[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH 02/20] qed: do not evict in-use L2 table cache entri
From: |
Kevin Wolf |
Subject: |
[Qemu-devel] [PATCH 02/20] qed: do not evict in-use L2 table cache entries |
Date: |
Mon, 12 Mar 2012 16:19:33 +0100 |
From: Stefan Hajnoczi <address@hidden>
The L2 table cache reduces QED metadata reads that would be required
when translating LBAs to offsets into the image file. Since requests
execute in parallel it is possible to share an L2 table between multiple
requests.
There is a potential data corruption issue when an in-use L2 table is
evicted from the cache because the following situation occurs:
1. An allocating write performs an update to L2 table "A".
2. Another request needs L2 table "B" and causes table "A" to be
evicted.
3. A new read request needs L2 table "A" but it is not cached.
As a result the L2 update from #1 can overlap with the L2 fetch from #3.
We must avoid doing overlapping I/O requests here since the worst case
outcome is that the L2 fetch completes before the L2 update and yields
stale data. In that case we would effectively discard the L2 update and
lose data clusters!
Thanks to Benoît Canet <address@hidden> for extensive testing
and debugging which lead to discovery of this bug.
Reported-by: Benoît Canet <address@hidden>
Signed-off-by: Stefan Hajnoczi <address@hidden>
Tested-by: Benoît Canet <address@hidden>
Signed-off-by: Kevin Wolf <address@hidden>
---
block/qed-l2-cache.c | 22 ++++++++++++++++++----
1 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/block/qed-l2-cache.c b/block/qed-l2-cache.c
index 02b81a2..e9b2aae 100644
--- a/block/qed-l2-cache.c
+++ b/block/qed-l2-cache.c
@@ -161,11 +161,25 @@ void qed_commit_l2_cache_entry(L2TableCache *l2_cache,
CachedL2Table *l2_table)
return;
}
+ /* Evict an unused cache entry so we have space. If all entries are in use
+ * we can grow the cache temporarily and we try to shrink back down later.
+ */
if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) {
- entry = QTAILQ_FIRST(&l2_cache->entries);
- QTAILQ_REMOVE(&l2_cache->entries, entry, node);
- l2_cache->n_entries--;
- qed_unref_l2_cache_entry(entry);
+ CachedL2Table *next;
+ QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next) {
+ if (entry->ref > 1) {
+ continue;
+ }
+
+ QTAILQ_REMOVE(&l2_cache->entries, entry, node);
+ l2_cache->n_entries--;
+ qed_unref_l2_cache_entry(entry);
+
+ /* Stop evicting when we've shrunk back to max size */
+ if (l2_cache->n_entries < MAX_L2_CACHE_SIZE) {
+ break;
+ }
+ }
}
l2_cache->n_entries++;
--
1.7.6.5
- [Qemu-devel] [PULL 00/20] Block patches, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 08/20] Add 'make check-block', Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 05/20] qcow2: Add error messages in qcow2_truncate, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 06/20] qemu-iotests: Mark some tests as quick, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 02/20] qed: do not evict in-use L2 table cache entries,
Kevin Wolf <=
- [Qemu-devel] [PATCH 01/20] Group snapshot: Fix format name for backing file, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 16/20] qcow2: Reduce number of I/O requests, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 03/20] qcow2: Add some tracing, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 17/20] coroutine: adding sigaltstack method (.c source), Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 18/20] coroutine: adding configure choose mechanism for coroutine backend, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 10/20] qapi: complete implementation of unions, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 04/20] block: handle -EBUSY in bdrv_commit_all(), Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 20/20] test-coroutine: add performance test for nesting, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 07/20] make check: Add qemu-iotests subset, Kevin Wolf, 2012/03/12
- [Qemu-devel] [PATCH 14/20] qcow2: Factor out count_cow_clusters, Kevin Wolf, 2012/03/12