static void * clientThread (void *arg) { client_t *c = (client_t *) arg; fd_set rfds, wfds; int ret; c->querybuf = sdsMakeRoomFor (sdsempty (), DEFAULT_QUERY_BUF_SIZE); c->replybuf = sdsMakeRoomFor (sdsempty (), DEFAULT_QUERY_BUF_SIZE); c->argc = 0; c->argv = NULL; c->argvlen = NULL; c->reqtype = 0; c->multibulklen = 0; c->bulklen = -1; c->rqst = arc_create_request (); c->flags = 0; c->total_append_command = 0; FD_ZERO (&rfds); FD_ZERO (&wfds); while (1) { struct timeval timeout; FD_CLR (c->fd, &rfds); FD_CLR (c->fd, &wfds); if (!(c->flags & REDIS_CLOSE_AFTER_REPLY)) FD_SET (c->fd, &rfds); if (sdslen (c->replybuf) > 0) FD_SET (c->fd, &wfds); timeout.tv_sec = 1; timeout.tv_usec = 0; ret = select (c->fd + 1, &rfds, &wfds, NULL, &timeout); if (ret == -1) { perror ("select"); freeClient (c); } if (server.shutdown_signal) { c->flags |= REDIS_CLOSE_AFTER_REPLY; } /* readable */ if (FD_ISSET (c->fd, &rfds)) { int pos = sdslen (c->querybuf); int avail = sdsavail (c->querybuf); ssize_t nread; if (avail == 0) { c->querybuf = sdsMakeRoomFor (c->querybuf, sdslen (c->querybuf)); avail = sdsavail (c->querybuf); } nread = read (c->fd, c->querybuf + pos, avail); if (nread > 0) { sdsIncrLen (c->querybuf, nread); processInputBuffer (c); if (c->total_append_command) { int arc_errno, arc_be_errno, be_errno; arc_ref_t *arc_ref; arc_ref = acquire_arc_ref (); ret = arc_do_request (arc_ref->arc, c->rqst, server.query_timeout_millis, &be_errno); if (ret == -1) { arc_errno = errno; arc_be_errno = be_errno; } else { ret = processReply (c, &be_errno); if (ret == -1) { arc_errno = errno; arc_be_errno = be_errno; } } arc_free_request (c->rqst); release_arc_ref (arc_ref); c->rqst = arc_create_request (); if (ret == -1) { if (arc_errno == ARC_ERR_TIMEOUT || (arc_errno == ARC_ERR_BACKEND && arc_be_errno == ARC_ERR_TIMEOUT)) { addReplyStr (c, "-ERR Redis Timeout\r\n"); } else { addReplyStr (c, "-ERR Internal Error\r\n"); } c->flags |= REDIS_CLOSE_AFTER_REPLY; } } } else { if (nread == -1 && errno == EAGAIN) { /* Skip */ } else { freeClient (c); } } } /* writable */ if (FD_ISSET (c->fd, &wfds)) { int pos = 0; int avail = sdslen (c->replybuf); ssize_t nwritten; nwritten = write (c->fd, c->replybuf + pos, avail); if (nwritten > 0) { avail -= nwritten; pos += nwritten; sdsrange (c->replybuf, pos, -1); } else { if (nwritten == -1 && errno == EAGAIN) { /* Skip */ } else { freeClient (c); } } } if (sdslen (c->replybuf) == 0 && (c->flags & REDIS_CLOSE_AFTER_REPLY)) { freeClient (c); } } return NULL; }
int redisvFormatCommand(char **target, const char *format, va_list ap) { const char *c = format; char *cmd = NULL; /* final command */ int pos; /* position in final command */ sds curarg, newarg; /* current argument */ int touched = 0; /* was the current argument touched? */ char **curargv = NULL, **newargv = NULL; int argc = 0; int totlen = 0; int j; /* Abort if there is not target to set */ if (target == NULL) return -1; /* Build the command string accordingly to protocol */ curarg = sdsempty(); if (curarg == NULL) return -1; while(*c != '\0') { if (*c != '%' || c[1] == '\0') { if (*c == ' ') { if (touched) { newargv = realloc(curargv,sizeof(char*)*(argc+1)); if (newargv == NULL) goto err; curargv = newargv; curargv[argc++] = curarg; totlen += bulklen(sdslen(curarg)); /* curarg is put in argv so it can be overwritten. */ curarg = sdsempty(); if (curarg == NULL) goto err; touched = 0; } } else { newarg = sdscatlen(curarg,c,1); if (newarg == NULL) goto err; curarg = newarg; touched = 1; } } else { char *arg; size_t size; /* Set newarg so it can be checked even if it is not touched. */ newarg = curarg; switch(c[1]) { case 's': arg = va_arg(ap,char*); size = strlen(arg); if (size > 0) newarg = sdscatlen(curarg,arg,size); break; case 'b': arg = va_arg(ap,char*); size = va_arg(ap,size_t); if (size > 0) newarg = sdscatlen(curarg,arg,size); break; case '%': newarg = sdscat(curarg,"%"); break; default: /* Try to detect printf format */ { char _format[16]; const char *_p = c+1; size_t _l = 0; va_list _cpy; /* Flags */ if (*_p != '\0' && *_p == '#') _p++; if (*_p != '\0' && *_p == '0') _p++; if (*_p != '\0' && *_p == '-') _p++; if (*_p != '\0' && *_p == ' ') _p++; if (*_p != '\0' && *_p == '+') _p++; /* Field width */ while (*_p != '\0' && isdigit(*_p)) _p++; /* Precision */ if (*_p == '.') { _p++; while (*_p != '\0' && isdigit(*_p)) _p++; } /* Copy va_list before consuming with va_arg */ va_copy(_cpy,ap); /* Integer conversion (without modifiers) */ if (strchr("diouxX",*_p) != NULL) { va_arg(ap,int); goto fmt_valid; } /* Double conversion (without modifiers) */ if (strchr("eEfFgGaA",*_p) != NULL) { va_arg(ap,double); goto fmt_valid; } /* Size: char */ if (_p[0] == 'h' && _p[1] == 'h') { _p += 2; if (*_p != '\0' && strchr("diouxX",*_p) != NULL) { va_arg(ap,int); /* char gets promoted to int */ goto fmt_valid; } goto fmt_invalid; } /* Size: short */ if (_p[0] == 'h') { _p += 1; if (*_p != '\0' && strchr("diouxX",*_p) != NULL) { va_arg(ap,int); /* short gets promoted to int */ goto fmt_valid; } goto fmt_invalid; } /* Size: long long */ if (_p[0] == 'l' && _p[1] == 'l') { _p += 2; if (*_p != '\0' && strchr("diouxX",*_p) != NULL) { va_arg(ap,long long); goto fmt_valid; } goto fmt_invalid; } /* Size: long */ if (_p[0] == 'l') { _p += 1; if (*_p != '\0' && strchr("diouxX",*_p) != NULL) { va_arg(ap,long); goto fmt_valid; } goto fmt_invalid; } fmt_invalid: va_end(_cpy); goto err; fmt_valid: _l = (_p+1)-c; if (_l < sizeof(_format)-2) { memcpy(_format,c,_l); _format[_l] = '\0'; newarg = sdscatvprintf(curarg,_format,_cpy); /* Update current position (note: outer blocks * increment c twice so compensate here) */ c = _p-1; } va_end(_cpy); break; } } if (newarg == NULL) goto err; curarg = newarg; touched = 1; c++; } c++; } /* Add the last argument if needed */ if (touched) { newargv = realloc(curargv,sizeof(char*)*(argc+1)); if (newargv == NULL) goto err; curargv = newargv; curargv[argc++] = curarg; totlen += bulklen(sdslen(curarg)); } else { sdsfree(curarg); } /* Clear curarg because it was put in curargv or was free'd. */ curarg = NULL; /* Add bytes needed to hold multi bulk count */ totlen += 1+intlen(argc)+2; /* Build the command at protocol level */ cmd = malloc(totlen+1); if (cmd == NULL) goto err; pos = sprintf(cmd,"*%d\r\n",argc); for (j = 0; j < argc; j++) { pos += sprintf(cmd+pos,"$%u\r\n",sdslen(curargv[j])); memcpy(cmd+pos,curargv[j],sdslen(curargv[j])); pos += sdslen(curargv[j]); sdsfree(curargv[j]); cmd[pos++] = '\r'; cmd[pos++] = '\n'; } assert(pos == totlen); cmd[pos] = '\0'; free(curargv); *target = cmd; return totlen; err: while(argc--) sdsfree(curargv[argc]); free(curargv); if (curarg != NULL) sdsfree(curarg); /* No need to check cmd since it is the last statement that can fail, * but do it anyway to be as defensive as possible. */ if (cmd != NULL) free(cmd); return -1; }
