Связь между клиентом и сервером неустойчива

Я модифицировал thegeekinthecorner примеры, чтобы иметь возможность непрерывно отправлять данные.
Я использую g ++ 4.9.2.

Я попытался удалить официальную последнюю версию OFED отсюда http://downloads.openfabrics.org/OFED/

OFED Distribution Software Installation Menu

1) View OFED Installation Guide
2) Install OFED Software
3) Show Installed Software
4) Configure IPoIB
5) Uninstall OFED Software

Q) Exit

Select Option [1-5]:5

Uninstalling the previous version of OFED
Running rpm -e --allmatches libibverbs libibverbs-devel libibverbs-utils libmthca libmlx4 libcxgb3 libnes libipathverbs libibcm libibumad libibumad-devel libibmad ibacm librdmacm librdmacm-utils librdmacm-devel opensm opensm-libs dapl perftest mstflint ibutils infiniband-diags qperf infinipath-psm opensm opensm-libs libipathverbs dapl libibcm libibmad libibumad libibumad-devel libibverbs libibverbs-devel libibverbs-utils libipathverbs libmthca libmlx4 librdmacm librdmacm-devel librdmacm-utils ibacm ibutils ibutils-libs libnes infinipath-psm
Failed to uninstall the previous installation
See /tmp/OFED.22320.logs/ofed_uninstall.log
[idf@node1 OFED-1.5.4-20110726-0732]$
[idf@node1 OFED-1.5.4-20110726-0732]$

Если вместо этого я просто пытаюсь установить его, я получаю это:

OFED Distribution Software Installation Menu

1) Basic (OFED modules and basic user level libraries)
2) HPC (OFED modules and libraries, MPI and diagnostic tools)
3) All packages (all of Basic, HPC)
4) Customize

Q) Exit

Select Option [1-4]:3

Please choose an implementation of MVAPICH2:

1) OFA (IB and iWARP)
2) uDAPL
Implementation [1]: 1

Enable ROMIO support [Y/n]:

Enable shared library support [Y/n]:

Enable Checkpoint-Restart support [y/N]:
Kernel 3.10.0-229.7.2.el7.x86_64 is not supported.
For the list of Supported Platforms and Operating Systems see
/mnt/gluster/Downloads/OFED-1.5.4-20110726-0732/docs/OFED_release_notes.txt
[idf@node1 OFED-1.5.4-20110726-0732]$

[idf@node2 Release]$ lspci | grep -i mel
02:00.0 InfiniBand: Mellanox Technologies MT26428 [ConnectX VPI PCIe 2.0 5GT/s - IB QDR / 10GigE] (rev b0)
[idf@node2 Release]$[idf@node1 Release]$ ibv_devinfo
hca_id: mlx4_0
transport:          InfiniBand (0)
fw_ver:             2.7.200
node_guid:          0025:90ff:ff1a:081c
sys_image_guid:         0025:90ff:ff1a:081f
vendor_id:          0x02c9
vendor_part_id:         26428
hw_ver:             0xB0
board_id:           SM_2092000001000
phys_port_cnt:          1
port:   1
state:          PORT_ACTIVE (4)
max_mtu:        4096 (5)
active_mtu:     4096 (5)
sm_lid:         1
port_lid:       2
port_lmc:       0x00
link_layer:     InfiniBand

[idf@node1 Release]$ ifconfig -a

ib0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 2044
inet 192.168.0.1  netmask 255.255.255.0  broadcast 192.168.0.255
inet6 fe80::225:90ff:ff1a:71  prefixlen 64  scopeid 0x20<link>
Infiniband hardware address can be incorrect! Please read BUGS section in ifconfig(8).
infiniband 80:00:00:48:FE:80:00:00:00:00:00:00:00:00:00:00:00:00:00:00  txqueuelen 256  (InfiniBand)
RX packets 5  bytes 280 (280.0 B)
RX errors 0  dropped 0  overruns 0  frame 0
TX packets 0  bytes 0 (0.0 B)
TX errors 0  dropped 27 overruns 0  carrier 0  collisions 0

