1fi_cq(3)                       Libfabric v1.7.0                       fi_cq(3)
2
3
4

NAME

6       fi_cq - Completion queue operations
7
8       fi_cq_open / fi_close
9              Open/close a completion queue
10
11       fi_control
12              Control CQ operation or attributes.
13
14       fi_cq_read / fi_cq_readfrom / fi_cq_readerr
15              Read a completion from a completion queue
16
17       fi_cq_sread / fi_cq_sreadfrom
18              A  synchronous (blocking) read that waits until a specified con‐
19              dition has been met before reading a completion from  a  comple‐
20              tion queue.
21
22       fi_cq_signal
23              Unblock any thread waiting in fi_cq_sread or fi_cq_sreadfrom.
24
25       fi_cq_strerror
26              Converts  provider  specific  error information into a printable
27              string
28

SYNOPSIS

30              #include <rdma/fi_domain.h>
31
32              int fi_cq_open(struct fid_domain *domain, struct fi_cq_attr *attr,
33                  struct fid_cq **cq, void *context);
34
35              int fi_close(struct fid *cq);
36
37              int fi_control(struct fid *cq, int command, void *arg);
38
39              ssize_t fi_cq_read(struct fid_cq *cq, void *buf, size_t count);
40
41              ssize_t fi_cq_readfrom(struct fid_cq *cq, void *buf, size_t count,
42                  fi_addr_t *src_addr);
43
44              ssize_t fi_cq_readerr(struct fid_cq *cq, struct fi_cq_err_entry *buf,
45                  uint64_t flags);
46
47              ssize_t fi_cq_sread(struct fid_cq *cq, void *buf, size_t count,
48                  const void *cond, int timeout);
49
50              ssize_t fi_cq_sreadfrom(struct fid_cq *cq, void *buf, size_t count,
51                  fi_addr_t *src_addr, const void *cond, int timeout);
52
53              int fi_cq_signal(struct fid_cq *cq);
54
55              const char * fi_cq_strerror(struct fid_cq *cq, int prov_errno,
56                    const void *err_data, char *buf, size_t len);
57

ARGUMENTS

59       domain Open resource domain
60
61       cq     Completion queue
62
63       attr   Completion queue attributes
64
65       context
66              User specified context associated with the completion queue.
67
68       buf    For read calls, the data buffer to write completions into.   For
69              write  calls,  a completion to insert into the completion queue.
70              For fi_cq_strerror, an optional buffer that  receives  printable
71              error information.
72
73       count  Number of CQ entries.
74
75       len    Length of data buffer
76
77       src_addr
78              Source address of a completed receive operation
79
80       flags  Additional flags to apply to the operation
81
82       command
83              Command of control operation to perform on CQ.
84
85       arg    Optional control argument
86
87       cond   Condition that must be met before a completion is generated
88
89       timeout
90              Time  in milliseconds to wait.  A negative value indicates infi‐
91              nite timeout.
92
93       prov_errno
94              Provider specific error value
95
96       err_data
97              Provider specific error data related to a completion
98

