merge hpn12v17

diff --git a/openssh/HPN12-README b/openssh/HPN12-README
index 8140a90ea64fc653033ac7d64ea6f0bdbdcb47d1..ecd76aef2d4a4f660886e6eb9a22bd44c699325e 100644 (file)
--- a/openssh/HPN12-README
+++ b/openssh/HPN12-README
@@ -1,4 +1,65 @@
-config options
+Notes:
+
+To use the NONE option you must have the NoneEnabled switch set on the server and
+you *must* have *both* NoneEnabled and NoneSwitch set to yes on the client. The NONE
+feature works with ALL ssh subsystems (as far as we can tell) *AS LONG AS* a tty is not 
+spawned. If a user uses the -T switch to prevent a tty being created the NONE cipher will
+be disabled. 
+
+The performance increase will only be as good as the network and TCP stack tuning
+on the reciever side of the connection allows. As a rule of thumb a user will need 
+at least 10Mb/s connection with a 100ms RTT to see a doubling of performance. The
+HPN-SSH home page describes this in greater detail. 
+
+http://www.psc.edu/networking/projects/hpn-ssh
+
+Buffer Sizes:
+
+If HPN is disabled the receive buffer size will be set to the 
+OpenSSH default of 64K.
+
+If an HPN system connects to a nonHPN system the receive buffer will
+be set to the HPNBufferSize value. The default is 2MB but user adjustable.
+
+If an HPN to HPN connection is established a number of different things might
+happen based on the user options and conditions. 
+
+Conditions: HPNBufferSize NOT Set, TCPRcvBufPoll disabled, TCPRcvBuf NOT Set
+HPN Buffer Size = TCP receive buffer value. 
+This is the default unmodified behaviour. Users on autotuning systesm should 
+enabled TCPRcvBufPoll in the ssh_cofig and sshd_config
+
+Conditions: HPNBufferSize SET, TCPRcvBufPoll disabled, TCPRcvBuf NOT Set
+HPN Buffer Size = minmum of TCP receive buffer and HPNBufferSize. 
+This would be the system defined TCP receive buffer (RWIN).
+
+Conditions: HPNBufferSize SET, TCPRcvBufPoll disabled, TCPRcvBuf SET
+HPN Buffer Size = minmum of TCPRcvBuf and HPNBufferSize. 
+Generally there is no need to set both.
+
+Conditions: HPNBufferSize NOT Set, TCPRcvBufPoll enabled, TCPRcvBuf NOT Set HPN 
+Buffer Size = Maximum HPN Buffer Size (64MB). 
+The maximum HPN Buffer size of 64MB is geared towards 10GigE transcontinental 
+connections. Users with less extravagant networks should reduce this via the 
+configuration files to a more reasonable size.
+
+Conditions: HPNBufferSize SET, TCPRcvBufPoll enabled, TCPRcvBuf NOT Set
+HPN Buffer Size = HPNBufferSize
+The buffer will grow up to the maximum size specified here. 
+
+Conditions: HPNBufferSize SET, TCPRcvBufPoll enabled, TCPRcvBuf SET
+HPN Buffer Size = minmum of TCPRcvBuf and HPNBufferSize. 
+Generally there is no need to set both of these, especially on autotuning 
+systems. However, if the users wishes to override the autotuning this would be 
+one way to do it.
+
+Conditions: HPNBufferSize NOT Set, TCPRcvBufPoll enabled, TCPRcvBuf SET
+HPN Buffer Size = TCPRcvBuf. 
+This will override autotuning and set the TCP recieve buffer to the user defined 
+value.
+
+
+HPN Specific Configuration options
 
 TcpRcvBuf=[int]KB client
       set the TCP socket receive buffer to n Kilobytes. It can be set up to the 
@@ -39,7 +100,12 @@ HPNBufferSize=[int]KB client/server
      This is the default buffer size the HPN functionality uses when interacting
 with nonHPN SSH installations. Conceptually this is similar to the TcpRcvBuf
 option as applied to the internal SSH flow control. This value can range from 
-1KB to 14MB (1-14336). Use of oversized or undersized buffers can cause performance
+1KB to 64MB (1-65536). Use of oversized or undersized buffers can cause performance
 problems depending on the length of the network path. The default size of this buffer
-is 2MB. TcpRcvBufPoll, if set to yes, will override this value. This behaviour may
-change in future versions. 
+is 2MB.
+
+
+Credits: This patch was conceived, designed, and led by Chris Rapier (rapier@psc.edu)
+         The majority of the actual coding for versions up to HPN12v1 was performed
+         by Michael Stevens (mstevens@andrew.cmu.edu). This work was financed, in part,
+         by Cisco System, Inc., and the National Science Foundation.