[ale] networking backpressure

[George Allen]

Maybe using NFS over TCP instead of UDP may help? Over TCP the dropped
packets will cause the window size to increase, which would 'dial
down' the two clients after the initial overflow.

On Tue, Apr 9, 2013 at 10:02 PM, Jim Kinney <jim.kinney at gmail.com> wrote:
> Migrating asap to zfs for arrays and still NFS4 for share and adding 10G
> Ethernet. Zfs likes NFS and supports it directly.
>
> On Apr 9, 2013 9:35 PM, "Scott McBrien" <smcbrien at gmail.com> wrote:
>>
>> Sounds like you guys need to move to either a solution other than NFS or
>> change your server to something like a NetApp filer or another such device
>> that's had it's NFS stack monkeyed with to support more volume.
>>
>> -Scott
>>
>> On Apr 9, 2013, at 9:20 PM, Chuck Payne <terrorpup at gmail.com> wrote:
>>
>> Jim,
>>
>> Sounds like the same issue I having. Driving me crazy to fix it. I got a
>> script doing a ifconfig down and then an up and that works, but it a
>> bandage.
>>
>> My mounts are soft.
>>
>> I have Gig cards and Gig Switches.
>>
>> I will follow this to see it helps with my issue.
>>
>> Pup
>>
>>
>>
>>
>> On Tue, Apr 9, 2013 at 3:08 PM, JD <jdp at algoloma.com> wrote:
>>>
>>> On 04/09/2013 02:33 PM, Mike Harrison wrote:
>>> > On Tue, 9 Apr 2013, Jim Kinney wrote:
>>> >> so what happens when a series of machines, each with 1G nic all try to
>>> >> read/write to the same NFS mount filesystem,
>>> >> also on a single 1G nic, and this goes on for hours at a time?
>>> >> Eventually, nic
>>> >> buffers fill and the OS is told to "hold that thought". But for how
>>> >> long? Will
>>> >> the OS continue to try
>>> >> the write until it succeeds? Or will the constant buffer overload just
>>> >> cause a
>>> >> nic to flush the buffer and hope for
>>> >> better luck next send?
>>>
>>> My use of NFS is a little dated ... seems it would depend on the type of
>>> mount
>>> used - spongy, soft, or hard.
>>> If hard, it will try again and again and will appear to lockup the
>>> machine, IME.
>>> With soft mounts, writes aren't guaranteed.
>>> Spongy has the good of hard and the good of soft mounts. It will give up
>>> after a
>>> specific amount of time and continue as best it can - providing errors as
>>> required.  NFS mounts have lots of tunable params, if I recall correctly.
>>>
>>> Also, the specific buffer size for the involved NICs would matter too,
>>> but
>>> filling a network buffer should happen relatively quickly.
>>> _______________________________________________
>>> Ale mailing list
>>> Ale at ale.org
>>> http://mail.ale.org/mailman/listinfo/ale
>>> See JOBS, ANNOUNCE and SCHOOLS lists at
>>> http://mail.ale.org/mailman/listinfo
>>
>>
>>
>>
>> --
>> Terror PUP a.k.a
>> Chuck "PUP" Payne
>>
>> (678) 636-9678
>> -----------------------------------------
>> Discover it! Enjoy it! Share it! openSUSE Linux.
>> -----------------------------------------
>> openSUSE -- en.opensuse.org/User:Terrorpup
>> openSUSE Ambassador/openSUSE Member
>> Community Manager -- Southeast Linux Foundation (SELF)
>> skype,twiiter,identica,friendfeed -- terrorpup
>> freenode(irc) --terrorpup/lupinstein
>> Register Linux Userid: 155363
>>
>> Have you tried SUSE Studio? Need to create a Live CD,  an app you want to
>> package and distribute , or create your own linux distro. Give SUSE Studio a
>> try. www.susestudio.com.
>> See you at Southeast Linux Fest, June 7-9, 2013 in Charlotte, NC.
>> www.southeastlinuxfest.org
>>
>> _______________________________________________
>> Ale mailing list
>> Ale at ale.org
>> http://mail.ale.org/mailman/listinfo/ale
>> See JOBS, ANNOUNCE and SCHOOLS lists at
>> http://mail.ale.org/mailman/listinfo
>>
>>
>> _______________________________________________
>> Ale mailing list
>> Ale at ale.org
>> http://mail.ale.org/mailman/listinfo/ale
>> See JOBS, ANNOUNCE and SCHOOLS lists at
>> http://mail.ale.org/mailman/listinfo
>>
>
> _______________________________________________
> Ale mailing list
> Ale at ale.org
> http://mail.ale.org/mailman/listinfo/ale
> See JOBS, ANNOUNCE and SCHOOLS lists at
> http://mail.ale.org/mailman/listinfo
>