From: NeilBrown Date: Mon, 26 Jun 2006 07:27:43 +0000 (-0700) Subject: [PATCH] md: split reshape portion of raid5 sync_request into a separate function X-Git-Tag: v2.6.18-rc1~638 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=52c03291a832d86c093996d0491a326de4a6b79b;p=linux-2.6 [PATCH] md: split reshape portion of raid5 sync_request into a separate function ... as raid5 sync_request is WAY too big. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 970eb03ec6..6d3a2a09cd 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2696,13 +2696,136 @@ static int make_request(request_queue_t *q, struct bio * bi) return 0; } -/* FIXME go_faster isn't used */ -static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster) +static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped) { + /* reshaping is quite different to recovery/resync so it is + * handled quite separately ... here. + * + * On each call to sync_request, we gather one chunk worth of + * destination stripes and flag them as expanding. + * Then we find all the source stripes and request reads. + * As the reads complete, handle_stripe will copy the data + * into the destination stripe and release that stripe. + */ raid5_conf_t *conf = (raid5_conf_t *) mddev->private; struct stripe_head *sh; int pd_idx; sector_t first_sector, last_sector; + int raid_disks; + int data_disks; + int i; + int dd_idx; + sector_t writepos, safepos, gap; + + if (sector_nr == 0 && + conf->expand_progress != 0) { + /* restarting in the middle, skip the initial sectors */ + sector_nr = conf->expand_progress; + sector_div(sector_nr, conf->raid_disks-1); + *skipped = 1; + return sector_nr; + } + + /* we update the metadata when there is more than 3Meg + * in the block range (that is rather arbitrary, should + * probably be time based) or when the data about to be + * copied would over-write the source of the data at + * the front of the range. + * i.e. one new_stripe forward from expand_progress new_maps + * to after where expand_lo old_maps to + */ + writepos = conf->expand_progress + + conf->chunk_size/512*(conf->raid_disks-1); + sector_div(writepos, conf->raid_disks-1); + safepos = conf->expand_lo; + sector_div(safepos, conf->previous_raid_disks-1); + gap = conf->expand_progress - conf->expand_lo; + + if (writepos >= safepos || + gap > (conf->raid_disks-1)*3000*2 /*3Meg*/) { + /* Cannot proceed until we've updated the superblock... */ + wait_event(conf->wait_for_overlap, + atomic_read(&conf->reshape_stripes)==0); + mddev->reshape_position = conf->expand_progress; + mddev->sb_dirty = 1; + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, mddev->sb_dirty == 0 || + kthread_should_stop()); + spin_lock_irq(&conf->device_lock); + conf->expand_lo = mddev->reshape_position; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + } + + for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) { + int j; + int skipped = 0; + pd_idx = stripe_to_pdidx(sector_nr+i, conf, conf->raid_disks); + sh = get_active_stripe(conf, sector_nr+i, + conf->raid_disks, pd_idx, 0); + set_bit(STRIPE_EXPANDING, &sh->state); + atomic_inc(&conf->reshape_stripes); + /* If any of this stripe is beyond the end of the old + * array, then we need to zero those blocks + */ + for (j=sh->disks; j--;) { + sector_t s; + if (j == sh->pd_idx) + continue; + s = compute_blocknr(sh, j); + if (s < (mddev->array_size<<1)) { + skipped = 1; + continue; + } + memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE); + set_bit(R5_Expanded, &sh->dev[j].flags); + set_bit(R5_UPTODATE, &sh->dev[j].flags); + } + if (!skipped) { + set_bit(STRIPE_EXPAND_READY, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + release_stripe(sh); + } + spin_lock_irq(&conf->device_lock); + conf->expand_progress = (sector_nr + i)*(conf->raid_disks-1); + spin_unlock_irq(&conf->device_lock); + /* Ok, those stripe are ready. We can start scheduling + * reads on the source stripes. + * The source stripes are determined by mapping the first and last + * block on the destination stripes. + */ + raid_disks = conf->previous_raid_disks; + data_disks = raid_disks - 1; + first_sector = + raid5_compute_sector(sector_nr*(conf->raid_disks-1), + raid_disks, data_disks, + &dd_idx, &pd_idx, conf); + last_sector = + raid5_compute_sector((sector_nr+conf->chunk_size/512) + *(conf->raid_disks-1) -1, + raid_disks, data_disks, + &dd_idx, &pd_idx, conf); + if (last_sector >= (mddev->size<<1)) + last_sector = (mddev->size<<1)-1; + while (first_sector <= last_sector) { + pd_idx = stripe_to_pdidx(first_sector, conf, conf->previous_raid_disks); + sh = get_active_stripe(conf, first_sector, + conf->previous_raid_disks, pd_idx, 0); + set_bit(STRIPE_EXPAND_SOURCE, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + