@@ -2816,6 +2816,10 @@
# @locking: whether to enable file locking. If set to 'auto', only enable
# when Open File Descriptor (OFD) locking API is available
# (default: auto, since 2.10)
+# @drop-cache: invalidate page cache during live migration. This prevents
+# stale data on the migration destination with cache.direct=off.
+# Currently only supported on Linux hosts.
+# (default: on, since: 4.0)
# @x-check-cache-dropped: whether to check that page cache was dropped on live
# migration. May cause noticeable delays if the image
# file is large, do not use in production.
@@ -2828,6 +2832,8 @@
'*pr-manager': 'str',
'*locking': 'OnOffAuto',
'*aio': 'BlockdevAioOptions',
+ '*drop-cache': {'type': 'bool',
+ 'if': 'defined(CONFIG_LINUX)'},
'*x-check-cache-dropped': 'bool' } }
##
@@ -154,6 +154,7 @@ typedef struct BDRVRawState {
bool page_cache_inconsistent:1;
bool has_fallocate;
bool needs_alignment;
+ bool drop_cache;
bool check_cache_dropped;
PRManager *pr_mgr;
@@ -162,6 +163,7 @@ typedef struct BDRVRawState {
typedef struct BDRVRawReopenState {
int fd;
int open_flags;
+ bool drop_cache;
bool check_cache_dropped;
} BDRVRawReopenState;
@@ -422,6 +424,13 @@ static QemuOptsList raw_runtime_opts = {
.type = QEMU_OPT_STRING,
.help = "id of persistent reservation manager object (default: none)",
},
+#if defined(__linux__)
+ {
+ .name = "drop-cache",
+ .type = QEMU_OPT_BOOL,
+ .help = "invalidate page cache during live migration (default: on)",
+ },
+#endif
{
.name = "x-check-cache-dropped",
.type = QEMU_OPT_BOOL,
@@ -511,6 +520,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
}
}
+ s->drop_cache = qemu_opt_get_bool(opts, "drop-cache", true);
s->check_cache_dropped = qemu_opt_get_bool(opts, "x-check-cache-dropped",
false);
@@ -869,6 +879,7 @@ static int raw_reopen_prepare(BDRVReopenState *state,
goto out;
}
+ rs->drop_cache = qemu_opt_get_bool_del(opts, "drop-cache", true);
rs->check_cache_dropped =
qemu_opt_get_bool_del(opts, "x-check-cache-dropped", false);
@@ -946,6 +957,7 @@ static void raw_reopen_commit(BDRVReopenState *state)
BDRVRawState *s = state->bs->opaque;
Error *local_err = NULL;
+ s->drop_cache = rs->drop_cache;
s->check_cache_dropped = rs->check_cache_dropped;
s->open_flags = rs->open_flags;
@@ -2531,6 +2543,10 @@ static void coroutine_fn raw_co_invalidate_cache(BlockDriverState *bs,
return;
}
+ if (!s->drop_cache) {
+ return;
+ }
+
if (s->open_flags & O_DIRECT) {
return; /* No host kernel page cache */
}
Commit dd577a26ff03b6829721b1ffbbf9e7c411b72378 ("block/file-posix: implement bdrv_co_invalidate_cache() on Linux") introduced page cache invalidation so that cache.direct=off live migration is safe on Linux. The invalidation takes a significant amount of time when the file is large and present in the page cache. Normally this is not the case for cross-host live migration but it can happen when migrating between QEMU processes on the same host. On same-host migration we don't need to invalidate pages for correctness anyway, so an option to skip page cache invalidation is useful. I investigated optimizing invalidation and detecting same-host migration, but both are hard to achieve so a user-visible option will suffice. As a bonus this option means that the cache invalidation feature will now be detectable by libvirt via QMP schema introspection. Suggested-by: Neil Skrypuch <neil@tembosocial.com> Tested-by: Neil Skrypuch <neil@tembosocial.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190307164941.3322-1-stefanha@redhat.com Message-Id: <20190307164941.3322-1-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 6 ++++++ block/file-posix.c | 16 ++++++++++++++++ 2 files changed, 22 insertions(+)