oob_tcp_msg.c

MPI stands for the Message Passing Interface. Written by the MPI Forum (a large committee comprising

/* 
 * Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
 *                         University Research and Technology
 *                         Corporation.  All rights reserved.
 * Copyright (c) 2004-2005 The University of Tennessee and The University
 *                         of Tennessee Research Foundation.  All rights
 *                         reserved.
 * Copyright (c) 2004-2005 High Performance Computing Center Stuttgart, 
 *                         University of Stuttgart.  All rights reserved.
 * Copyright (c) 2004-2005 The Regents of the University of California.
 *                         All rights reserved.
 * Copyright (c) 2006-2007 Los Alamos National Security, LLC. 
 *                         All rights reserved.
 * $COPYRIGHT$
 * 
 * Additional copyrights may follow
 * 
 * $HEADER$
 *
 * In windows, many of the socket functions return an EWOULDBLOCK
 * instead of \ things like EAGAIN, EINPROGRESS, etc. It has been
 * verified that this will \ not conflict with other error codes that
 * are returned by these functions \ under UNIX/Linux environments 
 */

#include "orte_config.h"
#include "opal/opal_socket_errno.h"

#include "orte/class/orte_proc_table.h"
#include "orte/orte_constants.h"
#include "orte/mca/ns/ns.h"
#include "orte/mca/oob/tcp/oob_tcp.h"
#include "orte/mca/oob/tcp/oob_tcp_msg.h"


static void mca_oob_tcp_msg_construct(mca_oob_tcp_msg_t*);
static void mca_oob_tcp_msg_destruct(mca_oob_tcp_msg_t*);
static void mca_oob_tcp_msg_ident(mca_oob_tcp_msg_t* msg, mca_oob_tcp_peer_t* peer);
static bool mca_oob_tcp_msg_recv(mca_oob_tcp_msg_t* msg, mca_oob_tcp_peer_t* peer);
static void mca_oob_tcp_msg_data(mca_oob_tcp_msg_t* msg, mca_oob_tcp_peer_t* peer);
static void mca_oob_tcp_msg_ping(mca_oob_tcp_msg_t* msg, mca_oob_tcp_peer_t* peer);


OBJ_CLASS_INSTANCE(
    mca_oob_tcp_msg_t,
    opal_list_item_t,
    mca_oob_tcp_msg_construct,
    mca_oob_tcp_msg_destruct);


static void mca_oob_tcp_msg_construct(mca_oob_tcp_msg_t* msg)
{
    OBJ_CONSTRUCT(&msg->msg_lock, opal_mutex_t);
    OBJ_CONSTRUCT(&msg->msg_condition, opal_condition_t);
}


static void mca_oob_tcp_msg_destruct(mca_oob_tcp_msg_t* msg)
{
    OBJ_DESTRUCT(&msg->msg_lock);
    OBJ_DESTRUCT(&msg->msg_condition);
}


/*
 *  Wait for a msg to complete.
 *  @param  msg (IN)   Message to wait on.
 *  @param  rc (OUT)   Return code (number of bytes read on success or error code on failure).
 *  @retval ORTE_SUCCESS or error code on failure.
 */

int mca_oob_tcp_msg_wait(mca_oob_tcp_msg_t* msg, int* rc)
{
#if OMPI_ENABLE_PROGRESS_THREADS
    OPAL_THREAD_LOCK(&msg->msg_lock);
    while(msg->msg_complete == false) {
        if(opal_event_progress_thread()) {
            int rc;
            OPAL_THREAD_UNLOCK(&msg->msg_lock);
            rc = opal_event_loop(OPAL_EVLOOP_ONCE);
            assert(rc >= 0);
            OPAL_THREAD_LOCK(&msg->msg_lock);
        } else {
           opal_condition_wait(&msg->msg_condition, &msg->msg_lock);
        }
    }
    OPAL_THREAD_UNLOCK(&msg->msg_lock);

#else
    /* wait for message to complete */
    while(msg->msg_complete == false) {
        /* msg_wait() is used in the "barrier" at the completion of
           MPI_FINALIZE, during which time BTLs may still need to
           progress pending outgoing communication, so we need to
           call opal_progress() here to make sure that communication
           gets pushed out so others can enter finalize (and send us
           the message we're here waiting for).  However, if we're
           in a callback from the event library that was triggered
           from a call to opal_progress(), opal_progress() will
           think another thread is already progressing the event
           engine (in the case of mpi threads enabled) and not
           progress the engine, meaning we'll never receive our
           message.  So we also need to progress the event library
           expicitly.  We use EVLOOP_NONBLOCK so that we can
           progress both the registered callbacks and the event
           library, as EVLOOP_ONCE may block for a short period of
           time. */
        opal_progress();
        opal_event_loop(OPAL_EVLOOP_NONBLOCK);
    }
#endif

