diff --git a/_service b/_service
index 3ae0afa..f9793e1 100644
--- a/_service
+++ b/_service
@@ -8,7 +8,7 @@
@PARENT_TAG@.@TAG_OFFSET@.%h
v(.*)
\1
- e43589a5113ad3db0a18a6a1a02b6e6f4ee317d6
+ f67fad269327a1a25731d89fb94548d89ae7ae63
libfabric*.tar
diff --git a/fabtests.changes b/fabtests.changes
deleted file mode 100644
index c79b424..0000000
--- a/fabtests.changes
+++ /dev/null
@@ -1,2058 +0,0 @@
--------------------------------------------------------------------
-Mon Mar 25 07:45:03 UTC 2024 - Nicolas Morey
-
-- Update to 1.20.1
- - Core
- - hmem/ze: Change the library name passed to dlopen
- - hmem/ze: map device id to physical device
- - hmem/ze: skip duplicate initialization
- - hmem/ze: dynamically allocate device resources based on number of devices
- - hmem/ze: fix hmem_ze_copy_engine variable look up
- - hmem/ze: Increase ZE_MAX_DEVICES to 32
- - man: Fix typo in fi_getinfo man page
- - Fix compiler warning when compiling with ICX
- - man: Fix fi_rxm.7 and fi_collective.3 man pages
- - man: Update EFA docs for FI_EFA_INTER_MIN_READ_WRITE_SIZE
- - EFA
- - efa_rdm_ep_record_tx_op_submitted() rm peer lookup
- - Remove peer lookup from efa_rdm_pke_sendv()
- - Make handshake response use txe
- - test: Only close SHM if SHM peer is Created
- - Handshake code allocs txe via efa util
- - Initialize txe.rma_iov_count to 0
- - Switch fi_addr to efa_rdm_peer in trigger_handshake
- - Downgrade EFA Endpoint Creation WARN to INFO
- - Init srx_ctx before use
- - Clean up generic_send path
- - Pass in efa_rdm_ep to efa_rdm_msg_generic_recv()
- - Make recv path slightly more efficient
- - re-org rma write to avoid duplicate checks
- - Add missing sync_memops call to writedata
- - use peer pointer from txe in read, write and send
- - Pass in peer pointer to txe
- - Get rid of noop instruction from empty #define
- - Remove noop memset
- - Fix the ibv cq error handling.
- - Don't do handshake for local read
- - Fix a typo in configure.m4
- - Make runt_size aligned
- - OPX
- - Initialize cq error data size
- - RXM
- - Fix data error with FI_OFI_RXM_USE_RNDV_WRITE=1
- - SHM
- - Fix coverity issue about resource leak
- - Adjust the order of smr_region fields.
- - Allocate peer device fds dynamically
- - Util
- - Fix coverity issue about missing lock
- - Implement timeout in util_wait_yield_run()
- - Fix bug in util_cq startup error case
- - util_mem_hooks: add missing parantheses
- - Verbs
- - Windows: Resolve regression in user data retrieval
- - Fabtests
- - efa: Close ibv device after use
- - efa: Get device MR limit from ibv_query_device
- - efa: Add simple unexpected test to MR exhaustion test
- - pytest: add a new ssh connection error pattern
-
--------------------------------------------------------------------
-Thu Feb 29 16:18:32 UTC 2024 - pgajdos@suse.com
-
-- Use %autosetup macro. Allows to eliminate the usage of deprecated
- %patchN
-
--------------------------------------------------------------------
-Sun Nov 19 17:27:58 UTC 2023 - Nicolas Morey
-
-- Update to 1.20.0 (jsc#PED-5777, jsc#PED-5893, jsc#PED-5889)
- - Core
- - General bug fixes and code clean-up
- - configure.ac: add extra check for 128 bit atomic support
- - hmem/synapseai: Refine the error handling and warning
- - Introduce FI_ENOMR
- - hmem/cuda: fix a bug when calculating aligned size.
- - Handle dmabuf for ofi_mr_cache* functions.
- - Handle dmabuf flag in ofi_mr_attr_update
- - Handle dmabuf for mr_map insert.
- - man: Fix the description of virtual address when FI_MR_DMABUF is set
- - man: Clarify the defition of FI_OPT_MIN_MULTI_RECV
- - hmem/cuda: Add dmabuf fd ops functions
- - include/ofi_atomic_queue: Properly align atomic values
- - Define fi_av_set_user_id
- - Support multiple auth keys per EP
- - Simplify restricted-dl feature
- - hmem: Only initalize synapseai if device exists
- - Add "--enable-profile" option
- - windows: Updated config.h
- - Add environment variable for selective HMEM initialization
- - Add restricted dlopen flag to configure options
- - hmem: generalize the use of OFI_HMEM_DATA to non-cuda iface
- - hmem: fail cuda_dev_register if gdrcopy is not enabled
- - Add 1.7 ABI compat
- - Define fi_domain_attr::max_ep_auth_key
- - hmem: Add new op to hmem_ops for getting dmabuf fd
- - hmem/cuda: Update cuda_gdrcopy_dev_register's signature
- - mr_cache: Define ofi_mr_info::flags
- - Add ABI compat for fi_cq_err_entry::src_addr
- - Define fi_cq_err_entry::src_addr
- - Add base_addr to fi_mr_dmabuf
- - hmem: Set FI_HMEM_HOST_ALLOC for ze addr valid
- - hmem: Support dev reg with FI_HMEM_ZE
- - tostr: Added fi_tostr() for data type struct fi_cq_err_entry.
- - hmem_ze: fix incorrect device id in copy function
- - Introduce new profiling interface for low-level statistics
- - hmem: Support dev reg with FI_HMEM_CUDA
- - hmem: Support dev reg with FI_HMEM_ROCR
- - hmem: Support dev reg with FI_HMEM_SYSTEM
- - hmem: Define optimized HMEM memcpy APIs
- - Implement memhooks atfork child handler
- - hmem: Support ofi_hmem_get_base_addr with sys mem
- - hmem: Add length field to ofi_hmem_get_base_addr
- - mr_cache: Improve cache hit rate
- - mr_cache: Purge dead regions in find
- - mr_cache: Update find to remove invalid MR entries
- - mr_cache: Update find with MM valid check
- - Add direct support for dma-buf memory registration
- - man/fi_tagged: Remove the peek for data ability
- - indexer: Add byte idx abstraction
- - Add missing FI_REMOTE_CQ_DATA for fi_inject_writedata
- - Add configure flags for more sanitizers
- - Fix fi_peer man page inconsistency
- - include/fi_peer: Add cq_data to rx_entry, allow peer to modify on unexp
- - Add XPMEM support
- - EFA
- - General bug fix and code clean-up
- - Do not abort on all deprecated env vars
- - Onboard fi_mr_dmabuf API in mem reg ops.
- - Try registering cuda memory via dmabuf when checking p2p
- - Introduce HAVE_EFA_DMABUF_MR macro in configure
- - Add read nack protocol docs
- - Receiver send NACK if runt read fails with ENOMR
- - Sender switch to long CTS protocol if runt read fails with ENOMR
- - Receiver send NACK if long read fails with ENOMR
- - Update efa_rdm_rxe_map_remove to accept msg_id and addr
- - Sender switch to long CTS protocol if long read fails with ENOMR
- - Introduce new READ_NACK feature
- - Use SHM's full inject size
- - Add testing for small messages without inject
- - Enable inject rdma write
- - Use bounce buffer for 0 byte writes
- - Onboard ofi_hmem_dev_register API
- - Update cuda_gdrcopy_dev_register's signature
- - Allocate pke_vec, recv_wr_vec, sge_vec from heap
- - Close shm resource when it is disabled in ep
- - Disable RUNTING for Neuron
- - Move cuda-sync-memops from MR to EP
- - Do not insert shm av inside efa progress engine
- - Enable shm when FI_HMEM and FI_ATOMIC are requested
- - Adjust posted receive size to pkt_size
- - Do not create SHM peer when SHM is disabled
- - Use correct threading model for shm
- - Restrict RDMA read to compatible EFA devices
- - Add EFA device version to handshake
- - Add missing locks in efa_cntr_wait.
- - Add writedata RNR fabtest
- - Handle RNRs from RDMA writedata
- - Check opt_len in efa_rdm_ep_getopt
- - Use correct tx/rx op_flags for shm
- - Hooks
- - dmabuf: Initialize fd to supress compiler warning
- - trace: Add log on FI_VAR_UNEXP_MSG_CNT when enabled.
- - trace: Fixed trace log format on some attributes.
- - OPX
- - Fix compiler warnings
- - PSM3
- - Fix compiler warnings
- - Update provider to sync with IEFS 11.5.1.1.1
- - RXM
- - Remove unused function
- - Use gdrcopy in rma when emulating injection
- - Use gdrcopy in eager send/recv
- - Add hmem gdrcopy functions
- - Remove unused dynamic rbuf support
- - SHM
- - General bug fixes and cleanup
- - Add ofi_buf_alloc error handling
- - Only copy header + msg on unexpected path
- - Add FI_HMEM atomic support
- - Add memory barrier before updating resp for atomic
- - Add more error output
- - Reduce atomic locking with ofi_mr_map_verify
- - Only increment tx cntr when inject rma succeeded.
- - Use peer cntr inc ops in smr_progress_cmd
- - Allow for inject protocol to buffer more unexpected messages
- - Change pending fs to bufpool to allow it to grow
- - Add unexpected SAR buffering
- - Use generic acronym for shm cap
- - Move CMA to use the p2p infrastructure
- - Add p2p abstraction
- - Load DSA dependency dynamically
- - Replace tx_lock with ep_lock
- - Calculate comp vars when writing completion
- - Move progress_sar above progress_cmd
- - Rename SAR status enum to be more clear
- - Make SAR protocol handle 0 byte transfer.
