<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/include/linux/sunrpc/svc.h, branch v7.0-rc7</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v7.0-rc7</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v7.0-rc7'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2026-01-28T15:15:42+00:00</updated>
<entry>
<title>sunrpc: allow svc_recv() to return -ETIMEDOUT and -EBUSY</title>
<updated>2026-01-28T15:15:42+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2026-01-06T18:59:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=a0022a38be1017fb302563eaee54ff904be48cea'/>
<id>urn:sha1:a0022a38be1017fb302563eaee54ff904be48cea</id>
<content type='text'>
To dynamically adjust the thread count, nfsd requires some information
about how busy things are.

Change svc_recv() to take a timeout value, and then allow the wait for
work to time out if it's set. If a timeout is not defined, then the
schedule will be set to MAX_SCHEDULE_TIMEOUT. If the task waits for the
full timeout, then have it return -ETIMEDOUT to the caller.

If it wakes up, finds that there is more work and that no threads are
available, then attempt to set SP_TASK_STARTING. If wasn't already set,
have the task return -EBUSY to cue to the caller that the service could
use more threads.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: split new thread creation into a separate function</title>
<updated>2026-01-28T15:15:42+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2026-01-06T18:59:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=7f221b340d16558919d963a2afed585d6a145fa4'/>
<id>urn:sha1:7f221b340d16558919d963a2afed585d6a145fa4</id>
<content type='text'>
Break out the part of svc_start_kthreads() that creates a thread into
svc_new_thread(), as a new exported helper function.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: introduce the concept of a minimum number of threads per pool</title>
<updated>2026-01-28T15:15:42+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2026-01-06T18:59:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=7ffc7ade2cb1138ea5d4ab55cb42c878d44165fb'/>
<id>urn:sha1:7ffc7ade2cb1138ea5d4ab55cb42c878d44165fb</id>
<content type='text'>
Add a new pool-&gt;sp_nrthrmin field to track the minimum number of threads
in a pool. Add min_threads parameters to both svc_set_num_threads() and
svc_set_pool_threads(). If min_threads is non-zero and less than the
max, svc_set_num_threads() will ensure that the number of running
threads is between the min and the max.

If the min is 0 or greater than the max, then it is ignored, and the
maximum number of threads will be started, and never spun down.

For now, the min_threads is always 0, but a later patch will pass the
proper value through from nfsd.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: track the max number of requested threads in a pool</title>
<updated>2026-01-28T15:15:42+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2026-01-06T18:59:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=6cd60f4274b19327ebc5afa0c814b13379c34370'/>
<id>urn:sha1:6cd60f4274b19327ebc5afa0c814b13379c34370</id>
<content type='text'>
The kernel currently tracks the number of threads running in a pool in
the "sp_nrthreads" field. In the future, where threads are dynamically
spun up and down, it'll be necessary to keep track of the maximum number
of requested threads separately from the actual number running.

Add a pool-&gt;sp_nrthrmax parameter to track this. When userland changes
the number of threads in a pool, update that value accordingly.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: split svc_set_num_threads() into two functions</title>
<updated>2026-01-28T15:15:42+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2026-01-06T18:59:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=e344f872628e769874c8cf30ec9a554bd55c26a3'/>
<id>urn:sha1:e344f872628e769874c8cf30ec9a554bd55c26a3</id>
<content type='text'>
svc_set_num_threads() will set the number of running threads for a given
pool. If the pool argument is set to NULL however, it will distribute
the threads among all of the pools evenly.

These divergent codepaths complicate the move to dynamic threading.
Simplify the API by splitting these two cases into different helpers:

Add a new svc_set_pool_threads() function that sets the number of
threads in a single, given pool. Modify svc_set_num_threads() to
distribute the threads evenly between all of the pools and then call
svc_set_pool_threads() for each.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>SUNRPC: Update svcxdr_init_decode() to call xdr_set_scratch_folio()</title>
<updated>2025-09-23T17:29:50+00:00</updated>
<author>
<name>Anna Schumaker</name>
<email>anna.schumaker@oracle.com</email>
</author>
<published>2025-06-30T18:53:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=d57e43b72bf2071caac90da323849c3983a695f0'/>
<id>urn:sha1:d57e43b72bf2071caac90da323849c3983a695f0</id>
<content type='text'>
The only snag here is that __folio_alloc_node() doesn't handle
NUMA_NO_NODE, so I also need to update svc_pool_map_get_node() to return
numa_mem_id() instead. I arrived at this approach by  looking at what
other users of __folio_alloc_node() do for this case.

Signed-off-by: Anna Schumaker &lt;anna.schumaker@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: rearrange struct svc_rqst for fewer cachelines</title>
<updated>2025-07-14T16:46:49+00:00</updated>
<author>
<name>Jeff Layton</name>
<email>jlayton@kernel.org</email>
</author>
<published>2025-06-20T12:16:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=2bac9a4c5f452d42a78ce07596ef88f75978b536'/>
<id>urn:sha1:2bac9a4c5f452d42a78ce07596ef88f75978b536</id>
<content type='text'>
This shrinks the struct by 4 bytes, but also takes it from 19 to 18
cachelines on x86_64.

Signed-off-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>SUNRPC: Bump the maximum payload size for the server</title>
<updated>2025-05-15T20:16:28+00:00</updated>
<author>
<name>Chuck Lever</name>
<email>chuck.lever@oracle.com</email>
</author>
<published>2025-04-28T19:37:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=1e7dbad6d1fe4b35ccd2aa8fea9496d837af4430'/>
<id>urn:sha1:1e7dbad6d1fe4b35ccd2aa8fea9496d837af4430</id>
<content type='text'>
Increase the maximum server-side RPC payload to 4MB. The default
remains at 1MB.

An API to adjust the operational maximum was added in 2006 by commit
596bbe53eb3a ("[PATCH] knfsd: Allow max size of NFSd payload to be
configured"). To adjust the operational maximum using this API, shut
down the NFS server. Then echo a new value into:

  /proc/fs/nfsd/max_block_size

And restart the NFS server.

Reviewed-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Reviewed-by: NeilBrown &lt;neil@brown.name&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>sunrpc: Remove the RPCSVC_MAXPAGES macro</title>
<updated>2025-05-15T20:16:27+00:00</updated>
<author>
<name>Chuck Lever</name>
<email>chuck.lever@oracle.com</email>
</author>
<published>2025-04-28T19:36:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=0af165bb903cdc005066494cc931076dafd76894'/>
<id>urn:sha1:0af165bb903cdc005066494cc931076dafd76894</id>
<content type='text'>
It is no longer used.

Reviewed-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Reviewed-by: NeilBrown &lt;neil@brown.name&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
<entry>
<title>SUNRPC: Remove svc_rqst :: rq_vec</title>
<updated>2025-05-15T20:16:25+00:00</updated>
<author>
<name>Chuck Lever</name>
<email>chuck.lever@oracle.com</email>
</author>
<published>2025-05-07T00:15:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=1259560b988c959abf9b84da0b9e56c2863b6837'/>
<id>urn:sha1:1259560b988c959abf9b84da0b9e56c2863b6837</id>
<content type='text'>
Clean up: This array is no longer used.

On a system with 8-byte pointers and 4KB pages, pahole reports that
the rq_vec[] array accounts for 4144 bytes.

Reviewed-by: Jeff Layton &lt;jlayton@kernel.org&gt;
Signed-off-by: Chuck Lever &lt;chuck.lever@oracle.com&gt;
</content>
</entry>
</feed>