    /* return status */
    if(NULL != rc) {
        *rc = msg->msg_rc;
    }
    return ORTE_SUCCESS;
}

/*
 *  Wait up to a timeout for the message to complete.
 *  @param  msg (IN)   Message to wait on.
 *  @param  rc (OUT)   Return code (number of bytes read on success or error code on failure).
 *  @retval ORTE_SUCCESS or error code on failure.
 */

int mca_oob_tcp_msg_timedwait(mca_oob_tcp_msg_t* msg, int* rc, struct timespec* abstime)
{
    struct timeval tv;
    uint32_t secs = abstime->tv_sec;
    uint32_t usecs = abstime->tv_nsec * 1000;
    gettimeofday(&tv,NULL);

#if OMPI_ENABLE_PROGRESS_THREADS
    OPAL_THREAD_LOCK(&msg->msg_lock);
    while(msg->msg_complete == false && 
          ((uint32_t)tv.tv_sec <= secs ||
	   ((uint32_t)tv.tv_sec == secs && (uint32_t)tv.tv_usec < usecs))) {
        if(opal_event_progress_thread()) {
            int rc;
            OPAL_THREAD_UNLOCK(&msg->msg_lock);
            rc = opal_event_loop(OPAL_EVLOOP_ONCE);
            assert(rc >= 0);
            OPAL_THREAD_LOCK(&msg->msg_lock);
        } else {
           opal_condition_timedwait(&msg->msg_condition, &msg->msg_lock, abstime);
        }
        gettimeofday(&tv,NULL);
    }
    OPAL_THREAD_UNLOCK(&msg->msg_lock);
#else
    /* wait for message to complete */
    while(msg->msg_complete == false &&
          ((uint32_t)tv.tv_sec <= secs ||
	   ((uint32_t)tv.tv_sec == secs && (uint32_t)tv.tv_usec < usecs))) {
        /* see comment in tcp_msg_wait, above */
        opal_progress();
        opal_event_loop(OPAL_EVLOOP_NONBLOCK);
        gettimeofday(&tv,NULL);
    }
#endif

    /* return status */
    if(NULL != rc) {
        *rc = msg->msg_rc;
    }
    if(msg->msg_rc < 0)
        return msg->msg_rc;
    return (msg->msg_complete ? ORTE_SUCCESS : ORTE_ERR_TIMEOUT);
}

/*
 *  Signal that a message has completed.
 *  @param  msg (IN)   Message to wait on.
 *  @param peer (IN) the peer of the message
 *  @retval ORTE_SUCCESS or error code on failure.
 */
int mca_oob_tcp_msg_complete(mca_oob_tcp_msg_t* msg, orte_process_name_t * peer)
{
    OPAL_THREAD_LOCK(&msg->msg_lock);
    msg->msg_complete = true;
    if(NULL != msg->msg_cbfunc) {
        opal_list_item_t* item;
        OPAL_THREAD_UNLOCK(&msg->msg_lock);

        /* post to a global list of completed messages */
        OPAL_THREAD_LOCK(&mca_oob_tcp_component.tcp_lock);
        opal_list_append(&mca_oob_tcp_component.tcp_msg_completed, (opal_list_item_t*)msg);
        if(opal_list_get_size(&mca_oob_tcp_component.tcp_msg_completed) > 1) {
            OPAL_THREAD_UNLOCK(&mca_oob_tcp_component.tcp_lock);
            return ORTE_SUCCESS;
        }
        OPAL_THREAD_UNLOCK(&mca_oob_tcp_component.tcp_lock);

        /* invoke message callback */
        msg->msg_cbfunc(msg->msg_rc, peer, msg->msg_uiov, msg->msg_ucnt, msg->msg_hdr.msg_tag, msg->msg_cbdata);