- - Move selection logic to smr_select_proto()
- - Sockets
- - Fix compiler warnings
- - Fix provider name and api version in returned fi_info struct
- - TCP
- - Add profiling interface support
- - Pass through rdm_ep flags to msg eps
- - Derive cq flags from op and msg flags
- - Do not progress ep that is disconnected
- - Set FI_MULTI_RECV for last completed RX slice
- - Return an error if invalid sequence number received
- - xnet_progress_rx() must only be called when connected
- - Reset ep->rx_avail to 0 after RX queue is flushed
- - Disable the EP if an error is detected for zero-copy
- - Add debug tracking of transfer entries
- - Negotiate support for rendezvous
- - Add rendezvous protocol option
- - Generalize xnet_send_ack
- - Flatten protocol header definitions
- - Remove unused dynamic rbuf support
- - Define tcp specific protocol ops
- - Remove unneeded and incorrect rx_entry init code
- - UCX
- - Add FI_HMEM support
- - Initialize ep_flush to 1
- - Util
- - General bug fixes
- - memhooks: Fix a bug when calculating mprotect region
- - Check the return value of ofi_genlock_init()
- - Update checks for FI_AV_AUTH_KEY
- - Define domain primary and secondary caps
- - Add profiling util functions
- - Update util_cq to support err_data
- - Update ofi_cq_readerr to use new memcpy
- - Update ofi_cq_err_memcpy to handle err_data
- - Zero util cancel err entry
- - Move FI_REMOTE/LOCAL_COMM to secondary caps
- - Alter domain max_ep_auth_key
- - Add domain checks for max_ep_auth_key
- - Revert util_cntr->ep_list_lock to ofi_mutex
- - Add NIC FID functions to ofi.h
- - Add EP and domain auth key checking
- - Add bounds checks to ibuf get
- - Define dlist_first_entry_or_null
- - Update util_getinfo to dup auth_key
- - Revert util_av, util_cq and util_cntr to mutex
- - Add missing calls to (de)initialize monitor's mutexes
- - Avoid attempting to cleanup an uninitialized MR cache
- - Rename ofi_mr_info fields
- - Add rv64g support to memory hooks
- - Verbs
- - Windows: Check error code from GetPrivateData
- - Add missing lock to protect SRX
- - Add synapseai dmabuf mr support
- - Bug fix for matching domain name with device name
- - Windows: Fetch rejected connection data
- - Add support for DMA-buf memory registration
- - Windows: Fix use-after-free in case of failure in fi_listen
- - Windows: Map ND request type to ibverbs opcode
- - Fix memory leak when creating EQ with unsupported wait object
- - Track ep state to prevent duplicate shutdown events
- - Fabtests
- - Update man page
- - pytests/efa: onboard dmabuf argument for test_mr
- - pytest: make do_dmabuf_reg_for_hmem an cmdline argument
- - Bump Libfabric API version.
- - mr_test: Add dmabuf support
- - Introduce ft_get_dmabuf_from_iov
- - unexpected_msg: Use ft_reg_mr to register memory
- - pytest: Allow registering mr with dmabuf
- - Add dmabuf support to ft_reg_mr
- - Add dmabuf ops for cuda.
- - Test max inject size
- - Add FI_HMEM support to fi_rdm_rma_event and fi_rdm tests
- - memcopy-xe: Fix data verification error for device buffer
- - dmabuf-rdma: Increase the number of NICs that can be tested
- - dmabuf-rdma: Remove redundant libze_ops definition
- - fi-mr-reg-xe: Skip native dmabuf reg test for system memory
- - Check if fi_info is returned correctly in case of FI_CONNREQ
- - cq_data: relax CQ data validation to cq_data_size
- - Add ZE host alloc function
- - Use common device host buffer for check_buf
- - hmem_ze: allocate one cq and cl on init
- - fi-mr-reg-xe: Add testing for dmabuf registration
- - scripts: use yaml safe_load
- - macos: Fix build error with clang
- - multinode: Use FI_DELIVERY_COMPLETE for 'barrier'
- - Handle partial read scenario for fi_xe_rdmabw test For cross node tests
- - pytest/efa: add cuda memory marker
- - pytest/efa: Skip some configuration for unexp msg test on neuron.
- - runfabtests.py: ignore error due to no tests are collected.
- - pytest/efa: extend unexpected msg test range
- - pytest/shm: extend unexpected msg test range
- - pytest: Allow running shm fabtests in parallel
- - unexpected_msg.c: Allow running the test with FI_DELIVERY_COMPLETE
- - runfabtests.sh: run fi_unexpected_msg with data validation
- - pytest/shm: Extend test_unexpected_message
- - unexpected_msg: Make tx/rx_size large enough
- - pytest/shm: Extend shm's rma bw test
- - Update shm.exclude
-
--------------------------------------------------------------------
-Mon Sep 4 07:47:59 UTC 2023 - Nicolas Morey
-
-- Update to 1.19.0
- - Core
- - General code cleanup and restructuring
- - Add ofi_hmem_any_ipc_enabled()
- - ofi_consume_iov allows 0-byte consume
- - ofi_consume_iov consistency
- - ofi_indexer: return error code when iterating
- - getinfo: Add post filters for domain and fabric names
- - Filter loopback device if iface is specified
- - bsock: Fix error checking for -EAGAIN
- - windows/osd: Remove unneeded check to silence coverity
- - windows/osd: Move variable declaration to silence coverity
- - Introduce gdrcopy awareness to hmem copy
- - mr/cache: Fix fi_mr_info initialization
- - hmem_cuda: remove gdrcopy from cuda hmem copy path
- - iouring: Fix wrong indent in ofi_sockapi_accept_uring()
- - Implement ofi_sockctx_uring_poll_add()
- - hmem: introduce gdrcopy from/to cuda iov functions
- - hmem: Deprecate `FI_HMEM_CUDA_ENABLE_XFER`
- - hmem_cuda: Restrict CUDA IPC based on peer accessibility
- - hmem_cuda: Log number of CUDA devices detected
- - hmem_cuda: Refactor global variables
- - tostr: Remove the extra dir "shared/" from "include/" and "src/" .
- - hmem_ze: fix ZE is valid check
- - hmem_rocr: fix offset calculation
- - hmem_rocr: use ofi spinlock functions
- - hmem_rocr: minor fixes
- - hmem_neuron: convert warn to info for nrt_get_dmabuf_fd not found
- - hmem_neuron: check existance of neuron devices during initialization
- - tostr: Moved Windows functions in shared/ofi_str.c to windows/osd.h
- - tostr: Add helper functions ofi_tostr_size() and ofi_tostr_count().
- - EFA
- - Onboard Peer API, use shm provider as a peer provider
- - Uses util SRX framework in shared receive procedures.
- - Register shm MR with hmem_data, allow shm to use gdrcopy for cuda data movement
- - Finish the refactor for rxr squash.
- - Use rdma-core WR API for send requests
- - Check optlen in getopt call
- - Fix the rdma-read support check in RMA and MSG operations
- - Optimize ep lock usage
- - Use an internal fi_mr_attr for memory registration
- - Hooks
- - Init field in mr_attr to silence coverity
- - Add profiling hook provider
- - Rename cq hooking functions' names
- - Added trace for resource creation operations
- - OPX
- - Initialize ofi_mr_info
- - Fix dput credit check
- - Only allocate replay buffer if psn is valid
- - Support SHM Intra-node communication between single server HFI devices
- - Fix incorrect packet size in packet header when sending CTS packet
- - Added check to address Coverity scan defect
- - Add multi-entry caching to TID rendezvous
- - Fall back to default domain name for TID fabric
- - Properly handle multiple IOVs in fi_opx_tsendmsg
- - Fix OPX Rzv RTS receive operation SHM error (DAOS-related)
- - Fix non-tagged sends may incorrectly set FI_TAGGED in send completions
- - Add more info to reliability IOV buffer validation check
- - Move dput packet build functions to new inline include
- - Use fi_mr_attr in fi_opx_mr
- - Disable Pre-NAKing by default, throttle until all outstanding replays ACK'd
- - Fix reliability bug when NAKing the last PSN
- - Update HeaderQ Register more frequently
- - No rbuf_wrap needed for expected receive (TID)
- - Fixes for Coverity scan issues
- - Enhanced tag matching
- - Tune expected recv for unaligned buffers
- - Observability: Add finer logging granularity
- - Reduce RTS immediate data and fix packet estimate for odd TID lengths
- - Add additional sources for FI_OPX_UUID
- - Peer
- - Add cq_data to rx_entry, allow peer to modify on unexp
- - Introduce peer cntr API
- - Add foreach_unspec_addr API
- - Add size as an input of the get_tag
- - PSM3
- - Sync with IEFS 11.5.0.0.172
- - SHM
- - Only poll IPC list when ROCR IPC is enabled
- - Allow for SAR and inject protocol to buffer more unexpected messages
- - Remove unused sar fields
- - Make SAR protocol handle 0 byte transfer
- - Load DSA dependency dynamically
- - Change recv entry freestack into bufpool
- - Remove shm signal
- - Use util peer cntr implementation
- - Make SHM default to domain level threading level
- - Replace internal shared receive implementation with util_srx
- - Lock entire progress loop
- - Fix ROCR data coherency
- - Add FI_LOCAL_COMM to shm attrs
- - Handle empty freestack
- - Fix bug in configure.m4 in atomics_happy assignment happy
- - Add memory barrier before update resp->status for SAR
- - Do not use inline/inject for read op
- - Allow shm to use gdrcopy
- - Refactor protocol selection code
- - Init map fi addrs to FI_ADDR_NOTAVAIL
- - TCP
- - General code cleanups
- - Restrict which EPs can be opened per domain
- - Increase CM error debug output
- - Avoid calling close() on an invalid socket after accept error
- - Mark the EP as disconnected before flushing the queues
- - Add assertion failures for xnet_{monitor,halt}_sock
- - Disable ofi_dynpoll_wait() for non-blocking progress
- - Move PEP pollin operations to io_uring
- - Move EP poll operations to io_uring
- - Early exit if ofi_bsock_flush() has operation in progress
- - Implement pollin sockctx in bsock
- - Add missing call to xnet_submit_uring()
- - Add return error to xnet_update_pollflag()
- - Remove the cancel sockctx from the EP structure
- - Move io_uring cqe from the stack to progress struct
- - Reduce stack size for epoll event array
- - handle NULL av in xnet_freeall_conns()
- - UCX
- - Publish FI_LOCAL_COMM and FI_REMOTE_COMM capabilities
- - Fix configure error with newer MOFED
- - Fix segfault in unsignalled completions
- - Util
- - Add FI_PEER support to util counter
- - Refactor the usage of cntrs
- - Change util_ep to be a genlock
- - Add util shared receive implementation
- - Update log message for invalid AV type message
- - Fix fi_mr_info initialization
- - Add peer ID to MR cache
- - Store hmem_data in ofi_mr_map
- - Split the cq progress and reading entries in ofi_cq_readfrom
- - Verbs
- - Add event lock to EQ to serialize closing ep
- - Remove saved_wc_list and use CQ directly
- - Consolidate peer_mem and dmabuf support check
- - Fix vrb_add_credits signature
- - Introduce new progress engine structure
- - Simplify (and correct) locking around progress operations
- - General code restructuring
- - Fabtests
- - Fix reading addressing options
- - Allow to change only the OOB address
- - Allow to use FI_ADDR_STR with -F
- - Fix bw buffer utilization
- - Separate RX and RMA counters
- - Fix tx counter with RMA
- - Add FI_CONTEXT mode to rdm_cntr_pingpong
- - Add HMEM support to fi_unexpected_msg test
- - Fix array OOB during fabtest list parsing
- - Enable shm tagged_peek test
- - Fix windows build warnings
- - Make tx_buf and rx_buf aligned to 64 bytes by default
- - Fix windows build warnings for sscanf
- - Use dummy ft_pin_core on macOS
- - Fix some header includes
- - sock_test: Do not use epoll if not available
- - recv_cancel: initialize error entry
- - Fix wrong size used to allocate tx_msg_buf
- - unexpected: change defaults to support tcp
- - unexpected: add unknown unexpected peer test
- - Enable a list of arbitrary message sizes
- - Enabled data validation for rma read & write
- - bw_rma operates on distinct buffer offsets
- - ft_post_rma issues reads from remote's tx_buf
- - General code cleanup and restructuring
- - rdm_tagged_peek: fix race condition synchronization
- - Add FI_LOCAL_COMM/FI_REMOTE_COMM presence check to fi_getinfo_test
- - Correct ft_exchange_keys in prefix-mode
- - Make rdm_tagged_peek test more general
- - Add unit test for fi_setopt
-
--------------------------------------------------------------------
-Mon Aug 7 16:54:07 UTC 2023 - Nicolas Morey
-
-- Drop support for obsolete TrueScale (bsc#1212146)
-
--------------------------------------------------------------------
-Mon Jul 3 16:15:56 UTC 2023 - Nicolas Morey
-
-- Update to 1.18.1
- - Core
- - Fix build warning for ofi_dynpoll_get_fd
- - EFA
- - Handle 0-byte writes
- - Apply byte_in_order_128_byte for all memory type
- - Increase default shm_av_size to 256
- - Force handshake before selecting rtm for non-system ifaces.
