Function for improved node descriptions
Subsystems (2)
v3 cover Function for improved node descriptions
Changes from Version 2:
Changed the function to skip over '%' fields that aren't supported and added code to ensure the string is null terminated no matter how it was formatted.
Changed the default description to more closely match the current OFED behavior. The new default is '%h HCA-%d'. For example:
homer HCA-mthca0
node-a2 HCA-qib1
lisa HCA-mlx4_0
Changes from Version 1:
Replaced the original substitution of the hostname for '@' with an implementation of the '%h' and '%d' fields.
Description:
The common practice in IB fabrics is to set the description of an HCA to be the hostname of the machine plus a description (i.e., "myhost hca-1", "myhost hca-2", etc..)
This has a limitation, however. The first is that if the machine's hostname is set via DHCP, the HCA description may be set before the hostname is, leading to an incorrect description. This can also occur if the machine's hostname changes for some other reason after boot.
This can cause difficulties and confusion when trying to maintain a large fabric - if all your nodes are described as "localhost HCA-1" it can be very difficult to figure out which node is suffering from symbol errors.
This patch addresses the problem by providing a function to build the node description. If the provided source string for the description contains a '%h' it will be replaced at read time with the hostname of the node. If the provided source string contains a '%d' it will be replaced at read time with the name of the HCA. For example, if the node description of the second HCA on node-a13 is set to'%h: %d', at read time this will be expanded to read "node-a2: qib1".
This ensures that even after a fabric has been completely initialized, if a node's hostname changes, that change will be reflected in the next "heavy" sweep of the SM, but also maintains compatibility with existing code since the behavior is unchanged if the description string does not contain a '%' character.
---
Michael Heinz (2):
Function for improved node descriptions Add support for ib_build_node_desc() to the HCAs.
drivers/infiniband/core/mad.c | 39 ++++++++++++++++++++++++++ drivers/infiniband/hw/ipath/ipath_mad.c | 2 + drivers/infiniband/hw/ipath/ipath_verbs.c | 3 +- drivers/infiniband/hw/mlx4/mad.c | 2 + drivers/infiniband/hw/mlx4/main.c | 2 + drivers/infiniband/hw/mthca/mthca_mad.c | 2 + drivers/infiniband/hw/mthca/mthca_provider.c | 2 + drivers/infiniband/hw/qib/qib_mad.c | 2 + drivers/infiniband/hw/qib/qib_verbs.c | 3 +- include/rdma/ib_mad.h | 9 ++++++ include/rdma/ib_verbs.h | 3 +- 11 files changed, 58 insertions(+), 11 deletions(-)
Signature · 5 lines
Signed-off-by: Michael Heinz <[email protected]> -- 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
PATCH v3 1/2 Function for improved node descriptions
Changes from Version 2:
Changed the function to skip over '%' fields that aren't supported and added code to ensure the string is null terminated no matter how it was formatted.
Changes from Version 1:
Replaced the original substitution of the hostname for '@' with an implementation of the '%h' and '%d' fields.
Description:
This patch adds a function to do variable substitution in the node description. If the node description contains a '%h' it will be replaced at read time with the hostname of the node. If the provided source string contains a '%d' it will be replaced at read time with the name of the HCA.
For example, if the node description of the second HCA on node-a13 is set to'%h: %d', at read time this will be expanded to read "node-a2: qib1".
--- drivers/infiniband/core/mad.c | 39 +++++++++++++++++++++++++++++++++++++++ include/rdma/ib_mad.h | 9 +++++++++ include/rdma/ib_verbs.h | 3 ++- 3 files changed, 50 insertions(+), 1 deletions(-)
drivers/infiniband/core/mad.c +39 -0
@@ -41,6 +41,7 @@#include "mad_rmpp.h" #include "smi.h" #include "agent.h" +#include "linux/utsname.h" MODULE_LICENSE ("Dual BSD/GPL" );MODULE_DESCRIPTION ("kernel IB MAD API" );
@@ -932,6 +933,44 @@ int ib_get_mad_data_offset(u8 mgmt_class) }EXPORT_SYMBOL (ib_get_mad_data_offset); +void ib_build_node_desc (struct ib_smp *smp,struct ib_device *dev) +{ +char *dest = smp->data; +char *end = dest +IB_DEVICE_DESC_MAX -1 ; +char *src = dev->node_desc; +char *field; + +while (*src && (dest < end)) { +if (*src !='%' ) { + *dest++ = *src++; + }else { + src++; +switch (*src) { +case 'h' : + field =init_utsname ()->nodename; + src++; +for (; *field && (*field !='.' ) && + (dest < end);) + *dest++ = *field++; +break ; +case 'd' : + field = dev->name; + src++; +for (; *field && (dest < end);) + *dest++ = *field++; +break ; +default : + src++; + } + } + } +if (dest < end) + *dest =0 ; +else + *end =0 ; +} +EXPORT_SYMBOL (ib_build_node_desc); +int ib_is_mad_class_rmpp (u8 mgmt_class) { if ((mgmt_class == IB_MGMT_CLASS_SUBN_ADM) ||
include/rdma/ib_mad.h +9 -0
@@ -40,6 +40,7 @@#include <linux/list.h> #include <rdma/ib_verbs.h> +#include <rdma/ib_smi.h> /* Management base version */ #define IB_MGMT_BASE_VERSION 1
@@ -637,6 +638,14 @@ int ib_is_mad_class_rmpp(u8 mgmt_class);int ib_get_mad_data_offset (u8 mgmt_class);/** +* ib_build_node_desc - copies the node description and replaces +* any @ markers with the present system node name. +* @dest: destination +* @src: source +*/ +void ib_build_node_desc (struct ib_smp *smp,struct ib_device *dev); + +/** * ib_get_rmpp_segment - returns the data buffer for a given RMPP segment. * @send_buf: Previously allocated send data buffer. * @seg_num: number of segment to return
include/rdma/ib_verbs.h +2 -1
@@ -938,6 +938,7 @@ enum ib_mad_result { };#define IB_DEVICE_NAME_MAX 64 +#define IB_DEVICE_DESC_MAX 64struct ib_cache {rwlock_t lock;
@@ -1165,7 +1166,7 @@ struct ib_device {int uverbs_abi_ver;u64 uverbs_cmd_mask; -char node_desc[64 ]; +char node_desc[IB_DEVICE_DESC_MAX ];__be64 node_guid;u32 local_dma_lkey;u8 node_type;
--
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
PATCH v3 2/2 Add support for ib_build_node_desc() to the HCAs.
