Redis中AOF與RDB持久化策略深入分析

// src/rdb.c
/* Save the DB on disk. Return C_ERR on error, C_OK on success. */
int rdbSave(char *filename, rdbSaveInfo *rsi) {
    char tmpfile[256];
    char cwd[MAXPATHLEN]; /* Current working dir path for error messages. */
    FILE *fp = NULL;
    rio rdb;
    int error = 0;
    snprintf(tmpfile,256,"temp-%d.rdb", (int) getpid());
    fp = fopen(tmpfile,"w");
    if (!fp) {
        char *cwdp = getcwd(cwd,MAXPATHLEN);
        serverLog(LL_WARNING,
            "Failed opening the RDB file %s (in server root dir %s) "
            "for saving: %s",
            filename,
            cwdp ? cwdp : "unknown",
            strerror(errno));
        return C_ERR;
    }
    rioInitWithFile(&rdb,fp);
    startSaving(RDBFLAGS_NONE);
    if (server.rdb_save_incremental_fsync)
        rioSetAutoSync(&rdb,REDIS_AUTOSYNC_BYTES);
    if (rdbSaveRio(&rdb,&error,RDBFLAGS_NONE,rsi) == C_ERR) {
        errno = error;
        goto werr;
    }
    /* Make sure data will not remain on the OS's output buffers */
    if (fflush(fp)) goto werr;
    if (fsync(fileno(fp))) goto werr;
    if (fclose(fp)) { fp = NULL; goto werr; }
    fp = NULL;
    /* Use RENAME to make sure the DB file is changed atomically only
     * if the generate DB file is ok. */
    if (rename(tmpfile,filename) == -1) {
        char *cwdp = getcwd(cwd,MAXPATHLEN);
        serverLog(LL_WARNING,
            "Error moving temp DB file %s on the final "
            "destination %s (in server root dir %s): %s",
            tmpfile,
            filename,
            cwdp ? cwdp : "unknown",
            strerror(errno));
        unlink(tmpfile);
        stopSaving(0);
        return C_ERR;
    }
    serverLog(LL_NOTICE,"DB saved on disk");
    server.dirty = 0;
    server.lastsave = time(NULL);
    server.lastbgsave_status = C_OK;
    stopSaving(1);
    return C_OK;
werr:
    serverLog(LL_WARNING,"Write error saving DB on disk: %s", strerror(errno));
    if (fp) fclose(fp);
    unlink(tmpfile);
    stopSaving(0);
    return C_ERR;
}

void saveCommand(client *c) {
    // 如果已經有子程序在進行RDB持久化
    if (server.child_type == CHILD_TYPE_RDB) {
        addReplyError(c,"Background save already in progress");
        return;
    }
    rdbSaveInfo rsi, *rsiptr;
    rsiptr = rdbPopulateSaveInfo(&rsi);
    // 持久化
    if (rdbSave(server.rdb_filename,rsiptr) == C_OK) {
        addReply(c,shared.ok);
    } else {
        addReplyErrorObject(c,shared.err);
    }
}

