ocfs2-1.4: fix sendfile locking
PATCH 1/1 ocfs2-1.4: fix sendfile locking
ocfs2_sendfile() was duplicating locking which happens later on in ocfs2_readpage(). The double locking would sometimes cause a lockup in nfsd, which uses ->sendfile() for fast read support. An easy way to see this is to mount an exported ocfs2 fs on a client and initiate two parallel read/write dd commands to the same file when there is low memory on the server.
Fix ocfs2_sendfile() so that it only takes and immediately drops the cluster lock. This is consistent with the locking in ocfs2_file_splice_read().
fs/ocfs2/file.c +5 -6
@@ -2511,15 +2511,14 @@ static ssize_t ocfs2_file_sendfile(strucmlog_errno (ret); goto bail; } +ocfs2_inode_unlock (inode,0 ); -down_read (&OCFS2_I (inode)->ip_alloc_sem); - +/* +* This uses ->readpage, so we don't want to hold any cluster +* locks before the call. +*/ ret =generic_file_sendfile (in_file, ppos, count, actor, target); -up_read (&OCFS2_I (inode)->ip_alloc_sem); - -ocfs2_inode_unlock (inode,0 ); - bail:mlog_exit (ret);return ret;
PATCH 1/1 ocfs2-1.4: fix sendfile locking
Quoted 36 lines · Mark Fasheh
ocfs2_sendfile()was duplicating locking which happens later on inocfs2_readpage(). The double locking would sometimes cause a lockup in nfsd, which uses ->sendfile() for fast read support. An easy way to see this is to mount an exported ocfs2 fs on a client and initiate two parallel read/write dd commands to the same file when there is low memory on the server.Fix
ocfs2_sendfile()so that it only takes and immediately drops the cluster lock. This is consistent with the locking inocfs2_file_splice_read().Signed-off-by Mark Fasheh <[email protected]>Index:
linux/fs/ocfs2/file.c
===================================================================fs/ocfs2/file.c +5
-6@@ -2511,15 +2511,14 @@ static ssize_t ocfs2_file_sendfile(strucmlog_errno (ret); goto bail; } +ocfs2_inode_unlock (inode,0 ); -down_read (&OCFS2_I (inode)->ip_alloc_sem); - +/* +* This uses ->readpage, so we don't want to hold any cluster +* locks before the call. +*/ ret =generic_file_sendfile (in_file, ppos, count, actor, target); -up_read (&OCFS2_I (inode)->ip_alloc_sem); - -ocfs2_inode_unlock (inode,0 ); - bail:mlog_exit (ret);return ret;