In reply to Michael HeinzChanges from Version 2:
Changed the default description to more closely match the current OFED behavior. The new default is '%h HCA-%d'. For example:
homer HCA-mthca0
node-a2 HCA-qib1
lisa HCA-mlx4_0
Changes from Version 1:
Changed the default node description for Mellanox and QLogic HCAs to read "%h: %d <description>" where '<description>' is the old default value.
Description:
Adds support for ib_build_node_desc() to the QLogic and Mellanox HCA drivers.
--- drivers/infiniband/hw/ipath/ipath_mad.c | 2 +- drivers/infiniband/hw/ipath/ipath_verbs.c | 3 +-- drivers/infiniband/hw/mlx4/mad.c | 2 +- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mthca/mthca_mad.c | 2 +- drivers/infiniband/hw/mthca/mthca_provider.c | 2 +- drivers/infiniband/hw/qib/qib_mad.c | 2 +- drivers/infiniband/hw/qib/qib_verbs.c | 3 +-- 8 files changed, 8 insertions(+), 10 deletions(-)
drivers/infiniband/hw/ipath/ipath_mad.c +1 -1
@@ -60,7 +60,7 @@ static int recv_subn_get_nodedescription(struct ib_smp *smp,if (smp->attr_mod) smp->status |=IB_SMP_INVALID_FIELD ; -memcpy (smp->data, ibdev->node_desc,sizeof (smp->data)); +ib_build_node_desc (smp, ibdev);return reply (smp); }
drivers/infiniband/hw/ipath/ipath_verbs.c +1 -2
@@ -2179,8 +2179,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd) dev->mmap = ipath_mmap; dev->dma_ops = &ipath_dma_mapping_ops; -snprintf (dev->node_desc,sizeof (dev->node_desc), -IPATH_IDSTR " %s" ,init_utsname ()->nodename); +strncpy (dev->node_desc,"%h HCA-%d" ,IB_DEVICE_DESC_MAX ); ret =ib_register_device (dev,NULL );if (ret)
drivers/infiniband/hw/mlx4/mad.c +1 -1
@@ -196,7 +196,7 @@ static void node_desc_override(struct ib_device *dev, mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP && mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {spin_lock (&to_mdev (dev)->sm_lock); -memcpy (((struct ib_smp *) mad)->data, dev->node_desc,64 ); +ib_build_node_desc ((struct ib_smp *) mad, dev);spin_unlock (&to_mdev (dev)->sm_lock); } }
drivers/infiniband/hw/mlx4/main.c +1 -1
@@ -713,7 +713,7 @@ static int init_node_data(struct mlx4_ib_dev *dev)if (err) goto out; -memcpy (dev->ib_dev.node_desc, out_mad->data,64 ); +strncpy (dev->ib_dev.node_desc,"%h HCA-%d" ,IB_DEVICE_DESC_MAX ); in_mad->attr_id =IB_SMP_ATTR_NODE_INFO ;
drivers/infiniband/hw/mthca/mthca_mad.c +1 -1
@@ -153,7 +153,7 @@ static void node_desc_override(struct ib_device *dev, mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP && mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {mutex_lock (&to_mdev (dev)->cap_mask_mutex); -memcpy (((struct ib_smp *) mad)->data, dev->node_desc,64 ); +ib_build_node_desc ((struct ib_smp *) mad, dev);mutex_unlock (&to_mdev (dev)->cap_mask_mutex); } }
drivers/infiniband/hw/mthca/mthca_provider.c +1 -1
@@ -1273,7 +1273,7 @@ static int mthca_init_node_data(struct mthca_dev *dev) goto out; } -memcpy (dev->ib_dev.node_desc, out_mad->data,64 ); +strncpy (dev->ib_dev.node_desc,"%h HCA-%d" ,IB_DEVICE_DESC_MAX ); in_mad->attr_id =IB_SMP_ATTR_NODE_INFO ;
drivers/infiniband/hw/qib/qib_mad.c +1 -1
@@ -260,7 +260,7 @@ static int subn_get_nodedescription(struct ib_smp *smp,if (smp->attr_mod) smp->status |=IB_SMP_INVALID_FIELD ; -memcpy (smp->data, ibdev->node_desc,sizeof (smp->data)); +ib_build_node_desc (smp, ibdev);return reply (smp); }
drivers/infiniband/hw/qib/qib_verbs.c +1 -2
@@ -2157,8 +2157,7 @@ int qib_register_ib_device(struct qib_devdata *dd) ibdev->mmap = qib_mmap; ibdev->dma_ops = &qib_dma_mapping_ops; -snprintf (ibdev->node_desc,sizeof (ibdev->node_desc), -QIB_IDSTR " %s" ,init_utsname ()->nodename); +strncpy (ibdev->node_desc,"%h HCA-%d" ,IB_DEVICE_DESC_MAX ); ret =ib_register_device (ibdev, qib_create_port_files);if (ret)
--
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