- - Only select readbase_rtm when both sides support rdma-read
- - Bugfix for initializing SHM offload
- - Correct CPPFLAGS during configure
- - Make setopt support sendrecv aligned 128 bytes
- - Make data size to be 128 byte multiples for in-order aligned send/recv
- - prepare local read pkt entry for in-order aligned send/recv.
- - Disable gdrcopy and cudamemcpy for in-order aligned recv.
- - Increase the pad size in rxr_pkt_entry
- - Make readcopy pkt pool 128 byte aligned
- - Introduce alignment to support in order aligned ops
- - Fix a bug when calling ibv_query_qp_data_in_order
- - RMA operations will ensure FI_ATOMIC cap
- - RMA operations will ensure FI_RMA cap
- - Unittest atomics without FI_ATOMIC cap.
- - Unittest RMA without FI_RMA cap.
- - Refactor pkt_entry assignment in poll_ibv loop
- - Fixes for RDMA Write and Writedata
- - RXM
- - Revert rxm util peer CQ support
- - Fix credit size parameter for flow ctrl
- - SHM
- - Fix DSA enable
- - Assert read op and inject proto are mutually exclusive
- - Fix ROCR data coherency
- - Add FI_LOCAL_COMM to shm attrs
- - Signal peer when peer is out of resources
- - Handle empty freestack
- - Fix bug in configure.m4 in atomics_happy assignment happy
- - Add memory barrier before update resp->status for SAR
- - Fix resource leak reported by coverity
- - Switch cmd_ctx pool from freestack to bufpool
- - Add iface parameter to smr_select_proto
- - TCP
- - Fix spinning on fi_trywait()
- - Handle truncation of active message
- - Handle prefetched data after reporting ETRUNC error
- - Progress all ep's on unexp_msg_list when posting recv
- - Removed unused saved_msg::ep field to fix assert
- - Continue receiving after truncation error
- - Create function to allocate internal msg buffer
- - Add runtime setting for max saved message size
- - Increase default max_saved value
- - Dynamically allocate large saved Rx buffers
- - Separate the max inject and recv buf size
- - Remove 1-line xnet_cq_add_progress function
- - Changed default wait object to epoll
- - Handle case where epoll isn't natively supported
- - Hold domain lock while deregistering memory
- - Rename DL package from libnet to libtcp
- - UCX
- - Align the provider version with the libfabric version
- - Verbs
- - Delay device initialization to when fi_getinfo is called
- - Consolidate peer_mem and dmabuf support check
- - verbs_nd: Init len to 0 for WCSGetProviderPath call
- - verbs_nd: Verify CQs are valid in rdma_create_qp
- - verbs_nd: Initialize ibv_wc fields
- - verbs_nd: Release lock in network direct error paths
- - Fix vrb_add_credits signature
- - Fix credit size parameter for flow ctrl
- - Recover RXM connection from verbs QP in error state
- - Fabtests
- - Add ze-dlopen functions to component tests
- - Call cudaSetDevice() for selected device
- - pytest/efa: Adjust get_efa_devices()
- - pytest/common: Support parallel neuron test
- - pytest/common: Use different cuda device for parallel cuda set
- - efa: Test_flood_peer.py increase timeout
- - pytest/efa: Test to flood peer during startup
- - fi-rdmabw-xe: Add option to set maximum message size
- - fi-rdmabw-xe: Add option to set batch size
-
--------------------------------------------------------------------
-Thu May 4 13:27:21 UTC 2023 - Frederic Crozat
-
-- Add _multibuild to define additional spec files as additional
- flavors.
- Eliminates the need for source package links in OBS.
-
--------------------------------------------------------------------
-Tue Apr 18 17:25:02 UTC 2023 - Nicolas Morey
-
-- Update to 1.18.0
- - Core
- - rocr: fix offset calculation
- - rocr: use ofi spinlock functions
- - rocr: minor fixes
- - neuron: convert warn to info for nrt_get_dmabuf_fd not found
- - neuron: check existance of neuron devices during initialization
- - neuron: Add support for neuron dma-buf
- - ze: update ZE to support new driver index specification
- - List variables read from config file
- - Add switch to prefer system-config over environment
- - Add basic system-config support for setting library variables
- - Move peer provider defines into new header
- - rocr: Support asynchronous memory copies
- - rocr: Add support for ROCR IPC
- - rocr: rename rocr data-structures
- - synpaseai: return 0 for host_register and host_deregister
- - fabric: Improve log level of provider mismatch
- - cuda: Allow CUDA IPC when P2P disabled
- - ze: add ZE command list pool to reuse command lists
- - cuda: implement cuda_get_xfer_setting for non cuda build
- - cuda: adjust FI_HMEM_CUDA_ENABLE_XFER behavior
- - cuda.c: Add const to param to remove warning
- - Add IFF_RUNNING check to indicate iface is up and running
- - io_uring support enhancements
- - EFA
- - Implement CUDA support on instance types that do not support GPUDirect RDMA
- - Implement fi_write using device's RDMA write capability
- - Enrich error messages with debug and connection info
- - Implement support for FI_OPT_EFA_USE_DEVICE_RDMA in fi_setopt
- - Implement support for FI_OPT_CUDA_API_PERMITTED in fi_setopt
- - Add support for neuron dma-buf
- - Use gdrcopy to improve the intra-node CUDA communication performance for small messages
- - Use shm provider's FI_AV_USER_ID support
- - Fix bugs in efa provider’s shm info initialization procedure
- - Hooks
- - dmabuf_peer_mem: Handle IPC handle caching in L0
- - trace: Add trace log for CM operation APIs
- - trace: Change tag in trace log to hex format
- - trace: Enhance trace log for data transfer API calls
- - trace: Add trace log for API fi_cq_readerr()
- - trace: Add trace log for CQ operation APIs
- - Add tracing hook provider
- - Net
- - Net provider optimizations have been integrated into the tcp provider.
- - Net provider has been removed as a reported provider.
- - OPX
- - Fixes for Coverity scan issues
- - Enhanced tag matching
- - Tune expected recv for unaligned buffers
- - Add finer logging granularity
- - Reduce RTS immediate data and fix packet estimate for odd TID lengths
- - Add additional sources for FI_OPX_UUID
- - Exclude opx from build if missing needed defines
- - Move some logs to optimized builds
- - Fix build warnings for unused return code from posix_memalign
- - Add reliability sanity check to detect when send buffer is illegally altered
- - SDMA Completion workaround for driver cache invalidation race condition
- - Fix replay payload pointer increment
- - Handle completion counter across multiple writes in SDMA
- - Cleanup pointers after free()
- - Modify domain creation to handle soft cache errors
- - Two biband performance improvements
- - Fixes based on Coverity Scan related to auto progress patch
- - Changed poll many argument to rx_caps instead of caps
- - Resync with server configured for Multi-Engines (DAOS CART Self Tests)
- - Remove import_monitor as ENOSYS case
- - Address memory leaks reported on OFIWG issues page
- - General code cleanup
- - Add replays over SDMA
- - Implement basic TID Cache
- - Revert work_pending check change
- - Fix use_immediate_blocks
- - Restore state after replay packet is NULL
- - Fix memory leak from early arrival packets
- - Fix segfault in SHM operations from uninitialized value in atomic path
- - Prevent SDMA work entries from being reused with outstanding replays
- - Set runtime as default for OPX_AV
- - Fix RTS replay immediate data
- - Fix errors caught by the upstream libfabric Coverity Scan
- - fi_getInfo - Support multiple HFI devices
- - Support OFI_PORT and Contiguous endpoint addresses for CART & Mercury
- - Add fi_opx_tid.h to Makefile.include
- - Fix progress checks and default domain
- - Revert is_intranode simplification.
- - Don't inline handle_ud_ping function
- - Allow atomic fetch ops to use SDMA for sufficiently large counts
- - Cleaned up FI_LOG_LEVEL=warn output
- - Cleaned up unused macros for FI_REMOTE_COMM and FI_LOCAL_COMM
- - Reset default progress to FI_PROGRESS_MANUAL
- - Fixed GCC 10 build error with Auto Progress
- - Add support for FI_PROGRESS_AUTO
- - Use max allowed packet size in SDMA path when expected TID is off
- - Expected receive (TID) rendezvous
- - RMA Read/Write operations over SDMA
- - Remove origin_rs from cts and dput packet header
- - Fix for hang in DAOS CART tests
- - Use single IOV for bounce buffer in SDMA requests.