DESCRIPTION

100       Completion queues are used to report events associated with data trans‐
101       fers.   They are associated with message sends and receives, RMA, atom‐
102       ic, tagged messages, and triggered events.  Reported events are usually
103       associated with a fabric endpoint, but may also refer to memory regions
104       used as the target of an RMA or atomic operation.
105
106   fi_cq_open
107       fi_cq_open allocates a new completion queue.  Unlike event queues, com‐
108       pletion  queues  are  associated with a resource domain and may be off‐
109       loaded entirely in provider hardware.
110
111       The properties and behavior  of  a  completion  queue  are  defined  by
112       struct fi_cq_attr.
113
114              struct fi_cq_attr {
115                  size_t               size;      /* # entries for CQ */
116                  uint64_t             flags;     /* operation flags */
117                  enum fi_cq_format    format;    /* completion format */
118                  enum fi_wait_obj     wait_obj;  /* requested wait object */
119                  int                  signaling_vector; /* interrupt affinity */
120                  enum fi_cq_wait_cond wait_cond; /* wait condition format */
121                  struct fid_wait     *wait_set;  /* optional wait set */
122              };
123
124       size   Specifies  the minimum size of a completion queue.  A value of 0
125              indicates that the provider may choose a default value.
126
127       flags  Flags that control the configuration of the CQ.
128
129       - FI_AFFINITY
130              Indicates that the signaling_vector field (see below) is valid.
131
132       format Completion queues allow the application to select the amount  of
133              detail  that it must store and report.  The format attribute al‐
134              lows the application to select one of  several  completion  for‐
135              mats,  indicating  the structure of the data that the completion
136              queue should return when read.  Supported formats and the struc‐
137              tures  that correspond to each are listed below.  The meaning of
138              the CQ entry fields are defined in the  Completion  Fields  sec‐
139              tion.
140
141       - FI_CQ_FORMAT_UNSPEC
142              If  an  unspecified  format is requested, then the CQ will use a
143              provider selected default format.
144
145       - FI_CQ_FORMAT_CONTEXT
146              Provides only user specified context that  was  associated  with
147              the completion.
148
149              struct fi_cq_entry {
150                  void     *op_context; /* operation context */
151              };
152              · .RS 2
153
154       FI_CQ_FORMAT_MSG
155              Provides  minimal data for processing completions, with expanded
156              support for reporting information about received messages.
157
158              struct fi_cq_msg_entry {
159                  void     *op_context; /* operation context */
160                  uint64_t flags;       /* completion flags */
161                  size_t   len;         /* size of received data */
162              };
163              · .RS 2
164
165       FI_CQ_FORMAT_DATA
166              Provides data associated with a  completion.   Includes  support
167              for  received  message length, remote CQ data, and multi-receive
168              buffers.
169
170              struct fi_cq_data_entry {
171                  void     *op_context; /* operation context */
172                  uint64_t flags;       /* completion flags */
173                  size_t   len;         /* size of received data */
174                  void     *buf;        /* receive data buffer */
175                  uint64_t data;        /* completion data */
176              };
177              · .RS 2
178
179       FI_CQ_FORMAT_TAGGED
180              Expands completion data to include support for the  tagged  mes‐
181              sage interfaces.
182
183              struct fi_cq_tagged_entry {
184                  void     *op_context; /* operation context */
185                  uint64_t flags;       /* completion flags */
186                  size_t   len;         /* size of received data */
187                  void     *buf;        /* receive data buffer */
188                  uint64_t data;        /* completion data */
189                  uint64_t tag;         /* received tag */
190              };
191
192       wait_obj
193              CQ's  may  be  associated with a specific wait object.  Wait ob‐
194              jects allow applications to block until the wait object is  sig‐
195              naled,  indicating  that  a  completion is available to be read.
196              Users may use fi_control to retrieve the underlying wait  object
197              associated  with a CQ, in order to use it in other system calls.
198              The following values may be used to specify the type of wait ob‐
199              ject   associated   with  a  CQ:  FI_WAIT_NONE,  FI_WAIT_UNSPEC,
200              FI_WAIT_SET, FI_WAIT_FD, and FI_WAIT_MUTEX_COND.  The default is
201              FI_WAIT_NONE.
202
203       - FI_WAIT_NONE
204              Used to indicate that the user will not block (wait) for comple‐
205              tions on the CQ.  When FI_WAIT_NONE is specified,  the  applica‐
206              tion may not call fi_cq_sread or fi_cq_sreadfrom.
207
208       - FI_WAIT_UNSPEC
209              Specifies  that  the  user will only wait on the CQ using fabric
210              interface calls, such as  fi_cq_sread  or  fi_cq_sreadfrom.   In
211              this case, the underlying provider may select the most appropri‐
212              ate or highest performing wait object available, including  cus‐
213              tom  wait  mechanisms.   Applications that select FI_WAIT_UNSPEC
214              are not guaranteed to retrieve the underlying wait object.
215
216       - FI_WAIT_SET
217              Indicates that the completion queue should use a wait set object
