[Cluster-devel] [GFS2 PATCH] GFS2: Limit number of transaction blocks requested for truncates

[Bob Peterson <rpeterso@redhat.com>]

Hi,

This patch limits the number of transaction blocks requested during
file truncates. If we have very large multi-terabyte files, and want
to delete or truncate them, they might span so many resource groups
that we overflow the journal blocks, and cause an assert failure.
By limiting the number of blocks in the transaction, we prevent this
overflow and give other running processes time to do transactions.

Note that this is a temporary solution. A long-term solution would
be to implement the non-recursive truncate that processes one
resource group at a time, and therefore, the transactions need
much fewer blocks.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 645721f..77f2ab1 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -720,6 +720,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrp_list rlist;
+	struct gfs2_trans *tr;
 	u64 bn, bstart;
 	u32 blen, btotal;
 	__be64 *p;
@@ -728,6 +729,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	unsigned int revokes = 0;
 	int x;
 	int error;
+	int jblocks_rqsted;
 
 	error = gfs2_rindex_update(sdp);
 	if (error)
@@ -791,12 +793,17 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
 		gfs2_rs_deltree(&ip->i_res);
 
-	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
-				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
-				 revokes);
+restart:
+	jblocks_rqsted = rg_blocks + RES_DINODE +
+		RES_INDIRECT + RES_STATFS + RES_QUOTA +
+		gfs2_struct2blk(sdp, revokes, sizeof(u64));
+	if (jblocks_rqsted > RES_MAX)
+		jblocks_rqsted = RES_MAX;
+	error = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
 	if (error)
 		goto out_rg_gunlock;
 
+	tr = current->journal_info;
 	down_write(&ip->i_rw_mutex);
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
@@ -810,6 +817,15 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		if (!*p)
 			continue;
 
+		/* check for max reasonable journal transaction blocks */
+		if (tr->tr_num_buf_new + RES_STATFS + RES_QUOTA >= RES_MAX) {
+			if (rg_blocks >= tr->tr_num_buf_new)
+				rg_blocks -= tr->tr_num_buf_new;
+			else
+				rg_blocks = 0;
+			break;
+		}
+
 		bn = be64_to_cpu(*p);
 
 		if (bstart + blen == bn)
@@ -827,6 +843,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		*p = 0;
 		gfs2_add_inode_blocks(&ip->i_inode, -1);
 	}
+	if (p == bottom)
+		rg_blocks = 0;
+
 	if (bstart) {
 		__gfs2_free_blocks(ip, bstart, blen, metadata);
 		btotal += blen;
@@ -844,6 +863,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 	gfs2_trans_end(sdp);
 
+	if (rg_blocks)
+		goto restart;
+
 out_rg_gunlock:
 	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
 out_rlist:
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index 1e6e7da..c212d16 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -25,6 +25,7 @@ struct gfs2_glock;
 #define RES_EATTR	1
 #define RES_STATFS	1
 #define RES_QUOTA	2
+#define RES_MAX		256 /* Must not exceed 8192 (min journal is 32MB) */
 
 /* reserve either the number of blocks to be allocated plus the rg header
  * block, or all of the blocks in the rg, whichever is smaller */