ceph: update the 'approaching max_size' code

The old 'approaching max_size' code expects MDS set max_size to
'2 * reported_size'. This is no longer true. The new code reports
file size when half of previous max_size increment has been used.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e71e6ca5ddfb09466bee7d8721d064a4a846176..82220e9aaf7de141bf4e0ce9ffdc1474d92c6aaa 100644 (file)
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1318,7 +1318,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
                          struct page *page, void *fsdata)
 {
        struct inode *inode = file_inode(file);
-       int check_cap = 0;
+       bool check_cap = false;
 
        dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
             inode, page, (int)pos, (int)copied, (int)len);

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 6752223dc81cfa5a184c58f3b281a1de92f0b1f0..f5552455223fab595c8a2880aab496ee85cdbc1d 100644 (file)
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1653,6 +1653,21 @@ static int try_nonblocking_invalidate(struct inode *inode)
        return -1;
 }
 
+bool __ceph_should_report_size(struct ceph_inode_info *ci)
+{
+       loff_t size = ci->vfs_inode.i_size;
+       /* mds will adjust max size according to the reported size */
+       if (ci->i_flushing_caps & CEPH_CAP_FILE_WR)
+               return false;
+       if (size >= ci->i_max_size)
+               return true;
+       /* half of previous max_size increment has been used */
+       if (ci->i_max_size > ci->i_reported_size &&
+           (size << 1) >= ci->i_max_size + ci->i_reported_size)
+               return true;
+       return false;
+}
+
 /*
  * Swiss army knife function to examine currently used and wanted
  * versus held caps.  Release, flush, ack revoked caps to mds as
@@ -1806,8 +1821,7 @@ retry_locked:
                        }
 
                        /* approaching file_max? */
-                       if ((inode->i_size << 1) >= ci->i_max_size &&
-                           (ci->i_reported_size << 1) < ci->i_max_size) {
+                       if (__ceph_should_report_size(ci)) {
                                dout("i_size approaching max_size\n");
                                goto ack;
                        }

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 29308a80d66ffa118b9aec996874d65a952c29aa..3d48c415f3cb197505b70686031a175c7e2ade1b 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1040,8 +1040,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
        int num_pages;
        int written = 0;
        int flags;
-       int check_caps = 0;
        int ret;
+       bool check_caps = false;
        struct timespec mtime = current_time(inode);
        size_t count = iov_iter_count(from);
 

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 4de6cdddf05928a29051e9996e75245732fee618..53f23c920266d1683292f4337d616a2390aa2752 100644 (file)
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1653,20 +1653,17 @@ out:
        return err;
 }
 
-int ceph_inode_set_size(struct inode *inode, loff_t size)
+bool ceph_inode_set_size(struct inode *inode, loff_t size)
 {
        struct ceph_inode_info *ci = ceph_inode(inode);
-       int ret = 0;
+       bool ret;
 
        spin_lock(&ci->i_ceph_lock);
        dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
        i_size_write(inode, size);
        inode->i_blocks = calc_inode_blocks(size);
 
-       /* tell the MDS if we are approaching max_size */
-       if ((size << 1) >= ci->i_max_size &&
-           (ci->i_reported_size << 1) < ci->i_max_size)
-               ret = 1;
+       ret = __ceph_should_report_size(ci);
 
        spin_unlock(&ci->i_ceph_lock);
        return ret;

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a973acd8beaff67b5b0e67b1217c9bb7419c9982..f8a0aba0d938e0a929ef85d18b314840f30c30d9 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -793,7 +793,7 @@ extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 
 extern int ceph_inode_holds_cap(struct inode *inode, int mask);
 
-extern int ceph_inode_set_size(struct inode *inode, loff_t size);
+extern bool ceph_inode_set_size(struct inode *inode, loff_t size);
 extern void __ceph_do_pending_vmtruncate(struct inode *inode);
 extern void ceph_queue_vmtruncate(struct inode *inode);
 
@@ -918,6 +918,7 @@ extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
                                       struct ceph_snap_context *snapc);
 extern void ceph_flush_snaps(struct ceph_inode_info *ci,
                             struct ceph_mds_session **psession);
+extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
 extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
                            struct ceph_mds_session *session);
 extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);