[ewg] [PATCH] RDMA/doc: Updated nes_release_notes.txt
miroslaw.walukiewicz at intel.com
miroslaw.walukiewicz at intel.com
Wed Feb 23 08:48:04 PST 2011
Updated a section "What's new" for NES driver and MPI usage
Signed-off-by: Mirek Walukiewicz <miroslaw.walukiewicz at intel.com>
---
docs/release_notes/nes_release_notes.txt | 150 ++++++++++++------------------
1 files changed, 60 insertions(+), 90 deletions(-)
diff --git a/docs/release_notes/nes_release_notes.txt b/docs/release_notes/nes_release_notes.txt
index 0233d90..f89b687 100644
--- a/docs/release_notes/nes_release_notes.txt
+++ b/docs/release_notes/nes_release_notes.txt
@@ -1,6 +1,6 @@
Open Fabrics Enterprise Distribution (OFED)
NetEffect Ethernet Cluster Server Adapter Release Notes
- September 2010
+ February 2011
@@ -10,20 +10,20 @@ support for the NetEffect Ethernet Cluster Server Adapters.
==========
What's New
==========
-OFED 1.5.2 contains several enhancements and bug fixes to iw_nes driver.
-
-* Add new feature iWarp Multicast Acceleration (IMA).
-* Add module option to disable extra doorbell read after a write.
-* Change CQ event notification to not fire event unless there is a
- new CQE not polled.
-* Fix payload calculation for post receive with more than one SGE.
-* Fix crash when CLOSE was indicated twice due to connection close
- during remote peer's timeout on pending MPA reply.
-* Fix ifdown hang by not calling ib_unregister_device() till removal
- of iw_nes module.
-* Handle RST when state of connection is in FIN_WAIT2.
-* Correct properties for various nes_query_{qp, port, device} calls.
-
+OFED 1.5.3 contains several enhancements and bug fixes to iw_nes driver.
+
+* Correct AEQE operation.
+* Add backports for 2.6.35 and 2.6.36 kernels.
+* Fix for problem of lack of HW limit checking for MG attach for IMA.
+* Fix for a problem with non-aligned buffers crash during post_recv for IMA.
+* Fix for possible crash when RAW QP resources are destroyed.
+* Fix for problem of RAW QP transition state to ERR.
+* Fix a problem with sending packets with VLAN flag for IMA.
+* Enable bonds on iw_nes.
+* Fix hazard of sending ibevent for unregistered device.
+* Fix for sending IB_EVENT_PORT_ERR/PORT_ACTIVE event on link state interrupt.
+* Fix SFP link down detection issue with switch port disable.
+* Fix incorrect SFP link status detection on driver init.
============================================
Required Setting - RDMA Unify TCP port space
@@ -121,115 +121,84 @@ mpd.hosts file
mpd.hosts is a text file with a list of nodes, one per line, in the MPI ring.
Use either fully qualified hostname or IP address.
+===========================
+100% CPU Utilization remark
+===========================
+Most of the RDMA applications use CQ Polling mode to decrease latency.
+This operational mode can cause 100% CPU utilization.
-=======================================
-Recommended Settings for HP MPI 2.2.7
-=======================================
-Add the following to mpirun command:
-
- -1sided
-
-Example mpirun command with uDAPL-2.0:
-
- mpirun -np 2 -hostfile /opt/mpd.hosts
- -UDAPL -prot -intra=shm
- -e MPI_HASIC_UDAPL=ofa-v2-iwarp
- -1sided
- /opt/hpmpi/help/hello_world
-
-Example mpirun command with uDAPL-1.2:
-
- mpirun -np 2 -hostfile /opt/mpd.hosts
- -UDAPL -prot -intra=shm
- -e MPI_HASIC_UDAPL=OpenIB-iwarp
- -1sided
- /opt/hpmpi/help/hello_world
-
-
-============================================================
-Recommended Settings for Platform MPI 7.1 (formerly HP-MPI)
-============================================================
-Add the following to mpirun command:
-
- -1sided
-
-Example mpirun command with uDAPL-2.0:
-
- mpirun -np 2 -hostfile /opt/mpd.hosts
- -UDAPL -prot -intra=shm
- -e MPI_HASIC_UDAPL=ofa-v2-iwarp
- -1sided
- /opt/platform_mpi/help/hello_world
-
-Example mpirun command with uDAPL-1.2:
-
- mpirun -np 2 -hostfile /opt/mpd.hosts
- -UDAPL -prot -intra=shm
- -e MPI_HASIC_UDAPL=OpenIB-iwarp
- -1sided
- /opt/platform_mpi/help/hello_world
-
+To switch to Event Driven mode and lower CPU utilization please refer to README or
+Release Notes for specific application.