- - Check for FI_MULTI_RECV with bitwise OR instead of AND
- - Fix for intermittent intra-node deadlock hang (DAOS CART tests)
- - Fix to RPC transport error failure (DAOS CART tests)
- - Fix for context->buf set to NULL
- - Fix bad asserts
- - Ensure atomicity of atomic ops
- - fi_opx_cq_poll_inline count and head check fix
- - Fix intermittent intra-node hang causing RPC timeouts (DAOS CART tests)
- - PSM3
- - Update provider to sync with IEFS 11.4.1.1.2
- - Fix warnings from build
- - Add oneapi ZE support to OFI configure
- - RXD
- - Ignore error path in av_close return
- - RXM
- - Handle NULL av in rxm_freeall_conns()
- - Implement the FI_OPT_CUDA_API_PERMITTED option
- - Write "len" field for remote write
- - Ignore error path domain_close return
- - Free coll_pool on ep close
- - Update rxm to use util_cq FI_PEER support functions
- - Fix incorrect CQ completion field
- - Rename srx to msg_srx
- - Disable FI_SOURCE if not requested
- - Memory leaks removed
- - Set offload_coll_mask based on actual configuration
- - Report on coll offload capabilities with OFI_OFFLOAD_PROV_ONLY
- - Fabric setups collective offload fabric
- - Create eq for collective offload provider
- - Close collective providers ep when rxm_ep is closed
- - Fix incorrect use of OFI_UNUSED()
- - Rework collective support to use collective provider(s)
- - SHM
- - Fix potential deadlock in smr_generic_rma()
- - smr_generic_rma() wwrite error completion with positive errno
- - Update SHM to use ROCR
- - Fix incorrect discard call when cleaning up unexpected queues
- - Separate smr_generic_msg into msg and tagged recv
- - Fix start_msg call
- - Implement the FI_OPT_CUDA_API_PERMITTED option
- - Assert not valid atomic op
- - Fix a bug in smr_av_insert
- - Optimize locking on the SAR path
- - Remove unneeded sar_cnt
- - Optimize locking
- - Enable multiple GPU/interface support
- - Remove HMEM specific calls from atomic path
- - Use util_cq FI_PEER support
- - Import shm as device host memory
- - Add HMEM flag to smr region
- - Fix user_id support
- - Write tx err comp to correct cq
- - Fix index when setting FI_ADDR_USER_ID
- - TCP
- - Provider source has been replaced by net provider source
- - Removed incorrect reporting of support for FI_ATOMIC
- - Do not save unmatched messages until we have the peer's fi_addr
- - Use internal flag for FI_CLAIM messages, versus a reserved tag bit
- - Fix updating error counter when discarding saved messages
- - Allow saved messages to be received after the underlying ep has been closed
- - Enhanced debug logging in connection path
- - Force CM progress on unconnected ep's when posting data transfers
- - Support connect and accept calls with io_uring
- - Fix segfault accessing an invalid fi_addr
- - Add io_uring support for CM message exchange
- - Move CM progress from fabric to EQ to improve multi-threaded performance
- - Fix small memory leak destroying an EQ
- - Fix race where same rx entry could be freed twice
- - Handle NULL av in rdm ep cleanup
- - Reduce stack use for epoll event array
- - UCX
- - New provider targeting Nvidia fabrics that layers over libucp
- - Util
- - Fix the behavior of cq_read for FI_PEER
- - rocr: Fix compilation issue
- - cuda: Use correct debug string calls
- - Free cq->peer_cq on close
- - Remove extra new line from av insert log
- - Check for count = 0 in ofi_ip_av_insert
- - rocr: Add support for ROCR IPC
- - Add FI_PEER support to util_cq
- - Disable FI_SOURCE if not requested
- - Remove FID events from the EQ when closing endpoint
- - Rework collective support to be a peer collective provider(s)
- - Allow FI_PEER to pass CQ, EQ and AV attr checking
- - Remove annoying WARNING message for FI_AFFINITY
- - Add utility collective provider
- - Verbs
- - Implement the FI_OPT_CUDA_API_PERMITTED option
- - Add support for ROCR IPC
- - Fabtests
- - Add fi_setopt_test unit test
- - Update ze device registration calls
- - fi-rdmabw-xe: Always use host buffer for synchronization
- - Fix bug in posting RMA operation
- - fi_cq_data: Extend test to fi_writedata
- - fi_cq_data: Extend validation of completion data
- - Rename fi_msg_inject tests to fi_inject_test to reflect its use
- - fi_rdm_stress: Add count option to json key/pair options
- - Add and fix OOB option handling in several tests
- - fi_eq_test: Fix incorrect return value
- - fi_rdm_multi_client: Increase the size of ep name buffer
- - Add FI_MR_RAW to default mr_mode
- - Support larger control messages needed by newer providers
- - fi-rdmabw-xe: Update to work with the ucx provider
- - fi_ubertest: Cleanup allocations in failure cases
- - Change ft_reg_mr to not assume hmem iface & device
- - fi_multinode: Bugfix multinode test for ze + verbs
- - fi_multinode: Remove unused validation print
- - fi_multinode: Skip tests for unsupported collective operations
- - fi_ubertest: Fix data validation with device memory
- - fi_peek_tagged: Restructure and expand test
-
--------------------------------------------------------------------
-Mon Mar 20 09:03:29 UTC 2023 - Nicolas Morey
-
-- Update to 1.17.1
- - Core
- - hmem_cuda Add const to param to remove warning
- - Fix typos in fi_ext.h
- - ofi_epoll: Remove unused hot_index struct member
- - EFA
- - Print local/peer addresses for RX write errors
- - Unit test to verify no copy with shm for small host message
- - Avoid unnecessary copy when sending data from shm
- - Compare pci bus id in hints
- - Fix double free in rxr endpoint init
- - Hooks
- - dmabuf_peer_mem: Handle IPC handle caching in L0
- - OPX
- - Exclude from build if missing needed defines
- - Move some logs to optimized builds
- - Fix build warnings for unused return code from posix_memalign
- - Add reliability sanity check to detect when send buffer is illegally altered
- - SDMA Completion workaround for driver cache invalidation race condition
- - Fix replay payload pointer increment
- - Handle completion counter across multiple writes in SDMA
- - Cleanup pointers after free()
- - Modify domain creation to handle soft cache errors
- - Two biband performance improvements
- - Fixes based on Coverity Scan related to auto progress patch
- - Changed poll many argument to rx_caps instead of caps
- - Resynch with server configured for Multi-Engines (DAOS CART Self Tests)
- - Remove import_monitor as ENOSYS case
- - Address memory leaks reported on OFIWG issues page
- - Remove unused fields
- - Fix unwanted print statement case
- - Add replays over SDMA
- - Implement basic TID Cache
- - Revert work_pending check change
- - Fix use_immediate_blocks
- - Restore state after replay packet is NULL
- - Fix memory leak from early arrival packets.
- - Fix segfault in SHM operations from uninitialized value in atomic path.
- - Prevent SDMA work entries from being reused with outstanding
- replays pointing to bounce buf.
- - Set runtime as default for OPX_AV
- - Fix RTS replay immediate data
- - Fix errors caught by the upstream libfabric Coverity Scan
- - Support multiple HFI devices
- - Support OFI_PORT and Contiguous endpoint addresses
- - Update man pages
- - Util
- - util_cq: Remove annoying WARNING message for FI_AFFINITY
-
--------------------------------------------------------------------
-Mon Dec 19 08:39:57 UTC 2022 - Nicolas Morey
-
-- Update to 1.17.0
- - Core
- - Add IFF_RUNNING check to indicate iface is up and running
- - General code cleanups
- - Add abstraction for common io_uring operations
- - Support ROCR get_base_addr
- - Add a 'flags' parameter to fi_barrier()
- - Introduce new calls for opening domain and endpoint with flags
- - Add ability to re-sort the fi_info list
- - Allowing layering of rxm over net provider
- - General cleanup of provider filtering functions
- - Add io_uring operations to be used by sockapi
- - Modify internal handling of async socket operations
- - Sockets operations are moved to a common sockapi abstraction
- - Add support for Ze host register/unregister
- - Add new offload provider type
- - Rename fi_prov_context and simplify its use
- - Convert interface prefix string checks to exact checks
- - EFA
- - Code cleanups and various bug fixes
- - Improved debug logging and warnings and assertions
- - Do not ignore hints->domain_attr->name
- - Fix the calculation of REQ header size for a packet entry
- - Fix default value for host memory's max_medium_msg_size
- - Add tracepoints to send/recv/read ops
- - Simplified emulated read protocol
- - Set use_device_rdma according to efa device id
- - Fix shm initialization path on error
- - Fix Implementation of FI_EFA_INTER_MIN_READ_MESSAGE_SIZE
- - Do not enable rdma_read if rxr_env.use_device_rdma is false
- - Remove de-allocated CUDA memory region during registration
- - Fix the error handling path of efa_mr_reg_impl()
- - Fix rxr_ep unit tests involving ibv_cq_ex
- - Add check of rdma-read capability for synapseai
- - Report correct default for runt_size parameter
- - Toggle cuda sync memops via environment variable.
- - Net
- - Continued fork of tcp provider, will eventually merge changes back
- - Fix inject support
- - Fix memory leak in peek/claim path
- - General code cleanups and bug fixes from initial fork
- - Allow looking ahead in tcp stream to handle out-of-order messages
- - Add message tracing ability
- - Fetch correct ep when posting to a loopback connection
- - Release lock in case of error in rdm_close
- - Fix error path in xnet_enable_rdm
- - Add missing progress lock in srx cleanup
- - Code restructuring and enhancements with longer term goal of supporting io_uring
- - Disable the progress thread in most situations
- - Rename DL from libxnet-fi to libnet-fi
- - Add missing initialization calls for DL provider
- - Add support for FI_PEEK, FI_CLAIM, and FI_DISCARD
- - Include source address with CQ entry
- - Fix support for FI_MULTI_RECV
- - OPX
- - Bug fixes and general code cleanup
- - Fix progress checks and default domain
- - Allow atomic fetch ops to use SDMA for sufficiently large counts
- - Cleaned up FI_LOG_LEVEL=warn output
- - Reset default progress to FI_PROGRESS_MANUAL
- - Fixed GCC 10 build error with Auto Progress
- - Add support for FI_PROGRESS_AUTO
- - Use max allowed packet size in SDMA path when expected TID is turned off
- - Expected receive (TID) rendezvous
- - RMA Read/Write operations over SDMA
- - Remove origin_rs from cts and dput packet header.
- - Fix for hang - unable to match inbound packets with receive
- context->src_addr (DAOS CART tests)
- - Use single IOV for bounce buffer in SDMA requests.
- - Check for FI_MULTI_RECV with bitwise OR instead of AND
- - Fix for intermittent intra-node deadlock hang (DAOS CART tests)
- - Fix to RPC transport error failure (DAOS CART tests)
- - Fix for context->buf set to NULL
- - Fix bad asserts
- - Ensure atomicity of atomic ops
- - fi_opx_cq_poll_inline count and head check fix
- - Fix intermittent intra-node hang causing RPC timeouts (DAOS CART tests)
- - Temporarily reduce SDMA queue ring size for possible driver bug workaround
- - Fix alignment issue and asserts
- - Enable more parallel SDMA operations
- - PSM3
- - Synced to IEFS 11.4.0.0.198
- - Tech Preview Ubuntu 22.04 Support
- - Tech Preview Intel DSA Support
- - Improved Intel GPU Support
- - Various performance improvements
- - Various bug fixes
- - RxM
- - Always use rendezvous protocol for ZE device memory send
- - Code cleanup
- - Add option to free resources on AV removal
- - SHM
- - Fix user_id support
- - Write tx err comp to correct cq
- - Fix index when setting FI_ADDR_USER_ID
- - Remove extraneous ofi_cirque_next() call
- - Add support for FI_AV_USER_ID
- - Fix multi_recv messaging
- - General code restructuring for maintainability
- - Implement shared completion queues
- - Decouple error processing from cq completion path to avoid switch
- - Fix incorrect op passed into recv cancel operation
- - Enhanced SHM implementation with DSA offload
- - Use multiple SAR buffers per copy operation
- - Fix ZE IPC race condition on startup
- - TCP
- - Minor updates in preparation for io_uring support (via net provider)
- - Util
- - Add option to free resources on AV removal
- - Add 'flags' parameter to new fi_barrier2() call
- - Add debugging in ofi_mr_map_verify
- - Rename internal bitmask struct to include ofi prefix
- - Verbs
- - Add option to disable dmabuf support
- - FI_SOCKADDR includes support of FI_SOCKADDR_IB
- - Fabtests
- - shared: Expand hmem support
- - fi_loopback: Add support for tagged messages
- - fi_mr_test: add support of hmem
- - fi_rdm_atomic: Fix hmem support
- - fi_rdm_tagged_peek: Read messages in order, code cleanup and fixes
- - fi_multinode: Add performance and runtime control options, cleanups
- - benchmarks: Add data verification to some bw tests
- - fi_multi_recv: Fix possible crash in cleanup
-- Drop prov-net-fix-error-path-in-xnet_enable_rdm.patch which was merged upstream.
