From: "H. Peter Anvin" <hpa@zytor.com>
This patch is functionally identical to the md-02-rebuild-needs-yield.patch
for RAID-5, and necessary for exactly the same reasons:
From: NeilBrown <neilb@cse.unsw.edu.au>
raid5 rebuild takes stripes so agressively that other access cannot get a
look-in.
With this patch, the rebuild pauses slightly if there is a shortage of
stripes to let other processes have a chance.
(akpm: this needs to be tested for yield()-starvation)
---
drivers/md/raid6main.c | 9 ++++++++-
1 files changed, 8 insertions(+), 1 deletion(-)
diff -puN drivers/md/raid6main.c~raid6-rebuild-needs-yield drivers/md/raid6main.c
--- 25/drivers/md/raid6main.c~raid6-rebuild-needs-yield 2004-01-19 00:04:07.000000000 -0800
+++ 25-akpm/drivers/md/raid6main.c 2004-01-19 00:04:07.000000000 -0800
@@ -1557,7 +1557,14 @@ static int sync_request (mddev_t *mddev,
first_sector = raid6_compute_sector(stripe*data_disks*sectors_per_chunk
+ chunk_offset, raid_disks, data_disks, &dd_idx, &pd_idx, conf);
- sh = get_active_stripe(conf, sector_nr, pd_idx, 0);
+ sh = get_active_stripe(conf, sector_nr, pd_idx, 1);
+ if (sh == NULL) {
+ sh = get_active_stripe(conf, sector_nr, pd_idx, 0);
+ /* make sure we don't swamp the stripe cache if someone else
+ * is trying to get access
+ */
+ yield();
+ }
spin_lock(&sh->lock);
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
_