/* BGSAVE [SCHEDULE] */
void bgsaveCommand(client *c) {
    int schedule = 0;
    /* The SCHEDULE option changes the behavior of BGSAVE when an AOF rewrite
     * is in progress. Instead of returning an error a BGSAVE gets scheduled. */
    if (c->argc > 1) {
        if (c->argc == 2 && !strcasecmp(c->argv[1]->ptr,"schedule")) {
            schedule = 1;
        } else {
            addReplyErrorObject(c,shared.syntaxerr);
            return;
        }
    }
    rdbSaveInfo rsi, *rsiptr;
    rsiptr = rdbPopulateSaveInfo(&rsi);
    if (server.child_type == CHILD_TYPE_RDB) {
        addReplyError(c,"Background save already in progress");
    } else if (hasActiveChildProcess()) {
        if (schedule) {
            server.rdb_bgsave_scheduled = 1;
            addReplyStatus(c,"Background saving scheduled");
        } else {
            addReplyError(c,
            "Another child process is active (AOF?): can't BGSAVE right now. "
            "Use BGSAVE SCHEDULE in order to schedule a BGSAVE whenever "
            "possible.");
        }
    } else if (rdbSaveBackground(server.rdb_filename,rsiptr) == C_OK) {
        addReplyStatus(c,"Background saving started");
    } else {
        addReplyErrorObject(c,shared.err);
    }
}
int rdbSaveBackground(char *filename, rdbSaveInfo *rsi) {
    pid_t childpid;
    if (hasActiveChildProcess()) return C_ERR;
    server.dirty_before_bgsave = server.dirty;
    server.lastbgsave_try = time(NULL);
	// 子程序
    if ((childpid = redisFork(CHILD_TYPE_RDB)) == 0) {
        int retval;
        /* Child */
        redisSetProcTitle("redis-rdb-bgsave");
        redisSetCpuAffinity(server.bgsave_cpulist);
        retval = rdbSave(filename,rsi);
        if (retval == C_OK) {
            sendChildCowInfo(CHILD_INFO_TYPE_RDB_COW_SIZE, "RDB");
        }
        exitFromChild((retval == C_OK) ? 0 : 1);
    } else {
        /* Parent */
        if (childpid == -1) {
            server.lastbgsave_status = C_ERR;
            serverLog(LL_WARNING,"Can't save in background: fork: %s",
                strerror(errno));
            return C_ERR;
        }
        serverLog(LL_NOTICE,"Background saving started by pid %ld",(long) childpid);
        server.rdb_save_time_start = time(NULL);
        server.rdb_child_type = RDB_CHILD_TYPE_DISK;
        return C_OK;
    }
    return C_OK; /* unreached */
}

int rdbLoad(char *filename, rdbSaveInfo *rsi, int rdbflags) {
    FILE *fp;
    rio rdb;
    int retval;
    if ((fp = fopen(filename,"r")) == NULL) return C_ERR;
    startLoadingFile(fp, filename,rdbflags);
    rioInitWithFile(&rdb,fp);
    retval = rdbLoadRio(&rdb,rdbflags,rsi);
    fclose(fp);
    stopLoading(retval==C_OK);
    return retval;
}