218              to  wait for completions.  If specified, the wait_set field must
219              reference an existing wait set object.
220
221       - FI_WAIT_FD
222              Indicates that the CQ should use a file descriptor as  its  wait
223              mechanism.   A file descriptor wait object must be usable in se‐
224              lect, poll, and epoll routines.  However, a provider may  signal
225              an  FD  wait object by marking it as readable, writable, or with
226              an error.
227
228       - FI_WAIT_MUTEX_COND
229              Specifies that the CQ should use a pthread mutex and cond  vari‐
230              able as a wait object.
231
232       - FI_WAIT_CRITSEC_COND
233              Windows  specific.   Specifies that the CQ should use a critical
234              section and condition variable as a wait object.
235
236       signaling_vector
237              If the FI_AFFINITY flag is set, this indicates the  logical  cpu
238              number  (0..max  cpu - 1) that interrupts associated with the CQ
239              should target.  This field should be treated as a  hint  to  the
240              provider and may be ignored if the provider does not support in‐
241              terrupt affinity.
242
243       wait_cond
244              By default, when a completion is inserted into a  CQ  that  sup‐
245              ports  blocking  reads (fi_cq_sread/fi_cq_sreadfrom), the corre‐
246              sponding wait object is signaled.  Users may specify a condition
247              that must first be met before the wait is satisfied.  This field
248              indicates how the provider  should  interpret  the  cond  field,
249              which describes the condition needed to signal the wait object.
250
251       A  wait  condition should be treated as an optimization.  Providers are
252       not required to meet the requirements of the condition before signaling
253       the  wait object.  Applications should not rely on the condition neces‐
254       sarily being true when a blocking read call returns.
255
256       If wait_cond is set to FI_CQ_COND_NONE, then no  additional  conditions
257       are  applied  to the signaling of the CQ wait object, and the insertion
258       of any new entry will trigger the wait condition.  If wait_cond is  set
259       to FI_CQ_COND_THRESHOLD, then the cond field is interpreted as a size_t
260       threshold value.  The threshold indicates the number  of  entries  that
261       are to be queued before at the CQ before the wait is satisfied.
262
263       This field is ignored if wait_obj is set to FI_WAIT_NONE.
264
265       wait_set
266              If  wait_obj is FI_WAIT_SET, this field references a wait object
267              to which the completion queue should attach.  When an  event  is
268              inserted  into  the completion queue, the corresponding wait set
269              will be signaled if all necessary conditions are met.   The  use
270              of  a wait_set enables an optimized method of waiting for events
271              across multiple event and completion queues.  This field is  ig‐
272              nored if wait_obj is not FI_WAIT_SET.
273
274   fi_close
275       The  fi_close  call releases all resources associated with a completion
276       queue.  Any completions which remain on the CQ when it  is  closed  are
277       lost.
278
279       When  closing  the CQ, there must be no opened endpoints, transmit con‐
280       texts, or receive contexts associated with the CQ.   If  resources  are
281       still  associated  with  the CQ when attempting to close, the call will
282       return -FI_EBUSY.
283
284   fi_control
285       The fi_control call is used to access provider or  implementation  spe‐
286       cific  details of the completion queue.  Access to the CQ should be se‐
287       rialized across all calls when fi_control is invoked, as it  may  redi‐
288       rect  the  implementation of CQ operations.  The following control com‐
289       mands are usable with a CQ.
290
291       FI_GETWAIT (void **)
292              This command allows the user to retrieve the low-level wait  ob‐
293              ject  associated  with the CQ.  The format of the wait-object is
294              specified during CQ creation, through the  CQ  attributes.   The
295              fi_control arg parameter should be an address where a pointer to
296              the returned wait object will be written.  See fi_eq.3 for addi‐
297              tion details using fi_control with FI_GETWAIT.
298
299   fi_cq_read
300       The fi_cq_read operation performs a non-blocking read of completion da‐
301       ta from the CQ.  The format of the completion event is determined using
302       the  fi_cq_format  option  that  was  specified when the CQ was opened.
303       Multiple completions may be retrieved from a CQ in a single call.   The
304       maximum  number  of entries to return is limited to the specified count
305       parameter, with the number of entries successfully read from the CQ re‐
306       turned by the call.  (See return values section below.)
307
308       CQs are optimized to report operations which have completed successful‐
309       ly.  Operations which fail are reported 'out of band'.  Such operations
310       are retrieved using the fi_cq_readerr function.  When an operation that
311       has completed with an unexpected error is encountered, it is placed in‐
312       to a temporary error queue.  Attempting to read from a CQ while an item
313       is in the error queue results in fi_cq_read failing with a return  code
314       of -FI_EAVAIL.  Applications may use this return code to determine when
315       to call fi_cq_readerr.
316
317   fi_cq_readfrom
318       The fi_cq_readfrom call behaves identical to fi_cq_read, with  the  ex‐
319       ception  that  it allows the CQ to return source address information to
320       the user for any received data.  Source address data is only  available
