* Fix some missing includes in a few places.
* Add the cr_request() functionality to the BLCR CRS component.
We are now dependent upon the 0.6.* series of BLCR.
* Made the CR notification mechanism a registered function.
This way we can have an OPAL-only version and it can be replaced at
runtime with the ORTE version.
* Add a 'opal_cr_allow_opal_only' parameter that will enable OPAL-only
CR functionality when the user wants it. Default: Disabled.
* Fix the placement of a checkpoint request check in MPI_Init
* Pull the OPAL notification mechanism into the SnapC framework.
* We no longer fork/exec the 'opal-checkpoint' command for local
checkpointing, the Local coordinator in the orted does this directly.
* The Local and Application coordinator talk together bypassing the OPAL
notifiation mechanism.
* Optimized the Local <-> App Coordinator communication.
* Improved the structure used to track vpid_snapshots in the local coord.
* Fix a race condition in which an application under heavy communication load
may produce an inconsistent global checkpoint.
This commit was SVN r16389.
The commit has been tested for C/R and Cray operations, and on Odin (SLURM, rsh) and RoadRunner (TM). I tried to update all environments, but obviously could not test them. I know that Windows needs some work, and have highlighted what is know to be needed in the odls process component.
This represents a lot of work by Brian, Tim P, Josh, and myself, with much advice from Jeff and others. For posterity, I have appended a copy of the email describing the work that was done:
As we have repeatedly noted, the modex operation in MPI_Init is the single greatest consumer of time during startup. To-date, we have executed that operation as an ORTE stage gate that held the process until a startup message containing all required modex (and OOB contact info - see #3 below) info could be sent to it. Each process would send its data to the HNP's registry, which assembled and sent the message when all processes had reported in.
In addition, ORTE had taken responsibility for monitoring process status as it progressed through a series of "stage gates". The process reported its status at each gate, and ORTE would then send a "release" message once all procs had reported in.
The incoming changes revamp these procedures in three ways:
1. eliminating the ORTE stage gate system and cleanly delineating responsibility between the OMPI and ORTE layers for MPI init/finalize. The modex stage gate (STG1) has been replaced by a collective operation in the modex itself that performs an allgather on the required modex info. The allgather is implemented using the orte_grpcomm framework since the BTL's are not active at that point. At the moment, the grpcomm framework only has a "basic" component analogous to OMPI's "basic" coll framework - I would recommend that the MPI team create additional, more advanced components to improve performance of this step.
The other stage gates have been replaced by orte_grpcomm barrier functions. We tried to use MPI barriers instead (since the BTL's are active at that point), but - as we discussed on the telecon - these are not currently true barriers so the job would hang when we fell through while messages were still in process. Note that the grpcomm barrier doesn't actually resolve that problem, but Brian has pointed out that we are unlikely to ever see it violated. Again, you might want to spend a little time on an advanced barrier algorithm as the one in "basic" is very simplistic.
Summarizing this change: ORTE no longer tracks process state nor has direct responsibility for synchronizing jobs. This is now done via collective operations within the MPI layer, albeit using ORTE collective communication services. I -strongly- urge the MPI team to implement advanced collective algorithms to improve the performance of this critical procedure.
2. reducing the volume of data exchanged during modex. Data in the modex consisted of the process name, the name of the node where that process is located (expressed as a string), plus a string representation of all contact info. The nodename was required in order for the modex to determine if the process was local or not - in addition, some people like to have it to print pretty error messages when a connection failed.
The size of this data has been reduced in three ways:
(a) reducing the size of the process name itself. The process name consisted of two 32-bit fields for the jobid and vpid. This is far larger than any current system, or system likely to exist in the near future, can support. Accordingly, the default size of these fields has been reduced to 16-bits, which means you can have 32k procs in each of 32k jobs. Since the daemons must have a vpid, and we require one daemon/node, this also restricts the default configuration to 32k nodes.
To support any future "mega-clusters", a configuration option --enable-jumbo-apps has been added. This option increases the jobid and vpid field sizes to 32-bits. Someday, if necessary, someone can add yet another option to increase them to 64-bits, I suppose.
(b) replacing the string nodename with an integer nodeid. Since we have one daemon/node, the nodeid corresponds to the local daemon's vpid. This replaces an often lengthy string with only 2 (or at most 4) bytes, a substantial reduction.
(c) when the mca param requesting that nodenames be sent to support pretty error messages, a second mca param is now used to request FQDN - otherwise, the domain name is stripped (by default) from the message to save space. If someone wants to combine those into a single param somehow (perhaps with an argument?), they are welcome to do so - I didn't want to alter what people are already using.
While these may seem like small savings, they actually amount to a significant impact when aggregated across the entire modex operation. Since every proc must receive the modex data regardless of the collective used to send it, just reducing the size of the process name removes nearly 400MBytes of communication from a 32k proc job (admittedly, much of this comm may occur in parallel). So it does add up pretty quickly.