static void repl() { sds historyfile = NULL; int history = 0; char *line; int argc; sds *argv; config.interactive = 1; linenoiseSetCompletionCallback(completionCallback); /* Only use history when stdin is a tty. */ if (isatty(fileno(stdin))) { history = 1; #ifdef _WIN32 if (getenv("USERPROFILE") != NULL) { historyfile = sdscatprintf(sdsempty(),"%s\\.rediscli_history",getenv("USERPROFILE")); linenoiseHistoryLoad(historyfile); } #else if (getenv("HOME") != NULL) { historyfile = sdscatprintf(sdsempty(),"%s/.rediscli_history",getenv("HOME")); linenoiseHistoryLoad(historyfile); } #endif } cliRefreshPrompt(); while((line = linenoise(context ? config.prompt : "not connected> ")) != NULL) { if (line[0] != '\0') { argv = sdssplitargs(line,&argc); if (history) linenoiseHistoryAdd(line); if (historyfile) linenoiseHistorySave(historyfile); if (argv == NULL) { printf("Invalid argument(s)\n"); free(line); continue; } else if (argc > 0) { if (strcasecmp(argv[0],"quit") == 0 || strcasecmp(argv[0],"exit") == 0) { exit(0); } else if (argc == 3 && !strcasecmp(argv[0],"connect")) { sdsfree(config.hostip); config.hostip = sdsnew(argv[1]); config.hostport = atoi(argv[2]); cliConnect(1); } else if (argc == 1 && !strcasecmp(argv[0],"clear")) { linenoiseClearScreen(); } else { long long start_time = mstime(), elapsed; int repeat, skipargs = 0; repeat = atoi(argv[0]); if (argc > 1 && repeat) { skipargs = 1; } else { repeat = 1; } if (cliSendCommand(argc-skipargs,argv+skipargs,repeat) != REDIS_OK) { cliConnect(1); /* If we still cannot send the command print error. * We'll try to reconnect the next time. */ if (cliSendCommand(argc-skipargs,argv+skipargs,repeat) != REDIS_OK) cliPrintContextError(); } elapsed = mstime()-start_time; if (elapsed >= 500) { printf("(%.2fs)\n",(double)elapsed/1000); } } } /* Free the argument vector */ while(argc--) sdsfree(argv[argc]); zfree(argv); } /* linenoise() returns malloc-ed lines like readline() */ free(line); } exit(0); }
static sds cliFormatReplyTTY(redisReply *r, char *prefix) { sds out = sdsempty(); switch (r->type) { case REDIS_REPLY_ERROR: out = sdscatprintf(out,"(error) %s\n", r->str); break; case REDIS_REPLY_STATUS: out = sdscat(out,r->str); out = sdscat(out,"\n"); break; case REDIS_REPLY_INTEGER: out = sdscatprintf(out,"(integer) %lld\n",r->integer); break; case REDIS_REPLY_STRING: /* If you are producing output for the standard output we want * a more interesting output with quoted characters and so forth */ out = sdscatrepr(out,r->str,r->len); out = sdscat(out,"\n"); break; case REDIS_REPLY_NIL: out = sdscat(out,"(nil)\n"); break; case REDIS_REPLY_ARRAY: if (r->elements == 0) { out = sdscat(out,"(empty list or set)\n"); } else { unsigned int i, idxlen = 0; char _prefixlen[16]; char _prefixfmt[16]; sds _prefix; sds tmp; /* Calculate chars needed to represent the largest index */ i = r->elements; do { idxlen++; i /= 10; } while(i); /* Prefix for nested multi bulks should grow with idxlen+2 spaces */ memset(_prefixlen,' ',idxlen+2); _prefixlen[idxlen+2] = '\0'; _prefix = sdscat(sdsnew(prefix),_prefixlen); /* Setup prefix format for every entry */ snprintf(_prefixfmt,sizeof(_prefixfmt),"%%s%%%dd) ",idxlen); for (i = 0; i < r->elements; i++) { /* Don't use the prefix for the first element, as the parent * caller already prepended the index number. */ out = sdscatprintf(out,_prefixfmt,i == 0 ? "" : prefix,i+1); /* Format the multi bulk entry */ tmp = cliFormatReplyTTY(r->element[i],_prefix); out = sdscatlen(out,tmp,sdslen(tmp)); sdsfree(tmp); } sdsfree(_prefix); } break; default: fprintf(stderr,"Unknown reply type: %d\n", r->type); exit(1); } return out; }
