Heavy iSCSI traffic triggers memory allocation complaints and system lockup

https://bugzilla.kernel.org/show_bug.cgi?id=10890

Alan <[email protected]> changed:

What |Removed |Added
----------------------------------------------------------------------------

                 CC|                            |[email protected]
          Component|Other                       |Other
     Kernel Version|2.6.25.6                    |3.1.0
         AssignedTo|[email protected] |scsi_drivers-other@kernel-b
                   |l.org                       |ugs.osdl.org
            Product|Other                       |SCSI Drivers
         Regression|---                         |No

Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.

Weird. I am just seeing this bz now. Could you try the patches in this thread

https://lkml.org/lkml/2012/5/17/215

a long with the attached patch for iscsi? The patchset is for swap over storage, but because we do not check for that case specifially I think they will allow you to dip into the reserves in your setup.

From 917d53f16d1e26b12e90e5e15df76a7a8bee35e8 Mon Sep 17 00:00:00 2001
From: Mike Christie <[email protected]>
Date: Thu, 3 May 2012 12:36:18 -0500
Subject: [PATCH 1/1] iscsi: Set SOCK_MEMALLOC for access to PFMEMALLOC
reserves

Set SOCK_MEMALLOC on the iscsi socket to allow access to PFMEMALLOC reserves to prevent deadlock.

---
 drivers/scsi/iscsi_tcp.c |   18 +++++++++++++-----
 1 files changed, 13 insertions(+), 5 deletions(-)

index 453a740..7360f4c 100644
@@ -370,17 +370,24 @@ static inline int iscsi_sw_tcp_xmit_qlen(struct iscsi_conn *conn)
 static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task)
 {
 	struct iscsi_conn *conn = task->conn;
-	int rc;
+	unsigned long pflags = current->flags;
+	int rc = 0;
+
+	current->flags |= PF_MEMALLOC;
 
 	while (iscsi_sw_tcp_xmit_qlen(conn)) {
 		rc = iscsi_sw_tcp_xmit(conn);
-		if (rc == 0)
-			return -EAGAIN;
+		if (rc == 0) {
+			rc = -EAGAIN;
+			break;
+		}
 		if (rc < 0)
-			return rc;
+			break;
+		rc = 0;
 	}
 
-	return 0;
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+	return rc;
 }
 
 /*

@@ -665,6 +672,7 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
 	sk->sk_reuse = 1;
 	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
 	sk->sk_allocation = GFP_ATOMIC;
+	sk_set_memalloc(sk);
 
 	iscsi_sw_tcp_conn_set_callbacks(conn);
 	tcp_sw_conn->sendpage = tcp_sw_conn->sock->ops->sendpage;

1.7.7.6

https://bugzilla.kernel.org/show_bug.cgi?id=10890

Alan <[email protected]> changed:

What |Removed |Added
----------------------------------------------------------------------------

             Status|NEW                         |RESOLVED
         Resolution|---                         |OBSOLETE

--- Comment #17 from Alan <[email protected]> --- This bug relates to a very old kernel. Closing as obsolete.

If you see it in a recent kernel please open a new bug

You are receiving this mail because:
You are watching the assignee of the bug.