first_sector += STRIPE_SECTORS; + } + return conf->chunk_size>>9; +} + +/* FIXME go_faster isn't used */ +static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster) +{ + raid5_conf_t *conf = (raid5_conf_t *) mddev->private; + struct stripe_head *sh; + int pd_idx; int raid_disks = conf->raid_disks; int data_disks = raid_disks - conf->max_degraded; sector_t max_sector = mddev->size << 1; @@ -2728,122 +2851,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i return 0; } - if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { - /* reshaping is quite different to recovery/resync so it is - * handled quite separately ... here. - * - * On each call to sync_request, we gather one chunk worth of - * destination stripes and flag them as expanding. - * Then we find all the source stripes and request reads. - * As the reads complete, handle_stripe will copy the data - * into the destination stripe and release that stripe. - */ - int i; - int dd_idx; - sector_t writepos, safepos, gap; - - if (sector_nr == 0 && - conf->expand_progress != 0) { - /* restarting in the middle, skip the initial sectors */ - sector_nr = conf->expand_progress; - sector_div(sector_nr, conf->raid_disks-1); - *skipped = 1; - return sector_nr; - } - - /* we update the metadata when there is more than 3Meg - * in the block range (that is rather arbitrary, should - * probably be time based) or when the data about to be - * copied would over-write the source of the data at - * the front of the range. - * i.e. one new_stripe forward from expand_progress new_maps - * to after where expand_lo old_maps to - */ - writepos = conf->expand_progress + - conf->chunk_size/512*(conf->raid_disks-1); - sector_div(writepos, conf->raid_disks-1); - safepos = conf->expand_lo; - sector_div(safepos, conf->previous_raid_disks-1); - gap = conf->expand_progress - conf->expand_lo; - - if (writepos >= safepos || - gap > (conf->raid_disks-1)*3000*2 /*3Meg*/) { - /* Cannot proceed until we've updated the superblock... */ - wait_event(conf->wait_for_overlap, - atomic_read(&conf->reshape_stripes)==0); - mddev->reshape_position = conf->expand_progress; - mddev->sb_dirty = 1; - md_wakeup_thread(mddev->thread); - wait_event(mddev->sb_wait, mddev->sb_dirty == 0 || - kthread_should_stop()); - spin_lock_irq(&conf->device_lock); - conf->expand_lo = mddev->reshape_position; - spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_for_overlap); - } - - for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) { - int j; - int skipped = 0; - pd_idx = stripe_to_pdidx(sector_nr+i, conf, conf->raid_disks); - sh = get_active_stripe(conf, sector_nr+i, - conf->raid_disks, pd_idx, 0); - set_bit(STRIPE_EXPANDING, &sh->state); - atomic_inc(&conf->reshape_stripes); - /* If any of this stripe is beyond the end of the old - * array, then we need to zero those blocks - */ - for (j=sh->disks; j--;) { - sector_t s; - if (j == sh->pd_idx) - continue; - s = compute_blocknr(sh, j); - if (s < (mddev->array_size<<1)) { - skipped = 1; - continue; - } - memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE); - set_bit(R5_Expanded, &sh->dev[j].flags); - set_bit(R5_UPTODATE, &sh->dev[j].flags); - } - if (!skipped) { - set_bit(STRIPE_EXPAND_READY, &sh->state); - set_bit(STRIPE_HANDLE, &sh->state); - } - release_stripe(sh); - } - spin_lock_irq(&conf->device_lock); - conf->expand_progress = (sector_nr + i)*(conf->raid_disks-1); - spin_unlock_irq(&conf->device_lock); - /* Ok, those stripe are ready. We can start scheduling - * reads on the source stripes. - * The source stripes are determined by mapping the first and last - * block on the destination stripes. - */ - raid_disks = conf->previous_raid_disks; - data_disks = raid_disks - 1; - first_sector = - raid5_compute_sector(sector_nr*(conf->raid_disks-1), - raid_disks, data_disks, - &dd_idx, &pd_idx, conf); - last_sector = - raid5_compute_sector((sector_nr+conf->chunk_size/512) - *(conf->raid_disks-1) -1, - raid_disks, data_disks, - &dd_idx, &pd_idx, conf); - if (last_sector >= (mddev->size<<1)) - last_sector = (mddev->size<<1)-1; - while (first_sector <= last_sector) { - pd_idx = stripe_to_pdidx(first_sector, conf, conf->previous_raid_disks); - sh = get_active_stripe(conf, first_sector, - conf->previous_raid_disks, pd_idx, 0); - set_bit(STRIPE_EXPAND_SOURCE, &sh->state); - set_bit(STRIPE_HANDLE, &sh->state); - release_stripe(sh); - first_sector += STRIPE_SECTORS; - } - return conf->chunk_size>>9; - } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) + return reshape_request(mddev, sector_nr, skipped); + /* if there is too many failed drives and we are trying * to resync, then assert that we are finished, because there is * nothing we can do.