<feed xmlns='http://www.w3.org/2005/Atom'>
<title>litmus-rt.git/drivers/infiniband/ulp/ipoib/Kconfig, branch linux-tip</title>
<subtitle>The LITMUS^RT kernel.</subtitle>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/'/>
<entry>
<title>IPoIB: Correct help text for INFINIBAND_IPOIB_DEBUG</title>
<updated>2008-07-25T03:37:25+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>rolandd@cisco.com</email>
</author>
<published>2008-07-25T03:37:25+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=9905922446f6dc02fd4650c8f59114d6bdb5b777'/>
<id>9905922446f6dc02fd4650c8f59114d6bdb5b777</id>
<content type='text'>
The help text for INFINIBAND_IPOIB_DEBUG refers to "ipoib_debugfs,"
which no longer exists.  Correct this to talk about the files under
debugfs that are really created.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The help text for INFINIBAND_IPOIB_DEBUG refers to "ipoib_debugfs,"
which no longer exists.  Correct this to talk about the files under
debugfs that are really created.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IPoIB/cm: Connected mode is no longer EXPERIMENTAL</title>
<updated>2008-07-25T03:37:25+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>rolandd@cisco.com</email>
</author>
<published>2008-07-25T03:37:25+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=99c3a5a9e388e0ac166c617aaf02150e778d2779'/>
<id>99c3a5a9e388e0ac166c617aaf02150e778d2779</id>
<content type='text'>
Connected mode is now tested and used by lots of people.  No need to
hide it under CONFIG_EXPERIMENTAL.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Connected mode is now tested and used by lots of people.  No need to
hide it under CONFIG_EXPERIMENTAL.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IPoIB: add LRO support</title>
<updated>2008-07-15T06:48:48+00:00</updated>
<author>
<name>Vladimir Sokolovsky</name>
<email>vlad@mellanox.co.il</email>
</author>
<published>2008-07-15T06:48:48+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=af40da894e96d5c826d38be3ea53ee00d9de0367'/>
<id>af40da894e96d5c826d38be3ea53ee00d9de0367</id>
<content type='text'>
Add "ipoib_use_lro" module parameter to enable LRO and an
"ipoib_lro_max_aggr" module parameter to set the max number of packets
to be aggregated.  Make LRO controllable and LRO statistics accessible
through ethtool.

Signed-off-by: Vladimir Sokolovsky &lt;vlad@mellanox.co.il&gt;
Signed-off-by: Eli Cohen &lt;eli@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add "ipoib_use_lro" module parameter to enable LRO and an
"ipoib_lro_max_aggr" module parameter to set the max number of packets
to be aggregated.  Make LRO controllable and LRO statistics accessible
through ethtool.

Signed-off-by: Vladimir Sokolovsky &lt;vlad@mellanox.co.il&gt;
Signed-off-by: Eli Cohen &lt;eli@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IB: Use menuconfig for InfiniBand menu</title>
<updated>2007-07-10T03:12:26+00:00</updated>
<author>
<name>Jan Engelhardt</name>
<email>jengelh@linux01.gwdg.de</email>
</author>
<published>2007-05-23T21:21:22+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=06cc85086e6896939f8c68f8518224748f6b0b2f'/>
<id>06cc85086e6896939f8c68f8518224748f6b0b2f</id>
<content type='text'>
Change Kconfig objects from "menu, config" into "menuconfig" so
that the user can disable the whole feature without having to
enter the menu first.

Signed-off-by: Jan Engelhardt &lt;jengelh@gmx.de&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Change Kconfig objects from "menu, config" into "menuconfig" so
that the user can disable the whole feature without having to
enter the menu first.

Signed-off-by: Jan Engelhardt &lt;jengelh@gmx.de&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IPoIB: Connected mode experimental support</title>
<updated>2007-02-10T16:00:48+00:00</updated>
<author>
<name>Michael S. Tsirkin</name>
<email>mst@mellanox.co.il</email>
</author>
<published>2007-02-05T20:12:23+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=839fcaba355abaffb7b44f0f4504093acb0b11cf'/>
<id>839fcaba355abaffb7b44f0f4504093acb0b11cf</id>
<content type='text'>
The following patch adds experimental support for IPoIB connected
mode, as defined by the draft from the IETF ipoib working group.  The
idea is to increase performance by increasing the MTU from the maximum
of 2K (theoretically 4K) supported by IPoIB on top of UD.  With this
code, I'm able to get 800MByte/sec or more with netperf without
options on a Mellanox 4x back-to-back DDR system.