3. routing RML messages to reduce connections. The default messaging system remains point-to-point - i.e., each proc opens a socket to every proc it communicates with and sends its messages directly. A new option uses the orteds as routers - i.e., each proc only opens a single socket to its local orted. All messages are sent from the proc to the orted, which forwards the message to the orted on the node where the intended recipient proc is located - that orted then forwards the message to its local proc (the recipient). This greatly reduces the connection storm we have encountered during startup.
It also has the benefit of removing the sharing of every proc's OOB contact with every other proc. The orted routing tables are populated during launch since every orted gets a map of where every proc is being placed. Each proc, therefore, only needs to know the contact info for its local daemon, which is passed in via the environment when the proc is fork/exec'd by the daemon. This alone removes ~50 bytes/process of communication that was in the current STG1 startup message - so for our 32k proc job, this saves us roughly 32k*50 = 1.6MBytes sent to 32k procs = 51GBytes of messaging.
Note that you can use the new routing method by specifying -mca routed tree - if you so desire. This mode will become the default at some point in the future.
There are a few minor additional changes in the commit that I'll just note in passing:
* propagation of command line mca params to the orteds - fixes ticket #1073. See note there for details.
* requiring of "finalize" prior to "exit" for MPI procs - fixes ticket #1144. See note there for details.
* cleanup of some stale header files
This commit was SVN r16364.
and implementation. This has shown drastic performance benefit when
transferring Many files at roughly the same time.
I tested this for many different filem operations and everything was working
fine. Let me know if you have any problems with this functionality.
Some Notes:
- opal-checkpoint now has a 'quiet' flag to keep it from being too verbose.
- FileM RSH component is fully non-blocking.
- FileM RSH component has incomming connection throttling since by default
ssh only allows 10 concurrent scp connections to any single host. This
default can be adjusted via an MCA parameter.
{{{-mca filem_rsh_max_incomming 10}}}
- There is an MCA parameter for max outgoing connections, but it is currently
not implemented. If someone needs it then it should not be hard to implement.
{{{-mca filem_rsh_max_outgoing 10}}}
- Changed the FileM request structure so that it is a bit more explicit and
flexible.
- Moved the 'preload-binary' and 'preload-files' functionality into odls/base
allowing for code reuse in the 'process' and 'default' ODLS components.
- Fixed a bug in the process name resolution which broke the 'preload-*'
functionality due to GPR table structure changes.
- The FileM RSH component might be able to see even more speedup from using a
thread pool to operate on the work_pool structures, but that is for future
work.
- Added a 'opal-show-help' file to ODLS Base
This commit was SVN r16252.
was taken form the $CWD to the storage directory. Now we just store directly
to the storage directory which can reduce NFS traffic if working in that mode.
A slight performance boost, but at the point you are using NFS you are paying
a penalty anyway. Now you just don't have to pay it twice :)
This commit was SVN r16099.
A subset of this patch needs to be applied to v1.2
Refs trac:928
This commit was SVN r15918.
The following Trac tickets were found above:
Ticket 928 --> https://svn.open-mpi.org/trac/ompi/ticket/928
was brought in. This supercedes the GLOBL patch that we had been using
with Libtool 2.1a versions prior to the lt_dladvise code. Autogen
tries to figure out which version you're on, so either will now work with
the trunk.
This commit was SVN r15903.
- If one wants to use this solution, remember to unload the project 'orte-restart' which is currently not working for Windows.
This commit was SVN r15680.
This is because internally 'self' uses dlopen to look at the application
running to determine if it can/should be used or not.
This commit was SVN r15673.
in a callback from the event library and post an RML receive, we'll
deadlock because the event library wouldn't be entered until the
event library was not already entered. Now just protect data structures
(which we were basically already doing) instead of code, like good
threading people ;).
This commit was SVN r15585.
* General TCP cleanup for OPAL / ORTE
* Simplifying the OOB by moving much of the logic into the RML
* Allowing the OOB RML component to do routing of messages
* Adding a component framework for handling routing tables
* Moving the xcast functionality from the OOB base to its own framework
Includes merge from tmp/bwb-oob-rml-merge revisions:
r15506, r15507, r15508, r15510, r15511, r15512, r15513
This commit was SVN r15528.
The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
r15506
r15507
r15508
r15510
r15511
r15512
r15513
asprintf and friends. This is not a failsafe; there are many cases
where this check will not be used. But at least it's something...
This commit was SVN r15500.
opal_net_get_hostname() rather than malloc, because no one was freeing
the buffer and the common use case was for printfs, where calling
free is a pain.
This commit was SVN r15494.
1. Galen's fine-grain control of queue pair resources in the openib
BTL.
1. Pasha's new implementation of asychronous HCA event handling.
Pasha's new implementation doesn't take much explanation, but the new
"multifrag" stuff does.