Ниже клиент и сервер. Когда я запускаю эту программу, клиенты будут отправлять сообщения, но количество отправляемых сообщений ошибочно, сообщения об ошибках часто

Клиент:

#include <iostream>
#include <thread>

#include <netdb.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <rdma/rdma_cma.h>

#define TEST_NZ(x) do { if ( (x)) die("error: " #x " failed (returned non-zero)." ); } while (0)
#define TEST_Z(x)  do { if (!(x)) die("error: " #x " failed (returned zero/null)."); } while (0)

const int BUFFER_SIZE = 2048;
const int TIMEOUT_IN_MS = 500; /* ms */

struct context
{
struct ibv_context *ctx;
struct ibv_pd *pd;
struct ibv_cq *cq;
struct ibv_comp_channel *comp_channel;

pthread_t cq_poller_thread;
};

struct connection
{
struct rdma_cm_id *id;
struct ibv_qp *qp;

struct ibv_mr *recv_mr;
struct ibv_mr *send_mr;

char *recv_region;
char *send_region;

int num_completions;
};

static pthread_t msgThread;

static void die(const char *reason);

static void build_context(struct ibv_context *verbs);
static void build_qp_attr(struct ibv_qp_init_attr *qp_attr);
static void * poll_cq(void *);
static void post_receives(struct connection *conn);
static void register_memory(struct connection *conn);

static int on_addr_resolved(struct rdma_cm_id *id);
static void on_completion(struct ibv_wc *wc);
static int on_connection(void *context);
static int on_disconnect(struct rdma_cm_id *id);
static int on_event(struct rdma_cm_event *event);
static int on_route_resolved(struct rdma_cm_id *id);

static struct context *s_ctx = NULL;

#include <mutex>              // std::mutex, std::unique_lock
#include <condition_variable> // std::condition_variable

std::mutex mtx;
std::condition_variable cv;

bool ok_to_send_next_message = 1;
bool message_available()
{
return 0 != ok_to_send_next_message;
}

int main(int argc, char **argv)
{
struct addrinfo *addr;
struct rdma_cm_event *event = NULL;
struct rdma_cm_id *conn= NULL;
struct rdma_event_channel *ec = NULL;

if (argc != 3)
die("usage: client <server-address> <server-port>");

TEST_NZ(getaddrinfo(argv[1], argv[2], NULL, &addr));

TEST_Z(ec = rdma_create_event_channel());
TEST_NZ(rdma_create_id(ec, &conn, NULL, RDMA_PS_TCP));
TEST_NZ(rdma_resolve_addr(conn, NULL, addr->ai_addr, TIMEOUT_IN_MS));

freeaddrinfo(addr);

while (0 == rdma_get_cm_event(ec, &event))
//while (rdma_get_cm_event(ec, &event))
{
std::cout << "rdma_get_cm_event\n";

struct rdma_cm_event event_copy;

memcpy(&event_copy, event, sizeof(*event));
rdma_ack_cm_event(event);

if (on_event(&event_copy))
break;
}

rdma_destroy_event_channel(ec);

return 0;
}

void die(const char *reason)
{
fprintf(stderr, "%s\n", reason);
exit(EXIT_FAILURE);
}

void build_context(struct ibv_context *verbs)
{
if (s_ctx)
{
if (s_ctx->ctx != verbs)
die("cannot handle events in more than one context.");

return;
}

s_ctx = (struct context *)malloc(sizeof(struct context));

s_ctx->ctx = verbs;

TEST_Z(s_ctx->pd = ibv_alloc_pd(s_ctx->ctx));
TEST_Z(s_ctx->comp_channel = ibv_create_comp_channel(s_ctx->ctx));
TEST_Z(s_ctx->cq = ibv_create_cq(s_ctx->ctx, 100, NULL, s_ctx->comp_channel, 0)); /* cqe=10 is arbitrary */
TEST_NZ(ibv_req_notify_cq(s_ctx->cq, 0));