321       for   those   endpoints   configured  with  FI_SOURCE  capability.   If
322       fi_cq_readfrom is called on an endpoint for which source addressing da‐
323       ta  is  not  available,  the  source address will be set to FI_ADDR_NO‐
324       TAVAIL.  The number of input src_addr entries must be the same  as  the
325       count parameter.
326
327       Returned  source  addressing  data is converted from the native address
328       used by the underlying fabric into an fi_addr_t, which may be  used  in
329       transmit operations.  Under most circumstances, returning fi_addr_t re‐
330       quires that the source address already have been inserted into the  ad‐
331       dress  vector associated with the receiving endpoint.  This is true for
332       address  vectors  of  type  FI_AV_TABLE.   In  select  providers   when
333       FI_AV_MAP  is  used,  source addresses may be converted algorithmically
334       into a usable fi_addr_t, even though the source address  has  not  been
335       inserted  into the address vector.  This is permitted by the API, as it
336       allows the provider to avoid address look-up as part of receive message
337       processing.   In no case do providers insert addresses into an AV sepa‐
338       rate from an application calling fi_av_insert or similar call.
339
340       For endpoints allocated using  the  FI_SOURCE_ERR  capability,  if  the
341       source  address  cannot  be  converted  into  a  valid fi_addr_t value,
342       fi_cq_readfrom will return -FI_EAVAIL, even if the data  were  received
343       successfully.  The completion will then be reported through fi_cq_read‐
344       err with error code -FI_EADDRNOTAVAIL.  See fi_cq_readerr for details.
345
346       If FI_SOURCE is specified without FI_SOURCE_ERR, source addresses which
347       cannot  be mapped to a usable fi_addr_t will be reported as FI_ADDR_NO‐
348       TAVAIL.
349
350   fi_cq_sread / fi_cq_sreadfrom
351       The fi_cq_sread and fi_cq_sreadfrom calls are the  blocking  equivalent
352       operations to fi_cq_read and fi_cq_readfrom.  Their behavior is similar
353       to the non-blocking calls, with the exception that the calls  will  not
354       return  until either a completion has been read from the CQ or an error
355       or timeout occurs.
356
357       It is invalid for applications to call these functions if  the  CQ  has
358       been configured with a wait object of FI_WAIT_NONE or FI_WAIT_SET.
359
360   fi_cq_readerr
361       The read error function, fi_cq_readerr, retrieves information regarding
362       any asynchronous operation which has completed with an  unexpected  er‐
363       ror.   fi_cq_readerr  is  a  non-blocking  call,  returning immediately
364       whether an error completion was found or not.
365
366       Error information is reported to the user through  struct fi_cq_err_en‐
367       try.  The format of this structure is defined below.
368
369              struct fi_cq_err_entry {
370                  void     *op_context; /* operation context */
371                  uint64_t flags;       /* completion flags */
372                  size_t   len;         /* size of received data */
373                  void     *buf;        /* receive data buffer */
374                  uint64_t data;        /* completion data */
375                  uint64_t tag;         /* message tag */
376                  size_t   olen;        /* overflow length */
377                  int      err;         /* positive error code */
378                  int      prov_errno;  /* provider error code */
379                  void    *err_data;    /*  error data */
380                  size_t   err_data_size; /* size of err_data */
381              };
382
383       The  general  reason  for  the error is provided through the err field.
384       Provider specific error information may also be available  through  the
385       prov_errno  and err_data fields.  Users may call fi_cq_strerror to con‐
386       vert provider specific error information into a  printable  string  for
387       debugging  purposes.   See  field details below for more information on
388       the use of err_data and err_data_size.
389
390       Note that error completions are generated for all operations, including
391       those  for  which  a completion was not requested (e.g.  an endpoint is
392       configured with FI_SELECTIVE_COMPLETION, but the request did  not  have
393       the  FI_COMPLETION  flag set).  In such cases, providers will return as
394       much information as made available by the underlying software and hard‐
395       ware  about  the  failure, other fields will be set to NULL or 0.  This
396       includes the op_context value, which may not have been provided or  was
397       ignored on input as part of the transfer.
398
399       Notable completion error codes are given below.
400
401       FI_EADDRNOTAVAIL
402              This  error code is used by CQs configured with FI_SOURCE_ERR to
403              report completions for which a usable fi_addr_t  source  address
404              could not be found.  An error code of FI_EADDRNOTAVAIL indicates
405              that the data transfer was successfully received and  processed,
406              with the fi_cq_err_entry fields containing information about the
407              completion.  The err_data field will be set to  the  source  ad‐
408              dress  data.   The  source address will be in the same format as
409              specified through the fi_info addr_format field for  the  opened
410              domain.   This  may be passed directly into an fi_av_insert call
411              to add the source address to the address vector.
412
413   fi_cq_signal
414       The fi_cq_signal call will unblock any thread waiting in fi_cq_sread or
415       fi_cq_sreadfrom.   This may be used to wake-up a thread that is blocked
416       waiting to read a completion operation.  The fi_cq_signal operation  is
417       only available if the CQ was configured with a wait object.
418

