[Samba] Transfer rates faster than 23MBps?

[Mark Smith]

I have not.  Unfortunately, that is not a trivial process.  I believe 
everything supports it, but it's a somewhat major change to my 
production systems.  It might be worth trying as a data point, however.

Given the iPerf tests, I really don't think it's a network bottleneck at 
this point.

-Mark

Pitti, Raul wrote:
> i am not an expert, but,
> do you have jumbo frame enabled on your nic and  switch?
> try using ethtools...
> 
> RP
> 
> Mark Smith wrote:
>> Mark Smith wrote:
>>> As a data point, I'm going to try a newer version of Samba.  (RHEL4 
>>> uses 3.0.10-RedHat-Heavily-Modified-Of-Course)  If that makes a 
>>> difference, then I have to decide whether it's worth it to me to keep 
>>> RedHat support or not.  (And when I say "I," I really mean "my 
>>> management.")
>>
>> I've just tried this.  Samba v3.0.23c, built locally from the Fedora 
>> Source RPM as distributed at samba.org, makes no noticeable 
>> difference:  still about 45 seconds.
>>
>>>> I have lots of memory.  I use these configurations in sysctl.conf to 
>>>> up the performance of send/recieve windows on my systems.  There's 
>>>> articles out there.  I don't have historical references handy.
>>>> YMMV.
>>>> net.core.wmem_max = 1048576
>>>> net.core.rmem_max = 1048576
>>>> net.ipv4.tcp_wmem = 4096 65536 1048575
>>>> net.ipv4.tcp_rmem = 4096 524288 1048575
>>>> net.ipv4.tcp_window_scaling = 1
>>>
>>> I have not tried tweaking the TCP stack in the OS.  I'll give that a 
>>> shot.
>>
>> The person at RedHat who's handling my ticket just suggested these 
>> very changes, without the last one.  They did not help.  The values he 
>> gave were a little different:
>>
>> ----- snip! -----
>> # increase TCP maximum buffer size
>> net.core.rmem_max = 16777216
>> net.core.wmem_max = 16777216
>>
>> # increase Linux autotuning TCP buffer limits
>> # min, default, and maximum number of bytes to use
>> net.ipv4.tcp_rmem = 4096 87380 16777216
>> net.ipv4.tcp_wmem = 4096 65536 16777216
>> ----- snip! -----
>>
>> I also tried your values, with the tcp_window_scaling, with no luck.
>>
>> -Mark
>