Changes between Version 20 and Version 21 of Internal/DesignNotes

Timestamp:

Apr 10, 2006, 4:47:10 AM (19 years ago)

Author:

kishore

Comment:

—

Internal/DesignNotes

@@ -25 +25 @@
 [[Image(Internal/DesignNotes:num-pkts-recvd.3.png)]]
 
-10000 packets were sent "as fast as possible". There was no "sleep" statement between two send events at the sender. The figures above show the number of packets lost per receiver (on the left) and the number of successful packet receptions (on the right). It is unclear from current experiments as to where this loss is occurring. Some sources of this loss could be 
+10000 packets were sent "as fast as possible". There was no "sleep" statement between two consecutive send events at the sender. The figures above show the number of packets lost per receiver (on the left) and the number of successful packet receptions (on the right). It is unclear from current experiments as to where this loss is occurring. Some sources of this loss could be 
  * buffer (between user-space and kernel-space, between kernel and driver, between driver and card) overflows at the sender or receiver?
  * the switches in the network cannot handle the load? Seems unlikely.
@@ -34 +34 @@
 [[Image(Internal/DesignNotes:num-pkts-recvd.2.png)]]
 
-5000 packets were sent "as fast as possible". There was no "sleep" statement between two send events at the sender. The figures above show the number of packets lost per receiver (on the left) and the number of successful packet receptions (on the right). It is unclear from current experiments as to where this loss is occurring.
+5000 packets were sent "as fast as possible". There was no "sleep" statement between two consecutive send events at the sender. The figures above show the number of packets lost per receiver (on the left) and the number of successful packet receptions (on the right). It is unclear from current experiments as to where this loss is occurring.
 
 = Design Notes for nodehandler =