-
--------------------------------------------------------------------
-Tue Nov 8 11:46:56 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Add prov-net-fix-error-path-in-xnet_enable_rdm.patch to fix a deadlock
- when no network interfaces are available (bsc#1205139)
-
--------------------------------------------------------------------
-Mon Oct 10 06:47:42 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Update to 1.16.1
- - Core
- - Fix windows implementation to remove fd from poll set
- - PSM3
- - Add missing files to release tarball
- - Util
- - Handle NULL address insertion to fi_av_insert
-- Drop prov-rxm-Disable-128-bit-atomics.patch which was merged upstream
-
--------------------------------------------------------------------
-Thu Oct 6 16:06:29 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Add prov-rxm-Disable-128-bit-atomics.patch to fix a potential
- segfault on misaligned buffers.
-
--------------------------------------------------------------------
-Fri Sep 30 11:44:45 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Update to 1.16.0 (jsc#PED-351, jsc#PED-190)
- - Core
- - Added HMEM IPC cache
- - Use exact string comparison checks for network interfaces
- - Restructuring of poll/epoll abstraction
- - Add ability to disable locks completely in debug builds
- - Serialize access to modifying the logging calls
- - Minor fixes to fi_tostr text formatting
- - Add hmem interface checks to memory registration
- - EFA
- - Added support of Synapse AI memory.
- - Improved error message
- - Net
- - Temporarily forked, optimized version of tcp provider
- - Focused on improved performance and scalability over tcp sockets
- - Fork ensures tcp provider stability while net provider is developed
- - Shares the tcp provider protocol and base implementation for msg endpoints
- - Integrates direct support for rdm endpoints, using a derivative from rxm
- - Implements own protocol for rdm endpoints, separate from rxm;tcp
- - OPX
- - Added initial support for SDMA
- - General performance enhancements
- - Performance improvements to reliability protocol
- - Improved deferred work pending complete
- - Added support for OPX_AV=runtime
- - Support iov memory registration ops
- - Added DAOS RPC support
- - Atomic ops enhancements
- - Improved documentation
- - Debug build enhancements
- - Fixed compiler warnings
- - Reduced time to compile prov/opx code
- - General bug fixes
- - Fixed PSN wrapping scaling
- - Added intranode fence
- - Addressed bugs discovered by coverity scan
- - PSM2
- - Fix sending CQ data in some instances of fi_tsendmsg
- - PSM3
- - Updated to match Intel Ethernet Fabric Suite (IEFS) 11.3 release
- - RxM
- - Update to read multiple completions at once from msg provider
- - Move RxM AV implementation to util code to share with net provider
- - Minor code cleanups
- - SHM
- - Implement and use ipc_cache
- - Add log messages for debugging and error tracking
- - Fix check for FI_MR_HMEM mr_mode
- - Move shm signal handlers initialization to EP
- - Added log messages for errors detected
- - TCP
- - Fix incorrect signaling of the CQ
- - Increase max number of poll events to retrieve
- - Acquire ep lock prior to flushing socket in shutdown
- - Verify ep state prior to progressing socket data
- - Read cm error data when receiving connreq response
- - Log error on connect failure
- - Fix assertion failure in CQ progress function
- - Util
- - Fix text in log of UFFD ioctl failure
- - Introduce cuda ipc monitor
- - Fix CQ memory leak handling overflow
- - Fix MR mode bit check for ver 1.5 and greater
- - Add max_array_size to track/check array overflow
- - Always progress transfers when reading from a CQ
- - Handle NULL address insertion
- - Try IPv4 before IPv6 addresses when starting name server
- - Fix IP util av default address length
- - Fix util IP getinfo path to read hints->addr_format
- - Fix debug print mismatch
- - Fix return code when memory allocation fails.
- - Fix build sign warning in ofi_bufpool_region_alloc
- - Minor code cleanups
- - Print warning if an addr is inserted into an AV again
- - Verbs
- - Fix support of FI_SOCKADDR_IB when requested by the application
- - Ensure all posted receives are flushed to the application
- - Update ofi_mr_cache_search API for hmem IPC support
- - Reduce logging verbosity for "no active ports"
- - Fix incorrect length used in memory registration
- - Various minor bug fixes for test failures
- - Fix a memory leak getting IB address
- - Implement verbs provider on Windows over NetworkDirect API
- - Set and check address format correctly
- - Only close qp if it was initialized
- - Portable detection of loopback device
- - Fabtests
- - multi_ep: Separate EP resources and fix MR registration
- - multi_recv: Fix possible crash and check for valid buffer
- - unexpected_msg: Fix printf compiler warning
- - dgram_pingpong.c: Use out-of-band sync
- - multinode: Make multinode tests platform agnostic, fix formatting
- - ubertest: Fix string comparison to include length, fix writedata completion check
- - av_test: add support for -e
- - New tests:
- - dmabuf-rdma: Component level test for dma-buf RDMA
- - sock_test: Component level performance test of poll, epoll, and select
- - rdm_stress: Multi-threaded, multi-process stress test for RDM endpoints
- - sighandler_test: Regression test for signal handler restoration
-- Drop patches fixed upstream:
- - prov-opx-Correctly-disable-OPX-if-unsupported.patch
- - disable-flatten-attr.patch
-
--------------------------------------------------------------------
-Mon Aug 1 20:01:18 UTC 2022 - Martin Liška
-
-- Add disable-flatten-attr.patch that drops flatten attribute.
- Note the flatten attribute results in huge compile time hog
- in inliner (same the binary size would be huge).
-- Use %make_build and enable LTO (boo#1133235).
-- Synchronize used Patches.
-
--------------------------------------------------------------------
-Thu Jun 23 10:36:09 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Update to 1.15.1
- - Core
- - Fix fi_info indentation error in fi_tostr
- - hmem_ze: Add runtime option to choose specific copy engine
- - Cleanup of configure HMEM checks
- - Fixed stringop-truncation in ofi_ifaddr_get_speed
- - Add utility provider log suffix to make logs easier to read
- - Fix truncation of ipv6 addressing
- - hmem: add support for AWS Trainium devices
- - Fix potential sscanf overflows
- - hmem: pass through device and flags when querying memory interface
- - Rework locking in several areas to convert spinlocks to mutexes
- - Add new locking abstractions to select lock types at runtime
- - Add new FI_PROTO_RXM_TCP for optimized rxm over tcp path
- - Fix windows implementation to remove fd from poll set
- - EFA
- - Added windows support through efawin (https://github.com/aws/efawin)
- - Added support of AWS neuron.
- - Added support of using gdrcopy to copy data from host to device.
- - Fixed a bug that cause 0 byte read to fail.
- - Fixed a memory corruption issue that can caused forked process to crash.
- - Extended testing coverage through new pytest based testing framework.
- - HOOKS
- - Add new hooking provider dmabuf_peer_mem
- - Enable DL build of hooking providers
- - Add HMEM memory registration hook
- - OPX
- - New provider supporting Cornelis Networks Omni-path hardware
- - PSM3
- - Updated psm3 to match IEFS 11.2.0.0 release
- - Added support for sockets (TCP/UDP) via a runtime selectable Hardware
- Abstraction Layer (HAL)
- - Added support for IPv6 addressing in RoCE and sockets
- - Added various NIC selection filtering options (wildcarded NIC name,
- address format, wildcarded IP subnet, link speed)
- - Performance tuning in conjunction with OneAPI and OneCCL
- - Improved PSM3_IDENTIFY output
- - Rename most internal symbols to psm3_
- - Corrected vulnerabilities found during Coverity scans
- - configure options refined and help text improved
- - PSM3_MULTI_EP has been deprecated (recommend always enabled, default
- is enabled [same default as previous releases])
- - Various bug fixes
- - RxM
- - Add check that atomic size is valid
- - Add support to passthru calls to tcp provider in specific
- - TCP
- - Add assert to verify RMA source/target msg sizes match
- - Wake-up threads blocked on CQ to update their poll events
- - Fix use of incorrect events in progress handler
- - Fixes for various compile warnings, mostly on Windows
- - Add support for FI_RMA_EVENT capability
- - Add support for completion counters
- - Fix check for CQ data in tagged messages
- - Add cancel support to shared rx context
- - Add src_addr receive buffer matching
- - Add provider control to assign a src_addr with an ep
- - Handle trecv with FI_PEEK flag
- - Allow binding a CQ with an SRX
- - Restructuring of code in source files
- - Handle EWOULDBLOCK returned by send call
- - Add hot (active) pollfd
- - SHM
- - Properly chain the original signal handlers
- - Avoid uninitialized variable with invalid atomic parameters
- - Fix 0 byte SAR read
- - Initialize len parameter to accept
- - Refactor and simplify protocol code
- - Remove broken support for 128-bit atomics
- - Fix FI_INJECT flag support
- - Add assert to verify RMA source/target msg sizes match
- - Set domain threading to thread safe
- - Fix possible use of uninitiated var in av_insert
- - Util
- - Fix sign warning in ofi_bufpool_region_alloc
- - Remove unused variable from ofi_bufpool_destroy
- - Fix check for valid datatype in ofi_atomic_valid
- - Return with error if util_coll_sched_copy fails
- - Fix use of uninitialized variable in ofi_ep_allreduce
- - Fix memory access in ip_av_insertsym
- - Track ep per collective operation not with multicast
- - Restructure collective av set creation/destruction
- - Change most locks from spin locks to mutexes
- - Allow selection of spinlocks for CQ and domain objects
- - Fix AV default addrlen
- - Update fi_getinfo checks to include hints->addr_
- - Handle NULL address insertion to fi_av_insert
- - Verbs
- - Initial changes for compiling on Windows (via NetworkDirect)
- - Add a failover path to dma-buf based memory registration
- - Replace use of spin locks with mutexes
- - Check for valid qp prior to cleanup
- - Set and check for address format correct in fi_getinfo
- - Fabtests
- - hmem_cuda: used device allocated host buff to fill device buf
- - Add python scripts to control test execution
- - test_configs: include util provider in core config file
- - Add option "--pin-core"
- - Only call nrt_init once
- - Fix a bug in ft_neuron_cleanup
- - Correct help for unit test programs
- - Remove duplicate help prints from fi_mcast
- - configure.ac: fix --enable-debug=no not properly detected
- - msg_inject: handle the case ft_tsendmsg return -FI_EAGAIN
- - Add AWS Trainium device support
- - fi_inj_complete: Add FI_INJECT to fabtests
- - inj_complete.c: Make arguments align with the other tests
- - dgram_pingpong: handle the error return of fi_recv
- - recv_cancel: Remove requirement for unexpected msg handling
- - poll: Fix crash if unable to allocate pollset
- - ubertest: Add GPU testing and validation support
- - Add HMEM options parsing support
- - Update and re-enable fi_multi_ep test
-- Add prov-opx-Correctly-disable-OPX-if-unsupported.patch to disable
- OPX compilation on non x86_64 systems
-
--------------------------------------------------------------------
-Tue Apr 19 07:27:42 UTC 2022 - Nicolas Morey-Chaisemartin
-
-- Update to 1.14.1
- - Core
- - Use non-shared memory allocations to use MADV_DONTFORK safely