COMPLETION FIELDS

420       The  CQ entry data structures share many of the same fields.  The mean‐
421       ings of these fields are the same for all CQ entry structure formats.
422
423       op_context
424              The operation context is the application specified context value
425              that  was  provided with an asynchronous operation.  The op_con‐
426              text field is valid for all completions that are associated with
427              an asynchronous operation.
428
429       For  completion events that are not associated with a posted operation,
430       this field will be set to NULL.  This includes completions generated at
431       the  target  in  response  to  RMA  write operations that carry CQ data
432       (FI_REMOTE_WRITE | FI_REMOTE_CQ_DATA flags set), when the FI_RX_CQ_DATA
433       mode bit is not required.
434
435       flags  This  specifies  flags  associated with the completed operation.
436              The Completion Flags section  below  lists  valid  flag  values.
437              Flags are set for all relevant completions.
438
439       len    This  len  field  only  applies  to completed receive operations
440              (e.g.  fi_recv, fi_trecv, etc.).  It indicates the size  of  re‐
441              ceived message data -- i.e.  how many data bytes were placed in‐
442              to  the   associated   receive   buffer   by   a   corresponding
443              fi_send/fi_tsend/et al call.  If an endpoint has been configured
444              with the FI_MSG_PREFIX mode, the len also reflects the  size  of
445              the prefix buffer.
446
447       buf    The  buf  field  is only valid for completed receive operations,
448              and only applies when the receive buffer  was  posted  with  the
449              FI_MULTI_RECV  flag.   In  this case, buf points to the starting
450              location where the receive data was placed.
451
452       data   The data field is only valid if the FI_REMOTE_CQ_DATA completion
453              flag is set, and only applies to receive completions.  If FI_RE‐
454              MOTE_CQ_DATA is set, this field will contain the completion data
455              provided  by  the  peer  as part of their transmit request.  The
456              completion data will be given in host byte order.
457
458       tag    A tag applies only to received messages  that  occur  using  the
459              tagged interfaces.  This field contains the tag that was includ‐
460              ed with the received message.  The tag will be in host byte  or‐
461              der.
462
463       olen   The  olen field applies to received messages.  It is used to in‐
464              dicate that a received message has overrun the available  buffer
465              space  and has been truncated.  The olen specifies the amount of
466              data that did not fit into the available receive buffer and  was
467              discarded.
468
469       err    This  err code is a positive fabric errno associated with a com‐
470              pletion.  The err value indicates the general reason for an  er‐
471              ror, if one occurred.  See fi_errno.3 for a list of possible er‐
472              ror codes.
473
474       prov_errno
475              On an error, prov_errno may contain a  provider  specific  error
476              code.  The use of this field and its meaning is provider specif‐
477              ic.  It is  intended  to  be  used  as  a  debugging  aid.   See
478              fi_cq_strerror  for  additional details on converting this error
479              value into a human readable string.
480
481       err_data
482              On an error, err_data may reference a provider  specific  amount
483              of data associated with an error.  The use of this field and its
484              meaning is provider specific.  It is intended to be  used  as  a
485              debugging  aid.   See  fi_cq_strerror  for additional details on
486              converting this error data into a human readable string.
487
488       err_data_size
489              On input, err_data_size indicates the size of the err_data  buf‐
490              fer  in bytes.  On output, err_data_size will be set to the num‐
491              ber of bytes copied to the err_data buffer.  The err_data infor‐
492              mation  is typically used with fi_cq_strerror to provide details
493              about the type of error that occurred.
494
495       For compatibility purposes, if err_data_size is 0 on input, or the fab‐
496       ric  was opened with release < 1.5, err_data will be set to a data buf‐
497       fer owned by the provider.  The contents  of  the  buffer  will  remain
498       valid  until  a subsequent read call against the CQ.  Applications must
499       serialize access to the CQ when processing errors to  ensure  that  the
500       buffer referenced by err_data does not change.
501

