On Wed, Apr 14, 2010 at 11:21 PM, NeilBrown <neilb@xxxxxxx> wrote:
> Hi all,
> I thought it was time I posted my patch queue for review to be sure
> it would be ready for the next merge window.
>
> Apart from sundry bug fixes and minor improvements there are two big
> themes here
> 1/ enhancements to level conversion so e.g. we can now convert RAID0
> to RAID5 or RAID10 (near-2 only) and back.
> 2/ general refactoring of bits of md code - some functions
> (e.g. do_md_stop) had become really big and were just a mess of
> stuff that all had to be done at much the same time. It is now
> broken into somewhat meaningful parts. There is a deeper reason
> for doing this refactoring .... you'll find out soon. :-)
>
> This is all available at
> git://neil.brown.name/md for-next
> and should be in linux-next in a day or two.
>
>
> All review, testing, and comments most welcome.
>
A few fixes/enhancements while playing with the takeover code are available at:
git://git.kernel.org/pub/scm/linux/kernel/git/djbw/md.git for-neil
Dan Williams (3):
md/raid4: permit raid0 takeover
md: notify mdstat waiters of level change
md: allow integers to be passed to md/level
drivers/md/md.c | 25 +++++++++++++++----------
drivers/md/raid5.c | 32 +++++++++++++++++---------------
2 files changed, 32 insertions(+), 25 deletions(-)
I'd like to get "raid6: fix recovery performance regression" in for
2.6.34. I pushed it out to the url below, let me know if you just
want me to send it directly.
git://git.kernel.org/pub/scm/linux/kernel/git/djbw/md.git fixes
Dan Williams (1):
raid6: fix recovery performance regression
crypto/async_tx/async_raid6_recov.c | 21 +++++++++++++--------
1 files changed, 13 insertions(+), 8 deletions(-)
Full diff of these 4 patches below (whitespace damaged):
diff --git a/crypto/async_tx/async_raid6_recov.c
b/crypto/async_tx/async_raid6_recov.c
index 943f2ab..3df6746 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -324,6 +324,7 @@ struct dma_async_tx_descriptor *
async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
struct page **blocks, struct async_submit_ctl *submit)
{
+ void *scribble = submit->scribble;
int non_zero_srcs, i;
BUG_ON(faila == failb);
@@ -332,11 +333,13 @@ async_raid6_2data_recov(int disks, size_t bytes,
int faila, int failb,
pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
- /* we need to preserve the contents of 'blocks' for the async
- * case, so punt to synchronous if a scribble buffer is not available
+ /* if a dma resource is not available or a scribble buffer is not
+ * available punt to the synchronous path. In the 'dma not
+ * available' case be sure to use the scribble buffer to
+ * preserve the content of 'blocks' as the caller intended.
*/
- if (!submit->scribble) {
- void **ptrs = (void **) blocks;
+ if (async_dma_find_channel(DMA_PQ) == NULL || !scribble) {
+ void **ptrs = scribble ? scribble : (void **) blocks;
async_tx_quiesce(&submit->depend_tx);
for (i = 0; i < disks; i++)
@@ -406,11 +409,13 @@ async_raid6_datap_recov(int disks, size_t bytes,
int faila,
pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
- /* we need to preserve the contents of 'blocks' for the async
- * case, so punt to synchronous if a scribble buffer is not available
+ /* if a dma resource is not available or a scribble buffer is not
+ * available punt to the synchronous path. In the 'dma not
+ * available' case be sure to use the scribble buffer to
+ * preserve the content of 'blocks' as the caller intended.
