- Update to v1.6.2 (fate#325852)
- Core
- Cleanup of debug messages
- Fix compile issues with older compilers
- Check that all debug compiler flags are supported by compiler
- GNI
- Fix problems with Scalable Endpoint creation
- Fix interoperability problem with HPC toolkit
- Improve configuration check for kdreg
- PSM
- Enforce FI_RMA_EVENT checking when updating counters
- Fix race condition in fi_cq_readerr()
- Always try to make progress when fi_cntr_read is called
- PSM2
- Revert "Avoid long delay in psm2_ep_close"
- Fix memory corruption related to sendv
- Performance tweak for bi-directional send/recv on KNL
- Fix CPU detection
- Enforce FI_RMA_EVENT checking when updating counters
- Remove stale info from address vector when disconnecting
- Fix race condition in fi_cq_readerr()
- Adjust reported context numbers for special cases
- Always try to make progress when fi_cntr_read is called
- Support control functions related to MR mode
- Unblock fi_cntr_wait on errors
- Properly update error counters
- Fix irregular performance drop for aggregated RMA operations
- Reset Tx/Rx context counter when fabric is initialized
- Fix incorrect completion event for iov send
- Fix occasional assertion failure in psm2_ep_close
- Avoid long delay in psm2_ep_close
- Fix potential duplication of iov send completion
- Replace some parameter checking with assertions
- Check iov limit in sendmsg
- Avoid adding FI_TRIGGER caps automatically
- Avoid unnecessary calls to psmx2_am_progress()
- RXM
- Fix incorrect increments of error counters for small messages
- Increment write completion counter for small transfers
- Use FI_UNIVERSE_SIZE when defining MSG provider CQ size
- Make TX, RX queue sizes independent of MSG provider
- Make deferred requests opt-in
- Fill missing rxm_conn in rx_buf when shared context is not used
- Fix an issue where MSG endpoint recv queue got empty resulting
in a hang
- Set FI_ORDER_NONE for tx and rx completion ordering
- Serialize access to repost_ready_list
- Reprocess unexpected messages on av update
- Fix a bug in matching directed receives
- Fix desc field when postponing RMA ops
- Fix incorrect reporting of mem_tag format
- Don't include FI_DIRECTED_RECV, FI_SOURCE caps if they're not needed
- Fix matching for RMA I/O vectors
- Fix reading pointer after freeing it.
- Avoid reading invalid AV entry
- Handle deleting the same address multiple times
- Fix crash in fi_av_remove if FI_SOURCE wasn't enabled
- Sockets
- Increase maximum messages size as MPICH bug work-around
- Fix use after free error handling triggered ops.
- Verbs
- Detect string format of wildcard address in node argument
- Don't report unusable fi_info (no source IP address)
- Don't assert when a verbs device exposes unsupported MTU types
- Report correct rma_iov_limit
- Add new variable - FI_VERBS_MR_CACHE_MERGE_REGIONS
- eq->err.err must return a positive error code
OBS-URL: https://build.opensuse.org/request/show/644645
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=32
- Update to v1.6.0
- Core
- Introduces support for performing RMA operations to persistent memory
See FI_RMA_PMEM capability in fi_getinfo.3
- Define additional errno values
- General code cleanups and restructuring
- Force provider ordering when using dynamically loaded providers
- Add const to fi_getinfo() hints parameter
- Improve use of epoll for better scalability
- Fixes to generic name service
- PSM
- Move environment variable reading out from fi_getinfo()
- Shortcut obviously unsuccessful fi_getinfo() calls
- Remove excessive name sever implementation
- Enable ordering of RMA operations
- PSM2
- Skip inactive units in round-robin context allocation
- Allow contexts be shared by Tx-only and Rx-only endpoints
- Use utility functions to check provider attributes
- Turn on FI_THREAD_SAFE support
- Make address vector operations thread-safe
- Move environment variable reading out from fi_getinfo()
- Reduce noise when optimizing tagged message functions
- Shortcut obviously unsuccessful fi_getinfo() calls
- Improve how Tx/Rx context limits are handled
- Support auto selection from two different tag layout schemes
- Add provider build options to debug output
- Support remote CQ data for tagged messages, add specialization.
