Sometimes wait_backup() meets condition on reshape finish:
array state : reshape
sync_completed : 0
this causes one more loop and hung on select() command
and there is no more changes of sync_completed.
This fix extends wait_backup()interface and for external metadata pings monitor
to speed up array state change and test already up to date state.
Other fix options:
- would be add to select() additional watching handle for 'sync_action' to detect reshape finish.
- or add break command on sync_completed == 0
Signed-off-by: Adam Kwolek <adam.kwolek@xxxxxxxxx>
---
Grow.c | 51 ++++++++++++++++++++++++++++++++++-----------------
mdadm.h | 3 ++-
mdmon.c | 3 ++-
super-intel.c | 2 +-
4 files changed, 39 insertions(+), 20 deletions(-)
diff --git a/Grow.c b/Grow.c
index a01051f..2ca1b6f 100644
--- a/Grow.c
+++ b/Grow.c
@@ -453,11 +453,13 @@ static __u32 bsb_csum(char *buf, int len)
return __cpu_to_le32(csum);
}
-static int child_shrink(int afd, struct mdinfo *sra, unsigned long blocks,
+static int child_shrink(struct supertype *st,
+ int afd, struct mdinfo *sra, unsigned long blocks,
int *fds, unsigned long long *offsets,
int disks, int chunk, int level, int layout, int data,
int dests, int *destfd, unsigned long long *destoffsets);
-static int child_same_size(int afd, struct mdinfo *sra, unsigned long blocks,
+static int child_same_size(struct supertype *st,
+ int afd, struct mdinfo *sra, unsigned long blocks,
int *fds, unsigned long long *offsets,
unsigned long long start,
int disks, int chunk, int level, int layout, int data,
@@ -1910,17 +1912,17 @@ int Grow_reshape(char *devname, int fd, int quiet, char *backup_file,
mlockall(MCL_FUTURE);
if (odata < ndata)
- done = child_grow(fd, sra, stripes,
+ done = child_grow(st, fd, sra, stripes,
fdlist, offsets,
odisks, ochunk, array.level, olayout, odata,
d - odisks, fdlist+odisks, offsets+odisks);
else if (odata > ndata)
- done = child_shrink(fd, sra, stripes,
+ done = child_shrink(st, fd, sra, stripes,
fdlist, offsets,
odisks, ochunk, array.level, olayout, odata,
d - odisks, fdlist+odisks, offsets+odisks);
else
- done = child_same_size(fd, sra, stripes,
+ done = child_same_size(st, fd, sra, stripes,
fdlist, offsets,
0,
odisks, ochunk, array.level, olayout, odata,
@@ -2120,7 +2122,8 @@ static int grow_backup(struct mdinfo *sra,
* every works.
*/
/* FIXME return value is often ignored */
-static int wait_backup(struct mdinfo *sra,
+static int wait_backup(struct supertype *st,
+ struct mdinfo *sra,
unsigned long long offset, /* per device */
unsigned long long blocks, /* per device */
unsigned long long blocks2, /* per device - hack */
@@ -2155,6 +2158,15 @@ static int wait_backup(struct mdinfo *sra,
close(fd);
return -1;
}
+ if (st && st->ss->external) {
+ int container_dev = (st->container_dev != NoMdDev
+ ? st->container_dev : st->devnum);
+ char *container = devnum2devname(container_dev);
+ if (container) {
+ ping_monitor(container);
+ free(container);
+ }
+ }
if (sysfs_get_str(sra, NULL, "sync_action",
action, 20) > 0 &&
strncmp(action, "reshape", 7) != 0)
@@ -2281,7 +2293,7 @@ static void validate(int afd, int bfd, unsigned long long offset)
}
}
-int child_grow(int afd, struct mdinfo *sra,
+int child_grow(struct supertype *st, int afd, struct mdinfo *sra,
unsigned long stripes, int *fds, unsigned long long *offsets,
int disks, int chunk, int level, int layout, int data,
int dests, int *destfd, unsigned long long *destoffsets)
@@ -2299,7 +2311,8 @@ int child_grow(int afd, struct mdinfo *sra,
dests, destfd, destoffsets,
0, °raded, buf);
validate(afd, destfd[0], destoffsets[0]);
- wait_backup(sra, 0, stripes * (chunk / 512), stripes * (chunk / 512),
+ wait_backup(st, sra, 0, stripes * (chunk / 512),
+ stripes * (chunk / 512),
dests, destfd, destoffsets,
0);
sysfs_set_num(sra, NULL, "suspend_lo", (stripes * (chunk/512)) * data);
@@ -2309,7 +2322,8 @@ int child_grow(int afd, struct mdinfo *sra,
return 1;
}
-static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
+static int child_shrink(struct supertype *st,
+ int afd, struct mdinfo *sra, unsigned long stripes,
int *fds, unsigned long long *offsets,
int disks, int chunk, int level, int layout, int data,
int dests, int *destfd, unsigned long long *destoffsets)
@@ -2326,7 +2340,8 @@ static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
