diff options
| author | Sage Weil <sage@newdream.net> | 2010-11-04 21:05:05 +0300 |
|---|---|---|
| committer | Sage Weil <sage@newdream.net> | 2010-11-08 18:29:05 +0300 |
| commit | cd045cb42a266882ac24bc21a3a8d03683c72954 (patch) | |
| tree | 2938560e8362804e829cc9feb23ef746d354140b /fs/ceph/caps.c | |
| parent | feb4cc9bb433bf1491ac5ffbba133f3258dacf06 (diff) | |
| download | linux-cd045cb42a266882ac24bc21a3a8d03683c72954.tar.xz | |
ceph: fix rdcache_gen usage and invalidate
We used to use rdcache_gen to indicate whether we "might" have cached
pages. Now we just look at the mapping to determine that. However, some
old behavior remains from that transition.
First, rdcache_gen == 0 no longer means we have no pages. That can happen
at any time (presumably when we carry FILE_CACHE). We should not reset it
to zero, and we should not check that it is zero.
That means that the only purpose for rdcache_revoking is to resolve races
between new issues of FILE_CACHE and an async invalidate. If they are
equal, we should invalidate. On success, we decrement rdcache_revoking,
so that it is no longer equal to rdcache_gen. Similarly, if we success
in doing a sync invalidate, set revoking = gen - 1. (This is a small
optimization to avoid doing unnecessary invalidate work and does not
affect correctness.)
Signed-off-by: Sage Weil <sage@newdream.net>
Diffstat (limited to 'fs/ceph/caps.c')
| -rw-r--r-- | fs/ceph/caps.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 04b207b0c842..60d27bc9eb83 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1430,8 +1430,8 @@ static int try_nonblocking_invalidate(struct inode *inode) invalidating_gen == ci->i_rdcache_gen) { /* success. */ dout("try_nonblocking_invalidate %p success\n", inode); - ci->i_rdcache_gen = 0; - ci->i_rdcache_revoking = 0; + /* save any racing async invalidate some trouble */ + ci->i_rdcache_revoking = ci->i_rdcache_gen - 1; return 0; } dout("try_nonblocking_invalidate %p failed\n", inode); |