Some notes on code:
1. SRQ is used for scalability to large cluster sizes
2. Only RC connections are used (UC does not support SRQ now)
3. Retry count is set to 0 since spec draft warns against retries
4. Each connection is used for data transfers in only 1 direction, so
   each connection is either active(TX) or passive (RX).  2 sides that
   want to communicate create 2 connections.
5. Each active (TX) connection has a separate CQ for send completions -
   this keeps the code simple without CQ resize and other tricks
6. To detect stale passive side connections (where the remote side is
   down), we keep an LRU list of passive connections (updated once per
   second per connection) and destroy a connection after it has been
   unused for several seconds. The LRU rule makes it possible to avoid
   scanning connections that have recently been active.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The following patch adds experimental support for IPoIB connected
mode, as defined by the draft from the IETF ipoib working group.  The
idea is to increase performance by increasing the MTU from the maximum
of 2K (theoretically 4K) supported by IPoIB on top of UD.  With this
code, I'm able to get 800MByte/sec or more with netperf without
options on a Mellanox 4x back-to-back DDR system.

Some notes on code:
1. SRQ is used for scalability to large cluster sizes
2. Only RC connections are used (UC does not support SRQ now)
3. Retry count is set to 0 since spec draft warns against retries
4. Each connection is used for data transfers in only 1 direction, so
   each connection is either active(TX) or passive (RX).  2 sides that
   want to communicate create 2 connections.
5. Each active (TX) connection has a separate CQ for send completions -
   this keeps the code simple without CQ resize and other tricks
6. To detect stale passive side connections (where the remote side is
   down), we keep an LRU list of passive connections (updated once per
   second per connection) and destroy a connection after it has been
   unused for several seconds. The LRU rule makes it possible to avoid
   scanning connections that have recently been active.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Still more typo fixes</title>
<updated>2006-10-03T20:36:44+00:00</updated>
<author>
<name>Matt LaPlante</name>
<email>kernel1@cyberdogtech.com</email>
</author>
<published>2006-10-03T20:36:44+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=cab00891c5489cb6d0cde0a55d39bd5f2871fa70'/>
<id>cab00891c5489cb6d0cde0a55d39bd5f2871fa70</id>
<content type='text'>
Signed-off-by: Adrian Bunk &lt;bunk@stusta.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Signed-off-by: Adrian Bunk &lt;bunk@stusta.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IB/ipoib: Remove broken link from Kconfig and documentation</title>
<updated>2006-08-03T17:48:31+00:00</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@voltaire.com</email>
</author>
<published>2006-07-13T08:00:39+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=8ddc7c5326064434048ec1ecfe57659e08345cc1'/>
<id>8ddc7c5326064434048ec1ecfe57659e08345cc1</id>
<content type='text'>
Remove references to the IPoIB IETF working group as it has been closed.

Signed-off-by: Or Gerlitz &lt;ogerlitz@voltaire.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;

</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Remove references to the IPoIB IETF working group as it has been closed.

Signed-off-by: Or Gerlitz &lt;ogerlitz@voltaire.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;

</pre>
</div>
</content>
</entry>
<entry>
<title>IPoIB: Always build debugging code unless CONFIG_EMBEDDED=y</title>
<updated>2006-04-02T21:39:19+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>rolandd@cisco.com</email>
</author>
<published>2006-04-02T21:39:19+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=f5545d24b8aa9fccd8071203e83bc9f4b26e17a6'/>
<id>f5545d24b8aa9fccd8071203e83bc9f4b26e17a6</id>
<content type='text'>
Don't allow CONFIG_INFINIBAND_IPOIB_DEBUG to be disabled unless
CONFIG_EMBEDDED is selected.  We want users (and especially distros)
to have this turned on unless they really need to save space, because
by the time we want debugging output, it's usually too late to rebuild
a kernel.  The debugging output can be controlled at runtime via the
debug_level module parameter in sysfs.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Don't allow CONFIG_INFINIBAND_IPOIB_DEBUG to be disabled unless
CONFIG_EMBEDDED is selected.  We want users (and especially distros)
to have this turned on unless they really need to save space, because
by the time we want debugging output, it's usually too late to rebuild
a kernel.  The debugging output can be controlled at runtime via the
debug_level module parameter in sysfs.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Linux-2.6.12-rc2</title>
<updated>2005-04-16T22:20:36+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@ppc970.osdl.org</email>
</author>
<published>2005-04-16T22:20:36+00:00</published>
<link rel='alternate' type='text/html' href='http://rtsrv.cs.unc.edu/cgit/cgit.cgi/litmus-rt.git/commit/?id=1da177e4c3f41524e886b7f1b8a0c1fc7321cac2'/>
<id>1da177e4c3f41524e886b7f1b8a0c1fc7321cac2</id>
<content type='text'>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!
</pre>
</div>
</content>
</entry>
</feed>
