Re: Raid Array with 3.5Tb

Remember the 3.5Tb Array i've been trying to build, i finally got around
to getting some source code changes that seem to work much better. 
Attached you will find a patch that fixes the raid5 code to a point
where it seems to re-sync and recover without complaining about maps not
being correct.  The patch below is build against a 2.6.3, but will patch
2.6.4 sources as well.  At this point i'd like to hear comments,
thoughts on the changes i've made.  Some notes:

1. raid0 seems to work fine at 3.5T
2. I have not looked at the raid6 code, but it does not work at 3.5Tb
3. Formatting the array with ext3 takes a very long time, not sure why
yet.

Here is the patch:
diff -urN -X /home/efelix/.cvsignore kernel-source-2.6.3/drivers/md/md.c
kernel-source-2.6.3evan1/drivers/md/md.c

--- kernel-source-2.6.3/drivers/md/md.c	2004-02-19 08:54:51.000000000
+0000
+++ kernel-source-2.6.3evan1/drivers/md/md.c	2004-03-17

21:52:25.000000000 +0000

@@ -3138,13 +3138,14 @@
 static void md_do_sync(mddev_t *mddev)
 {
 	mddev_t *mddev2;
-	unsigned int max_sectors, currspeed = 0,
-		j, window;
+	unsigned int currspeed = 0,
+		 window;
+	sector_t max_sectors,j;
 	unsigned long mark[SYNC_MARKS];
-	unsigned long mark_cnt[SYNC_MARKS];
+	sector_t mark_cnt[SYNC_MARKS];
 	int last_mark,m;
 	struct list_head *tmp;
-	unsigned long last_check;
+	sector_t last_check;
 
 	/* just incase thread restarts... */
 	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))

@@ -3282,7 +3283,7 @@
 		 */
 		cond_resched();
 
-		currspeed =

(j-mddev->resync_mark_cnt)/2/((jiffies-mddev->resync_mark)/HZ +1) +1;
+		currspeed = ((unsigned
long)(j-mddev->resync_mark_cnt))/2/((jiffies-mddev->resync_mark)/HZ +1)
+1;
 
 		if (currspeed > sysctl_speed_limit_min) {
 			if ((currspeed > sysctl_speed_limit_max) ||
diff -urN -X /home/efelix/.cvsignore
kernel-source-2.6.3/drivers/md/raid5.c
kernel-source-2.6.3evan1/drivers/md/raid5.c

--- kernel-source-2.6.3/drivers/md/raid5.c	2004-02-19 08:54:52.000000000
+0000
+++ kernel-source-2.6.3evan1/drivers/md/raid5.c	2004-03-17

20:46:52.000000000 +0000

@@ -181,7 +181,7 @@
 
 static void raid5_build_block (struct stripe_head *sh, int i);
 
-static inline void init_stripe(struct stripe_head *sh, unsigned long

sector, int pd_idx)
+static inline void init_stripe(struct stripe_head *sh, sector_t sector,
int pd_idx)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = conf->raid_disks, i;

@@ -218,7 +218,7 @@
 	insert_hash(conf, sh);
 }
 
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, unsigned

long sector)
+static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t
sector)
 {
 	struct stripe_head *sh;
 

@@ -231,7 +231,7 @@
 	return NULL;
 }
 
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf,

unsigned long sector, 
+static struct stripe_head *get_active_stripe(raid5_conf_t *conf,
sector_t sector, 
 					     int pd_idx, int noblock) 
 {
 	struct stripe_head *sh;

@@ -495,7 +495,7 @@
  * Input: a 'big' sector number,
  * Output: index of the data and parity disk, and the sector # in them.
  */
-static unsigned long raid5_compute_sector(sector_t r_sector, unsigned

int raid_disks,
+static sector_t raid5_compute_sector(sector_t r_sector, unsigned int
raid_disks,
 			unsigned int data_disks, unsigned int * dd_idx,
 			unsigned int * pd_idx, raid5_conf_t *conf)
 {

@@ -556,7 +556,7 @@
 	/*
 	 * Finally, compute the new sector number
 	 */
-	new_sector = stripe * sectors_per_chunk + chunk_offset;
+	new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset;
 	return new_sector;
 }
 

@@ -567,7 +567,7 @@
 	int raid_disks = conf->raid_disks, data_disks = raid_disks - 1;
 	sector_t new_sector = sh->sector, check;
 	int sectors_per_chunk = conf->chunk_size >> 9;
-	long stripe;
+	sector_t stripe;
 	int chunk_offset;
 	int chunk_number, dummy1, dummy2, dd_idx = i;
 	sector_t r_sector;

@@ -1388,7 +1389,7 @@
 	unsigned long stripe;
 	int chunk_offset;
 	int dd_idx, pd_idx;
-	unsigned long first_sector;
+	sector_t first_sector;
 	int raid_disks = conf->raid_disks;
 	int data_disks = raid_disks-1;
 

@@ -1401,7 +1402,7 @@
 	stripe = x;
 	BUG_ON(x != stripe);
 
-	first_sector =

raid5_compute_sector(stripe*data_disks*sectors_per_chunk
+	first_sector =
raid5_compute_sector((sector_t)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, 1);
 	if (sh == NULL) {
diff -urN -X /home/efelix/.cvsignore
kernel-source-2.6.3/include/linux/raid/md_k.h
kernel-source-2.6.3evan1/include/linux/raid/md_k.h

--- kernel-source-2.6.3/include/linux/raid/md_k.h	2004-02-19

08:55:57.000000000 +0000

+++ kernel-source-2.6.3evan1/include/linux/raid/md_k.h	2004-03-10

21:14:39.000000000 +0000

@@ -211,9 +211,9 @@
 
 	struct mdk_thread_s		*thread;	/* management thread */
 	struct mdk_thread_s		*sync_thread;	/* doing resync or reconstruct */
-	unsigned long			curr_resync;	/* blocks scheduled */
+	sector_t			curr_resync;	/* blocks scheduled */
 	unsigned long			resync_mark;	/* a recent timestamp */
-	unsigned long			resync_mark_cnt;/* blocks written at resync_mark */
+	sector_t			resync_mark_cnt;/* blocks written at resync_mark */
 
 	/* recovery/resync flags 
 	 * NEEDED:   we might need to start a resync/recover
-------------------

Evan

On Fri, 2004-01-16 at 03:18, Neil Brown wrote:

On Thursday January 15, evan.felix@pnl.gov wrote:

quoted

I've been attempting to create a large raid 5 device using the linux
2.6.1 kernel, with the Large Block Device configured on.  I have in

the

quoted

system 16 250G disks.  I built an array with mdadm -C -n 15 -x 1
/dev/md2 /dev/sd[a-p]

The resync/recovery seemed to be going fine, but at some point i

started

quoted

seeing:

kernel: compute_blocknr: map not correct
kernel: compute_blocknr: map not correct

...

quoted

Has anyone else made an array this large? and does anybody have any
pointers on where i can start looking at code to fix this?

I would look in  drivers/md/raid5.c and compute_blocknr() in that
file.

I would change "chunk_number" to a sector_t and change:
        chunk_number = stripe * data_disks + i;
to read
        chunk_number = (sector_t)stripe * data_disks + i;

Possibly "stripe" and "chunk_number" should both be "sector_t", but
I'm not at all sure.

Please let me know if it helps.

NeilBrown

-- 
-------------------------
Evan Felix
Administrator of Supercomputer #5 in Top 500, Nov 2003
Environmental Molecular Sciences Laboratory
Pacific Northwest National Laboratory
Operated for the U.S. DOE by Battelle