- - Fix incorrect use of gdr_copy_from_mapping
- - Ensure proper timeout time for pollfds to avoid early exit
- - EFA
- - Handle read completion properly for multi_recv
- - Use shm's inject write when possible
- - Support 0 byte read
- - RxM
- - Ensure signaling the CQ fd after writing completion
- - Fix inject path for sending tagged messages with cq data
- - Negotiate credit based flow control support over CM
- - Add PID to CM messages to detect stale vs duplicate connections
- - Fix race handling unexpected messages from unknown peers
- - Fix possible leak of stack data in cm_accept
- - Restrict reported caps based on core provider
- - Delay starting listen until endpoint fully initialized
- - Verify valid atomic size
- - Sockets
- - Fix coverity reports on uninitialized data
- - Check for NULL pointers passed to memcpy
- - Add missing error return code from sock_ep_enable
- - TCP
- - Fix performance regression resulting from sparse pollfd sets
- - Fix assertion failure in CQ progress function
- - Do not generate error completions for inject msgs
- - Fix use of incorrect event names in progress handler
- - Fix check for CQ data in tagged messages
- - Make start_op array a static to reduce memory
- - Wake-up threads blocked on CQ to update their poll events
- - Verbs
- - Generate error completions for all failed transmits
- - Set all fields in the fi_fabric_attr for FI_CONNREQ events
- - Set proper completion flags for all failed transfer
- - Ensure that all attributes are provided when opening an endpoint
- - Fix error handling in vrb_eq_read
- - Fix memory leak in error case in vrb_get_sib
- - Work-around bug in verbs HW not reported correct send opcodes
- - Only call ibv_reg_dmabuf_mr when kernel support exists
- - Add a failover path to dma-buf based memory registration
- - Negotiate credit based flow control support over CM
-
--------------------------------------------------------------------
-Mon Nov 22 07:57:54 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.14.0
- - Add time stamps to log messages
- - Fix gdrcopy calculation of memory region size when aligned
- - Allow user to disable use of p2p transfers
- - Update fi_tostr print FI_SHARED_CONTEXT text instead of value
- - Update fi_tostr to output field names matching header file names
- - Fix narrow race condition in ofi_init
- - Add new fi_log_sparse API to rate limit repeated log output
- - Define memory registration for buffers used for collective operations
- - EFA, SHM, TCP, RXM, and verbs fixes
-
--------------------------------------------------------------------
-Wed Nov 3 07:53:20 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Enable PSM3 provider (jsc#SLE-18754)
-
--------------------------------------------------------------------
-Fri Oct 29 11:13:43 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.13.2
- - Sort DL providers to ensure consistent load ordering
- - Update hooking providers to handle fi_open_ops calls to avoid crashes
- - Replace cassert with assert.h to avoid C++ headers in C code
- - Enhance serialization for memory monitors to handle external monitors
- - EFA, SHM, TCP, RxM and vers fixes
-
--------------------------------------------------------------------
-Wed Aug 25 07:41:46 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.13.1
- - Enable loading ZE library with dlopen()
- - Add IPv6 support to fi_pingpong
- - EFA, PSM3 and SHM fixes
-
--------------------------------------------------------------------
-Wed Jul 7 11:13:26 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.13.0
- - Fix behavior of fi_param_get parsing an invalid boolean value
- - Add new APIs to open, export, and import specialized fid's
- - Define ability to import a monitor into the registration cache
- - Add API support for INT128/UINT128 atomics
- - Fix incorrect check for provider name in getinfo filtering path
- - Allow core providers to return default attributes which are lower then
- maximum supported attributes in getinfo call
- - Add option prefer external providers (in order discovered) over internal
- providers, regardless of provider version
- - Separate Ze (level-0) and DRM dependencies
- - Always maintain a list of all discovered providers
- - Fix incorrect CUDA warnings
- - Fix bug in cuda init/cleanup checking for gdrcopy support
- - Shift order providers are called from in fi_getinfo, move psm2 ahead of
- psm3 and efa ahead of psmX
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Fri Apr 2 07:30:34 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.12.1
- - Fix initialization checks for CUDA HMEM support
- - Fail if a memory monitor is requested but not available
- - Adjust priority of psm3 provider to prefer HW specific providers,
- such as efa and psm2
- - EFA and PSM3 fixes
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Tue Mar 9 08:43:43 UTC 2021 - Nicolas Morey-Chaisemartin
-
-- Update to 1.12.0
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Wed Dec 16 08:29:07 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.11.2 (bsc#1181983)
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Mon Oct 12 10:40:29 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.11.1 (jsc#SLE-13312)
- - See NEWS.md for changelog
--------------------------------------------------------------------
-Tue Aug 18 08:12:27 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.11.0
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Thu May 14 08:59:09 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.10.1
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Mon Apr 27 13:04:26 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.10.0
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Thu Mar 19 08:29:38 UTC 2020 - Nicolas Morey-Chaisemartin
-
-- Update to 1.9.1 (bsc#1160275)
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Mon Nov 25 09:39:53 UTC 2019 - Nicolas Morey-Chaisemartin
-
-- Update to 1.9.0 (jsc#SLE-8257)
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Tue Oct 1 05:57:27 UTC 2019 - Nicolas Morey-Chaisemartin
-
-- Update to 1.8.1 (jsc#SLE-8257)
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Fri Sep 6 07:10:57 UTC 2019 - Nicolas Morey-Chaisemartin
-
-- Update to 1.8.0
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Wed Apr 24 17:13:07 UTC 2019 - Martin Liška
-
-- Disable LTO (boo#1133235).
-
--------------------------------------------------------------------
-Tue Apr 9 06:46:41 UTC 2019 - Nicolas Morey-Chaisemartin
-
-- Update to 1.7.1
- - See NEWS.md for changelog
-
--------------------------------------------------------------------
-Mon Feb 11 10:34:29 UTC 2019 - Jan Engelhardt
-
-- Remove silly Prefix: value, we do not support that in SUSE anyway.
-- Update summaries, make use of %make_install.
-
--------------------------------------------------------------------
-Thu Feb 7 07:24:21 UTC 2019 - nmoreychaisemartin@suse.com
-
-- Update to v1.7.0
- - fabtests and libfabric repos have been merged upstream
- - Core
- - Add ability to report NIC details with fi_info data
- - Improve MR cache notification mechanisms
- - Set sockaddr address format correctly
- - Avoid possible null dereference in eq_read
- - Handle FI_PEEK in CQ/EQ readerr
- - Add debug messages to name server
- - Feature and performance enhancements added to internal buffer pool
- - Add support for huge pages
- - Decrease memory use for idle buffer pools
- - Refactor utility AV functionality
- - Generic counter support enhancements
- - Optimize EP and CQ locking based on application threading level
- - Enhance common support for EQ error handling
- - Add free/alloc memory notification hooks for MR cache support
- - Fix memory monitor unsubscribe handling
- - Add CQ fd wait support
- - Add CQ overflow protection
- - Enhance IPv6 addressing support for AVs
- - Enhancements to support for AV address lookup
- - Fixes for emulated epoll support
- - Allow layering of multiple utility providers
- - Minor bug fixes and optimization
- - Hook
- - Improved hooking infrastructure
- - Add support for installing multiple hooks
- - Support hooks provided by external libraries.
- - GNI
- - Fix CQ readfrom overwriting src_addr in case of multiple events
- - Signal wait set if error entry is added to CQ
- - Fix state data issue with SMSG buffers
- - Enhance and fix possible misuse of default authorization key
- - Add cancel support for SEP
- - Rework SEP setup
- - Suppress huge page counting for ARM
- - Fix incorrect check of FI_SYNC_ERR flag
- - PSM2
- - Requires PSM2 library version 10.2.260 or later
- - Clean up connection state in fi_av_remove
- - Use psm2_info_query to read HFI device info
- - Clean up CQ/counter poll list when endpoint is closed
- - Support shared address vector
- - Optimize CQ event conversion with psm2_mq_ipeek_dequeue_multi
- - Lock optimization for FI_THREAD_DOMAIN
- - Use new PSM2 fast path isend/irecv functions for large size RMA
- - Support building with latest PSM2 source code (version 11.2.68)
- - Support fabric direct
- - RxD
- - Initial release of RxD provider
- - Provides reliable datagram semantics over unreliable datagram EPs
- - Target is to improve scalability for very large clusters relative to RxM
- - RxM
- - Decrease memory use needed to maintain large number of connections
- - Set correct op_context and flags on CQ error completions
- - Fix file descriptor memory leaks
- - Introduce new protocol optimized for medium message transfers
- - Improve Rx software performance path
- - Use shared receive contexts if required by underlying provider
- - Handle addresses inserted multiple times into AV (for AV map)
- - Performance optimizations for single-thread applications
- - Rework deferred transmit processing
- - Separate and optimize eager and rendezvous protocol processing.
- - Fix passing incorrect addresses for AV insert/remove
- - Fix CM address handling
- - Fix race condition accessing connection handles
- - Simplify small RMA code path
- - Increment correct counter when processing FI_READ events
- - Dynamically grow the number of connections that can be supported
- - Fix padding in wire protocol structures
- - Report correct fi_addr when FI_SOURCE is requested
- - Fix truncating rendezvous messages
- - Fix use after free error in Rx buffer processing
- - Add support for manual progress
- - Make Tx/Rx queue sizes independent of MSG EP sizes
- - Decrease time needed to repost buffers to the MSG EP Rx queue.
- - Miscellaneous bug fixes
- - Sockets
- - Enable MSG EPs when user calls fi_accept
- - Fix fabric names to be underlying IP address
- - Add connection timeout environment variable.
- - Use size of addresses, not structures
- - Add debug messages to display selected addresses
- - Use loopback address in place of localhost
- - Simplify listen paths
- - Add support for IPv6
- - Code restructuring
- - Avoid unneeded address to string to address translations
- - Check length of iovec entries prior to access buffers
- - Fix segfault
- - Avoid acquiring nested spinlocks resulting in hangs
- - Fix use after free error in triggered op handling
- - New connection manager for MSG EPs to reduce number of threads
- - Avoid retrying recv operations if connection has been broken
- - Fixes for Windows socket support
- - TCP
- - Initial release of optimized socket based tcp provider
- - Supports MSG EPs, to be used in conjunction with RxM provider
- - Targets eventual replacement of sockets provider
- - Verbs
- - Remove RDM EP support. Use RxM and RxD for RDM EPs.