COMPLETION FLAGS

503       Completion flags provide additional details regarding the completed op‐
504       eration.  The following completion flags are defined.
505
506       FI_SEND
507              Indicates that the completion was for a  send  operation.   This
508              flag may be combined with an FI_MSG or FI_TAGGED flag.
509
510       FI_RECV
511              Indicates that the completion was for a receive operation.  This
512              flag may be combined with an FI_MSG or FI_TAGGED flag.
513
514       FI_RMA Indicates that an RMA operation completed.   This  flag  may  be
515              combined  with  an  FI_READ, FI_WRITE, FI_REMOTE_READ, or FI_RE‐
516              MOTE_WRITE flag.
517
518       FI_ATOMIC
519              Indicates that an atomic operation completed.  This flag may  be
520              combined  with  an  FI_READ, FI_WRITE, FI_REMOTE_READ, or FI_RE‐
521              MOTE_WRITE flag.
522
523       FI_MSG Indicates that a message-based operation completed.   This  flag
524              may be combined with an FI_SEND or FI_RECV flag.
525
526       FI_TAGGED
527              Indicates  that a tagged message operation completed.  This flag
528              may be combined with an FI_SEND or FI_RECV flag.
529
530       FI_MULTICAST
531              Indicates that a multicast operation completed.  This  flag  may
532              be  combined  with FI_MSG and relevant flags.  This flag is only
533              guaranteed to be valid for received messages if the endpoint has
534              been configured with FI_SOURCE.
535
536       FI_READ
537              Indicates  that a locally initiated RMA or atomic read operation
538              has completed.  This flag may be  combined  with  an  FI_RMA  or
539              FI_ATOMIC flag.
540
541       FI_WRITE
542              Indicates that a locally initiated RMA or atomic write operation
543              has completed.  This flag may be  combined  with  an  FI_RMA  or
544              FI_ATOMIC flag.
545
546       FI_REMOTE_READ
547              Indicates that a remotely initiated RMA or atomic read operation
548              has completed.  This flag may be  combined  with  an  FI_RMA  or
549              FI_ATOMIC flag.
550
551       FI_REMOTE_WRITE
552              Indicates  that  a remotely initiated RMA or atomic write opera‐
553              tion has completed.  This flag may be combined with an FI_RMA or
554              FI_ATOMIC flag.
555
556       FI_REMOTE_CQ_DATA
557              This  indicates  that remote CQ data is available as part of the
558              completion.
559
560       FI_MULTI_RECV
561              This flag applies to receive buffers that were posted  with  the
562              FI_MULTI_RECV flag set.  This completion flag indicates that the
563              original receive buffer referenced by the  completion  has  been
564              consumed  and  was  released by the provider.  Providers may set
565              this flag on the last message that is received into  the  multi-
566              recv  buffer,  or  may generate a separate completion that indi‐
567              cates that the buffer has been released.
568
569       Applications can distinguish between these two cases by  examining  the
570       completion  entry  flags  field.  If additional flags, such as FI_RECV,
571       are set, the completion is associated with a received message.  In this
572       case, the buf field will reference the location where the received mes‐
573       sage was placed into the multi-recv buffer.  Other fields in  the  com‐
574       pletion  entry  will  be  determined based on the received message.  If
575       other flag bits are zero, the provider is reporting that the multi-recv
576       buffer  has  been  released, and the completion entry is not associated
577       with a received message.
578
579       FI_MORE
580              See the 'Buffered Receives' section in fi_msg(3)  for  more  de‐
581              tails.  This flag is associated with receive completions on end‐
582              points that have FI_BUFFERED_RECV mode  enabled.   When  set  to
583              one,  it  indicates that the buffer referenced by the completion
584              is limited by the FI_OPT_BUFFERED_LIMIT threshold, and addition‐
585              al  message  data  must be retrieved by the application using an
586              FI_CLAIM operation.
587
588       FI_CLAIM
589              See the 'Buffered Receives' section in fi_msg(3)  for  more  de‐
590              tails.   This flag is set on completions associated with receive
591              operations that claim buffered receive  data.   Note  that  this
592              flag   only   applies   to   endpoints   configured   with   the
593              FI_BUFFERED_RECV mode bit.
594

