fsverity: Remove WQ_UNBOUND from fsverity read workqueue

commit f959325e6ac3f499450088b8d9c626d1177be160 upstream.

WQ_UNBOUND causes significant scheduler latency on ARM64/Android.  This
is problematic for latency sensitive workloads, like I/O
post-processing.

Removing WQ_UNBOUND gives a 96% reduction in fsverity workqueue related
scheduler latency and improves app cold startup times by ~30ms.
WQ_UNBOUND was also removed from the dm-verity workqueue for the same
reason [1].

This code was tested by running Android app startup benchmarks and
measuring how long the fsverity workqueue spent in the runnable state.

Before
Total workqueue scheduler latency: 553800us
After
Total workqueue scheduler latency: 18962us

[1]: https://lore.kernel.org/all/20230202012348.885402-1-nhuck@google.com/

Signed-off-by: Nathan Huckleberry <nhuck@google.com>
Fixes: 8a1d0f9cac ("fs-verity: add data verification hooks for ->readpages()")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230310193325.620493-1-nhuck@google.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Nathan Huckleberry
2023-03-10 11:33:25 -08:00
committed by Greg Kroah-Hartman
parent 33f341c1fc
commit e66f3039c7

View File

@@ -279,15 +279,15 @@ EXPORT_SYMBOL_GPL(fsverity_enqueue_verify_work);
int __init fsverity_init_workqueue(void) int __init fsverity_init_workqueue(void)
{ {
/* /*
* Use an unbound workqueue to allow bios to be verified in parallel * Use a high-priority workqueue to prioritize verification work, which
* even when they happen to complete on the same CPU. This sacrifices * blocks reads from completing, over regular application tasks.
* locality, but it's worthwhile since hashing is CPU-intensive.
* *
* Also use a high-priority workqueue to prioritize verification work, * For performance reasons, don't use an unbound workqueue. Using an
* which blocks reads from completing, over regular application tasks. * unbound workqueue for crypto operations causes excessive scheduler
* latency on ARM64.
*/ */
fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue", fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue",
WQ_UNBOUND | WQ_HIGHPRI, WQ_HIGHPRI,
num_online_cpus()); num_online_cpus());
if (!fsverity_read_workqueue) if (!fsverity_read_workqueue)
return -ENOMEM; return -ENOMEM;