- - Improve address handling and report in fi_getinfo
- - Handle FI_PEER when calling CQ/EQ readerr functions
- - Add support for XRC QPs.
- - Ignore destination address when allocating a PEP
- - Add workaround for i40iw incorrect return values when posting sends
- - Fix completion handling for FI_SELECTIVE_COMPLETION EP setting
- - Change format of fabric name to use hex instead of decimal values
- - Fix handling of err_data with EQ readerr
- - Report correct size of max_err_data
- - Fast path performance improvements
- - Improve progress under high system load
- - Optimize completion processing when handling hidden completions
- - Optimize RMA and MSG transfers by pre-formatting work requests
- - Remove locks based on application threading model
- - Add overflow support for CQ error events
- - Minor cleanups and bug fixes
-
--------------------------------------------------------------------
-Thu Oct 25 10:52:50 UTC 2018 - nmoreychaisemartin@suse.com
-
-- 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
-
--------------------------------------------------------------------
-Thu Mar 15 06:51:08 UTC 2018 - nmoreychaisemartin@suse.com
-
-- Update to v1.6.0
- - Fixes stack smashing when using the verbs provider (bsc#1089190)
- - 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
-
--------------------------------------------------------------------
-Wed Dec 20 08:49:03 UTC 2017 - nmoreychaisemartin@suse.com
-
-- 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
-
--------------------------------------------------------------------
-Mon Nov 20 16:27:13 UTC 2017 - nmoreychaisemartin@suse.com
-
-- 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)
-
--------------------------------------------------------------------
-Mon Oct 9 23:28:31 UTC 2017 - stefan.bruens@rwth-aachen.de
-
-- Fix github issue #3393:
- Add 0001-prov-psm-Eliminate-psm2-compat-library-delay-with-hf.patch
-
--------------------------------------------------------------------
-Thu Oct 5 07:10:28 UTC 2017 - nmoreychaisemartin@suse.com
-
-- 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
- - Fix crash using atomic operations for MSG EPs
-- Fix dependency to libfabric1 for libfabric-devel in baselibs.conf
-
--------------------------------------------------------------------
-Tue Sep 5 09:56:19 UTC 2017 - nmoreychaisemartin@suse.com
-
-- Update _service to allow auto updates from github
-
--------------------------------------------------------------------
-Thu Aug 10 08:29:42 UTC 2017 - nmoreychaisemartin@suse.com
-
-- 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
-- libfabric-devel requires libfabric1, not libfabric
-- Fix baselibs.conf
-
--------------------------------------------------------------------
-Tue Jul 4 09:21:35 UTC 2017 - nmoreychaisemartin@suse.com
-
-- Enable build on all archs
-- Enable mlx build
-
--------------------------------------------------------------------
-Fri Jun 30 07:42:15 UTC 2017 - nmoreychaisemartin@suse.com
-
-- Add x86 build without libpsm2
-
--------------------------------------------------------------------
-Tue May 16 06:43:19 UTC 2017 - nmoreychaisemartin@suse.com
-
-- Update to v1.4.2 (bsc#1036907).
-
--------------------------------------------------------------------
-Thu May 11 18:14:41 UTC 2017 - nmoreychaisemartin@suse.com
-
-- Update to v1.4.2-rc1 (bsc#1036907).
-- Update notes:
- - Fix for OS X clock_gettime() portability issue.
- - Updated default counter wait object for improved performance
- - Fix multi-threaded RMA progress stalls
- - Updated default counter wait object for improved performance
- - Fix multi-threaded RMA progress stalls
- - Fix error in fi_cq_sreadfrom aborting before timeout expires
- - Set atomic iov count correct correctly inside fi_atomicv
- - Fix handling of apps that call fork. Move ibv_fork_init() before
- calling any other verbs call.
- - Fix crash in fi_write when connection is not yet established and
- write data size is below inline threshold.
- - Fix issues not handling multiple ipoib interfaces
- - Reduce lock contention on buffer pools in send/completion handling
- code.
-
-
-
--------------------------------------------------------------------
-Wed Apr 5 10:19:28 UTC 2017 - josef.moellers@suse.com
-
-- This version fixes bnc#990184
- (bnc#990184)
-
--------------------------------------------------------------------
-Thu Mar 23 16:21:53 UTC 2017 - jengelh@inai.de
-
-- RPM group fix
-
--------------------------------------------------------------------
-Fri Mar 10 15:58:55 UTC 2017 - josef.moellers@suse.com
-
-- PSM provider notes
- - Defer initialization of the PSM library to allow runtime selection from
- different versions of the same provider before fi_getinfo is called.
-- PSM2 provider notes
- - Defer initialization of the PSM2 library to allow runtime selection from
- different versions of the same provider before fi_getinfo is called.
- - General bug fixes.
-- UDP provider notes
- - Fix setting address format in fi_getinfo call.
-- usNIC provider notes
- - Fixed compilation issues with newer versions of libibverbs.
- (fate#321883)
--------------------------------------------------------------------
-Mon Jan 16 13:12:14 CET 2017 - ndas@suse.de
-
-- Updated to version 1.4.0 for general stability(fate#321883)
-- Summary of changes as follow:
- - Add new options, `-f` and `-d`, to fi_info that can be used to
- specify hints about the fabric and domain name. Change port to `-P`
- and provider to `-p` to be more in line with fi_pingpong.
-
- *GNI provider notes
-
- - General bug fixes, plugged memory leaks, performance improvements,
- improved error handling and warning messages, etc.
- - Additional API support:
- - FI_THREAD_COMPLETION
- - FI_RMA_EVENT
- - iov length up to 8 for messaging data transfers
-
- *PSM provider notes
-
- - General bug fixes
- - Use utility provider for EQ, wait object, and poll set
- - Allow multi-recv to post buffer larger than message size limit
-
- *PSM2 provider notes
-
- - General bug fixes
- - Add support for multi-iov RMA read and aromic operations
- - Allow multi-recv to post buffer larger than message size limit
-
-
- *Verbs provider notes
-
- - Add fork support. It is enabled by default and can be turned off by
- setting the FI_FORK_UNSAFE variable to "yes". This can improve
- performance of memory registrations but also makes fork unsafe. The
- following are the limitations of fork support:
- - Fabric resources like endpoint, CQ, EQ, etc. should not be used in
- the forked process.
- - The memory registered using fi_mr_reg has to be page aligned since
- ibv_reg_mr marks the entire page that a memory region belongs to
- as not to be re-mapped when the process is forked (MADV_DONTFORK).
- - Fix a bug where source address info was not being returned in
- fi_info when destination node is specified.
-
--------------------------------------------------------------------
-Fri May 6 12:51:41 CEST 2016 - nads@suse.de
-
-- Updated to version 1.3.0 for better PSM2 support as suggested by
- fate#319253, comment #9.
-
- [*libfabric-libtool.patch]
-
- Summary of changes as follow:
- *PSM provider notes
- - Remove PSM2 related code.
- *PSM2 provider notes
- - Add support for multi-iov send, tagged send, and RMA write.
- - Use utility provider for EQ, wait object, and poll set.
- *GNI provider notes
- - General bug fixes, plugged memory leaks, etc.
- - Added support for the following APIs:
- - fi_endpoint: fi_getopt, fi_setopt, fi_rx_size_left, fi_tx_size_left, fi_stx_context
- - fi_cq: fi_sread, fi_sreadfrom
- - fi_msg: FI_MULTI_RECV (flag)
- - fi_domain: FI_PROGRESS_AUTO (flag)
- - fi_direct: FI_DIRECT
- - Added support for FI_EP_DGRAM (datagram endpoint):
- - Memory registration improvements:
- - Initial support for Cray Cluster Compatibility Mode (CCM)
- *MXM provider notes
- - Initial release
- *Sockets provider notes
- - Enable FABRIC_DIRECT
- - Enable sockets-provider to run on FreeBSD
- - Add support for fi_trywait
- - Add support for map_addr in shared-av creation
- - Add shared-av support on OSX
- - General bug fixes
- *UDP provider notes
- - Initial release
- *usNIC provider notes
- - Implement fi_recvv and fi_recvmsg for FI_EP_RDM. [PR #1594]
- - Add support for FI_INJECT flag in the FI_EP_RDM implementation of fi_sendv.
- [PR #1594]
- - Handle FI_PEEK flag in fi_eq_sread. [PR #1758]
- - Implement waitsets [PR #1893]
- - Implement fi_trywait [PR #1893]
- - Fix progress thread deadlock [PR #1893]
- - Implement FD based CQ sread [PR #1893]
- *Verbs provider notes
- - Add support for fi_trywait
- - verbs/RDM
- - Add support for RMA operations.
- - Add support for fi_cq_sread and fi_cq_sreadfrom
- - Rework connection management to make it work with fabtests and also allow
- connection to self.
- - Other bug fixes and performance improvements.
-
--------------------------------------------------------------------
-Wed Apr 6 16:20:41 CEST 2016 - ndas@suse.de
-
-- Moved man pages to main package.
-- Fixed invalid library group.
-
--------------------------------------------------------------------
-Wed Apr 6 15:40:25 CEST 2016 - ndas@suse.de
-
-- Packaging version 1.2.0 for fate#319253
-
--------------------------------------------------------------------
-Fri Feb 12 10:18:49 CET 2016 - pth@suse.de
-
-- Use explicit file list instead of wildcards
-- Package fi_info.
-- Remove libtool.m4 from the package so that autoreconf installs
- a current version.
-
--------------------------------------------------------------------
-Thu Feb 11 10:18:41 CET 2016 - pth@suse.de
-
-- Initial package, based on the OFED specfile for libfabric
-- Add libfabric-libtool.patch to disable static builds by default.
diff --git a/fabtests.spec b/fabtests.spec
index b607863..a8a91b1 100644
--- a/fabtests.spec
+++ b/fabtests.spec
@@ -16,10 +16,10 @@
#
-%define git_ver .0.e43589a5113a
+%define git_ver .0.f67fad269327
Name: fabtests
-Version: 1.20.1
+Version: 1.21.0
Release: 0
Summary: Test suite for libfabric API
License: BSD-2-Clause OR GPL-2.0-only
diff --git a/libfabric-1.20.1.0.e43589a5113a.tar.bz2 b/libfabric-1.20.1.0.e43589a5113a.tar.bz2
deleted file mode 100644
index 0f5763c..0000000
--- a/libfabric-1.20.1.0.e43589a5113a.tar.bz2
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b4d802a256faf5fd2563aaf10f262ba995b04d79ada3991bc47f63b7521a30ea
-size 3437761
diff --git a/libfabric-1.21.0.0.f67fad269327.tar.bz2 b/libfabric-1.21.0.0.f67fad269327.tar.bz2
new file mode 100644
index 0000000..2ae20c2
--- /dev/null
+++ b/libfabric-1.21.0.0.f67fad269327.tar.bz2
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766162bc9b3fbd6d57c40d230c076f7314a64ce28bee9eadf2fb1b046355a148
+size 3463094
diff --git a/libfabric.changes b/libfabric.changes
index c79b424..415f043 100644
--- a/libfabric.changes
+++ b/libfabric.changes
@@ -1,3 +1,175 @@
+-------------------------------------------------------------------
+Wed Apr 3 11:32:43 UTC 2024 - Nicolas Morey
+
+- Enable ucx and new efa provider on 64b architectures.
