c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-24 03:08:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

Parallelize vdev_load

Browse Source 
metaslab_init is the slowest part of importing a mature pool, and it
must be repeated hundreds of times for each top-level vdev.  But its
speed is dominated by a few serialized disk accesses.  That can lead to
import times of > 1 hour for pools with many top-level vdevs on spinny
disks.

Speed up the import by using a taskqueue to parallelize vdev_load across
all top-level vdevs.

This also requires adding mutex protection to
metaslab_class_t.mc_historgram.  The mc_histogram fields were
unprotected when that code was first written in "Illumos 4976-4984 -
metaslab improvements" (OpenZFS
f3a7f6610f).  The lock wasn't added until
3dfb57a35e, though it's unclear exactly
which fields it's supposed to protect.  In any case, it wasn't until
vdev_load was parallelized that any code attempted concurrent access to
those fields.

Sponsored by: Axcient
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alan Somers <asomers@gmail.com>
Closes #11470
This commit is contained in:
Alan Somers
2021-01-11 17:00:19 -07:00
committed by Brian Behlendorf
parent dfb44c500e
commit a0e01997ec
3 changed files with 46 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/vdev.c
+39 -3
View File
@@ -1724,6 +1724,14 @@ vdev_probe(vdev_t *vd, zio_t *zio)
return (NULL);
}
static void
vdev_load_child(void *arg)
{
vdev_t *vd = arg;
vd->vdev_load_error = vdev_load(vd);
}
static void
vdev_open_child(void *arg)
{
@@ -3350,18 +3358,46 @@ vdev_checkpoint_sm_object(vdev_t *vd, uint64_t *sm_obj)
int
vdev_load(vdev_t *vd)
{
int children = vd->vdev_children;
int error = 0;
taskq_t *tq = NULL;
/*
* It's only worthwhile to use the taskq for the root vdev, because the
* slow part is metaslab_init, and that only happens for top-level
* vdevs.
*/
if (vd->vdev_ops == &vdev_root_ops && vd->vdev_children > 0) {
tq = taskq_create("vdev_load", children, minclsyspri,
children, children, TASKQ_PREPOPULATE);
}
/*
* Recursively load all children.
*/
for (int c = 0; c < vd->vdev_children; c++) {
error = vdev_load(vd->vdev_child[c]);
if (error != 0) {
return (error);
vdev_t *cvd = vd->vdev_child[c];
if (tq == NULL || vdev_uses_zvols(cvd)) {
cvd->vdev_load_error = vdev_load(cvd);
} else {
VERIFY(taskq_dispatch(tq, vdev_load_child,
cvd, TQ_SLEEP) != TASKQID_INVALID);
}
}
if (tq != NULL) {
taskq_wait(tq);
taskq_destroy(tq);
}
for (int c = 0; c < vd->vdev_children; c++) {
int error = vd->vdev_child[c]->vdev_load_error;
if (error != 0)
return (error);
}
vdev_set_deflate_ratio(vd);
/*