I2P_Developers/i2p.www
3
0
Fork 5
Code Issues 27 Pull Requests Actions 1 Packages Projects Releases Wiki Activity

updated to include which tweaks were already implemented

Browse Source
This commit is contained in:
jrandom
2004-07-19 15:59:10 +00:00
committed by zzz
parent 6f0f1a4993
commit d214851646
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
pages/performance.html
View File

@@ -7,16 +7,16 @@ performance of I2P - some of the following are CPU related, others bandwidth
related, and others still are protocol related. However, all of those related, and others still are protocol related. However, all of those
dimensions affect the latency, throughput, and percieved performance of the dimensions affect the latency, throughput, and percieved performance of the
network, as they reduce contention for scarce resources. This list is of course network, as they reduce contention for scarce resources. This list is of course
not comprehensive, but it does cover the major ones that I see.</p> not comprehensive, but it does cover the major ones that are seen.</p>
<h2>Native math</h2> <h2>Native math <b>[implemented]</b></h2>
<p>When I last profiled the I2P code, the vast majority of time was spent within <p>When I last profiled the I2P code, the vast majority of time was spent within
one function: java.math.BigInteger's one function: java.math.BigInteger's
<a href="http://java.sun.com/j2se/1.4.2/docs/api/java/math/BigInteger.html#modPow(java.math.BigInteger,%20java.math.BigInteger)">modPow</a>. <a href="http://java.sun.com/j2se/1.4.2/docs/api/java/math/BigInteger.html#modPow(java.math.BigInteger,%20java.math.BigInteger)">modPow</a>.
Rather than try to tune this method, we'll call out to Rather than try to tune this method, we'll call out to
<a href="http://www.swox.com/gmp/">GNU MP</a> - an insanely fast math library <a href="http://www.swox.com/gmp/">GNU MP</a> - an insanely fast math library
(with tuned assembler for many architectures). (<i>Editor: see (with tuned assembler for many architectures). (<i>Editor: see
<a href="jbigi">NativeBigInteger for faster public key cryptography</a></i>)</p> <a href="jbigi.html">NativeBigInteger for faster public key cryptography</a></i>)</p>
<p>ugha and duck are working on the C/JNI glue code, and the existing java code <p>ugha and duck are working on the C/JNI glue code, and the existing java code
is already deployed with hooks for that whenever its ready. Preliminary results is already deployed with hooks for that whenever its ready. Preliminary results
look fantastic - running the router with the native GMP modPow is providing over look fantastic - running the router with the native GMP modPow is providing over
@@ -24,7 +24,7 @@ a 800% speedup in encryption performance, and the load was cut in half. This
was just on one user's machine, and things are nowhere near ready for packaging was just on one user's machine, and things are nowhere near ready for packaging
and deployment, yet.</p> and deployment, yet.</p>
<h2>Garlic wrapping a "reply" LeaseSet</h2> <h2>Garlic wrapping a "reply" LeaseSet <b>[implemented]</b></h2>
<p>This algorithm tweak will only be relevent for applications that want their <p>This algorithm tweak will only be relevent for applications that want their
peers to reply to them (though that includes everything that uses I2PTunnel or peers to reply to them (though that includes everything that uses I2PTunnel or
mihi's ministreaming lib):</p> mihi's ministreaming lib):</p>
@@ -91,7 +91,7 @@ doesn't pass our test within 60 seconds "dead"?</p>
as tuneable parameters to allow for more appropriate tradeoffs between as tuneable parameters to allow for more appropriate tradeoffs between
bandwidth, latency, and CPU usage.</p> bandwidth, latency, and CPU usage.</p>
<h2>More efficient TCP rejection</h2> <h2>More efficient TCP rejection <b>[implemented]</b></h2>
<p>At the moment, all TCP connections do all of their peer validation after <p>At the moment, all TCP connections do all of their peer validation after
going through the full (expensive) Diffie-Hellman handshaking to negotiate a going through the full (expensive) Diffie-Hellman handshaking to negotiate a
private session key. This means that if someone's clock is really wrong, or private session key. This means that if someone's clock is really wrong, or
@@ -103,7 +103,7 @@ verification/validation within the encryption boundary, we'll want to update the
protocol to do some of it first, so that we can reject them cleanly protocol to do some of it first, so that we can reject them cleanly
without wasting much CPU or other resources.</p> without wasting much CPU or other resources.</p>
<h2>Adjust the tunnel testing</h2> <h2>Adjust the tunnel testing <b>[implemented]</b></h2>
<p>Rather than going with the fairly random scheme we have now, we should use a <p>Rather than going with the fairly random scheme we have now, we should use a
more context aware algorithm for testing tunnels. e.g. if we already know its more context aware algorithm for testing tunnels. e.g. if we already know its
passing valid data correctly, there's no need to test it, while if we haven't passing valid data correctly, there's no need to test it, while if we haven't
@@ -111,7 +111,7 @@ seen any data through it recently, perhaps its worthwhile to throw some data its
way. This will reduce the tunnel contetion due to excess messages, as well as way. This will reduce the tunnel contetion due to excess messages, as well as
improve the speed at which we detect - and address - failing tunnels.</p> improve the speed at which we detect - and address - failing tunnels.</p>
<h2>Compress some data structures</h2> <h2>Compress some data structures <b>[implemented]</b></h2>
<p>The I2NP messages and the data they contain is already defined in a fairly <p>The I2NP messages and the data they contain is already defined in a fairly
compact structure, though one attribute of the RouterInfo structure is not - compact structure, though one attribute of the RouterInfo structure is not -
"options" is a plain ASCII name = value mapping. Right now, we're filling it "options" is a plain ASCII name = value mapping. Right now, we're filling it