// src/server.h
/* Append only defines */
#define AOF_FSYNC_NO 0
#define AOF_FSYNC_ALWAYS 1
#define AOF_FSYNC_EVERYSEC 2
// src/aof.c
void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;
    mstime_t latency;
	// 如果當前aof_buf緩衝區為空
    if (sdslen(server.aof_buf) == 0) {
        /* Check if we need to do fsync even the aof buffer is empty,
         * because previously in AOF_FSYNC_EVERYSEC mode, fsync is
         * called only when aof buffer is not empty, so if users
         * stop write commands before fsync called in one second,
         * the data in page cache cannot be flushed in time. */
        if (server.aof_fsync == AOF_FSYNC_EVERYSEC &&
            server.aof_fsync_offset != server.aof_current_size &&
            server.unixtime > server.aof_last_fsync &&
            !(sync_in_progress = aofFsyncInProgress())) {
            goto try_fsync;
        } else {
            return;
        }
    }
    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = aofFsyncInProgress();
    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 postponing, 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++;
            serverLog(LL_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.");
        }
    }
    /* 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 */
    if (server.aof_flush_sleep && sdslen(server.aof_buf)) {
        usleep(server.aof_flush_sleep);
    }
    latencyStartMonitor(latency);
    nwritten = aofWrite(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
    latencyEndMonitor(latency);
    /* We want to capture different events for delayed writes:
     * when the delay happens with a pending fsync, or with a saving child
     * active, and when the above two conditions are missing.
     * We also use an additional event name to save all samples which is
     * useful for graphing / monitoring purposes. */
    if (sync_in_progress) {
        latencyAddSampleIfNeeded("aof-write-pending-fsync",latency);
    } else if (hasActiveChildProcess()) {
        latencyAddSampleIfNeeded("aof-write-active-child",latency);
    } else {
        latencyAddSampleIfNeeded("aof-write-alone",latency);
    }
    latencyAddSampleIfNeeded("aof-write",latency);
    /* We performed the write so reset the postponed flush sentinel to zero. */
    server.aof_flush_postponed_start = 0;
    if (nwritten != (ssize_t)sdslen(server.aof_buf)) {
        static time_t last_write_error_log = 0;
        int can_log = 0;
        /* Limit logging rate to 1 line per AOF_WRITE_LOG_ERROR_RATE seconds. */
        if ((server.unixtime - last_write_error_log) > AOF_WRITE_LOG_ERROR_RATE) {
            can_log = 1;
            last_write_error_log = server.unixtime;
        }
        /* Log the AOF write error and record the error code. */
        if (nwritten == -1) {
            if (can_log) {
                serverLog(LL_WARNING,"Error writing to the AOF file: %s",
                    strerror(errno));
                server.aof_last_write_errno = errno;
            }
        } else {
            if (can_log) {
                serverLog(LL_WARNING,"Short write while writing to "
                                       "the AOF file: (nwritten=%lld, "
                                       "expected=%lld)",
                                       (long long)nwritten,
                                       (long long)sdslen(server.aof_buf));
            }
            if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
                if (can_log) {
                    serverLog(LL_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));
                }
            } else {
                /* If the ftruncate() succeeded we can set nwritten to
                 * -1 since there is no longer partial data into the AOF. */
                nwritten = -1;
            }
            server.aof_last_write_errno = ENOSPC;
        }
        /* Handle the AOF write error. */
        if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
            /* We can't recover when the fsync policy is ALWAYS since the reply
             * for the client is already in the output buffers (both writes and
             * reads), and the changes to the db can't be rolled back. Since we
             * have a contract with the user that on acknowledged or observed
             * writes are is synced on disk, we must exit. */
            serverLog(LL_WARNING,"Can't recover from AOF write error when the AOF fsync policy is 'always'. Exiting...");
            exit(1);
        } else {
            /* Recover from failed write leaving data into the buffer. However
             * set an error to stop accepting writes as long as the error
             * condition is not cleared. */
            server.aof_last_write_status = C_ERR;
            /* Trim the sds buffer if there was a partial write, and there
             * was no way to undo it with ftruncate(2). */
            if (nwritten > 0) {
                server.aof_current_size += nwritten;
                sdsrange(server.aof_buf,nwritten,-1);
            }
            return; /* We'll try again on the next call... */
        }
    } else {
        /* Successful write(2). If AOF was in error state, restore the
         * OK state and log the event. */
        if (server.aof_last_write_status == C_ERR) {
            serverLog(LL_WARNING,
                "AOF write error looks solved, Redis can write again.");
            server.aof_last_write_status = C_OK;
        }
    }
    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();
    }
try_fsync:
    /* 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 && hasActiveChildProcess())
        return;
    /* Perform the fsync if needed. */
    if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
        /* redis_fsync is defined as fdatasync() for Linux in order to avoid
         * flushing metadata. */
        latencyStartMonitor(latency);
        /* Let's try to get this data on the disk. To guarantee data safe when
         * the AOF fsync policy is 'always', we should exit if failed to fsync
         * AOF (see comment next to the exit(1) after write error above). */
        if (redis_fsync(server.aof_fd) == -1) {
            serverLog(LL_WARNING,"Can't persist AOF for fsync error when the "
              "AOF fsync policy is 'always': %s. Exiting...", strerror(errno));
            exit(1);
        }
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-fsync-always",latency);
        server.aof_fsync_offset = server.aof_current_size;
        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_fsync_offset = server.aof_current_size;
        }
        server.aof_last_fsync = server.unixtime;
    }
}