TEST_NZ(pthread_create(&s_ctx->cq_poller_thread, NULL, poll_cq, NULL));
}

void *SendMessages(void *context)
{
static int loopcount = 0;
while(1)
{
std::unique_lock<std::mutex> lck(mtx);
cv.wait(lck, message_available);
//std::this_thread::sleep_for(std::chrono::microseconds(50));

ok_to_send_next_message = 0;

struct connection *conn = (struct connection *)context;
struct ibv_send_wr wr, *bad_wr = NULL;
struct ibv_sge sge;

std::cout << "looping send..." << loopcount << '\n' << std::flush;

memset(&wr, 0, sizeof(wr));

wr.wr_id = (uintptr_t)conn;
wr.opcode = IBV_WR_SEND;
wr.sg_list = &sge;
wr.num_sge = 1;
wr.send_flags = IBV_SEND_SIGNALED;

sge.addr = (uintptr_t)conn->send_region;
sge.length = BUFFER_SIZE;
sge.lkey = conn->send_mr->lkey;

snprintf(conn->send_region, BUFFER_SIZE, "message from active/client side with count %d", loopcount++);
TEST_NZ(ibv_post_send(conn->qp, &wr, &bad_wr));
}
}

void build_qp_attr(struct ibv_qp_init_attr *qp_attr)
{
std::cout << "build_qp_attr\n";

memset(qp_attr, 0, sizeof(*qp_attr));

qp_attr->send_cq = s_ctx->cq;
qp_attr->recv_cq = s_ctx->cq;
qp_attr->qp_type = IBV_QPT_RC;

qp_attr->cap.max_send_wr = 100;
qp_attr->cap.max_recv_wr = 100;
qp_attr->cap.max_send_sge = 1;
qp_attr->cap.max_recv_sge = 1;
}

void * poll_cq(void *ctx)
{
struct ibv_cq *cq;
struct ibv_wc wc;

while (1)
{
TEST_NZ(ibv_get_cq_event(s_ctx->comp_channel, &cq, &ctx));
ibv_ack_cq_events(cq, 1);
TEST_NZ(ibv_req_notify_cq(cq, 0));

int ne;
struct ibv_wc wc;

do
{
std::cout << "polling\n";
ne = ibv_poll_cq(cq, 1, &wc);
}
while(ne == 0);

on_completion(&wc);

//if (wc.opcode == IBV_WC_SEND)
if (wc.status == IBV_WC_SUCCESS)
{
{
ok_to_send_next_message = 1;
//while (message_available()) std::this_thread::yield();
//std::cout << "past yield\n";
std::unique_lock<std::mutex> lck(mtx);
cv.notify_one();
}
}
}

return NULL;
}

void post_receives(struct connection *conn)
{
std::cout << "post_receives\n";

struct ibv_recv_wr wr, *bad_wr = NULL;
struct ibv_sge sge;

wr.wr_id = (uintptr_t)conn;
wr.next = NULL;
wr.sg_list = &sge;
wr.num_sge = 1;

sge.addr = (uintptr_t)conn->recv_region;
sge.length = BUFFER_SIZE;
sge.lkey = conn->recv_mr->lkey;

TEST_NZ(ibv_post_recv(conn->qp, &wr, &bad_wr));
}

void register_memory(struct connection *conn)
{
std::cout << "register_memory\n";

conn->send_region = (char *)malloc(BUFFER_SIZE);
conn->recv_region = (char *)malloc(BUFFER_SIZE);

TEST_Z(conn->send_mr = ibv_reg_mr(
s_ctx->pd,
conn->send_region,
BUFFER_SIZE,
IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE));