/* Write the append only file buffer on disk. * * Since we are required to write the AOF before replying to the client, * and the only way the client socket can get a write is entering when the * the event loop, we accumulate all the AOF writes in a memory * buffer and write it on disk using this function just before entering * the event loop again. * * About the 'force' argument: * * When the fsync policy is set to 'everysec' we may delay the flush if there * is still an fsync() going on in the background thread, since for instance * on Linux write(2) will be blocked by the background fsync anyway. * When this happens we remember that there is some aof buffer to be * flushed ASAP, and will try to do that in the serverCron() function. * * However if force is set to 1 we'll write regardless of the background * fsync. */ void flushAppendOnlyFile(int force) { ssize_t nwritten; int sync_in_progress = 0; if (sdslen(server.aof_buf) == 0) return; if (server.aof_fsync == AOF_FSYNC_EVERYSEC) sync_in_progress = bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC) != 0; if (server.aof_fsync == AOF_FSYNC_EVERYSEC && !force) { /* With this append fsync policy we do background fsyncing. * If the fsync is still in progress we can try to delay * the write for a couple of seconds. */ if (sync_in_progress) { if (server.aof_flush_postponed_start == 0) { /* No previous write postponinig, remember that we are * postponing the flush and return. */ server.aof_flush_postponed_start = server.unixtime; return; } else if (server.unixtime - server.aof_flush_postponed_start < 2) { /* We were already waiting for fsync to finish, but for less * than two seconds this is still ok. Postpone again. */ return; } /* Otherwise fall trough, and go write since we can't wait * over two seconds. */ server.aof_delayed_fsync++; redisLog(REDIS_NOTICE,"Asynchronous AOF fsync is taking too long (disk is busy?). Writing the AOF buffer without waiting for fsync to complete, this may slow down Redis."); } } /* If you are following this code path, then we are going to write so * set reset the postponed flush sentinel to zero. */ server.aof_flush_postponed_start = 0; /* We want to perform a single write. This should be guaranteed atomic * at least if the filesystem we are writing is a real physical one. * While this will save us against the server being killed I don't think * there is much to do about the whole server stopping for power problems * or alike */ nwritten = write(server.aof_fd,server.aof_buf,sdslen(server.aof_buf)); if (nwritten != (signed)sdslen(server.aof_buf)) { /* Ooops, we are in troubles. The best thing to do for now is * aborting instead of giving the illusion that everything is * working as expected. */ if (nwritten == -1) { redisLog(REDIS_WARNING,"Exiting on error writing to the append-only file: %s",strerror(errno)); } else { redisLog(REDIS_WARNING,"Exiting on short write while writing to " "the append-only file: %s (nwritten=%ld, " "expected=%ld)", strerror(errno), (long)nwritten, (long)sdslen(server.aof_buf)); if (ftruncate(server.aof_fd, server.aof_current_size) == -1) { redisLog(REDIS_WARNING, "Could not remove short write " "from the append-only file. Redis may refuse " "to load the AOF the next time it starts. " "ftruncate: %s", strerror(errno)); } } exit(1); } server.aof_current_size += nwritten; /* Re-use AOF buffer when it is small enough. The maximum comes from the * arena size of 4k minus some overhead (but is otherwise arbitrary). */ if ((sdslen(server.aof_buf)+sdsavail(server.aof_buf)) < 4000) { sdsclear(server.aof_buf); } else { sdsfree(server.aof_buf); server.aof_buf = sdsempty(); } /* Don't fsync if no-appendfsync-on-rewrite is set to yes and there are * children doing I/O in the background. */ if (server.aof_no_fsync_on_rewrite && (server.aof_child_pid != -1 || server.rdb_child_pid != -1)) return; /* Perform the fsync if needed. */ if (server.aof_fsync == AOF_FSYNC_ALWAYS) { /* aof_fsync is defined as fdatasync() for Linux in order to avoid * flushing metadata. */ aof_fsync(server.aof_fd); /* Let's try to get this data on the disk */ server.aof_last_fsync = server.unixtime; } else if ((server.aof_fsync == AOF_FSYNC_EVERYSEC && server.unixtime > server.aof_last_fsync)) { if (!sync_in_progress) aof_background_fsync(server.aof_fd); server.aof_last_fsync = server.unixtime; } }
