<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/include/linux/iocontext.h, branch linux-2.6.28.y</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=linux-2.6.28.y</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=linux-2.6.28.y'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2008-07-03T11:21:14+00:00</updated>
<entry>
<title>block: blkdev.h cleanup, move iocontext stuff to iocontext.h</title>
<updated>2008-07-03T11:21:14+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-06-30T18:42:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=da9cbc87395308a21465bd25441297bbba0477e1'/>
<id>urn:sha1:da9cbc87395308a21465bd25441297bbba0477e1</id>
<content type='text'>
Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>io context: increment task attachment count in ioc_task_link()</title>
<updated>2008-04-15T07:25:33+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-04-15T07:25:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=d237e5c7ce82b6c7e1aa50348520a0c5a47274fa'/>
<id>urn:sha1:d237e5c7ce82b6c7e1aa50348520a0c5a47274fa</id>
<content type='text'>
Thanks to Nikanth Karthikesan &lt;knikanth@suse.de&gt; for reporting this.

Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>cfq-iosched: fix rcu freeing of cfq io contexts</title>
<updated>2008-04-02T13:42:20+00:00</updated>
<author>
<name>Fabio Checconi</name>
<email>fabio@gandalf.sssup.i</email>
</author>
<published>2008-04-02T12:31:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=34e6bbf23c8f43e8713d9bd092680f1660494b4a'/>
<id>urn:sha1:34e6bbf23c8f43e8713d9bd092680f1660494b4a</id>
<content type='text'>
SLAB_DESTROY_BY_RCU is not a direct substitute for normal call_rcu()
freeing, since it'll page freeing but NOT object freeing. So change
cfq to do the freeing on its own.

Signed-off-by: Fabio Checconi &lt;fabio@gandalf.sssup.it&gt;
Acked-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>cfq-iosched: add hlist for browsing parallel to the radix tree</title>
<updated>2008-02-19T09:04:00+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-02-19T09:02:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=ffc4e7595734cf768fa60cea8a4d545dfef8231a'/>
<id>urn:sha1:ffc4e7595734cf768fa60cea8a4d545dfef8231a</id>
<content type='text'>
It's cumbersome to browse a radix tree from start to finish, especially
since we modify keys when a process exits. So add a hlist for the single
purpose of browsing over all known cfq_io_contexts, used for exit,
io prio change, etc.

This fixes http://bugzilla.kernel.org/show_bug.cgi?id=9948

Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>block: cfq: make the io contect sharing lockless</title>
<updated>2008-01-28T09:50:33+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-01-24T07:44:49+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=4ac845a2e9a816ed5a7b301f56dcc0a3d0b1ba4d'/>
<id>urn:sha1:4ac845a2e9a816ed5a7b301f56dcc0a3d0b1ba4d</id>
<content type='text'>
The io context sharing introduced a per-ioc spinlock, that would protect
the cfq io context lookup. That is a regression from the original, since
we never needed any locking there because the ioc/cic were process private.

The cic lookup is changed from an rbtree construct to a radix tree, which
we can then use RCU to make the reader side lockless. That is the performance
critical path, modifying the radix tree is only done on process creation
(when that process first does IO, actually) and on process exit (if that
process has done IO).

As it so happens, radix trees are also much faster for this type of
lookup where the key is a pointer. It's a very sparse tree.

Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>io context sharing: preliminary support</title>
<updated>2008-01-28T09:50:31+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-01-24T07:53:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=d38ecf935fcb10264a6bc190855d9595165e6eeb'/>
<id>urn:sha1:d38ecf935fcb10264a6bc190855d9595165e6eeb</id>
<content type='text'>
Detach task state from ioc, instead keep track of how many processes
are accessing the ioc.

Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
<entry>
<title>ioprio: move io priority from task_struct to io_context</title>
<updated>2008-01-28T09:50:29+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>jens.axboe@oracle.com</email>
</author>
<published>2008-01-24T07:52:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=fd0928df98b9578be8a786ac0cb78a47a5e17a20'/>
<id>urn:sha1:fd0928df98b9578be8a786ac0cb78a47a5e17a20</id>
<content type='text'>
This is where it belongs and then it doesn't take up space for a
process that doesn't do IO.

Signed-off-by: Jens Axboe &lt;jens.axboe@oracle.com&gt;
</content>
</entry>
</feed>
