summaryrefslogtreecommitdiff
path: root/src/lib/libssl/test/times
diff options
context:
space:
mode:
Diffstat (limited to 'src/lib/libssl/test/times')
-rw-r--r--src/lib/libssl/test/times16
1 files changed, 8 insertions, 8 deletions
diff --git a/src/lib/libssl/test/times b/src/lib/libssl/test/times
index 738d569b8f..6b66eb342e 100644
--- a/src/lib/libssl/test/times
+++ b/src/lib/libssl/test/times
@@ -1,7 +1,7 @@
1 1
2More number for the questions about SSL overheads.... 2More number for the questions about SSL overheads....
3 3
4The following numbers were generated on a pentium pro 200, running linux. 4The following numbers were generated on a Pentium pro 200, running Linux.
5They give an indication of the SSL protocol and encryption overheads. 5They give an indication of the SSL protocol and encryption overheads.
6 6
7The program that generated them is an unreleased version of ssl/ssltest.c 7The program that generated them is an unreleased version of ssl/ssltest.c
@@ -11,7 +11,7 @@ interface.
11 11
12How do I read this? The protocol and cipher are reasonable obvious. 12How do I read this? The protocol and cipher are reasonable obvious.
13The next number is the number of connections being made. The next is the 13The next number is the number of connections being made. The next is the
14number of bytes exchanged bewteen the client and server side of the protocol. 14number of bytes exchanged between the client and server side of the protocol.
15This is the number of bytes that the client sends to the server, and then 15This is the number of bytes that the client sends to the server, and then
16the server sends back. Because this is all happening in one process, 16the server sends back. Because this is all happening in one process,
17the data is being encrypted, decrypted, encrypted and then decrypted again. 17the data is being encrypted, decrypted, encrypted and then decrypted again.
@@ -55,10 +55,10 @@ SSLv3 DES-CBC3-SHA 1000 x 102400 336.61s 323.82s
55 55
56What does this all mean? Well for a server, with no session-id reuse, with 56What does this all mean? Well for a server, with no session-id reuse, with
57a transfer size of 10240 bytes, using RC4-MD5 and a 512bit server key, 57a transfer size of 10240 bytes, using RC4-MD5 and a 512bit server key,
58a pentium pro 200 running linux can handle the SSLv3 protocol overheads of 58a Pentium pro 200 running Linux can handle the SSLv3 protocol overheads of
59about 49 connections a second. Reality will be quite different :-). 59about 49 connections a second. Reality will be quite different :-).
60 60
61Remeber the first number is 1000 full ssl handshakes, the second is 61Remember the first number is 1000 full ssl handshakes, the second is
621 full and 999 with session-id reuse. The RSA overheads for each exchange 621 full and 999 with session-id reuse. The RSA overheads for each exchange
63would be one public and one private operation, but the protocol/MAC/cipher 63would be one public and one private operation, but the protocol/MAC/cipher
64cost would be quite similar in both the client and server. 64cost would be quite similar in both the client and server.
@@ -72,21 +72,21 @@ eric (adding numbers to speculation)
72 killer in SSL. Often delays in the TCP protocol will make session-id 72 killer in SSL. Often delays in the TCP protocol will make session-id
73 reuse look slower that new sessions, but this would not be the case on 73 reuse look slower that new sessions, but this would not be the case on
74 a loaded server. 74 a loaded server.
75- The TCP round trip latencies, while slowing indervidual connections, 75- The TCP round trip latencies, while slowing individual connections,
76 would have minimal impact on throughput. 76 would have minimal impact on throughput.
77- Instead of sending one 102400 byte buffer, one 8k buffer is sent until 77- Instead of sending one 102400 byte buffer, one 8k buffer is sent until
78- the required number of bytes are processed. 78- the required number of bytes are processed.
79- The SSLv3 connections were actually SSLv2 compatable SSLv3 headers. 79- The SSLv3 connections were actually SSLv2 compatible SSLv3 headers.
80- A 512bit server key was being used except where noted. 80- A 512bit server key was being used except where noted.
81- No server key verification was being performed on the client side of the 81- No server key verification was being performed on the client side of the
82 protocol. This would slow things down very little. 82 protocol. This would slow things down very little.
83- The library being used is SSLeay 0.8.x. 83- The library being used is SSLeay 0.8.x.
84- The normal mesauring system was commands of the form 84- The normal measuring system was commands of the form
85 time ./ssltest -num 1000 -bytes 102400 -cipher DES-CBC-SHA -reuse 85 time ./ssltest -num 1000 -bytes 102400 -cipher DES-CBC-SHA -reuse
86 This modified version of ssltest should be in the next public release of 86 This modified version of ssltest should be in the next public release of
87 SSLeay. 87 SSLeay.
88 88
89The general cipher performace number for this platform are 89The general cipher performance number for this platform are
90 90
91SSLeay 0.8.2a 04-Sep-1997 91SSLeay 0.8.2a 04-Sep-1997
92built on Fri Sep 5 17:37:05 EST 1997 92built on Fri Sep 5 17:37:05 EST 1997