MFH @r294567

AIO daemons have always been kernel processes to facilitate switching to
user VM spaces while servicing jobs. Update various comments and data
structures that refer to AIO daemons as threads to refe

AIO daemons have always been kernel processes to facilitate switching to
user VM spaces while servicing jobs. Update various comments and data
structures that refer to AIO daemons as threads to refer to processes
instead.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4999

show more ...

Remove unused variables for socket AIO.

In r55943, a per-process queue of pending socket AIO requests (requests
waiting for the socket to become ready) was added so that they could be
cancelled duri

Remove unused variables for socket AIO.

In r55943, a per-process queue of pending socket AIO requests (requests
waiting for the socket to become ready) was added so that they could be
cancelled during process rundown. In r154765, the rundown code was
changed to handle jobs in this state (JOBST_JOBQSOCK) directly removing
the need for the extra queue. However, the per-process queue head and
global lock were never removed.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4997

show more ...

MFH

Sponsored by: The FreeBSD Foundation

Various cleanups to the main function for AIO kernel processes:

- Pull the vmspace logic out into helper functions and reduce duplication.
Operations on the vmspace are all isolated to vm_map.c, b

Various cleanups to the main function for AIO kernel processes:

- Pull the vmspace logic out into helper functions and reduce duplication.
Operations on the vmspace are all isolated to vm_map.c, but it now exports
a new 'vmspace_switch_aio' for use by AIO kernel processes.
- When an AIO kernel process wants to exit, break out of the main loop and
perform cleanup after the loop end. This reduces a lot of indentation and
allows cleanup to more closely mirror setup actions before the loop starts.
- Convert a DIAGNOSTIC to KASSERT().
- Replace mycp with more typical 'p'.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4990

show more ...

Don't create a dedicated session for each AIO kernel process.

This code dates back to the initial AIO support and the commit log does
not explain why it is needed. However, I cannot find anything i

Don't create a dedicated session for each AIO kernel process.

This code dates back to the initial AIO support and the commit log does
not explain why it is needed. However, I cannot find anything in the
AIO code or the various file methods (fo_read/fo_write) that would change
behavior due to using a private session instead of proc0's session.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4988

show more ...

Merge ^/head r293850 through r294089.

Remove aiod_timeout.

It hasn't been used since the AIO code was made MPSAFE 10 years ago.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4

Remove aiod_timeout.

It hasn't been used since the AIO code was made MPSAFE 10 years ago.

Reviewed by: kib
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D4946

show more ...

Rename aiod_bio taskqueue to aiod_kick.

This taskqueue is not used to handle bio requests. It is only used to
run aio_kick_nowait() to spin up new aio daemon processes.

Reviewed by: kib
Differenti

Rename aiod_bio taskqueue to aiod_kick.

This taskqueue is not used to handle bio requests. It is only used to
run aio_kick_nowait() to spin up new aio daemon processes.

Reviewed by: kib
Differential Revision: https://reviews.freebsd.org/D4904

show more ...

MFH r289384-r293170

Sponsored by: The FreeBSD Foundation

Catch up with head (r291075).

Merge from head

Merge from head

Sponsored by: Gandi.net

The aio_waitcomplete(2) syscall should not sleep when the given timeout
is 0. Without this change it was sleeping for one tick. Maybe not a big
deal, but it makes share/dtrace/blocking script to repo

The aio_waitcomplete(2) syscall should not sleep when the given timeout
is 0. Without this change it was sleeping for one tick. Maybe not a big
deal, but it makes share/dtrace/blocking script to report that.

Reviewed by: jhb
Differential Revision: https://reviews.freebsd.org/D3814
Sponsored by: Wheel Systems, http://wheelsystems.com

show more ...

Merge from head

Catch up with head, primarily for the 1.14.4.0 firmware.

Merge ^/head r285153 through r285283.

Mutex memory is not zeroed, add MTX_NEW.

Reported and tested by: pho
Sponsored by: The FreeBSD Foundation
MFC after: 1 week

fd: make 'rights' a manadatory argument to fget* functions

Catch up with HEAD (r280229-r284686).

Merge sync of head

Merge from head

MFH: r281855-r282312

Sponsored by: The FreeBSD Foundation

Make AIO to not allocate pbufs for unmapped I/O like r281825.

While there, make few more performance optimizations.

On 40-core system doing many 512-byte AIO reads from array of raw SSDs
this chang

Make AIO to not allocate pbufs for unmapped I/O like r281825.

While there, make few more performance optimizations.

On 40-core system doing many 512-byte AIO reads from array of raw SSDs
this change removes lock congestions inside pbuf allocator and devfs,
and bottleneck on single AIO completion taskqueue thread. It improves
peak AIO performance from ~600K to ~1.3M IOPS.

MFC after: 2 weeks

show more ...

Reintegrate head revisions r273096-r277147

Sponsored by: The FreeBSD Foundation