Note that "svn merge" was not used to bring this new code from the
/tmp/ib_multifrag branch -- something Bad happened in the periodic
trunk pulls on that branch making an actual merge back to the trunk
effectively impossible (i.e., lots and lots of arbitrary conflicts and
artifical changes). :-(
== Fine-grain control of queue pair resources ==
Galen's fine-grain control of queue pair resources to the OpenIB BTL
(thanks to Gleb for fixing broken code and providing additional
functionality, Pasha for finding broken code, and Jeff for doing all
the svn work and regression testing).
Prior to this commit, the OpenIB BTL created two queue pairs: one for
eager size fragments and one for max send size fragments. When the
use of the shared receive queue (SRQ) was specified (via "-mca
btl_openib_use_srq 1"), these QPs would use a shared receive queue for
receive buffers instead of the default per-peer (PP) receive queues
and buffers. One consequence of this design is that receive buffer
utilization (the size of the data received as a percentage of the
receive buffer used for the data) was quite poor for a number of
applications.
The new design allows multiple QPs to be specified at runtime. Each
QP can be setup to use PP or SRQ receive buffers as well as giving
fine-grained control over receive buffer size, number of receive
buffers to post, when to replenish the receive queue (low water mark)
and for SRQ QPs, the number of outstanding sends can also be
specified. The following is an example of the syntax to describe QPs
to the OpenIB BTL using the new MCA parameter btl_openib_receive_queues:
{{{
-mca btl_openib_receive_queues \
"P,128,16,4;S,1024,256,128,32;S,4096,256,128,32;S,65536,256,128,32"
}}}
Each QP description is delimited by ";" (semicolon) with individual
fields of the QP description delimited by "," (comma). The above
example therefore describes 4 QPs.
The first QP is:
P,128,16,4
Meaning: per-peer receive buffer QPs are indicated by a starting field
of "P"; the first QP (shown above) is therefore a per-peer based QP.
The second field indicates the size of the receive buffer in bytes
(128 bytes). The third field indicates the number of receive buffers
to allocate to the QP (16). The fourth field indicates the low
watermark for receive buffers at which time the BTL will repost
receive buffers to the QP (4).
The second QP is:
S,1024,256,128,32
Shared receive queue based QPs are indicated by a starting field of
"S"; the second QP (shown above) is therefore a shared receive queue
based QP. The second, third and fourth fields are the same as in the
per-peer based QP. The fifth field is the number of outstanding sends
that are allowed at a given time on the QP (32). This provides a
"good enough" mechanism of flow control for some regular communication
patterns.
QPs MUST be specified in ascending receive buffer size order. This
requirement may be removed prior to 1.3 release.
This commit was SVN r15474.
Remove the matching logic out of dynamic path into an
extra function. Add the corresponing check to the static
component path.
This commit was SVN r15458.
There are several interesting things:
1. less NFS traffic [as we potentially access less files]
2. faster loading time [in case the user tune it's execution environment]
3. (1) + (2) -> faster startup time [at least everything which do not depend on the network]
4. MX bug will go away if the pml is specified.
5. No useless BTL will be opened, which will solve few others issues.
This commit was SVN r15402.
VxWorks. Still some issues remaining, I'm sure.
Refs trac:1010
This commit was SVN r15320.
The following Trac tickets were found above:
Ticket 1010 --> https://svn.open-mpi.org/trac/ompi/ticket/1010
* Make orted.1 man page be non-descriptive because it's really an
internal command.
* Re-work the opal_wrapper man page logic a bit so that we can have a
real opal_wrapper.1 installed that says "don't look here -- look at
mpicc (etc.)"
This commit was SVN r15264.
* Remove the 'opal_mca_base_param_use_amca_sets' global variable
* Harness the fact that you can (read should) call the cmd_line functions
before initializing opal_init_util(). This pushes the MCA/GMCA/AMCA
command line options into the environment before OPAL inits and starts
to use these values. By putting the cmd_line parse before opal_init_util
in orterun and orted we only parse the *MCA parameter files once, and
correctly (alleviating the need to 'recache' the files on init.)
* Small bits of cleanup.
This commit was SVN r15219.
param says we should Also, check for != 0, rather than == 1, as there
are way too many double locks, but they'll get warned when we do the
double lock. No need to warn again, in a meaningless way.
Originally part of r15167, reverted with r15172.
This commit was SVN r15173.
The following SVN revision numbers were found above:
r15167 --> open-mpi/ompi@faa401dc47
r15172 --> open-mpi/ompi@5f16251808
OBJ_NEW
* Need to single when the passive unlock has left an expose epoch for
the win_free case
* Clean up some debugging output
* fix missing variable initialization
This commit was SVN r15167.
flex (which, incidentally, emit ''more'' warnings than earlier
versions). Grumble.
This commit was SVN r15166.
The following SVN revision numbers were found above:
r15158 --> open-mpi/ompi@57d09c10f7
Ensure that the AM_CONDITIONALs are ''always'' run, even if we
--enable-mca-no-build the paffinity/linux component.
This commit was SVN r15095.
The following Trac tickets were found above:
Ticket 1057 --> https://svn.open-mpi.org/trac/ompi/ticket/1057
