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>

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 9fa08662a88df54652895f472369e04ecc0b144d..2a5404c1c42f4efd1be78f5d24eed337c24429e3 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -819,7 +819,7 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
                used |= CEPH_CAP_FILE_CACHE;
        if (ci->i_wr_ref)
                used |= CEPH_CAP_FILE_WR;
-       if (ci->i_wrbuffer_ref)
+       if (ci->i_wb_ref || ci->i_wrbuffer_ref)
                used |= CEPH_CAP_FILE_BUFFER;
        return used;
 }
@@ -1990,11 +1990,11 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got)
        if (got & CEPH_CAP_FILE_WR)
                ci->i_wr_ref++;
        if (got & CEPH_CAP_FILE_BUFFER) {
-               if (ci->i_wrbuffer_ref == 0)
+               if (ci->i_wb_ref == 0)
                        ihold(&ci->vfs_inode);
-               ci->i_wrbuffer_ref++;
-               dout("__take_cap_refs %p wrbuffer %d -> %d (?)\n",
-                    &ci->vfs_inode, ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref);
+               ci->i_wb_ref++;
+               dout("__take_cap_refs %p wb %d -> %d (?)\n",
+                    &ci->vfs_inode, ci->i_wb_ref-1, ci->i_wb_ref);
        }
 }
 
@@ -2169,12 +2169,12 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
                if (--ci->i_rdcache_ref == 0)
                        last++;
        if (had & CEPH_CAP_FILE_BUFFER) {
-               if (--ci->i_wrbuffer_ref == 0) {
+               if (--ci->i_wb_ref == 0) {
                        last++;
                        put++;
                }
-               dout("put_cap_refs %p wrbuffer %d -> %d (?)\n",
-                    inode, ci->i_wrbuffer_ref+1, ci->i_wrbuffer_ref);
+               dout("put_cap_refs %p wb %d -> %d (?)\n",
+                    inode, ci->i_wb_ref+1, ci->i_wb_ref);
        }
        if (had & CEPH_CAP_FILE_WR)
                if (--ci->i_wr_ref == 0) {

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 03d6dafda61fbf6300902cb0aa9bdd85947c70e3..70b6a4839c386be5fa4b40b48c3bf6521eda7ca7 100644 (file)
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -355,6 +355,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
        ci->i_rd_ref = 0;
        ci->i_rdcache_ref = 0;
        ci->i_wr_ref = 0;
+       ci->i_wb_ref = 0;
        ci->i_wrbuffer_ref = 0;
        ci->i_wrbuffer_ref_head = 0;
        ci->i_shared_gen = 0;

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b1f1b8bb127127c4936305501e688e5285fa4eef..f5cabefa98dc03cee37b12e8c961a4f208e970a4 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -293,7 +293,7 @@ struct ceph_inode_info {
 
        /* held references to caps */
        int i_pin_ref;
-       int i_rd_ref, i_rdcache_ref, i_wr_ref;
+       int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
        int i_wrbuffer_ref, i_wrbuffer_ref_head;
        u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
        u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */