<feed xmlns='http://www.w3.org/2005/Atom'>
<title>user/sven/linux-bitkeeper.git/net/sunrpc/timer.c, branch master</title>
<subtitle>Linux Kernel BitKeeper History</subtitle>
<id>https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/atom?h=master</id>
<link rel='self' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/'/>
<updated>2004-05-20T11:47:06Z</updated>
<entry>
<title>Following a suggestion by Jamie Lokier</title>
<updated>2004-05-20T11:47:06Z</updated>
<author>
<name>Trond Myklebust</name>
<email>trond.myklebust@fys.uio.no</email>
</author>
<published>2004-05-20T11:47:06Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=6da1abab69dc2d6b12123fba230f539028743b0f'/>
<id>urn:sha1:6da1abab69dc2d6b12123fba230f539028743b0f</id>
<content type='text'>
RPC: Make "major" timeouts be of fixed length "timeo&lt;&lt;retrans"
     rather than counting the number of retransmissions. The
     clock starts at the first attempt to send each request.
                                                                                
RPC: Ensure that we "slow start" the RTT estimation after a
     major timeout has occurred.
</content>
</entry>
<entry>
<title>[SUNRPC]: Remove unneeded version.h inclusion.</title>
<updated>2003-08-30T13:35:48Z</updated>
<author>
<name>Felipe Damasio</name>
<email>felipewd@terra.com.br</email>
</author>
<published>2003-08-30T13:35:48Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=eceabb8f825c07936bc52950b1d86ec8e13205ed'/>
<id>urn:sha1:eceabb8f825c07936bc52950b1d86ec8e13205ed</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Increase the minimum RTO timer value to 1/10 second. This is more</title>
<updated>2003-08-21T11:33:03Z</updated>
<author>
<name>Trond Myklebust</name>
<email>trond.myklebust@fys.uio.no</email>
</author>
<published>2003-08-21T11:33:03Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=4bdeac8fa5d5c6a4408ef42ec66a715c36fd27a6'/>
<id>urn:sha1:4bdeac8fa5d5c6a4408ef42ec66a715c36fd27a6</id>
<content type='text'>
in line with what is done for TCP.

Signedness corrections when updating RTT.

Be conservative when calculating RTO. Round up the residues.
</content>
</entry>
<entry>
<title>Back out some congestion control changes that were causing trouble,</title>
<updated>2003-08-21T11:29:14Z</updated>
<author>
<name>Trond Myklebust</name>
<email>trond.myklebust@fys.uio.no</email>
</author>
<published>2003-08-21T11:29:14Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=df9e22888f4ad5dc4f06f7e339de0b12e59626d7'/>
<id>urn:sha1:df9e22888f4ad5dc4f06f7e339de0b12e59626d7</id>
<content type='text'>
among other things, for the "soft" mount option.
</content>
</entry>
<entry>
<title>[PATCH] RTO estimator cleanup patch</title>
<updated>2002-11-08T11:28:49Z</updated>
<author>
<name>Chuck Lever</name>
<email>cel@citi.umich.edu</email>
</author>
<published>2002-11-08T11:28:49Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=2752e0097c8078cc5d186043bbbc0cb6b0c2521e'/>
<id>urn:sha1:2752e0097c8078cc5d186043bbbc0cb6b0c2521e</id>
<content type='text'>
clean up RPC client's RTO estimator.
</content>
</entry>
<entry>
<title>[PATCH] fix jiffies wrap in new RPC RTO estimator</title>
<updated>2002-11-08T11:28:43Z</updated>
<author>
<name>Chuck Lever</name>
<email>cel@citi.umich.edu</email>
</author>
<published>2002-11-08T11:28:43Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=a7ec0168a72658356d790ae71e500778a6aafde0'/>
<id>urn:sha1:a7ec0168a72658356d790ae71e500778a6aafde0</id>
<content type='text'>
the new RPC RTO estimator has some jiffies wrap problems.
</content>
</entry>
<entry>
<title>[PATCH] RPC over UDP congestion control updates [2/8]</title>
<updated>2002-07-16T08:53:43Z</updated>
<author>
<name>Trond Myklebust</name>
<email>trond.myklebust@fys.uio.no</email>
</author>
<published>2002-07-16T08:53:43Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=fa7b279e012a6d72d09e1e7873e0c0f8e06dbc15'/>
<id>urn:sha1:fa7b279e012a6d72d09e1e7873e0c0f8e06dbc15</id>
<content type='text'>
Implement a count of the number of timeouts that have occured since
we last recorded a successful reply from the server.

For the moment this information is merely used in order to improve the
estimate of whether or not the server is down. It will be used in
patch 3/8 in order to improve the timeout backoff algorithm.
</content>
</entry>
<entry>
<title>[PATCH] RPC over UDP congestion control updates [1/8]</title>
<updated>2002-07-16T08:53:29Z</updated>
<author>
<name>Trond Myklebust</name>
<email>trond.myklebust@fys.uio.no</email>
</author>
<published>2002-07-16T08:53:29Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux-bitkeeper.git/commit/?id=77d7903022dbd92040f4afdfb5e05d9005a88a7f'/>
<id>urn:sha1:77d7903022dbd92040f4afdfb5e05d9005a88a7f</id>
<content type='text'>
Implement the basic round trip timing algorithm in order to adapt the
timeout values for the most common NFS operations to the server's
rate of response.
Algorithm is described in Van Jacobson's paper 1998 paper
on http://www-nrg.ee.lbl.gov/nrg-papers.html, and is the same as is
used for most TCP stacks.

Following the *BSD code, we implement separate rtt timers for GETATTR,
LOOKUP, READ/READDIR/READLINK, and WRITE. In addition to this, there
is one extra timer for the COMMIT operation.
All the remaining RPC calls use the current system in which a fixed
timeout value gets set by the 'timeo' mount option.

In case of a timeout, the current exponential backoff algoritm is
implemented. Subsequent patches will improve this...
</content>
</entry>
</feed>
