Skip to contentSkip to conversation

opensm/osm_vl15intf.c Log change

PATCH Applied Line Holen 4 participants 5 messages Nov 27, 2009 – Dec 16, 2009 3 messages not in the archive InfiniBand

lore
Share & tools
lore

Line Holen

author
#0 lore raw

PATCH 1/1 opensm/osm_vl15intf.c Log change

Added transaction ID to a message

Signed-off-by Line Holen <[email protected]>

---

opensm/opensm/osm_vl15intf.c +3 -1
index c380a55..cc3ff33 100644
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2009 Sun Microsystems, Inc. All rights reserved.
  * Copyright (c) 2004-2009 Voltaire, Inc. All rights reserved.
  * Copyright (c) 2002-2006 Mellanox Technologies LTD. All rights reserved.
  * Copyright (c) 1996-2003 Intel Corporation. All rights reserved.

@@ -91,7 +92,8 @@ static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t * p_madw)
 	}
 
 	OSM_LOG(p_vl->p_log, OSM_LOG_ERROR, "ERR 3E03: "
-		"MAD send failed (%s)\n", ib_get_err_str(status));
+		"MAD send failed (%s), TID 0x%" PRIx64 "\n",
+		ib_get_err_str(status), cl_ntoh64(p_madw->p_mad->trans_id));
 
 	/*
 	   The MAD was never successfully sent, so

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

A message that is not in the archive (sent off-list or not yet received): 4B0FD804.2020309-UdXhSnd/[email protected]

#3 lore raw
In reply to a message not in the archive
Quoted 19 lines · Line Holen

Added transaction ID to a message

Signed-off-by Line Holen <[email protected]>

---

opensm/opensm/osm_vl15intf.c +1 -0
index c380a55..cc3ff33 100644
@@ -1,4 +1,5 @@
  /*
+ * Copyright (c) 2009 Sun Microsystems, Inc. All rights reserved.
  * Copyright (c) 2004-2009 Voltaire, Inc. All rights reserved.
  * Copyright (c) 2002-2006 Mellanox Technologies LTD. All rights reserved.
  * Copyright (c) 1996-2003 Intel Corporation. All rights reserved.

@@ -91,7 +92,8 @@ static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t * p_madw)
        }
Quoted 4 lines

       OSM_LOG(p_vl->p_log, OSM_LOG_ERROR, "ERR 3E03: "
-               "MAD send failed (%s)\n", ib_get_err_str(status));
+               "MAD send failed (%s), TID 0x%" PRIx64 "\n",
+               ib_get_err_str(status), cl_ntoh64(p_madw->p_mad->trans_id));

I don't think it's safe to touch the MAD once it's been returned to the pool. So either this change needs to be reverted or the transaction ID (and any other info to be printed on error) saved and logged on error.

-- Hal

Quoted 8 lines

       /*
          The MAD was never successfully sent, so
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

A message that is not in the archive (sent off-list or not yet received): f0e08f230912150812r8fa3a89kf62aa2412e8b824-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org

#5 lore raw
Quoted 20 lines · Hal Rosenstock
Quoted 19 lines · Line Holen

Added transaction ID to a message

Signed-off-by Line Holen<[email protected]>

---

opensm/opensm/osm_vl15intf.c +1 -0
index c380a55..cc3ff33 100644
@@ -1,4 +1,5 @@
  /*
+ * Copyright (c) 2009 Sun Microsystems, Inc. All rights reserved.
  * Copyright (c) 2004-2009 Voltaire, Inc. All rights reserved.
  * Copyright (c) 2002-2006 Mellanox Technologies LTD. All rights reserved.
  * Copyright (c) 1996-2003 Intel Corporation. All rights reserved.

@@ -91,7 +92,8 @@ static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t * p_madw)
        }
Quoted 9 lines

opensm/opensm/osm_vl15intf.c static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t * p_madw) · line 96

Quoted 4 lines
opensm/opensm/osm_vl15intf.c +2 -1
        OSM_LOG(p_vl->p_log, OSM_LOG_ERROR, "ERR 3E03: "
-               "MAD send failed (%s)\n", ib_get_err_str(status));
+               "MAD send failed (%s), TID 0x%" PRIx64 "\n",
+               ib_get_err_str(status), cl_ntoh64(p_madw->p_mad->trans_id));

I don't think it's safe to touch the MAD once it's been returned to the pool. So either this change needs to be reverted or the transaction ID (and any other info to be printed on error) saved and logged on error.

I'm actually seeing OSM crashing on this line
pretty reliably. For now I've issued a revert
patch.

-- Yevgeny

Quoted 10 lines

-- Hal

Quoted 8 lines
opensm/opensm/osm_vl15intf.c +0 -1
        /*
           The MAD was never successfully sent, so
--

To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

Quoted 5 lines

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

A message that is not in the archive (sent off-list or not yet received): 4B28AA3A.8090700-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org

#7 lore raw
Quoted 34 lines · Yevgeny Kliteynik
Quoted 22 lines · Hal Rosenstock
Quoted 21 lines · Line Holen

Added transaction ID to a message

Signed-off-by Line Holen<[email protected]>

---

opensm/opensm/osm_vl15intf.c +1 -0
index c380a55..cc3ff33 100644
@@ -1,4 +1,5 @@
  /*
+ * Copyright (c) 2009 Sun Microsystems, Inc. All rights reserved.
  * Copyright (c) 2004-2009 Voltaire, Inc. All rights reserved.
  * Copyright (c) 2002-2006 Mellanox Technologies LTD. All rights

reserved.
* Copyright (c) 1996-2003 Intel Corporation. All rights reserved.

opensm/opensm/osm_vl15intf.c +0 -0
@@ -91,7 +92,8 @@ static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t
 * p_madw)
        }
Quoted 10 lines

opensm/opensm/osm_vl15intf.c static void vl15_send_mad(osm_vl15_t * p_vl, osm_madw_t * p_madw)

Quoted 5 lines
opensm/opensm/osm_vl15intf.c +2 -1
        OSM_LOG(p_vl->p_log, OSM_LOG_ERROR, "ERR 3E03: "
-               "MAD send failed (%s)\n", ib_get_err_str(status));
+               "MAD send failed (%s), TID 0x%" PRIx64 "\n",
+               ib_get_err_str(status),
 cl_ntoh64(p_madw->p_mad->trans_id));

I don't think it's safe to touch the MAD once it's been returned to the pool. So either this change needs to be reverted or the transaction ID (and any other info to be printed on error) saved and logged on error.

Quoted 3 lines

I'm actually seeing OSM crashing on this line
pretty reliably. For now I've issued a revert
patch.

I'll shortly send an alternative patch which preserves Line's tid printing in vl15_send_mad.

-- Hal

Quoted 20 lines

-- Yevgeny

Quoted 15 lines

-- Hal

Quoted 8 lines
opensm/opensm/osm_vl15intf.c +0 -0
        /*

The MAD was never successfully sent, so
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html