Files
rocm-systems/src/misc/ipcsocket.cc
T
Sylvain Jeaugey 178b6b7590 2.22.3-1
Rework core for NVIDIA Trusted Computing
 * Compress work structs so that they are shared between channels
 * Utilize the full amount of kernel argument space permitted (4k)
   before resorting to work fifo.
 * Rework the task preprocessing phase.
 * Use a separate abortDevFlag which is kept in sync with abortFlag
   using cudaMemcpy operations.
 * Rename src/include/align.h to src/include/bitops.h

Add lazy connection establishment for collective operations
 * Move buffer allocation and connection establishment to the first
   collective operation using that algorithm.
 * Accelerate init time and reduce memory usage.
 * Avoid allocating NVLS buffers if all calls are registered.
 * Compute algo/proto in ncclLaunchCollTasksInfo early on.
 * Connect peers in ncclCollPreconnectFunc if not connected already.
 * Also move shared buffer creation to the first send/recv call.

Accelerate intra-node NVLink detection
 * Make each rank only detect NVLinks attached to its GPU.
 * Fuse XMLs to reconstruct the full NVLink topology

Add init profiling to report time spend in different init phases.
 * Report timings of bootstrap, allgather, search, connect, etc.
 * Add new "PROFILE" category for NCCL_DEBUG_SUBSYS.

Add support for PCI p2p on split PCI switches
 * Detect split PCI switches through a kernel module exposing
   switch information.
 * Update the topology XML and graph to add those inter-switch
   connections.

Add cost estimation API
 * Add a new ncclGroupEndSimulate primitive to return the estimated
   time a group would take.

Net/IB: Add separate traffic class for fifo messages
 * Add NCCL_IB_FIFO_TC to control the traffic class of fifo messages
   independently from NCCL_IB_TC.
   Merges PR #1194

Net/IB: Add support for IB router
 * Use flid instead of lid if subnets do not match
 * Warn if flid is 0

Optimizations and fixes for device network offload (unpack)
 * Double the default number of channels
 * Cache netDeviceType
 * Fix save/increment head logic to enable Tree support.

Support ncclGroupStart/End for ncclCommAbort/Destroy
 * Allow Abort/Destroy to be called within a group when managing
   multiple GPUs with a single process.

Improve Tuner API
 * Provide to the plugin the original cost table so that the plugin
   can leave unknown or disabled algo/proto combinations untouched.
 * Remove nvlsSupport and collnetSupport.

Do not print version to stdout when using a debug file
 * Also print version from all processes with INFO debug level.
   Fixes issue #1271

Fix clang warnings in NVTX headers
 * Update NVTX headers to the latest version
   Fixes issue #1270

Disable port fusion in heterogeneous systems
 * Do not fuse ports if a mix of multi-port and single port are detected.

Fix NVLS graphs search for dual NICs.
 * Fix NVLS graph search when we have more than one NIC per GPU.

Fix crash with collnetDirect
 * Add separate graph search for collnetDirect, testing alltoall paths
   and working similarly to the NVLS search.

Fix hang when nodes have different CPU types
 * Add the CPU type to the rank peer info.
 * Align all ranks on the CPU type after the first allgather.
 * Only use the aligned CPU type for all tuning operations.
   Fixes issue #1136
   Fixes issue #1184

Fix performance of registered send/recv operations
 * Allow for single full size operations
 * Add INFO to confirm the registration of send/recv buffers.

Move all sync ops to finalize stage
 * Ensure ncclCommDestroy is non-blocking if ncclCommFinalize has
   been called.

Improve error reporting during SHM segment creation

Improve support of various compilers
   Merges PR #1177
   Merges PR #1228

Allow net and tuner plugins to be statically linked
 * Search for ncclNet or ncclTuner symbols in the main binary.
   Merges PR #979

Plugin examples includes cleanup
 * Harmonize err.h and common.h usage.
 * Add mixed plugin with both net and tuner.
2024-06-19 01:57:16 -07:00