/* A background append only file rewriting (BGREWRITEAOF) terminated its work. * Handle this. */ void backgroundRewriteDoneHandler(int exitcode, int bysignal) { if (!bysignal && exitcode == 0) { int newfd, oldfd; char tmpfile[256]; long long now = ustime(); redisLog(REDIS_NOTICE, "Background AOF rewrite terminated with success"); /* Flush the differences accumulated by the parent to the * rewritten AOF. */ snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int)server.aof_child_pid); newfd = open(tmpfile,O_WRONLY|O_APPEND); if (newfd == -1) { redisLog(REDIS_WARNING, "Unable to open the temporary AOF produced by the child: %s", strerror(errno)); goto cleanup; } if (aofRewriteBufferWrite(newfd) == -1) { redisLog(REDIS_WARNING, "Error trying to flush the parent diff to the rewritten AOF: %s", strerror(errno)); close(newfd); goto cleanup; } redisLog(REDIS_NOTICE, "Parent diff successfully flushed to the rewritten AOF (%lu bytes)", aofRewriteBufferSize()); /* The only remaining thing to do is to rename the temporary file to * the configured file and switch the file descriptor used to do AOF * writes. We don't want close(2) or rename(2) calls to block the * server on old file deletion. * * There are two possible scenarios: * * 1) AOF is DISABLED and this was a one time rewrite. The temporary * file will be renamed to the configured file. When this file already * exists, it will be unlinked, which may block the server. * * 2) AOF is ENABLED and the rewritten AOF will immediately start * receiving writes. After the temporary file is renamed to the * configured file, the original AOF file descriptor will be closed. * Since this will be the last reference to that file, closing it * causes the underlying file to be unlinked, which may block the * server. * * To mitigate the blocking effect of the unlink operation (either * caused by rename(2) in scenario 1, or by close(2) in scenario 2), we * use a background thread to take care of this. First, we * make scenario 1 identical to scenario 2 by opening the target file * when it exists. The unlink operation after the rename(2) will then * be executed upon calling close(2) for its descriptor. Everything to * guarantee atomicity for this switch has already happened by then, so * we don't care what the outcome or duration of that close operation * is, as long as the file descriptor is released again. */ if (server.aof_fd == -1) { /* AOF disabled */ /* Don't care if this fails: oldfd will be -1 and we handle that. * One notable case of -1 return is if the old file does * not exist. */ oldfd = open(server.aof_filename,O_RDONLY|O_NONBLOCK); } else { /* AOF enabled */ oldfd = -1; /* We'll set this to the current AOF filedes later. */ } /* Rename the temporary file. This will not unlink the target file if * it exists, because we reference it with "oldfd". */ if (rename(tmpfile,server.aof_filename) == -1) { redisLog(REDIS_WARNING, "Error trying to rename the temporary AOF file: %s", strerror(errno)); close(newfd); if (oldfd != -1) close(oldfd); goto cleanup; } if (server.aof_fd == -1) { /* AOF disabled, we don't need to set the AOF file descriptor * to this new file, so we can close it. */ close(newfd); } else { /* AOF enabled, replace the old fd with the new one. */ oldfd = server.aof_fd; server.aof_fd = newfd; if (server.aof_fsync == AOF_FSYNC_ALWAYS) aof_fsync(newfd); else if (server.aof_fsync == AOF_FSYNC_EVERYSEC) aof_background_fsync(newfd); server.aof_selected_db = -1; /* Make sure SELECT is re-issued */ aofUpdateCurrentSize(); server.aof_rewrite_base_size = server.aof_current_size; /* Clear regular AOF buffer since its contents was just written to * the new AOF from the background rewrite buffer. */ sdsfree(server.aof_buf); server.aof_buf = sdsempty(); } server.aof_lastbgrewrite_status = REDIS_OK; redisLog(REDIS_NOTICE, "Background AOF rewrite finished successfully"); /* Change state from WAIT_REWRITE to ON if needed */ if (server.aof_state == REDIS_AOF_WAIT_REWRITE) server.aof_state = REDIS_AOF_ON; /* Asynchronously close the overwritten AOF. */ if (oldfd != -1) bioCreateBackgroundJob(REDIS_BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL); redisLog(REDIS_VERBOSE, "Background AOF rewrite signal handler took %lldus", ustime()-now); } else if (!bysignal && exitcode != 0) { server.aof_lastbgrewrite_status = REDIS_ERR; redisLog(REDIS_WARNING, "Background AOF rewrite terminated with error"); } else { server.aof_lastbgrewrite_status = REDIS_ERR; redisLog(REDIS_WARNING, "Background AOF rewrite terminated by signal %d", bysignal); } cleanup: aofRewriteBufferReset(); aofRemoveTempFile(server.aof_child_pid); server.aof_child_pid = -1; server.aof_rewrite_time_last = time(NULL)-server.aof_rewrite_time_start; server.aof_rewrite_time_start = -1; /* Schedule a new rewrite if we are waiting for it to switch the AOF ON. */ if (server.aof_state == REDIS_AOF_WAIT_REWRITE) server.aof_rewrite_scheduled = 1; }
static void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) { sds buf = sdsempty(); int j; ssize_t nwritten; time_t now; robj *tmpargv[3]; /* The DB this command was targetting is not the same as the last command * we appendend. To issue a SELECT command is needed. */ if (dictid != server.appendseldb) { char seldb[64]; snprintf(seldb,sizeof(seldb),"%d",dictid); buf = sdscatprintf(buf,"*2\r\n$6\r\nSELECT\r\n$%lu\r\n%s\r\n", (unsigned long)strlen(seldb), seldb); server.appendseldb = dictid; } /* "Fix" the argv vector if the command is EXPIRE. We want to translate * EXPIREs into EXPIREATs calls */ if (cmd->proc == expireCommand) { long when; tmpargv[0] = createStringObject("EXPIREAT",8); tmpargv[1] = argv[1]; incrRefCount(argv[1]); when = time(NULL)+strtol(argv[2]->ptr,NULL,10); tmpargv[2] = createObject(REDIS_STRING, sdscatprintf(sdsempty(),"%ld",when)); argv = tmpargv; } /* Append the actual command */ buf = sdscatprintf(buf,"*%d\r\n",argc); for (j = 0; j < argc; j++) { robj *o = argv[j]; o = getDecodedObject(o); buf = sdscatprintf(buf,"$%lu\r\n",(unsigned long)sdslen(o->ptr)); buf = sdscatlen(buf,o->ptr,sdslen(o->ptr)); buf = sdscatlen(buf,"\r\n",2); decrRefCount(o); } /* Free the objects from the modified argv for EXPIREAT */ if (cmd->proc == expireCommand) { for (j = 0; j < 3; j++) decrRefCount(argv[j]); } /* We want to perform a single write. This should be guaranteed atomic * at least if the filesystem we are writing is a real physical one. * While this will save us against the server being killed I don't think * there is much to do about the whole server stopping for power problems * or alike */ nwritten = write(server.appendfd,buf,sdslen(buf)); /* If a background append only file rewriting is in progress we want to * accumulate the differences between the child DB and the current one * in a buffer, so that when the child process will do its work we * can append the differences to the new append only file. */ if (server.bgrewritechildpid != -1) server.bgrewritebuf = sdscatlen(server.bgrewritebuf,buf,sdslen(buf)); sdsfree(buf); now = time(NULL); if (server.appendfsync == APPENDFSYNC_ALWAYS || (server.appendfsync == APPENDFSYNC_EVERYSEC && now-server.lastfsync > 1)) { fsync(server.appendfd); /* Let's try to get this data on the disk */ server.lastfsync = now; } }