TEST_Z(conn->recv_mr = ibv_reg_mr(
s_ctx->pd,
conn->recv_region,
BUFFER_SIZE,
IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE));
}

int on_addr_resolved(struct rdma_cm_id *id)
{
std::cout << "on_addr_resolved\n";

struct ibv_qp_init_attr qp_attr;
struct connection *conn;

build_context(id->verbs);
build_qp_attr(&qp_attr);

TEST_NZ(rdma_create_qp(id, s_ctx->pd, &qp_attr));

id->context = conn = (struct connection *)malloc(sizeof(struct connection));

conn->id = id;
conn->qp = id->qp;
conn->num_completions = 0;

register_memory(conn);
post_receives(conn);

TEST_NZ(rdma_resolve_route(id, TIMEOUT_IN_MS));

return 0;
}

void on_completion(struct ibv_wc *wc)
{
std::cout << "on_completion\n";

struct connection *conn = (struct connection *)(uintptr_t)wc->wr_id;

if (wc->status != IBV_WC_SUCCESS)
{
//die("\ton_completion: status is not IBV_WC_SUCCESS.");
printf("\ton_completion: status is not IBV_WC_SUCCESS.");
printf("\t it is %d ", wc->status);
}

printf("\n");

if (wc->opcode & IBV_WC_RECV)
printf("\treceived message: %s\n", conn->recv_region);
else if (wc->opcode == IBV_WC_SEND)
printf("\tsend completed successfully.\n");
else
die("\ton_completion: completion isn't a send or a receive.");

if (5 == ++conn->num_completions)
rdma_disconnect(conn->id);
}

int on_connection(void *context)
{
std::cout << "on_connection\n";

TEST_NZ(pthread_create(&msgThread, NULL, SendMessages, context));

return 0;
}

int on_disconnect(struct rdma_cm_id *id)
{
struct connection *conn = (struct connection *)id->context;

printf("disconnected.\n");

rdma_destroy_qp(id);

ibv_dereg_mr(conn->send_mr);
ibv_dereg_mr(conn->recv_mr);

free(conn->send_region);
free(conn->recv_region);

free(conn);

rdma_destroy_id(id);

return 1; /* exit event loop */
}

int on_route_resolved(struct rdma_cm_id *id)
{
struct rdma_conn_param cm_params;

printf("route resolved.\n");

memset(&cm_params, 0, sizeof(cm_params));
TEST_NZ(rdma_connect(id, &cm_params));

return 0;
}

int on_event(struct rdma_cm_event *event)
{
int r = 0;

if (event->event == RDMA_CM_EVENT_ADDR_RESOLVED)
r = on_addr_resolved(event->id);
else if (event->event == RDMA_CM_EVENT_ROUTE_RESOLVED)
r = on_route_resolved(event->id);
else if (event->event == RDMA_CM_EVENT_ESTABLISHED)
r = on_connection(event->id->context);
else if (event->event == RDMA_CM_EVENT_DISCONNECTED)
r = on_disconnect(event->id);
else
die("on_event: unknown event.");

return r;
}

Сервер:

#include <iostream>

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <inttypes.h>

#include <rdma/rdma_cma.h>

#define TEST_NZ(x) do { if ( (x)) die("error: " #x " failed (returned non-zero)." ); } while (0)
#define TEST_Z(x)  do { if (!(x)) die("error: " #x " failed (returned zero/null)."); } while (0)

const int BUFFER_SIZE = 2048;

struct context
{
struct ibv_context *ctx;
struct ibv_pd *pd;
struct ibv_cq *cq;
struct ibv_comp_channel *comp_channel;

pthread_t cq_poller_thread;
};

struct connection
{
struct ibv_qp *qp;

struct ibv_mr *recv_mr;
struct ibv_mr *send_mr;

char *recv_region;
char *send_region;
};

static void die(const char *reason);

