Support re-prioritizing asynchronous prefetches

When sequential scrubs were merged, all calls to arc_read()
(including prefetch IOs) were given ZIO_PRIORITY_ASYNC_READ.
Unfortunately, this behaves badly with an existing issue where
prefetch IOs cannot be re-prioritized after the issue. The
result is that synchronous reads end up in the same vdev_queue
as the scrub IOs and can have (in some workloads) multiple
seconds of latency.

This patch incorporates 2 changes. The first ensures that all
scrub IOs are given ZIO_PRIORITY_SCRUB to allow the vdev_queue
code to differentiate between these I/Os and user prefetches.
Second, this patch introduces zio_change_priority() to provide
the missing capability to upgrade a zio's priority.

Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #6921 
Closes #6926
This commit is contained in:
Tom Caputi
2017-12-21 12:13:06 -05:00
committed by Brian Behlendorf
parent 993669a7bf
commit a8b2e30685
11 changed files with 124 additions and 43 deletions
+1
View File
@@ -98,6 +98,7 @@ struct arc_callback {
boolean_t acb_noauth;
uint64_t acb_dsobj;
zio_t *acb_zio_dummy;
zio_t *acb_zio_head;
arc_callback_t *acb_next;
};