- Support opening multiple domains
- Put trigger implementation into a separate file
- Update makefile and configure script
- Replace allocated context with reserved space in psm2_mq_req
- Limit exported symbols for DSO provider
- Reduce HW context usage for certain TX only endpoints
- Remove unnecessary dependencies from the configure script
- Refactor the handling of op context type
- Optimize the conversion between 96-bit and 64-bit tags
- Code refactoring for completion generation
- Remove obsolete feature checking code
- Report correct source address for scalable endpoints
- Allow binding any number of endpoints to a CQ/counter
- Add shared Tx context support
- Add alternative implementation for completion polling
- Change the default value of FI_PSM2_DELAY to 0
- Add an environment variable for automatic connection cleanup
- Abstract the completion polling mechanism
- Use the new psm2_am_register_handlers_2 function when available
- Allow specialization when FI_COMPLETION op_flag is set.
- Put Tx/Rx context related functions into a separate file
- Enable PSM2 multi-ep feature by default
- Add option to build with PSM2 source included
- Simplify the code for checking endpoint capabilities
- Simplify the handling of self-targeted RMA operations
- Allow all free contexts be used for scalable endpoints
- Enable ordering of RMA operations
- Enable multiple endpoints over PSM2 multi-ep support
- Support multiple Tx/Rx contexts in address vector
- Remove the virtual lane mechanism
- Less code duplication in tagged, add more specialization.
- Allow PSM2 epid be reused within the same session
- Turn on user adjustable inject size for all operations
- Use pre-allocated memory pool for RMA requests
- Add support for lazy connection
- Various bug fixes
- SHM
- Initial release of shared memory provider
- See the fi_shm.7 man page for details on available features and limitations
- Sockets
- Scalability enhancements
- Fix issue associating a connection with an AV entry that could result in
application hangs
- Add support for new persistent memory capabilities
- Fix fi_cq_signal to unblock threads waiting on cq sread calls
- Fix epoll_wait loop handling to avoid out of memory errors
- Add support for TCP keepalives, controllable via environment variables
- Reduce the number of threads allocated for handling connections
- Several code cleanups in response to static code analysis reports
- Fix reporting multiple completion events for the same request in error cases
- usNIC
- Minor adjustments to match new core MR mode bits functionality
- Several code cleanups in response to static code analysis reports
- Verbs
- Code cleanups and simplifications
- General code optimizations to improve performance
- Fix handling of wildcard addresses
- Check for fatal errors during connection establishment
- Support larger inject sizes
- Fix double locking issue
- Add support for memory registration caching (disabled by default)
- Enable setting thread affinity for CM threads
- Fix hangs in MPI closing RDM endpoints
- Add support for different CQ formats
- Fix RMA read operations over iWarp devices
- Optimize CM progress handling
- Several bug fixes
OBS-URL: https://build.opensuse.org/request/show/587420
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=30
- Update to v1.5.3
- Core
- Handle malloc failures
- Ensure global lock is initialized on Windows
- Fix spelling and formatting errors in man pages
- PSM
- Fix print format mismatches
- Remove 15 second startup delay when no hardware is installed
- Preserve FI_MR_SCALABLE mode bit for backwards compatability
- PSM2
- Fix print format mismatches
- Allow all to all communication between scalable endpoints
- Preserve FI_MR_SCALABLE mode bit for backwards compatability
- Fix reference counting issue with opened domains
- Fix segfault for RMA/atomic operations to local scalable endpoints
- Fix resource counting related issues for Tx/Rx contexts
- Allow completion suppression when fi_context is non-NULL
- Use correct queue for triggered operations with scalable endpoints
- Sockets
- Fix check for invalid connection handle
- Fix crash in fi_av_remove
- Util
- Fix number of bits used for connection index
- Verbs
- Fix incorrect CQ entry data for MSG endpoints
- Properly check for errors from getifaddrs
- Retry getifaddr on failure because of busy netlink sockets
- Ack CM events on error paths
- Remove 0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch
as it was merged upstream
OBS-URL: https://build.opensuse.org/request/show/558744
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=28
- Update to v1.5.2
- Core
- Fix Power PC 32-bit build
- Sockets
- Fix incorrect reporting of counter attributes
- Verbs
- Fix reporting attributes based on device limits
- Fix incorrect CQ size reported for iWarp NICs
- Update man page with known issues for specific NICs
- Fix FI_RX_CQ_DATA mode check
- Disable on-demand paging by default (can cause data corruption)
- Disable loopback (localhost) addressing (causing failures in MPI)
OBS-URL: https://build.opensuse.org/request/show/544093
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=26
- Update to v1.5.1
- Core
- Fix initialization used by DL providers to avoid crash
- Add checks for null hints and improperly terminated strings
- Check for invalid core names passed to fabric open
- Provide consistent provider ordering when using DL providers
- Fix OFI_LIKELY definitions when GNUC is not present
- GNI
- Add ability to detect local PE rank
- Fix compiler/config problems
- Fix CQ read error corruption
- Remove tests of deprecated interfaces
- PSM
- Fix CQ corruption reporting errors
- Always generate a completion on error
- PSM2
- Fix CQ corruption reporting errors
- Always generate a completion on error
- Add checks to handle out of memory errors
- Add NULL check for iov in atomic readv/writev calls
- Fix FI_PEEK src address matching
- Fix bug in scalable endpoint address resolution
- Fix segfault bug in RMA completion generation
- Sockets
- Fix missing FI_CLAIM src address data on completion
- Fix CQ corruption reporting errors
- Fix serialization issue wrt out of order CPU writes to Tx ring buffer
- Verbs
- Allow modifying rnr retry timout to improve performance
- Add checks to handle out of memory errors
OBS-URL: https://build.opensuse.org/request/show/532702
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=21
- Update to v1.5.0
* Authorization keys Authorization keys, commonly referred to as job keys,
are used to isolate processes from communicating with other processes
for security purposes.