static void build_context(struct ibv_context *verbs);
static void build_qp_attr(struct ibv_qp_init_attr *qp_attr);
static void * poll_cq(void *);
static void post_receives(struct connection *conn);
static void register_memory(struct connection *conn);

static void on_completion(struct ibv_wc *wc);
static int on_connect_request(struct rdma_cm_id *id);
static int on_connection(void *context);
static int on_disconnect(struct rdma_cm_id *id);
static int on_event(struct rdma_cm_event *event);

static struct context *s_ctx = NULL;

int main(int argc, char **argv)
{
struct sockaddr_in6 addr;
struct rdma_cm_event *event = NULL;
struct rdma_cm_id *listener = NULL;
struct rdma_event_channel *ec = NULL;
uint16_t port = 0;

memset(&addr, 0, sizeof(addr));
addr.sin6_family = AF_INET6;

TEST_Z(ec = rdma_create_event_channel());
TEST_NZ(rdma_create_id(ec, &listener, NULL, RDMA_PS_TCP));
TEST_NZ(rdma_bind_addr(listener, (struct sockaddr *)&addr));
TEST_NZ(rdma_listen(listener, 100)); /* backlog=10 is arbitrary */

//printf("[ %"PRIu32" ]\n", *addr.sin6_addr.s6_addr32);

port = ntohs(rdma_get_src_port(listener));

printf("listening on port %d.\n", port);

while (rdma_get_cm_event(ec, &event) == 0)
{
struct rdma_cm_event event_copy;

memcpy(&event_copy, event, sizeof(*event));
rdma_ack_cm_event(event);

if (on_event(&event_copy))
break;
}

rdma_destroy_id(listener);
rdma_destroy_event_channel(ec);

return 0;
}

void die(const char *reason)
{
fprintf(stderr, "%s\n", reason);
exit(EXIT_FAILURE);
}

void build_context(struct ibv_context *verbs)
{
if (s_ctx)
{
if (s_ctx->ctx != verbs)
die("cannot handle events in more than one context.");

return;
}

s_ctx = (struct context *)malloc(sizeof(struct context));

s_ctx->ctx = verbs;

TEST_Z(s_ctx->pd = ibv_alloc_pd(s_ctx->ctx));
TEST_Z(s_ctx->comp_channel = ibv_create_comp_channel(s_ctx->ctx));
TEST_Z(s_ctx->cq = ibv_create_cq(s_ctx->ctx, 100, NULL, s_ctx->comp_channel, 0)); /* cqe=10 is arbitrary */
TEST_NZ(ibv_req_notify_cq(s_ctx->cq, 0));

TEST_NZ(pthread_create(&s_ctx->cq_poller_thread, NULL, poll_cq, NULL));
}

void build_qp_attr(struct ibv_qp_init_attr *qp_attr)
{
memset(qp_attr, 0, sizeof(*qp_attr));

qp_attr->send_cq = s_ctx->cq;
qp_attr->recv_cq = s_ctx->cq;
qp_attr->qp_type = IBV_QPT_RC;

qp_attr->cap.max_send_wr = 100;
qp_attr->cap.max_recv_wr = 100;
qp_attr->cap.max_send_sge = 1;
qp_attr->cap.max_recv_sge = 1;
}

void * poll_cq(void *ctx)
{
struct ibv_cq *cq;
struct ibv_wc wc;

while (1)
{
TEST_NZ(ibv_get_cq_event(s_ctx->comp_channel, &cq, &ctx));
ibv_ack_cq_events(cq, 1);
TEST_NZ(ibv_req_notify_cq(cq, 0));

while (ibv_poll_cq(cq, 1, &wc))
{
std::cout << "polling\n";
on_completion(&wc);
}
}

return NULL;
}

void post_receives(struct connection *conn)
{
std::cout << "post_receives\n";

struct ibv_recv_wr wr, *bad_wr = NULL;
struct ibv_sge sge;

wr.wr_id = (uintptr_t)conn;
wr.next = NULL;
wr.sg_list = &sge;
wr.num_sge = 1;

sge.addr = (uintptr_t)conn->recv_region;
sge.length = BUFFER_SIZE;
sge.lkey = conn->recv_mr->lkey;

