| commit | d3d0720d4a7a46e93e055e5b0f1a8bd612743ed6 | [log] [tgz] |
|---|---|---|
| author | Henry C Chang <henry.cy.chang@gmail.com> | Wed May 11 10:29:54 2011 +0000 |
| committer | Sage Weil <sage@newdream.net> | Wed May 11 10:44:48 2011 -0700 |
| tree | 39d657139336012f05d7573116a0ba2405e85de7 | |
| parent | a26a185d27b49e1656b335ef8ad1a32f7a0e7d7f [diff] |
ceph: do not use i_wrbuffer_ref as refcount for Fb cap We increments i_wrbuffer_ref when taking the Fb cap. This breaks the dirty page accounting and causes looping in __ceph_do_pending_vmtruncate, and ceph client hangs. This bug can be reproduced occasionally by running blogbench. Add a new field i_wb_ref to inode and dedicate it to Fb reference counting. Signed-off-by: Henry C Chang <henry.cy.chang@gmail.com> Signed-off-by: Sage Weil <sage@newdream.net>