COMPLETION EVENT SEMANTICS

596       Libfabric defines several completion 'levels', identified using  opera‐
597       tional  flags.  Each flag indicates the soonest that a completion event
598       may be generated by a provider, and the assumptions that an application
599       may  make  upon processing a completion.  The operational flags are de‐
600       fined below, along with an example of how a  provider  might  implement
601       the  semantic.   Note that only meeting the semantic is required of the
602       provider and not the implementation.  Providers may implement  stronger
603       completion semantics than necessary for a given operation, but only the
604       behavior defined by the completion level is guaranteed.
605
606       To help understand the conceptual  differences  in  completion  levels,
607       consider  mailing  a letter.  Placing the letter into the local mailbox
608       for pick-up is similar to 'inject complete'.  Having the letter  picked
609       up  and dropped off at the destination mailbox is equivalent to 'trans‐
610       mit complete'.  The 'delivery complete' semantic is a stronger  guaran‐
611       tee, with a person at the destination signing for the letter.  However,
612       the person who signed for the letter is not  necessarily  the  intended
613       recipient.   The  'match  complete'  option is similar to delivery com‐
614       plete, but requires the intended recipient to sign for the letter.
615
616       The 'commit complete' level has different semantics than the previously
617       mentioned  levels.   Commit  complete would be closer to the the letter
618       arriving at the destination and being placed into a fire proof safe.
619
620       The operational flags for the described completion levels  are  defined
621       below.
622
623       FI_INJECT_COMPLETE
624              Indicates  that a completion should be generated when the source
625              buffer(s) may be reused.  A completion guarantees that the  buf‐
626              fers will not be read from again and the application may reclaim
627              them.  No other guarantees are made with respect to the state of
628              the operation.
629
630       Example:  A  provider  may generate this completion event after copying
631       the source buffer into a network buffer, either in host  memory  or  on
632       the NIC.  An inject completion does not indicate that the data has been
633       transmitted onto the network, and a local error could occur  after  the
634       completion  event  has  been generated that could prevent it from being
635       transmitted.
636
637       Inject complete allows  for  the  fastest  completion  reporting  (and,
638       hence,  buffer reuse), but provides the weakest guarantees against net‐
639       work errors.
640
641       Note: This flag is used to control when a completion entry is  inserted
642       into  a  completion queue.  It does not apply to operations that do not
643       generate a completion queue entry, such as the fi_inject operation, and
644       is not subject to the inject_size message limit restriction.
645
646       FI_TRANSMIT_COMPLETE
647              Indicates  that a completion should be generated when the trans‐
648              mit operation has completed relative to the local provider.  The
649              exact behavior is dependent on the endpoint type.
650
651       For reliable endpoints:
652
653       Indicates  that a completion should be generated when the operation has
654       been delivered to the peer endpoint.  A completion guarantees that  the
655       operation is no longer dependent on the fabric or local resources.  The
656       state of the operation at the peer endpoint is not defined.
657
658       Example: A provider may generate a transmit complete event upon receiv‐
659       ing  an  ack  from  the peer endpoint.  The state of the message at the
660       peer is unknown and may be buffered in the target NIC at the  time  the
661       ack has been generated.
662
663       For unreliable endpoints:
664
665       Indicates  that a completion should be generated when the operation has
666       been delivered to the fabric.  A completion guarantees that the  opera‐
667       tion is no longer dependent on local resources.  The state of the oper‐
668       ation within the fabric is not defined.
669
670       FI_DELIVERY_COMPLETE
671              Indicates that a completion should not be generated until an op‐
672              eration  has  been  processed by the destination endpoint(s).  A
673              completion guarantees that the result of the operation is avail‐
674              able; however, additional steps may need to be taken at the des‐
675              tination to retrieve the results.  For example,  an  application
676              may  need to provide a receive buffers in order to retrieve mes‐
677              sages that were buffered by the provider.
678
679       Delivery complete indicates that the message has been processed by  the
680       peer.  If an application buffer was ready to receive the results of the
681       message when it arrived, then delivery complete indicates that the data
682       was placed into the application's buffer.
683
684       This  completion  mode  applies only to reliable endpoints.  For opera‐
685       tions that return data to the initiator, such  as  RMA  read  or  atom‐
686       ic-fetch,  the  source  endpoint  is also considered a destination end‐
687       point.  This is the default completion mode for such operations.
688
689       FI_MATCH_COMPLETE
690              Indicates that a completion should be generated only  after  the
691              operation has been matched with an application specified buffer.
692              Operations using this completion semantic are dependent  on  the
693              application at the target claiming the message or results.  As a
694              result, match complete may involve additional provider level ac‐
695              knowledgements or lengthy delays.  However, this completion mod‐
696              el enables peer applications to synchronize their execution.
697
698       FI_COMMIT_COMPLETE
699              Indicates that a completion should not be generated (locally  or
700              at  the  peer)  until  the result of an operation have been made
701              persistent.  A completion guarantees that  the  result  is  both
702              available and durable, in the case of power failure.
703
704       This  completion mode applies only to operations that target persistent
705       memory regions over reliable endpoints.  This completion mode is exper‐
706       imental.
707

