Revert llist conversion for metadata writeback.
Create new list for priority metadata updates, which are triggered
by FUA requests.
Write metadata for all other requests in batch after some delay.
Add new parameter to specify delay time.
Always submit COW and discard io to prio list.
https://virtu
When mapping request, save all flags, rather then only operation
type. Use it later to check if the request is FUA or not.
Unfortunately there is no REQ_FUA equivalent on IOCB layer, but
IOCB_DSYNC is usually translated to it, as can be seen in
__iomap_dio_rw().
https://virtuozzo.atlassian.net/bro
Create new flush pio when we see REQ_PREFLUSH flag. Call original
pio after the flush is done.
https://virtuozzo.atlassian.net/browse/VSTOR-91817
Signed-off-by: Andrey Zhadchenko
---
drivers/md/dm-ploop-map.c | 39 ++-
1 file changed, 34 insertions(+), 5 delet
Drop ploop_cluster_is_in_top_delta(), because
- it internally searches md on every call
- it takes read lock every time
https://virtuozzo.atlassian.net/browse/VSTOR-91817
Signed-off-by: Andrey Zhadchenko
---
drivers/md/dm-ploop-map.c | 15 +++
1 file changed, 11 insertions(+), 4 de
Drop extra ploop_cluster_is_in_top_delta() as we are planning to
access BAT anyway
https://virtuozzo.atlassian.net/browse/VSTOR-91817
Signed-off-by: Andrey Zhadchenko
---
drivers/md/dm-ploop-map.c | 28
1 file changed, 12 insertions(+), 16 deletions(-)
diff --git a/
The commit is pushed to "branch-rh9-5.14.0-427.37.1.vz9.78.x-ovz" and will
appear at g...@bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.37.1.vz9.78.1
-->
commit f5c8ab1a9c6222df1bfae5dd5946bc046940fc73
Author: Alexey Kuznetsov
Date: Fri Oct 25 22:24:11 2024 +0800
fs/fuse: kio:
The commit is pushed to "branch-rh9-5.14.0-427.37.1.vz9.78.x-ovz" and will
appear at g...@bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.37.1.vz9.78.1
-->
commit cfdd1dfd9bfbf5eff20798cc994b8f66321e3a86
Author: Alexey Kuznetsov
Date: Fri Oct 25 22:25:34 2024 +0800
fs/fuse: rela
From: Alexey Kuznetsov
No actual impact on performance as all the chunks are sent
in parallel, yet it is huge resource overconsumption.
Affects: #VSTOR-94452
https://virtuozzo.atlassian.net/browse/VSTOR-94452
Signed-off-by: Alexey Kuznetsov
Feature: vStorage
---
fs/fuse/kio/pcs/pcs_map.c | 2
From: Alexey Kuznetsov
Ancient bug, which was not caught only because nobody tried
to do a thing like:
fallocate -p -l 4g FILE
It is noop! Pretends to succeed but actually does nothing.
https://virtuozzo.atlassian.net/browse/VSTOR-94452
Signed-off-by: Alexey Kuznetsov
Feature: vStorage
---
The commit is pushed to "branch-rh9-5.14.0-427.37.1.vz9.78.x-ovz" and will
appear at g...@bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.37.1.vz9.78.1
-->
commit 2b184a76c68b0b0d558cde0b4c56bd7c99f50f13
Author: Alexey Kuznetsov
Date: Fri Oct 25 22:23:01 2024 +0800
fs/fuse: kio:
No actual impact on performance as all the chunks are sent
in parallel, yet it is huge resource overconsumption.
Affects: #VSTOR-94452
Signed-off-by: Alexey Kuznetsov
---
fs/fuse/kio/pcs/pcs_map.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/fuse/kio/pcs/pcs_map.c b/fs
Drop inode_lock while executing fallocate.
This is a kludge. Why this cannot be a genuine thing.
Traditionally all synchchronous linux file operations are
strictly serialized. The axiom is that file modifications
are to be atomic in the sense that if two writes are issued
from different threads s
Ancient bug, which was not caught only because nobody tried
to do a thing like:
fallocate -p -l 4g FILE
It is noop! Pretends to succeed but actually does nothing.
Signed-off-by: Alexey Kuznetsov
---
fs/fuse/kio/pcs/pcs_cluster.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff
From: Alexey Kuznetsov
Drop inode_lock while executing fallocate.
This is a kludge. Why this cannot be a genuine thing.
Traditionally all synchchronous linux file operations are
strictly serialized. The axiom is that file modifications
are to be atomic in the sense that if two writes are issued
On 24.10.24 11:04, Andrey Zhadchenko wrote:
On 10/21/24 12:13, Alexander Atanasov wrote:
@@ -775,7 +775,6 @@ static void
ploop_advance_local_after_bat_wb(struct ploop *ploop,
i = PLOOP_MAP_OFFSET;
dst_clu = piwb->kmpage;
- write_lock_irqsave(&ploop->bat_rwlock, flags);
15 matches
Mail list logo