*/
- if (!scribble) {
- void **ptrs = (void **) blocks;
+ if (async_dma_find_channel(DMA_PQ) == NULL || !scribble) {
+ void **ptrs = scribble ? scribble : (void **) blocks;
async_tx_quiesce(&submit->depend_tx);
for (i = 0; i < disks; i++)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f177de0..e3ec0fd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2935,9 +2935,10 @@ level_show(mddev_t *mddev, char *page)
static ssize_t
level_store(mddev_t *mddev, const char *buf, size_t len)
{
- char level[16];
+ char clevel[16];
ssize_t rv = len;
struct mdk_personality *pers;
+ long level;
void *priv;
mdk_rdev_t *rdev;
@@ -2970,19 +2971,22 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
}
/* Now find the new personality */
- if (len == 0 || len >= sizeof(level))
+ if (len == 0 || len >= sizeof(clevel))
return -EINVAL;
- strncpy(level, buf, len);
- if (level[len-1] == '\n')
+ strncpy(clevel, buf, len);
+ if (clevel[len-1] == '\n')
len--;
- level[len] = 0;
+ clevel[len] = 0;
+ if (strict_strtol(clevel, 10, &level))
+ level = LEVEL_NONE;
- request_module("md-%s", level);
+ if (request_module("md-%s", clevel) != 0)
+ request_module("md-level-%s", clevel);
spin_lock(&pers_lock);
- pers = find_pers(LEVEL_NONE, level);
+ pers = find_pers(level, clevel);
if (!pers || !try_module_get(pers->owner)) {
spin_unlock(&pers_lock);
- printk(KERN_WARNING "md: personality %s not loaded\n", level);
+ printk(KERN_WARNING "md: personality %s not loaded\n", clevel);
return -EINVAL;
}
spin_unlock(&pers_lock);
@@ -2995,7 +2999,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
if (!pers->takeover) {
module_put(pers->owner);
printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
- mdname(mddev), level);
+ mdname(mddev), clevel);
return -EINVAL;
}
@@ -3011,7 +3015,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
mddev->delta_disks = 0;
module_put(pers->owner);
printk(KERN_WARNING "md: %s: %s would not accept array\n",
- mdname(mddev), level);
+ mdname(mddev), clevel);
return PTR_ERR(priv);
}
@@ -3075,6 +3079,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
sysfs_notify(&mddev->kobj, NULL, "level");
+ md_new_event(mddev);
return rv;
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 042651b..d09c263 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5607,10 +5607,17 @@ static void raid5_quiesce(mddev_t *mddev, int state)
}
-static void *raid5_takeover_raid0(mddev_t *mddev)
+static void *raid45_takeover_raid0(mddev_t *mddev, int level)
{
+ struct raid0_private_data *raid0_priv = mddev->private;
- mddev->new_level = 5;
+ /* for raid0 takeover only one zone is supported */
+ if (raid0_priv->nr_strip_zones > 1) {
+ printk(KERN_ERR "md: cannot takeover raid0 with more than one zone.\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ mddev->new_level = level;
mddev->new_layout = ALGORITHM_PARITY_N;
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->raid_disks += 1;
@@ -5746,22 +5753,13 @@ static int raid6_check_reshape(mddev_t *mddev)
static void *raid5_takeover(mddev_t *mddev)
{
/* raid5 can take over:
- * raid0 - if all devices are the same - make it a raid4 layout
+ * raid0 - if there is only one strip zone - make it a raid4 layout
* raid1 - if there are two drives. We need to know the chunk size
* raid4 - trivial - just use a raid4 layout.
* raid6 - Providing it is a *_6 layout
*/
- if (mddev->level == 0) {
- /* for raid0 takeover only one zone is supported */
- struct raid0_private_data *raid0_priv
- = mddev->private;
- if (raid0_priv->nr_strip_zones > 1) {
- printk(KERN_ERR "md: cannot takeover raid 0 with more than one zone.\n");
- return ERR_PTR(-EINVAL);
- }
- return raid5_takeover_raid0(mddev);
- }
-
+ if (mddev->level == 0)
+ return raid45_takeover_raid0(mddev, 5);
if (mddev->level == 1)
return raid5_takeover_raid1(mddev);
if (mddev->level == 4) {
@@ -5777,8 +5775,12 @@ static void *raid5_takeover(mddev_t *mddev)
static void *raid4_takeover(mddev_t *mddev)
{
- /* raid4 can take over raid5 if layout is right.
+ /* raid4 can take over:
+ * raid0 - if there is only one strip zone
+ * raid5 - if layout is right
*/
+ if (mddev->level == 0)
+ return raid45_takeover_raid0(mddev, 4);
if (mddev->level == 5 &&
mddev->layout == ALGORITHM_PARITY_N) {
mddev->new_layout = 0;
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
