NDT-DEV email list created

[Kavitha Kumar <>]

Hi Alan/Eli/others,

    Here's a RPM/source that I think will fix the issue you reported. Would you be able to test this on your setup ?

Thanks,

Kavitha

---

From: Eli Dart <>
Date: December 21, 2012, 11:23:00 AM EST
To: Alan Whinery <>
Cc: TLPW PerfSONAR Club <>
Subject: Re: Funny web100clt output
Reply-To: <>

On 12/20/12 11:16 PM, Alan Whinery wrote:

I found this amusing:

Checking for Middleboxes . . . . . . . . . . . . . . . . . .  Done

checking for firewalls . . . . . . . . . . . . . . . . . . .  Done

running 10s outbound test (client to server) . . . . .  875.96 Mb/s

running 10s inbound test (server to client) . . . . . . 758.64 Mb/s

The slowest link in the end-to-end path is a 10 Gbps 10 Gigabit

Ethernet/OC-192 subnet

Information: The receive buffer should be

-26815615860811546501625050117287787328309182590883722076948913662186352464796058042772490767901870558730916594732010558223785459518905051590698094924136448

kbytes to maximize throughput

Seems a sanity check is lacking.

The scenario is ~1 ms rtt, two machines in the same room,  one router

between, one's connected at 1 Gbps (hence the slowest link guess is

wrong), one's connected at 10 Gbps.

But the prescribed receive buffer is apparently some sort of negative

RAM, probably makes use of FTL neutrinos...

That looks like a signed vs. unsigned bug for a 64 bit integer...

       --eli

Happy Holidays.

Alan

--
Eli Dart                                            NOC: (510) 486-7600
ESnet Network Engineering Group (AS293)                  (800) 333-7638
Lawrence Berkeley National Laboratory
PGP Key fingerprint = C970 F8D3 CFDD 8FFF 5486 343A 2D31 4478 5F82 B2B3