==============================================
-Recommended Settings for Intel MPI 3.2.x/4.0.x
+Recommended Settings for Intel MPI 4.0.x
==============================================
Add the following to mpiexec command:
-genv I_MPI_FALLBACK_DEVICE 0
- -genv I_MPI_DEVICE rdma:OpenIB-iwarp
+ -genv I_MPI_FABRICS shm:dapl
+ -genv I_MPI_DAPL_PROVIDER ofa-v2-iwarp
-genv I_MPI_USE_RENDEZVOUS_RDMA_WRITE 1
Example mpiexec command line for uDAPL-2.0:
mpiexec -genv I_MPI_FALLBACK_DEVICE 0
- -genv I_MPI_DEVICE rdma:ofa-v2-iwarp
+ -genv I_MPI_FABRICS shm:dapl
+ -genv I_MPI_DAPL_PROVIDER ofa-v2-iwarp
-genv I_MPI_USE_RENDEZVOUS_RDMA_WRITE 1
-ppn 1 -n 2
- /opt/intel/impi/3.2.2/bin64/IMB-MPI1
+ /opt/intel/impi/4.0.0.025/bin64/IMB-MPI1
Example mpiexec command line for uDAPL-1.2:
mpiexec -genv I_MPI_FALLBACK_DEVICE 0
- -genv I_MPI_DEVICE rdma:OpenIB-iwarp
+ -genv I_MPI_DEVICE shm:dapl
+ -genv I_MPI_DAPL_PROVIDER OpenIB-iwarp
-genv I_MPI_USE_RENDEZVOUS_RDMA_WRITE 1
-ppn 1 -n 2
- /opt/intel/impi/3.2.2/bin64/IMB-MPI1
+ /opt/intel/impi/4.0.0.025/bin64/IMB-MPI1
+
+Intel MPI use CQ Polling mode as a default.
+To switch to wait mode add the following to mpiexec command:
+ -genv I_MPI_WAIT_MODE 1
+NOTE: Wait mode supports the sock device only.
========================================
Recommended Setting for MVAPICH2 and OFA
========================================
-Add the following to the mpirun command:
-
- -env MV2_USE_IWARP_MODE 1
+Example mpirun_rsh command line:
-Example mpiexec command line:
-
- mpiexec -l -n 2
- -env MV2_USE_IWARP_MODE 1
- /usr/mpi/gcc/mvapich2-1.5/tests/osu_benchmarks-3.1.1/osu_latency
+ mpirun_rsh -ssh -np 2 -hostfile /root/mpd.hosts
+ /usr/mpi/gcc/mvapich2-1.6/tests/osu_benchmarks-3.1.1/osu_latency
+MVAPICH2 use CQ Polling mode as a default.
+To switch to Blocking mode add the following to mpirun_rsh command:
+ MV2_USE_BLOCKING=1
==========================================
Recommended Setting for MVAPICH2 and uDAPL
==========================================
-Add the following to the mpirun command for 64 or more processes:
+Add the following to the mpirun_rsh command for 64 or more processes:
-env MV2_ON_DEMAND_THRESHOLD <number of processes>
-Example mpirun command with uDAPL-2.0:
+Example mpirun_rsh command with uDAPL-2.0:
- mpiexec -l -n 64
- -env MV2_DAPL_PROVIDER ofa-v2-iwarp
- -env MV2_ON_DEMAND_THRESHOLD 64
- /usr/mpi/gcc/mvapich2-1.5/tests/IMB-3.2/IMB-MPI1
+ mpirun_rsh -ssh -np 64 -hostfile /root/mpd.hosts
+ MV2_DAPL_PROVIDER=ofa-v2-iwarp
+ MV2_ON_DEMAND_THRESHOLD=64
+ /usr/mpi/gcc/mvapich2-1.6/tests/IMB-3.2/IMB-MPI1
-Example mpirun command with uDAPL-1.2:
+Example mpirun_rsh command with uDAPL-1.2:
- mpiexec -l -n 64
- -env MV2_DAPL_PROVIDER OpenIB-iwarp
- -env MV2_ON_DEMAND_THRESHOLD 64
- /usr/mpi/gcc/mvapich2-1.5/tests/IMB-3.2/IMB-MPI1
+ mpirun_rsh -ssh -np 64 -hostfile /root/mpd.hosts
+ MV2_DAPL_PROVIDER=OpenIB-iwarp
+ MV2_ON_DEMAND_THRESHOLD=64
+ /usr/mpi/gcc/mvapich2-1.6/tests/IMB-3.2/IMB-MPI1
+MVAPICH2 use CQ Polling mode as a default.
+To switch to Blocking mode add the following to mpirun_rsh command:
+ MV2_USE_BLOCKING=1
===========================
Modify Settings in Open MPI
@@ -240,9 +209,8 @@ for your environment:
http://www.open-mpi.org/faq/?category=tuning#setting-mca-params
-
=======================================
-Recommended Settings for Open MPI 1.4.2
+Recommended Settings for Open MPI 1.4.3
=======================================
Allow the sender to use RDMA Writes:
@@ -254,8 +222,10 @@ Example mpirun command line:
-mca btl openib,self,sm
-mca btl_mpi_leave_pinned 0
-mca btl_openib_flags 2
- /usr/mpi/gcc/openmpi-1.4.2/tests/IMB-3.2/IMB-MPI1
+ /usr/mpi/gcc/openmpi-1.4.3/tests/IMB-3.2/IMB-MPI1
+OpenMPI use CQ Polling mode as a default.
+No command parameter available to swith to Event Driven mode.
===================================
iWARP Multicast Acceleration (IMA)
More information about the ewg
mailing list