* Multicast support Datagram endpoints can now support multicast communication.
* (Experimental) socket-like endpoint types New FI_SOCK_STREAM and FI_SOCK_DGRAM
endpoint types are introduced. These endpoint types target support of cloud
and enterprise based middleware and applications.
* Tagged atomic support Atomic operations can now target tagged receive
buffers, in addition to RMA buffers.
* (Experimental) deferred work queues Deferred work queues are enhanced triggerred
operations. They target support for collective-based operations.
* New mode bits: FI_RESTRICTED_COMP and FI_NOTIFY_FLAGS_ONLY These mode bits
support optimized completion processing to minimize software overhead.
* Multi-threaded error reporting Reading CQ and EQ errors now allow the application
to provide the error buffer, eliminating the need for the application to
synchronize between multiple threads when handling errors.
* FI_SOURCE_ERR capability This feature allows the provider to validate and
report the source address for any received messages.
* FI_ADDR_STR string based addressing Applications can now request and use
addresses provided using a standardized string format. This makes it easier
to pass full addressing data through a command line, or handle address exchange
through text files.
* Communication scope capabilities: FI_LOCAL_COMM and FI_REMOTE_COMM Used to
indicate if an application requires communication with peers on the same
node and/or remote nodes.
* New memory registration modes The FI_BASIC_MR and FI_SCALABLE_MR memory registration
modes have been replaced by more refined registration mode bits. This allows
applications to make better use of provider hardware capabilities when dealing
with registered memory regions.
* New mode bit: FI_CONTEXT2 Some providers need more than the size provided by the
FI_CONTEXT mode bit setting. To accomodate such providers, an FI_CONTEXT2 mode bit
was added. This mode bit doubles the amount of context space that an application
allocates on behalf of the provider.
* PSM provider notes
* Improve the name server functionality and move to the utility code
* Handle updated mr_mode definitions
* Add support of 32 and 64 bit atomic values
* PSM2 provider notes
* Add option to adjust the locking level
* Improve the name server functionality and move to the utility code
* Add support for string address format
* Add an environment vaiable for message inject size
* Handle FI_DISCARD in tagged receive functions
* Handle updated mr_mode definitions
* Add support for scalable endpoint
* Add support of 32 and 64 bit atomic values
* Add FI_SOURCE_ERR to the supported caps
* Improve the method of checking device existence
* Sockets provider notes
* Updated and enhanced atomic operation support.
* Add support for experimental deferred work queue operations.
* Fixed counter signaling when used with wait sets.
* Improved support on Windows.
* Cleaned up event reporting for destroyed endpoints.
* Fixed several possible crash scenarios.
* Fixed handling socket disconnect events which could hang the provider.
* UDP provider notes
* Add support for multicast data transfers
* Verbs provider notes
* Fix an issue where if the user requests higher values for tx, rx
context sizes than default it wasn't honored.
* Introduce env variables for setting default tx, rx context sizes and iov limits.
* Report correct completion ordering supported by MSG endpoints.
* Fix rpmbuild warnings
OBS-URL: https://build.opensuse.org/request/show/515855
OBS-URL: https://build.opensuse.org/package/show/science:HPC/libfabric?expand=0&rev=16