TEST_NZ(ibv_post_recv(conn->qp, &wr, &bad_wr));
}

void register_memory(struct connection *conn)
{
conn->send_region = (char *)malloc(BUFFER_SIZE);
conn->recv_region = (char *)malloc(BUFFER_SIZE);

TEST_Z(conn->send_mr = ibv_reg_mr(
s_ctx->pd,
conn->send_region,
BUFFER_SIZE,
IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE));

TEST_Z(conn->recv_mr = ibv_reg_mr(
s_ctx->pd,
conn->recv_region,
BUFFER_SIZE,
IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE));
}

void on_completion(struct ibv_wc *wc)
{
if (wc->status != IBV_WC_SUCCESS)
die("on_completion: status is not IBV_WC_SUCCESS.");

if (wc->opcode & IBV_WC_RECV)
{
struct connection *conn = (struct connection *)(uintptr_t)wc->wr_id;
post_receives(conn);
printf("received message: %s\n", conn->recv_region);
}
else if (wc->opcode == IBV_WC_SEND)
{
printf("send completed successfully.\n");
}
}

int on_connect_request(struct rdma_cm_id *id)
{
struct ibv_qp_init_attr qp_attr;
struct rdma_conn_param cm_params;
struct connection *conn;

printf("received connection request.\n");

build_context(id->verbs);
build_qp_attr(&qp_attr);

TEST_NZ(rdma_create_qp(id, s_ctx->pd, &qp_attr));

id->context = conn = (struct connection *)malloc(sizeof(struct connection));
conn->qp = id->qp;

register_memory(conn);
post_receives(conn);

memset(&cm_params, 0, sizeof(cm_params));
TEST_NZ(rdma_accept(id, &cm_params));

return 0;
}

int on_connection(void *context)
{
struct connection *conn = (struct connection *)context;
struct ibv_send_wr wr, *bad_wr = NULL;
struct ibv_sge sge;

snprintf(conn->send_region, BUFFER_SIZE, "message from passive/server side with pid %d", getpid());

printf("connected. posting send...\n");

memset(&wr, 0, sizeof(wr));

wr.opcode = IBV_WR_SEND;
wr.sg_list = &sge;
wr.num_sge = 1;
wr.send_flags = IBV_SEND_SIGNALED;

sge.addr = (uintptr_t)conn->send_region;
sge.length = BUFFER_SIZE;
sge.lkey = conn->send_mr->lkey;

TEST_NZ(ibv_post_send(conn->qp, &wr, &bad_wr));

return 0;
}

int on_disconnect(struct rdma_cm_id *id)
{
struct connection *conn = (struct connection *)id->context;

printf("peer disconnected.\n");

rdma_destroy_qp(id);

ibv_dereg_mr(conn->send_mr);
ibv_dereg_mr(conn->recv_mr);

free(conn->send_region);
free(conn->recv_region);

free(conn);

rdma_destroy_id(id);

return 0;
}

int on_event(struct rdma_cm_event *event)
{
std::cout << "on_event\n";

int r = 0;

if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST)
r = on_connect_request(event->id);
else if (event->event == RDMA_CM_EVENT_ESTABLISHED)
r = on_connection(event->id->context);
else if (event->event == RDMA_CM_EVENT_DISCONNECTED)
r = on_disconnect(event->id);
else
die("on_event: unknown event.");

return r;
}

Вот пара трасс. Полностью случайный номер отправленного сообщения:

[idf@node1 Release]$ ./TGKITCClient 192.168.0.1 47819
rdma_get_cm_event
on_addr_resolved
build_qp_attr
register_memory
post_receives
rdma_get_cm_event
route resolved.
rdma_get_cm_event
on_connection
looping send...0
polling
on_completion
received message: message from passive/server side with pid 4188

polling
on_completion
send completed successfully.

looping send...1
polling
on_completion
send completed successfully.