sysfs_set_str(sra, NULL, "sync_action", "reshape");
sysfs_set_num(sra, NULL, "suspend_lo", 0);
sysfs_set_num(sra, NULL, "suspend_hi", 0);
- rv = wait_backup(sra, 0, start - stripes * (chunk/512), stripes * (chunk/512),
+ rv = wait_backup(st, sra, 0, start - stripes * (chunk/512),
+ stripes * (chunk/512),
dests, destfd, destoffsets, 0);
if (rv < 0)
return 0;
@@ -2336,7 +2351,7 @@ static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
dests, destfd, destoffsets,
0, °raded, buf);
validate(afd, destfd[0], destoffsets[0]);
- wait_backup(sra, start, stripes*(chunk/512), 0,
+ wait_backup(st, sra, start, stripes*(chunk/512), 0,
dests, destfd, destoffsets, 0);
sysfs_set_num(sra, NULL, "suspend_lo", (stripes * (chunk/512)) * data);
free(buf);
@@ -2345,7 +2360,7 @@ static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
return 1;
}
-int child_same_size(int afd,
+int child_same_size(struct supertype *st, int afd,
struct mdinfo *sra, unsigned long stripes,
int *fds, unsigned long long *offsets,
unsigned long long start,
@@ -2384,7 +2399,7 @@ int child_same_size(int afd,
start += stripes * 2; /* where to read next */
size = sra->component_size / (chunk/512);
while (start < size) {
- if (wait_backup(sra, (start-stripes*2)*(chunk/512),
+ if (wait_backup(st, sra, (start-stripes*2)*(chunk/512),
stripes*(chunk/512), 0,
dests, destfd, destoffsets,
part) < 0)
@@ -2402,12 +2417,14 @@ int child_same_size(int afd,
part = 1 - part;
validate(afd, destfd[0], destoffsets[0]);
}
- if (wait_backup(sra, (start-stripes*2) * (chunk/512), stripes * (chunk/512), 0,
+ if (wait_backup(st, sra, (start-stripes*2) * (chunk/512),
+ stripes * (chunk/512), 0,
dests, destfd, destoffsets,
part) < 0)
return 0;
sysfs_set_num(sra, NULL, "suspend_lo", ((start-stripes)*(chunk/512)) * data);
- wait_backup(sra, (start-stripes) * (chunk/512), tailstripes * (chunk/512), 0,
+ wait_backup(st, sra, (start-stripes) * (chunk/512),
+ tailstripes * (chunk/512), 0,
dests, destfd, destoffsets,
1-part);
sysfs_set_num(sra, NULL, "suspend_lo", (size*(chunk/512)) * data);
@@ -2829,7 +2846,7 @@ int Grow_continue(int mdfd, struct supertype *st, struct mdinfo *info,
close(mdfd);
mlockall(MCL_FUTURE);
if (info->delta_disks < 0)
- done = child_shrink(-1, info, stripes,
+ done = child_shrink(st, -1, info, stripes,
fds, offsets,
info->array.raid_disks,
info->array.chunk_size,
@@ -2843,7 +2860,7 @@ int Grow_continue(int mdfd, struct supertype *st, struct mdinfo *info,
*/
unsigned long long start = info->reshape_progress / ndata;
start /= (info->array.chunk_size/512);
- done = child_same_size(-1, info, stripes,
+ done = child_same_size(st, -1, info, stripes,
fds, offsets,
start,
info->array.raid_disks,
diff --git a/mdadm.h b/mdadm.h
index ceffb81..1fb1cbc 100644
--- a/mdadm.h
+++ b/mdadm.h
@@ -500,7 +500,8 @@ extern int reshape_open_backup_file(char *backup,
extern unsigned long compute_backup_blocks(int nchunk, int ochunk,
unsigned int ndata, unsigned int odata);
extern struct mdinfo *sysfs_get_unused_spares(int container_fd, int fd);
-extern int child_grow(int afd, struct mdinfo *sra, unsigned long stripes,
+extern int child_grow(struct supertype *st,
+ int afd, struct mdinfo *sra, unsigned long stripes,
int *fds, unsigned long long *offsets,
int disks, int chunk, int level, int layout, int data,
int dests, int *destfd, unsigned long long *destoffsets);
diff --git a/mdmon.c b/mdmon.c
index ebadff7..85890de 100644
--- a/mdmon.c
+++ b/mdmon.c
@@ -559,7 +559,8 @@ int reshape_open_backup_file(char *backup_file,
return -1;
}
-int child_grow(int afd, struct mdinfo *sra,
+int child_grow(struct supertype *st,
+ int afd, struct mdinfo *sra,
unsigned long stripes, int *fds, unsigned long long *offsets,
int disks, int chunk, int level, int layout, int data,
int dests, int *destfd, unsigned long long *destoffsets)
diff --git a/super-intel.c b/super-intel.c
index bee28bc..0896f1d 100644
--- a/super-intel.c
+++ b/super-intel.c
@@ -7893,7 +7893,7 @@ int imsm_child_grow(struct supertype *st,
sra->new_chunk = sra->array.chunk_size;
stripes = blocks / (sra->array.chunk_size/512) / odata;
- child_grow(validate_fd, sra, stripes,
+ child_grow(st, validate_fd, sra, stripes,
fdlist, offsets,
odisks, sra->array.chunk_size,
sra->array.level, sra->array.layout, odata,
--
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