        /* dispatch any completed events */
        OPAL_THREAD_LOCK(&mca_oob_tcp_component.tcp_lock);
        opal_list_remove_item(&mca_oob_tcp_component.tcp_msg_completed, (opal_list_item_t*)msg);
        MCA_OOB_TCP_MSG_RETURN(msg);
        while(NULL != 
            (item = opal_list_remove_first(&mca_oob_tcp_component.tcp_msg_completed))) {
            msg = (mca_oob_tcp_msg_t*)item;
            OPAL_THREAD_UNLOCK(&mca_oob_tcp_component.tcp_lock);
            msg->msg_cbfunc(
                msg->msg_rc, 
                &msg->msg_peer, 
                msg->msg_uiov, 
                msg->msg_ucnt, 
                msg->msg_hdr.msg_tag, 
                msg->msg_cbdata);
            OPAL_THREAD_LOCK(&mca_oob_tcp_component.tcp_lock);
            MCA_OOB_TCP_MSG_RETURN(msg);
        }
        OPAL_THREAD_UNLOCK(&mca_oob_tcp_component.tcp_lock);

    } else {
        opal_condition_broadcast(&msg->msg_condition);
        OPAL_THREAD_UNLOCK(&msg->msg_lock);
    }
    return ORTE_SUCCESS;
}

/*
 * The function that actually sends the data!
 * @param msg a pointer to the message to send
 * @param peer the peer we are sending to
 * @retval true if the entire message has been sent
 * @retval false if the entire message has not been sent
 */
bool mca_oob_tcp_msg_send_handler(mca_oob_tcp_msg_t* msg, struct mca_oob_tcp_peer_t * peer)
{
    int rc;
    while(1) {
        rc = writev(peer->peer_sd, msg->msg_rwptr, msg->msg_rwnum);
        if(rc < 0) {
            if(opal_socket_errno == EINTR)
                continue;
            /* In windows, many of the socket functions return an EWOULDBLOCK instead of \
               things like EAGAIN, EINPROGRESS, etc. It has been verified that this will \
               not conflict with other error codes that are returned by these functions \
               under UNIX/Linux environments */
            else if (opal_socket_errno == EAGAIN || opal_socket_errno == EWOULDBLOCK)
                return false;
            else {
                opal_output(0, "[%lu,%lu,%lu]-[%lu,%lu,%lu] mca_oob_tcp_msg_send_handler: writev failed: %s (%d)", 
                    ORTE_NAME_ARGS(orte_process_info.my_name), 
                    ORTE_NAME_ARGS(&(peer->peer_name)), 
                    strerror(opal_socket_errno),
                    opal_socket_errno);
                mca_oob_tcp_peer_close(peer);
                msg->msg_rc = ORTE_ERR_CONNECTION_FAILED;
                return true;
            }
        }

        msg->msg_rc += rc;
        do {/* while there is still more iovecs to write */
            if(rc < (int)msg->msg_rwptr->iov_len) {
                msg->msg_rwptr->iov_len -= rc;
                msg->msg_rwptr->iov_base = (ompi_iov_base_ptr_t)((char *) msg->msg_rwptr->iov_base + rc);
                break;
            } else {
                rc -= msg->msg_rwptr->iov_len;
                (msg->msg_rwnum)--;
                (msg->msg_rwptr)++;
                if(0 == msg->msg_rwnum) {
                    return true;
                }
            }
        } while(msg->msg_rwnum);
    }
}

/*
 * Receives message data.
 * @param msg the message to be recieved into
 * @param peer the peer to recieve from
 * @retval true if the whole message was received
 * @retval false if the whole message was not received
 */
bool mca_oob_tcp_msg_recv_handler(mca_oob_tcp_msg_t* msg, struct mca_oob_tcp_peer_t * peer)
{
    /* has entire header been received */
    if(msg->msg_rwptr == msg->msg_rwiov) {
        if(mca_oob_tcp_msg_recv(msg, peer) == false)
            return false;

        /* allocate a buffer for the receive */
        MCA_OOB_TCP_HDR_NTOH(&msg->msg_hdr);
        if(msg->msg_hdr.msg_size > 0) {
             msg->msg_rwbuf = malloc(msg->msg_hdr.msg_size);
             if(NULL == msg->msg_rwbuf) {
                 opal_output(0, "[%lu,%lu,%lu]-[%lu,%lu,%lu] mca_oob_tcp_msg_recv_handler: malloc(%d) failed\n", 
                     ORTE_NAME_ARGS(orte_process_info.my_name),
                     ORTE_NAME_ARGS(&(peer->peer_name)),
                     msg->msg_hdr.msg_size);
                 mca_oob_tcp_peer_close(peer);
                 return false;
             }
             msg->msg_rwiov[1].iov_base = (ompi_iov_base_ptr_t)msg->msg_rwbuf;
             msg->msg_rwiov[1].iov_len = msg->msg_hdr.msg_size;