bf251437e9
Many changes were necessary this time around:
* QAPI was changed to avoid redundant has_* variables, see commit
44ea9d9be3 ("qapi: Start to elide redundant has_FOO in generated C")
for details. This affected many QMP commands added by Proxmox too.
* Pending querying for migration got split into two functions, one to
estimate, one for exact value, see commit c8df4a7aef ("migration:
Split save_live_pending() into state_pending_*") for details. Relevant
for savevm-async and PBS dirty bitmap.
* Some block (driver) functions got converted to coroutines, so the
Proxmox block drivers needed to be adapted.
* Alloc track auto-detaching during PBS live restore got broken by
AioContext-related changes resulting in a deadlock. The current, hacky
method was replaced by a simpler one. Stefan apparently ran into a
problem with that when he wrote the driver, but there were
improvements in the stream job code since then and I didn't manage to
reproduce the issue. It's a separate patch "alloc-track: fix deadlock
during drop" for now, you can find the details there.
* Async snapshot-related changes:
- The pending querying got adapted to the above-mentioned split and
a patch is added to optimize it/make it more similar to what
upstream code does.
- Added initialization of the compression counters (for
future-proofing).
- It's necessary the hold the BQL (big QEMU lock = iothread mutex)
during the setup phase, because block layer functions are used there
and not doing so leads to racy, hard-to-debug crashes or hangs. It's
necessary to change some upstream code too for this, a version of
the patch "migration: for snapshots, hold the BQL during setup
callbacks" is intended to be upstreamed.
- Need to take the bdrv graph read lock before flushing.
* hmp_info_balloon was moved to a different file.
* Needed to include a new headers from time to time to still get the
correct functions.
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
78 lines
2.9 KiB
Diff
78 lines
2.9 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
|
|
Date: Mon, 6 Apr 2020 12:16:38 +0200
|
|
Subject: [PATCH] PVE: [Up] glusterfs: allow partial reads
|
|
|
|
This should deal with qemu bug #1644754 until upstream
|
|
decides which way to go. The general direction seems to be
|
|
away from sector based block APIs and with that in mind, and
|
|
when comparing to other network block backends (eg. nfs)
|
|
treating partial reads as errors doesn't seem to make much
|
|
sense.
|
|
|
|
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
|
|
---
|
|
block/gluster.c | 10 +++++++++-
|
|
1 file changed, 9 insertions(+), 1 deletion(-)
|
|
|
|
diff --git a/block/gluster.c b/block/gluster.c
|
|
index f11a40aa9e..6756e6b886 100644
|
|
--- a/block/gluster.c
|
|
+++ b/block/gluster.c
|
|
@@ -58,6 +58,7 @@ typedef struct GlusterAIOCB {
|
|
int ret;
|
|
Coroutine *coroutine;
|
|
AioContext *aio_context;
|
|
+ bool is_write;
|
|
} GlusterAIOCB;
|
|
|
|
typedef struct BDRVGlusterState {
|
|
@@ -753,8 +754,10 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret,
|
|
acb->ret = 0; /* Success */
|
|
} else if (ret < 0) {
|
|
acb->ret = -errno; /* Read/Write failed */
|
|
+ } else if (acb->is_write) {
|
|
+ acb->ret = -EIO; /* Partial write - fail it */
|
|
} else {
|
|
- acb->ret = -EIO; /* Partial read/write - fail it */
|
|
+ acb->ret = 0; /* Success */
|
|
}
|
|
|
|
aio_co_schedule(acb->aio_context, acb->coroutine);
|
|
@@ -1021,6 +1024,7 @@ static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs,
|
|
acb.ret = 0;
|
|
acb.coroutine = qemu_coroutine_self();
|
|
acb.aio_context = bdrv_get_aio_context(bs);
|
|
+ acb.is_write = true;
|
|
|
|
ret = glfs_zerofill_async(s->fd, offset, bytes, gluster_finish_aiocb, &acb);
|
|
if (ret < 0) {
|
|
@@ -1201,9 +1205,11 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
|
|
acb.aio_context = bdrv_get_aio_context(bs);
|
|
|
|
if (write) {
|
|
+ acb.is_write = true;
|
|
ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
|
|
gluster_finish_aiocb, &acb);
|
|
} else {
|
|
+ acb.is_write = false;
|
|
ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
|
|
gluster_finish_aiocb, &acb);
|
|
}
|
|
@@ -1266,6 +1272,7 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
|
|
acb.ret = 0;
|
|
acb.coroutine = qemu_coroutine_self();
|
|
acb.aio_context = bdrv_get_aio_context(bs);
|
|
+ acb.is_write = true;
|
|
|
|
ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
|
|
if (ret < 0) {
|
|
@@ -1314,6 +1321,7 @@ static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs,
|
|
acb.ret = 0;
|
|
acb.coroutine = qemu_coroutine_self();
|
|
acb.aio_context = bdrv_get_aio_context(bs);
|
|
+ acb.is_write = true;
|
|
|
|
ret = glfs_discard_async(s->fd, offset, bytes, gluster_finish_aiocb, &acb);
|
|
if (ret < 0) {
|