
epair0a: flags=8943<UP,BROADCAST,RUNNING,PROMISC,SIMPLEX,MULTICAST> metric 0 mtu 1500
    options=8<VLAN_MTU>
    ether 02:30:62:00:08:0a
    inet6 fe80::30:62ff:fe00:80a%epair0a prefixlen 64 scopeid 0x8 
    nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>
    media: Ethernet 10Gbase-T (10Gbase-T <full-duplex>)
    status: active

I will also add that I haven't found a spare Intel PCIe card yet and I'll probably have to buy one.

But here's something I did do: I destroyed the ZFS volume, restarted the server, created a new ZFS volume, added my datasets to it just as they were before and ran another copy of rsync. This time it ran completely successfully. I even went ahead and did another drag and drop within the File Manager of the same files from an earlier post I made (that had failed several times) and that copied flawlessly too. Permissions/other settings are identical if I look at each configuration that I had made.

Feel free to add any further comments you may have.

I'm not going to mark this as solved yet because I'm not sure if this is just a fluke. I'll post back with more results as I continue to use the server.

 

[c32767a]

Here's ifconfig -a


But here's something I did do: I destroyed the ZFS volume, restarted the server, created a new ZFS volume, added my datasets to it just as they were before and ran another copy of rsync. This time it ran completely successfully. I even went ahead and did another drag and drop within the File Manager of the same files from an earlier post I made (that had failed several times) and that copied flawlessly too. Permissions/other settings are identical if I look at each configuration that I had made.

Feel free to add any further comments you may have.

I'm not going to mark this as solved yet because I'm not sure if this is just a fluke. I'll post back with more results as I continue to use the server.

I was mostly curious if you had a negotiation mismatch on your ethernet interface, but it looks correct.

I don't have anything to add on the destroy/create thing..

 

[link1896]

I have an R210 with the same issue. Virtualized FreeNAS 9.2.1.7 with esxi 5.5. Transfers of small files were ok, or a bunch of small files under 5-8gb total, but large files would slow down to a crawl then fail. Packet loss was high. I removed the sas raid card and added an intel NIC, now happily transferring 40gb files at 70-80 mb/s.

This r210 is running Zentyal and FreeNAS under esxi 5.5. All backed up elsewhere, no precious data held here. The small energy footprint of the R210, for 24/7 operation is of significant importance.

My R210 spec:

X3470 @ 2.93ghz
16GB ECC (4 x 4gb)
1TB SATA x 2. (RAID grade)
120gb Intel SSD 330 x 1
Intel THGMP 4 port NIC

 

[cyberjock]

ESXi is going to have performance problems requiring tuning of ESXi. Sorry but I won't go into more detail about it.

 

[Curtipus]

ESXi is going to have performance problems requiring tuning of ESXi. Sorry but I won't go into more detail about it.

I think you misread what link1896 was trying to tell me. He had said that he was having the same problem I was and that he solved it by using intel NICs. His choice of virtualization could very well have an impact, too, but he wasn't asking for assistance with that.

For whatever reason, I haven't noticed any further problems myself since my last post. It's all working very nicely and I'm a happy camper.

 

[jgreco]

His choice of virtualization could very well have an impact, too, but he wasn't asking for assistance with that.

The moment you virtualize, the hypervisor becomes part of the equation. If you're suddenly having network issues, come here for help, and you're virtualizing, then the virtualization aspect is fair game for discussion regardless of whether or not it was specifically requested...

 

[Curtipus]

The moment you virtualize, the hypervisor becomes part of the equation. If you're suddenly having network issues, come here for help, and you're virtualizing, then the virtualization aspect is fair game for discussion regardless of whether or not it was specifically requested...

I don't know why you felt the need to tell me this? My problem is not with virtualization as my setup at fault here isn't even using it and I already understand the risks with virtualization.

 

[jgreco]

I don't know why you felt the need to tell me this?

Because it takes quite a pair to walk into a forum as a new participant and tell high volume posters what someone was or wasn't asking for assistance with. It was a polite way of scolding you for saying the text I quoted above.