^C
[idf@node1 Release]$

А потом

[idf@node1 Release]$ ./TGKITCClient 192.168.0.1 55148
rdma_get_cm_event
on_addr_resolved
build_qp_attr
register_memory
post_receives
rdma_get_cm_event
route resolved.
rdma_get_cm_event
on_connection
looping send...0
polling
on_completion
received message: message from passive/server side with pid 4279

polling
on_completion
send completed successfully.

looping send...1
polling
on_completion
send completed successfully.

looping send...2
polling
on_completion
send completed successfully.

looping send...3
polling
on_completion
send completed successfully.

looping send...4
polling
on_completion
send completed successfully.

looping send...5
polling
on_completion
send completed successfully.

looping send...6
polling
on_completion
send completed successfully.

looping send...7
polling
on_completion
send completed successfully.

looping send...8
rdma_get_cm_event
disconnected.
polling
on_completion
send completed successfully.

on_completion: status is not IBV_WC_SUCCESS.     it is 5 [idf@node1 Release]$

Вот сторона сервера:

on_event
peer disconnected.
on_event
received connection request.
post_receives
on_event
connected. posting send...
polling
send completed successfully.
polling
post_receives
received message: message from active/client side with count 0
polling
post_receives
received message: message from active/client side with count 1
polling
post_receives
received message: message from active/client side with count 2
polling
post_receives
received message: message from active/client side with count 3
polling
post_receives
received message: message from active/client side with count 4
polling
post_receives
received message: message from active/client side with count 5
polling
post_receives
received message: message from active/client side with count 6
polling
post_receives
received message: message from active/client side with count 7
on_event
peer disconnected.

1

Решение

Убедитесь, что на платах установлены самые последние драйверы и прошивки. Кроме того, использование пакетов RDMA, включенных в большинство дистрибутивов ОС, при попытке запустить IB — опасная игра.

Для таких приложений настоятельно рекомендуется использовать Open Fabrics Enterprise Distribution для предоставления openib, opensm и множества других полезных пакетов, связанных с инфинитами, для аналитической диагностики и настройки сети. Официальные пакеты OFED можно найти на Сайт OpenFabrics.

Исходя из вопроса, похоже, что IPoIB используется, но конкретная конфигурация не упоминается. IPoIB не обязательно лучший способ использовать преимущества аппаратных ресурсов, доступных в платах IB.

В дополнение к этим соображениям убедитесь, что подсеть менеджер настроен и настроен правильно. Некоторые коммутаторы имеют встроенные менеджеры подсетей, доступ к которым можно настроить через интерфейс управления, в других случаях может иметь смысл запускать и настраивать диспетчер подсетей на одном из используемых вами узлов. OpenSM — это обычный диспетчер подсетей, который входит в состав дистрибутивов OFED, и для настройки и настройки диспетчера подсетей доступно множество интерактивных руководств в зависимости от типа настраиваемой сети.

OFED также включает в себя различные инструменты тестирования и профилирования IB. ibdiagnet это полезный инструмент для устранения проблем с сетью IB. В Интернете доступно множество руководств, которые показывают различные способы использования инструмента, а также других инструментов, включенных в OFED.

В зависимости от типа используемого коммутатора IB могут быть дополнительно некоторые инструменты управления сетью и диагностики, которые позволят провести дальнейший анализ сети. Конфигурация оборудования IB и низкоуровневого программного обеспечения, которое управляет им, иногда более критична для общей производительности, чем фактический выполняемый код. Но с учетом вышесказанного, может быть целесообразно перекомпилировать и связать с соответствующими библиотеками из правильной версии OFED, если будут сделаны значительные изменения в конфигурации программного обеспечения.

0

Другие решения


По вопросам рекламы [email protected]