aof.c

/*
 * Copyright (c) 2009-2012, Salvatore Sanfilippo <antirez at gmail dot com>
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *   * Redistributions of source code must retain the above copyright notice,
 *     this list of conditions and the following disclaimer.
 *   * Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *   * Neither the name of Redis nor the names of its contributors may be used
 *     to endorse or promote products derived from this software without
 *     specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "redis.h"
#include "bio.h"
#include "rio.h"

#include <signal.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/types.h>
#ifndef _WIN32
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/wait.h>
#endif

void aofUpdateCurrentSize(void);

/* ----------------------------------------------------------------------------
 * AOF rewrite buffer implementation.
 *
 * The following code implement a simple buffer used in order to accumulate
 * changes while the background process is rewriting the AOF file.
 *
 * We only need to append, but can't just use realloc with a large block
 * because 'huge' reallocs are not always handled as one could expect
 * (via remapping of pages at OS level) but may involve copying data.
 *
 * For this reason we use a list of blocks, every block is
 * AOF_RW_BUF_BLOCK_SIZE bytes.
 * ------------------------------------------------------------------------- */

#define AOF_RW_BUF_BLOCK_SIZE (1024*1024*10)    /* 10 MB per block */

typedef struct aofrwblock {
    unsigned long used, free;
    char buf[AOF_RW_BUF_BLOCK_SIZE];
} aofrwblock;

/* This function free the old AOF rewrite buffer if needed, and initialize
 * a fresh new one. It tests for server.aof_rewrite_buf_blocks equal to NULL
 * so can be used for the first initialization as well. */
void aofRewriteBufferReset(void) {
    if (server.aof_rewrite_buf_blocks)
        listRelease(server.aof_rewrite_buf_blocks);

    server.aof_rewrite_buf_blocks = listCreate();
    listSetFreeMethod(server.aof_rewrite_buf_blocks,zfree);
}

/* Return the current size of the AOF rerwite buffer. */
unsigned long aofRewriteBufferSize(void) {
    unsigned long size;
    listNode *ln = listLast(server.aof_rewrite_buf_blocks);
    aofrwblock *block = ln ? ln->value : NULL;

    if (block == NULL) return 0;
    size =
        (listLength(server.aof_rewrite_buf_blocks)-1) * AOF_RW_BUF_BLOCK_SIZE;
    size += block->used;
    return size;
}

/* Append data to the AOF rewrite buffer, allocating new blocks if needed. */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) {
    listNode *ln = listLast(server.aof_rewrite_buf_blocks);
    aofrwblock *block = ln ? ln->value : NULL;

    while(len) {
        /* If we already got at least an allocated block, try appending
         * at least some piece into it. */
        if (block) {
            unsigned long thislen = (block->free < len) ? block->free : len;
            if (thislen) {  /* The current block is not already full. */
                memcpy(block->buf+block->used, s, thislen);
                block->used += thislen;
                block->free -= thislen;
                s += thislen;
                len -= thislen;
            }
        }

        if (len) { /* First block to allocate, or need another block. */
            int numblocks;

            block = zmalloc(sizeof(*block));
            block->free = AOF_RW_BUF_BLOCK_SIZE;
            block->used = 0;
            listAddNodeTail(server.aof_rewrite_buf_blocks,block);

            /* Log every time we cross more 10 or 100 blocks, respectively
             * as a notice or warning. */
            numblocks = listLength(server.aof_rewrite_buf_blocks);
            if (((numblocks+1) % 10) == 0) {
                int level = ((numblocks+1) % 100) == 0 ? REDIS_WARNING :
                                                         REDIS_NOTICE;
                redisLog(level,"Background AOF buffer size: %lu MB",
                    aofRewriteBufferSize()/(1024*1024));
            }
        }
    }
}

/* Write the buffer (possibly composed of multiple blocks) into the specified
 * fd. If no short write or any other error happens -1 is returned,
 * otherwise the number of bytes written is returned. */
ssize_t aofRewriteBufferWrite(int fd) {
    listNode *ln;
    listIter li;
    ssize_t count = 0;

    listRewind(server.aof_rewrite_buf_blocks,&li);
    while((ln = listNext(&li))) {
        aofrwblock *block = listNodeValue(ln);
        ssize_t nwritten;

        if (block->used) {
#ifdef _WIN32
            nwritten = send(fd,block->buf,block->used,0);
#else
            nwritten = write(fd,block->buf,block->used);
#endif
            if (nwritten != block->used) {
                if (nwritten == 0) errno = EIO;
                return -1;
            }
            count += nwritten;
        }
    }
    return count;
}

/* ----------------------------------------------------------------------------
 * AOF file implementation
 * ------------------------------------------------------------------------- */

/* Starts a background task that performs fsync() against the specified
 * file descriptor (the one of the AOF file) in another thread. */
void aof_background_fsync(int fd) {
#ifdef _WIN32
    bioCreateBackgroundJob(REDIS_BIO_AOF_FSYNC,(void*)(size_t)fd,NULL,NULL);
#else
    bioCreateBackgroundJob(REDIS_BIO_AOF_FSYNC,(void*)(long)fd,NULL,NULL);
#endif
}