NOTES

709       A  completion  queue must be bound to at least one enabled endpoint be‐
710       fore any operation such  as  fi_cq_read,  fi_cq_readfrom,  fi_cq_sread,
711       fi_cq_sreadfrom etc.  can be called on it.
712
713       Completion flags may be suppressed if the FI_NOTIFY_FLAGS_ONLY mode bit
714       has been set.  When enabled, only the following flags are guaranteed to
715       be  set  in  completion  data  when  they are valid: FI_REMOTE_READ and
716       FI_REMOTE_WRITE (when FI_RMA_EVENT capability bit has been set), FI_RE‐
717       MOTE_CQ_DATA, and FI_MULTI_RECV.
718
719       If  a  completion  queue  has  been  overrun, it will be placed into an
720       'overrun' state.  Read operations will continue to  return  any  valid,
721       non-corrupted  completions,  if available.  After all valid completions
722       have been retrieved, any attempt to read the CQ will result in  it  re‐
723       turning an FI_EOVERRUN error event.  Overrun completion queues are con‐
724       sidered fatal and may not be used to report additional completions once
725       the overrun occurs.
726

RETURN VALUES

728       fi_cq_open / fi_cq_signal
729              Returns  0 on success.  On error, a negative value corresponding
730              to fabric errno is returned.
731
732       fi_cq_read / fi_cq_readfrom / fi_cq_readerr fi_cq_sread /  fi_cq_sread‐
733       from  :  On  success, returns the number of completion events retrieved
734       from the completion queue.  On error, a negative value corresponding to
735       fabric  errno  is  returned.  If no completions are available to return
736       from the CQ, -FI_EAGAIN will be returned.
737
738       fi_cq_strerror
739              Returns a character string interpretation of the  provider  spe‐
740              cific error returned with a completion.
741
742       Fabric errno values are defined in rdma/fi_errno.h.
743

SEE ALSO

745       fi_getinfo(3),   fi_endpoint(3),  fi_domain(3),  fi_eq(3),  fi_cntr(3),
746       fi_poll(3)
747

AUTHORS

749       OpenFabrics.
750
751
752
753Libfabric Programmer's Manual     2018-11-28                          fi_cq(3)
Impressum