From 88202a0c84e1951d6630d1d557d4801a8cc5b5ef Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Jan 2006 00:21:36 -0800 Subject: [PATCH] md: allow sync-speed to be controlled per-device Also export current (average) speed and status in sysfs. Signed-off-by: Neil Brown Acked-by: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/md.txt | 22 ++++++++++ drivers/md/md.c | 110 +++++++++++++++++++++++++++++++++++++++++++--- include/linux/raid/md_k.h | 4 ++ 3 files changed, 131 insertions(+), 5 deletions(-) diff --git a/Documentation/md.txt b/Documentation/md.txt index b8d172b254f7..03a13c462cf2 100644 --- a/Documentation/md.txt +++ b/Documentation/md.txt @@ -207,6 +207,28 @@ All md devices contain: available. It will then appear at md/dev-XXX (depending on the name of the device) and further configuration is then possible. + sync_speed_min + sync_speed_max + This are similar to /proc/sys/dev/raid/speed_limit_{min,max} + however they only apply to the particular array. + If no value has been written to these, of if the word 'system' + is written, then the system-wide value is used. If a value, + in kibibytes-per-second is written, then it is used. + When the files are read, they show the currently active value + followed by "(local)" or "(system)" depending on whether it is + a locally set or system-wide value. + + sync_completed + This shows the number of sectors that have been completed of + whatever the current sync_action is, followed by the number of + sectors in total that could need to be processed. The two + numbers are separated by a '/' thus effectively showing one + value, a fraction of the process that is complete. + + sync_speed + This shows the current actual speed, in K/sec, of the current + sync_action. It is averaged over the last 30 seconds. + As component devices are added to an md array, they appear in the 'md' directory as new directories named diff --git a/drivers/md/md.c b/drivers/md/md.c index 825e235b791b..1b76fb29fb70 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -81,10 +81,22 @@ static DEFINE_SPINLOCK(pers_lock); * idle IO detection. * * you can change it via /proc/sys/dev/raid/speed_limit_min and _max. + * or /sys/block/mdX/md/sync_speed_{min,max} */ static int sysctl_speed_limit_min = 1000; static int sysctl_speed_limit_max = 200000; +static inline int speed_min(mddev_t *mddev) +{ + return mddev->sync_speed_min ? + mddev->sync_speed_min : sysctl_speed_limit_min; +} + +static inline int speed_max(mddev_t *mddev) +{ + return mddev->sync_speed_max ? + mddev->sync_speed_max : sysctl_speed_limit_max; +} static struct ctl_table_header *raid_table_header; @@ -2197,6 +2209,90 @@ md_scan_mode = __ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt); +static ssize_t +sync_min_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%d (%s)\n", speed_min(mddev), + mddev->sync_speed_min ? "local": "system"); +} + +static ssize_t +sync_min_store(mddev_t *mddev, const char *buf, size_t len) +{ + int min; + char *e; + if (strncmp(buf, "system", 6)==0) { + mddev->sync_speed_min = 0; + return len; + } + min = simple_strtoul(buf, &e, 10); + if (buf == e || (*e && *e != '\n') || min <= 0) + return -EINVAL; + mddev->sync_speed_min = min; + return len; +} + +static struct md_sysfs_entry md_sync_min = +__ATTR(sync_speed_min, S_IRUGO|S_IWUSR, sync_min_show, sync_min_store); + +static ssize_t +sync_max_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%d (%s)\n", speed_max(mddev), + mddev->sync_speed_max ? "local": "system"); +} + +static ssize_t +sync_max_store(mddev_t *mddev, const char *buf, size_t len) +{ + int max; + char *e; + if (strncmp(buf, "system", 6)==0) { + mddev->sync_speed_max = 0; + return len; + } + max = simple_strtoul(buf, &e, 10); + if (buf == e || (*e && *e != '\n') || max <= 0) + return -EINVAL; + mddev->sync_speed_max = max; + return len; +} + +static struct md_sysfs_entry md_sync_max = +__ATTR(sync_speed_max, S_IRUGO|S_IWUSR, sync_max_show, sync_max_store); + + +static ssize_t +sync_speed_show(mddev_t *mddev, char *page) +{ + unsigned long resync, dt, db; + resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active)); + dt = ((jiffies - mddev->resync_mark) / HZ); + if (!dt) dt++; + db = resync - (mddev->resync_mark_cnt); + return sprintf(page, "%ld\n", db/dt/2); /* K/sec */ +} + +static struct md_sysfs_entry +md_sync_speed = __ATTR_RO(sync_speed); + +static ssize_t +sync_completed_show(mddev_t *mddev, char *page) +{ + unsigned long max_blocks, resync; + + if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) + max_blocks = mddev->resync_max_sectors; + else + max_blocks = mddev->size << 1; + + resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active)); + return sprintf(page, "%lu / %lu\n", resync, max_blocks); +} + +static struct md_sysfs_entry +md_sync_completed = __ATTR_RO(sync_completed); + static struct attribute *md_default_attrs[] = { &md_level.attr, &md_raid_disks.attr, @@ -2210,6 +2306,10 @@ static struct attribute *md_default_attrs[] = { static struct attribute *md_redundancy_attrs[] = { &md_scan_mode.attr, &md_mismatches.attr, + &md_sync_min.attr, + &md_sync_max.attr, + &md_sync_speed.attr, + &md_sync_completed.attr, NULL, }; static struct attribute_group md_redundancy_group = { @@ -4433,10 +4533,10 @@ static void md_do_sync(mddev_t *mddev) printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev)); printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:" - " %d KB/sec/disc.\n", sysctl_speed_limit_min); + " %d KB/sec/disc.\n", speed_min(mddev)); printk(KERN_INFO "md: using maximum available idle IO bandwidth " "(but not more than %d KB/sec) for reconstruction.\n", - sysctl_speed_limit_max); + speed_max(mddev)); is_mddev_idle(mddev); /* this also initializes IO event counters */ /* we don't use the checkpoint if there's a bitmap */ @@ -4477,7 +4577,7 @@ static void md_do_sync(mddev_t *mddev) skipped = 0; sectors = mddev->pers->sync_request(mddev, j, &skipped, - currspeed < sysctl_speed_limit_min); + currspeed < speed_min(mddev)); if (sectors == 0) { set_bit(MD_RECOVERY_ERR, &mddev->recovery); goto out; @@ -4542,8 +4642,8 @@ static void md_do_sync(mddev_t *mddev) currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 /((jiffies-mddev->resync_mark)/HZ +1) +1; - if (currspeed > sysctl_speed_limit_min) { - if ((currspeed > sysctl_speed_limit_max) || + if (currspeed > speed_min(mddev)) { + if ((currspeed > speed_max(mddev)) || !is_mddev_idle(mddev)) { msleep(500); goto repeat; diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 68b929c079ab..617b9506c760 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -143,6 +143,10 @@ struct mddev_s sector_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ + /* if zero, use the system-wide default */ + int sync_speed_min; + int sync_speed_max; + int ok_start_degraded; /* recovery/resync flags * NEEDED: we might need to start a resync/recover -- cgit v1.2.3-59-g8ed1b