+- Use a single changes file for libfabric and fabtests.
+- Update to 1.21.0
+ - Core
+ - Various update and fixed in man pages
+ - Fix xpmem memory corruption
+ - Extend FI_PROVIDER_PATH to allow setting preferred DL provider
+ - Add a SECURITY.md file
+ - Document preferred threading model for scalable endpoints
+ - Move FI_PRIORITY to internal flag
+ - Remove FI_PROV_SPECIFIC
+ - Remove unimplemented or unused features
+ - Support cntr byte counting
+ - configure: Do not check for xpmem if disabled
+ - Add FI_PROGRESS_CONTROL_UNIFIED
+ - hmem/cuda: Get multiple attributes at once in cuda_is_addr_valid
+ - configure: Add -pipe by default to CFLAGS
+ - Selectively generate warnings on failed loading of DL providers
+ - hmem: introduce ofi_dev_reg_copy_*_iov ops
+ - Print provider path on fabric creation
+ - Introduce FI_OPT_SHARED_MEMORY_PERMITTED
+ - README.md: Add badge for openssf scorecard
+ - man: Regulate the fi_setopt call sequence.
+ - man: Clarify the usage of FI_RMOTE_CQ_DATA flag
+ - man: Add ucx provider to the fi_provider man page
+ - configure.ac: add extra check for 128 bit atomic support
+ - include/osd: align atomic complex definitions
+ - hmem/synapseai: Refine the error handling and warning
+ - Specify C11 standard for Visual Studio builds
+ - configure: Do not check for xpmem if disabled
+ - man page fixes
+ - EFA
+ - General improvement and bug fixes
+ - Propagate errnos from core functions untouched
+ - Create 1:1 relationship between libfabric CQs and IBV CQs
+ - Do not progress ep inside transmission call when hitting EAGAIN
+ - Remove unnecessary check in rdma write.
+ - Handle rx pkts error without ope
+ - Add a new rx pkt counter
+ - Enable runting for neuron with a different runt size
+ - Distinguish unresponsive receiver errors
+ - Remove unnecessary handshake in send path
+ - Don't fail the whole domain init if cudamalloc failed
+ - Introduce efa specific domain operations
+ - Implement FI_OPT_SHARED_MEMORY_PERMITTED
+ - Do not memset rxe to 0 on init
+ - Reduce # of error cases in happy path
+ - Add FI_EFA_USE_HUGE_PAGE to efa man page.
+ - Don't do handshake for local fi_write
+ - Add pingpong test after exhausting MRs
+ - Introduce utilities to exhaust MRs on EFA device
+ - Test EFA with a 1GiB message
+ - Do not abort on all deprecated env vars
+ - Onboard fi_mr_dmabuf API in mem reg ops.
+ - Try registering cuda memory via dmabuf when checking p2p
+ - Introduce HAVE_EFA_DMABUF_MR macro in configure
+ - Use long CTS protocol if long read and runting read protocols fail
+ because of memory registration limits
+ - Remove unnecessary check in rdma write.
+ - Enable runting for neuron with a different runt size
+ - Handle rx pkts error without ope
+ - Distinguish unresponsive receiver errors
+ - Add `efa_show_help()`
+ - Refactor error code definitions
+ - Remove error message assertions from CQ unit tests
+ - Refactor `efa_strerror()`
+ - Doxyfile: Configure tabs to 8 spaces
+ - Rename Doxyfile
+ - Hooks
+ - dmabuf_peer_mem: initialize fd to supress compiler warning
+ - NETDIR
+ -Removed. The functionality is intergrated into the verbs provider.
+ - OPX
+ - Fix compiler warnings and coverity issues
+ - General improvement and bug fixes
+ - Add GPU support to expected TID
+ - RZV RTS packet exclude empty immediate data
+ - Add more efficient check for cuda-resident user buffer
+ - Improve default HFI selection logic in multi rail environments
+ - Flush dead list opportunistically
+ - Add RISC-V support
+ - Make update HDRQ register frequency configurable at build time
+ - Removed all references to the reliability nack threshold env var
+ - Added missing tuneables, rearraged to match fi_info -e output
+ - Use BAR load/store macros
+ - Check HFI driver version to allow GPU-enabled build/run
+ - Added kernel and driver version check to allow/disallow expected receive TID
+ - Fix max SHM connections to allow up to 16 HFIs
+ - Use FI_HMEM_SYSTEM for Cuda-Managed (Unified) memory
+ - Handle FI_OPT_CUDA_API_PERMITTED
+ - Use contiguous send when only one iov present
+ - Always replay TID packets over SDMA
+ - Add Virtual Lane and Partition pkey (FI_OPX_SL and FI_OPX_PKEY)
+ - Forced AV type to be AV Map when requested AV is unsupported
+ - Reduce size of opx_shm_tx
+ - Add GPU support for RMA Atomic operations
+ - Add GPU support for RMA reads and writes
+ - Add HMEM debug counters
+ - Print debug counters upon receiving SIGUSR1
+ - Fix multi-receive to work with contiguous rzv payload
+ - Initial support for GPU / FI_HMEM
+ - Limit multipacket eager implementation to tagged sends
+ - Read, verify and store some hfi chip attributes
+ - PSM3
+ - Update provider to sync with IEFS 11.6.0.0.231
+ - Fix some conditional build errors
+ - RSTREAM
+ - Removed.
+ - RXM
+ - Add option to auto detect hmem iface of user buffers
+ - SHM
+ - Manually align 8 byte fields in memory region
+ - Close device_fds for connected peers when the EP is closed
+ - Print shm name and error code when failed to open
+ - Mark send as completed when a message is discarded
+ - Don't close dmabuf-fd when a request is done
+ - Revert the smr_region fields adjustment
+ - Fix various coverity issues
+ - Add ep to cq ep list once in cq bind
+ - Add ofi_buf_alloc error handling
+ - Revert the smr_region fields adjustment
+ - Don't close dmabuf-fd when a request is done
+ - Mark send as completed when a message is discarded
+ - Print shm name and error code when failed to open
+ - Close device_fds for connected peers when the EP is closed
+ - SOCKETS
+ - fix compiler warnings and coverity issues
+ - UCX
+ - Fix incorrect enum value in FI_DBG() and FI_WARN()
+ - USNIC
+ - Turn off compiler warnings of possible string truncation
+ - Util
+ - Make ep_list_lock noop for FI_PROGRESS_CONTROL_UNIFIED
+ - Save control progress model to util_domain
+ - Set import monitor state to idle upon close
+ - Add name field to memory monitors
+ - memhooks: Fix a bug when calculating mprotect region
+ - Modify domain_attr based on FI_AV_AUTH_KEY
+ - Verbs
+ - Non-blocking EP creation
+ - Address cm_id resource leak in rdma_reject path
+ - Redirected error handle logic for dmabuf failure in verbs
+ - Added rocr dmabuf support under verbs
+ - Windows: Check error code from GetPrivateData
+ - Add missing lock to protect SRX
+ - Fix compiler warnings about out of boundary access
+ - Fabtests
+ - Fix various coverity issues
+ - General improvement and bug fixes
+ - Add multi_ep test
+ - Serialize the run of fi_cq_test
+ - Utilize `junitparser` module directly
+ - Add progress models to SHM/EFA fabtests
+ - Add option to change progress model
+ - efa/rnr_cq_read_err: poll cq when hitting EAGAIN
+ - Allow testing multi_ep with shared/non-shared cq and av
+ - Print warning for HMEM iface init failure
+ - efa: Add small tx_rx size test
+ - pytest: Make ssh connection error pattern less stringent
+ - Add new exclude file for io_uring tests
+ - Add rma_pingpong benchmark
+ - efa: Make 1G tests run faster
+ - pytests: add command line argument for dmabuf reg
+ - Bump Libfabric API version.
+ - Add option to support dmabuf MR
+ - Add dmabuf ops for cuda.
+ - Replace strtok with strtok_r
+ - Add new exclude file for io_uring tests
+
-------------------------------------------------------------------
Mon Mar 25 07:45:03 UTC 2024 - Nicolas Morey
diff --git a/libfabric.spec b/libfabric.spec
index a60bc30..db9e01d 100644
--- a/libfabric.spec
+++ b/libfabric.spec
@@ -17,10 +17,17 @@
#
-%define git_ver .0.e43589a5113a
+%define git_ver .0.f67fad269327
+
+%ifarch aarch64 %power64 x86_64 s390x
+%if 0%{?suse_version} > 1530
+%define with_ucx 1
+%endif
+%define with_efa 1
+%endif
Name: libfabric
-Version: 1.20.1
+Version: 1.21.0
Release: 0
Summary: User-space RDMA Fabric Interfaces
License: BSD-2-Clause OR GPL-2.0-only
@@ -40,6 +47,13 @@ BuildRequires: libpsm2-devel
BuildRequires: fdupes
BuildRequires: librdmacm-devel
BuildRequires: libtool
+%if 0%{?with_ucx}
+BuildRequires: libucm-devel
+BuildRequires: libucp-devel
+ # 1.10 Needed for UCS_MEMORY_TYPE_UNKNOWN
+BuildRequires: libucs-devel >= 1.10
+BuildRequires: libuct-devel
+%endif
BuildRequires: pkg-config
%define lib_major 1
@@ -73,6 +87,12 @@ autoreconf -fi
# defaults: with-dlopen and without-valgrind can be over-rode:
%configure %{?_without_dlopen} %{?_with_valgrind} \
--enable-sockets --enable-verbs --enable-usnic \
+%if 0%{?with_efa}
+ --enable-efa \
+%endif
+%if 0%{?with_ucx}
+ --enable-ucx \
+%endif
%ifarch x86_64
--enable-psm2 \
--enable-psm3 \
@@ -128,6 +148,9 @@ rm -f %{buildroot}%{_libdir}/*.la
%ifarch x86_64
%{_includedir}/rdma/fi_ext_psm2.h
%endif
+%if 0%{?with_efa}
+%{_includedir}/rdma/fi_ext_efa.h
+%endif
%{_mandir}/man3/*
%{_mandir}/man7/*
diff --git a/pre_checkin.sh b/pre_checkin.sh
index e4ce5b4..814aea6 100644
--- a/pre_checkin.sh
+++ b/pre_checkin.sh
@@ -1,7 +1,6 @@
#!/bin/bash
# This script has to be run prior to a check-in if changes were done
# to spec and/or changes
-cp libfabric.changes fabtests.changes
GIT_VER=$(grep "%define git_ver" libfabric.spec)
VERSION=$(egrep "^Version:" libfabric.spec)
sed -i -e 's/^%define git_ver.*$/'"$GIT_VER/" -e 's/^Version:.*$/'"$VERSION/" fabtests.spec