From db3540522e955c1ebb391f4f5324dff4f20ecd09 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 24 May 2011 11:46:31 -0700 Subject: ceph: fix cap flush race reentrancy In e9964c10 we change cap flushing to do a delicate dance because some inodes on the cap_dirty list could be in a migrating state (got EXPORT but not IMPORT) in which we couldn't actually flush and move from dirty->flushing, breaking the while (!empty) { process first } loop structure. It worked for a single sync thread, but was not reentrant and triggered infinite loops when multiple syncers came along. Instead, move inodes with dirty to a separate cap_dirty_migrating list when in the limbo export-but-no-import state, allowing us to go back to the simple loop structure (which was reentrant). This is cleaner and more robust. Audited the cap_dirty users and this looks fine: list_empty(&ci->i_dirty_item) is still a reliable indicator of whether we have dirty caps (which list we're on is irrelevant) and list_del_init() calls still do the right thing. Signed-off-by: Sage Weil --- fs/ceph/mds_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ceph/mds_client.h') diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 4e3a9cc0bba6..7d8a0d662d56 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -278,6 +278,7 @@ struct ceph_mds_client { u64 cap_flush_seq; struct list_head cap_dirty; /* inodes with dirty caps */ + struct list_head cap_dirty_migrating; /* ...that are migration... */ int num_cap_flushing; /* # caps we are flushing */ spinlock_t cap_dirty_lock; /* protects above items */ wait_queue_head_t cap_flushing_wq; -- cgit v1.2.1