233 lines
6.5 KiB
C++

/*
* Copyright (c) 2016-2023, NVIDIA CORPORATION. All rights reserved.
*
* See COPYRIGHT for license information
*/
#include "ipcsocket.h"
#include "utils.h"
#include <stdlib.h>
#include <string.h>
#include <errno.h>
// Enable Linux abstract socket naming
#define USE_ABSTRACT_SOCKET
#define NCCL_IPC_SOCKNAME_STR "/tmp/nccl-socket-%d-%lx"
/*
* Create a Unix Domain Socket
*/
ncclResult_t ncclIpcSocketInit(ncclIpcSocket *handle, int rank, uint64_t hash, volatile uint32_t* abortFlag) {
int fd = -1;
struct sockaddr_un cliaddr;
char temp[NCCL_IPC_SOCKNAME_LEN] = "";
if (handle == NULL) {
return ncclInternalError;
}
handle->fd = -1;
handle->socketName[0] = '\0';
if ((fd = socket(AF_UNIX, SOCK_DGRAM, 0)) < 0) {
WARN("UDS: Socket creation error : %s (%d)", strerror(errno), errno);
return ncclSystemError;
}
bzero(&cliaddr, sizeof(cliaddr));
cliaddr.sun_family = AF_UNIX;
// Create unique name for the socket.
int len = snprintf(temp, NCCL_IPC_SOCKNAME_LEN, NCCL_IPC_SOCKNAME_STR, rank, hash);
if (len > (sizeof(cliaddr.sun_path) - 1)) {
WARN("UDS: Cannot bind provided name to socket. Name too large");
return ncclInternalError;
}
#ifndef USE_ABSTRACT_SOCKET
unlink(temp);
#endif
TRACE(NCCL_INIT, "UDS: Creating socket %s", temp);
strncpy(cliaddr.sun_path, temp, len);
#ifdef USE_ABSTRACT_SOCKET
cliaddr.sun_path[0] = '\0'; // Linux abstract socket trick
#endif
if (bind(fd, (struct sockaddr *)&cliaddr, sizeof(cliaddr)) < 0) {
WARN("UDS: Binding to socket %s failed : %s (%d)", temp, strerror(errno), errno);
close(fd);
return ncclSystemError;
}
handle->fd = fd;
strcpy(handle->socketName, temp);
handle->abortFlag = abortFlag;
// Mark socket as non-blocking
if (handle->abortFlag) {
int flags;
EQCHECK(flags = fcntl(fd, F_GETFL), -1);
SYSCHECK(fcntl(fd, F_SETFL, flags | O_NONBLOCK), "fcntl");
}
return ncclSuccess;
}
ncclResult_t ncclIpcSocketGetFd(struct ncclIpcSocket* handle, int* fd) {
if (handle == NULL) {
WARN("ncclSocketGetFd: pass NULL socket");
return ncclInvalidArgument;
}
if (fd) *fd = handle->fd;
return ncclSuccess;
}
ncclResult_t ncclIpcSocketClose(ncclIpcSocket *handle) {
if (handle == NULL) {
return ncclInternalError;
}
if (handle->fd <= 0) {
return ncclSuccess;
}
#ifndef USE_ABSTRACT_SOCKET
if (handle->socketName[0] != '\0') {
unlink(handle->socketName);
}
#endif
close(handle->fd);
return ncclSuccess;
}
ncclResult_t ncclIpcSocketRecvMsg(ncclIpcSocket *handle, void *hdr, int hdrLen, int *recvFd) {
struct msghdr msg = {0, 0, 0, 0, 0, 0, 0};
struct iovec iov[1];
// Union to guarantee alignment requirements for control array
union {
struct cmsghdr cm;
char control[CMSG_SPACE(sizeof(int))];
} control_un;
struct cmsghdr *cmptr;
char dummy_buffer[1];
int ret;
msg.msg_control = control_un.control;
msg.msg_controllen = sizeof(control_un.control);
if (hdr == NULL) {
iov[0].iov_base = (void *)dummy_buffer;
iov[0].iov_len = sizeof(dummy_buffer);
} else {
iov[0].iov_base = hdr;
iov[0].iov_len = hdrLen;
}
msg.msg_iov = iov;
msg.msg_iovlen = 1;
while ((ret = recvmsg(handle->fd, &msg, 0)) <= 0) {
