c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2025-10-26 18:05:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Increase default zfs_rebuild_vdev_limit to 64MB

Browse Source 
When testing distributed rebuild performance with more capable
hardware it was observed than increasing the zfs_rebuild_vdev_limit
to 64M reduced the rebuild time by 17%.  Beyond 64MB there was
some improvement (~2%) but it was not significant when weighed
against the increased memory usage. Memory usage is capped at 1/4
of arc_c_max.

Additionally, vr_bytes_inflight_max has been moved so it's updated
per-metaslab to allow the size to be adjust while a rebuild is
running.

Reviewed-by: Akash B <akash-b@hpe.com>
Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #14428
This commit is contained in:
Brian Behlendorf 2023-01-24 15:23:32 -08:00
parent fa28e26e42
commit cdbe1d65c4
2 changed files with 19 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
man/man4/zfs.4
View File

@ -1712,7 +1712,7 @@ completes in order to verify the checksums of all blocks which have been
resilvered. resilvered.
This is enabled by default and strongly recommended. This is enabled by default and strongly recommended.
. .
.It Sy zfs_rebuild_vdev_limit Ns = Ns Sy 33554432 Ns B Po 32MB Pc Pq ulong .It Sy zfs_rebuild_vdev_limit Ns = Ns Sy 67108864 Ns B Po 64 MiB Pc Pq ulong
Maximum amount of I/O that can be concurrently issued for a sequential Maximum amount of I/O that can be concurrently issued for a sequential
resilver per leaf device, given in bytes. resilver per leaf device, given in bytes.
. .

27
module/zfs/vdev_rebuild.c
View File

@ -34,6 +34,7 @@
#include <sys/zio.h> #include <sys/zio.h>
#include <sys/dmu_tx.h> #include <sys/dmu_tx.h>
#include <sys/arc.h> #include <sys/arc.h>
#include <sys/arc_impl.h>
#include <sys/zap.h> #include <sys/zap.h>
/* /*
@ -116,13 +117,12 @@ unsigned long zfs_rebuild_max_segment = 1024 * 1024;
* segment size is also large (zfs_rebuild_max_segment=1M). This helps keep * segment size is also large (zfs_rebuild_max_segment=1M). This helps keep
* the queue depth short. * the queue depth short.
* *
* 32MB was selected as the default value to achieve good performance with * 64MB was observed to deliver the best performance and set as the default.
* a large 90-drive dRAID HDD configuration (draid2:8d:90c:2s). A sequential * Testing was performed with a 106-drive dRAID HDD pool (draid2:11d:106c)
* rebuild was unable to saturate all of the drives using smaller values. * and a rebuild rate of 1.2GB/s was measured to the distribute spare.
* With a value of 32MB the sequential resilver write rate was measured at * Smaller values were unable to fully saturate the available pool I/O.
* 800MB/s sustained while rebuilding to a distributed spare.
*/ */
unsigned long zfs_rebuild_vdev_limit = 32 << 20; unsigned long zfs_rebuild_vdev_limit = 64 << 20;
/* /*
* Automatically start a pool scrub when the last active sequential resilver * Automatically start a pool scrub when the last active sequential resilver
@ -754,6 +754,7 @@ vdev_rebuild_thread(void *arg)
{ {
vdev_t *vd = arg; vdev_t *vd = arg;
spa_t *spa = vd->vdev_spa; spa_t *spa = vd->vdev_spa;
vdev_t *rvd = spa->spa_root_vdev;
int error = 0; int error = 0;
/* /*
@ -786,9 +787,6 @@ vdev_rebuild_thread(void *arg)
vr->vr_pass_bytes_scanned = 0; vr->vr_pass_bytes_scanned = 0;
vr->vr_pass_bytes_issued = 0; vr->vr_pass_bytes_issued = 0;
vr->vr_bytes_inflight_max = MAX(1ULL << 20,
zfs_rebuild_vdev_limit * vd->vdev_children);
uint64_t update_est_time = gethrtime(); uint64_t update_est_time = gethrtime();
vdev_rebuild_update_bytes_est(vd, 0); vdev_rebuild_update_bytes_est(vd, 0);
@ -804,6 +802,17 @@ vdev_rebuild_thread(void *arg)
metaslab_t *msp = vd->vdev_ms[i]; metaslab_t *msp = vd->vdev_ms[i];
vr->vr_scan_msp = msp; vr->vr_scan_msp = msp;
/*
* Calculate the max number of in-flight bytes for top-level
* vdev scanning operations (minimum 1MB, maximum 1/4 of
* arc_c_max shared by all top-level vdevs). Limits for the
* issuing phase are done per top-level vdev and are handled
* separately.
*/
uint64_t limit = (arc_c_max / 4) / MAX(rvd->vdev_children, 1);
vr->vr_bytes_inflight_max = MIN(limit, MAX(1ULL << 20,
zfs_rebuild_vdev_limit * vd->vdev_children));
/* /*
* Removal of vdevs from the vdev tree may eliminate the need * Removal of vdevs from the vdev tree may eliminate the need
* for the rebuild, in which case it should be canceled. The * for the rebuild, in which case it should be canceled. The