if (errno != EAGAIN && errno != EWOULDBLOCK && errno != EINTR) {
WARN("UDS: Receiving data over socket failed : %d", errno);
return ncclSystemError;
}
if (handle->abortFlag && __atomic_load_n(handle->abortFlag, __ATOMIC_ACQUIRE)) return ncclInternalError;
}
if (recvFd != NULL) {
if (((cmptr = CMSG_FIRSTHDR(&msg)) != NULL) && (cmptr->cmsg_len == CMSG_LEN(sizeof(int)))) {
if ((cmptr->cmsg_level != SOL_SOCKET) || (cmptr->cmsg_type != SCM_RIGHTS)) {
WARN("UDS: Receiving data over socket failed");
return ncclSystemError;
}
memmove(recvFd, CMSG_DATA(cmptr), sizeof(*recvFd));
} else {
WARN("UDS: Receiving data over socket %s failed", handle->socketName);
return ncclSystemError;
}
TRACE(NCCL_INIT|NCCL_P2P, "UDS: Got recvFd %d from socket %s", *recvFd, handle->socketName);
}
return ncclSuccess;
}
ncclResult_t ncclIpcSocketRecvFd(ncclIpcSocket *handle, int *recvFd) {
return ncclIpcSocketRecvMsg(handle, NULL, 0, recvFd);
}
ncclResult_t ncclIpcSocketSendMsg(ncclIpcSocket *handle, void *hdr, int hdrLen, const int sendFd, int rank, uint64_t hash) {
struct msghdr msg = {0, 0, 0, 0, 0, 0, 0};
struct iovec iov[1];
char temp[NCCL_IPC_SOCKNAME_LEN];
union {
struct cmsghdr cm;
char control[CMSG_SPACE(sizeof(int))];
} control_un;
struct cmsghdr *cmptr;
char dummy_buffer[1];
struct sockaddr_un cliaddr;
// Construct client address to send this shareable handle to
bzero(&cliaddr, sizeof(cliaddr));
cliaddr.sun_family = AF_UNIX;
int len = snprintf(temp, NCCL_IPC_SOCKNAME_LEN, NCCL_IPC_SOCKNAME_STR, rank, hash);
if (len > (sizeof(cliaddr.sun_path) - 1)) {
WARN("UDS: Cannot connect to provided name for socket. Name too large");
return ncclInternalError;
}
(void) strncpy(cliaddr.sun_path, temp, len);
#ifdef USE_ABSTRACT_SOCKET
cliaddr.sun_path[0] = '\0'; // Linux abstract socket trick
#endif
TRACE(NCCL_INIT, "UDS: Sending hdr %p len %d to UDS socket %s", hdr, hdrLen, temp);
if (sendFd != -1) {
TRACE(NCCL_INIT, "UDS: Sending fd %d to UDS socket %s", sendFd, temp);
msg.msg_control = control_un.control;
msg.msg_controllen = sizeof(control_un.control);
cmptr = CMSG_FIRSTHDR(&msg);
cmptr->cmsg_len = CMSG_LEN(sizeof(int));
cmptr->cmsg_level = SOL_SOCKET;
cmptr->cmsg_type = SCM_RIGHTS;
memmove(CMSG_DATA(cmptr), &sendFd, sizeof(sendFd));
}
msg.msg_name = (void *)&cliaddr;
msg.msg_namelen = sizeof(struct sockaddr_un);
if (hdr == NULL) {
iov[0].iov_base = (void *)dummy_buffer;
iov[0].iov_len = sizeof(dummy_buffer);
} else {
iov[0].iov_base = hdr;
iov[0].iov_len = hdrLen;
}
msg.msg_iov = iov;
msg.msg_iovlen = 1;
msg.msg_flags = 0;
ssize_t sendResult;
while ((sendResult = sendmsg(handle->fd, &msg, 0)) < 0) {
if (errno != EAGAIN && errno != EWOULDBLOCK && errno != EINTR) {
WARN("UDS: Sending data over socket %s failed : %s (%d)", temp, strerror(errno), errno);
return ncclSystemError;
}
if (handle->abortFlag && __atomic_load_n(handle->abortFlag, __ATOMIC_ACQUIRE)) return ncclInternalError;
}
return ncclSuccess;
}
ncclResult_t ncclIpcSocketSendFd(ncclIpcSocket *handle, const int sendFd, int rank, uint64_t hash) {
return ncclIpcSocketSendMsg(handle, NULL, 0, sendFd, rank, hash);
}