/* Called when the user switches from "appendonly yes" to "appendonly no"
 * at runtime using the CONFIG command. */
void stopAppendOnly(void) {
    redisAssert(server.aof_state != REDIS_AOF_OFF);
    flushAppendOnlyFile(1);
    aof_fsync(server.aof_fd);
    close(server.aof_fd);

    server.aof_fd = -1;
    server.aof_selected_db = -1;
    server.aof_state = REDIS_AOF_OFF;
    /* rewrite operation in progress? kill it, wait child exit */
    if (server.aof_child_pid != -1) {
#ifdef _WIN32
        bkgdsave_termthread();
        server.rdbbkgdfsave.state = BKSAVE_IDLE;
        /* turn off copy on write */
        cowBkgdSaveStop();
        redisLog(REDIS_NOTICE,"Killing running AOF rewrite child: %ld",
            (long) server.aof_child_pid);
#else
        int statloc;

        redisLog(REDIS_NOTICE,"Killing running AOF rewrite child: %ld",
            (long) server.aof_child_pid);
        if (kill(server.aof_child_pid,SIGUSR1) != -1)
            wait3(&statloc,0,NULL);
#endif
        /* reset the buffer accumulating changes while the child saves */
        aofRewriteBufferReset();
        aofRemoveTempFile(server.aof_child_pid);
        server.aof_child_pid = -1;
        server.aof_rewrite_time_start = -1;
    }
}

/* Called when the user switches from "appendonly no" to "appendonly yes"
 * at runtime using the CONFIG command. */
int startAppendOnly(void) {
    server.aof_last_fsync = server.unixtime;
#ifdef _WIN32
    server.aof_fd = open(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT|_O_BINARY,_S_IREAD|_S_IWRITE);
#else
    server.aof_fd = open(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
#endif
    redisAssert(server.aof_state == REDIS_AOF_OFF);
    if (server.aof_fd == -1) {
        redisLog(REDIS_WARNING,"Redis needs to enable the AOF but can't open the append only file: %s",strerror(errno));
        return REDIS_ERR;
    }
    if (rewriteAppendOnlyFileBackground() == REDIS_ERR) {
        close(server.aof_fd);
        redisLog(REDIS_WARNING,"Redis needs to enable the AOF but can't trigger a background AOF rewrite operation. Check the above logs for more info about the error.");
        return REDIS_ERR;
    }
    /* We correctly switched on AOF, now wait for the rerwite to be complete
     * in order to append data on disk. */
    server.aof_state = REDIS_AOF_WAIT_REWRITE;
    return REDIS_OK;
}

/* 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,(unsigned int)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;
    }
}

sds catAppendOnlyGenericCommand(sds dst, int argc, robj **argv) {
    char buf[32];
    int len, j;
    robj *o;

    buf[0] = '*';
    len = 1+ll2string(buf+1,sizeof(buf)-1,argc);
    buf[len++] = '\r';
    buf[len++] = '\n';
    dst = sdscatlen(dst,buf,len);

    for (j = 0; j < argc; j++) {
        o = getDecodedObject(argv[j]);
        buf[0] = '$';
        len = 1+ll2string(buf+1,sizeof(buf)-1,sdslen(o->ptr));
        buf[len++] = '\r';
        buf[len++] = '\n';
        dst = sdscatlen(dst,buf,len);
        dst = sdscatlen(dst,o->ptr,sdslen(o->ptr));
        dst = sdscatlen(dst,"\r\n",2);
        decrRefCount(o);
    }
    return dst;
}

/* Create the sds representation of an PEXPIREAT command, using
 * 'seconds' as time to live and 'cmd' to understand what command
 * we are translating into a PEXPIREAT.
 *
 * This command is used in order to translate EXPIRE and PEXPIRE commands
 * into PEXPIREAT command so that we retain precision in the append only
 * file, and the time is always absolute and not relative. */
sds catAppendOnlyExpireAtCommand(sds buf, struct redisCommand *cmd, robj *key, robj *seconds) {
    long long when;
    robj *argv[3];

    /* Make sure we can use strtol */
    seconds = getDecodedObject(seconds);
    when = strtoll(seconds->ptr,NULL,10);
    /* Convert argument into milliseconds for EXPIRE, SETEX, EXPIREAT */
    if (cmd->proc == expireCommand || cmd->proc == setexCommand ||
        cmd->proc == expireatCommand)
    {
        when *= 1000;
    }
    /* Convert into absolute time for EXPIRE, PEXPIRE, SETEX, PSETEX */
    if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
        cmd->proc == setexCommand || cmd->proc == psetexCommand)
    {
        when += mstime();
    }
    decrRefCount(seconds);

    argv[0] = createStringObject("PEXPIREAT",9);
    argv[1] = key;
    argv[2] = createStringObjectFromLongLong(when);
    buf = catAppendOnlyGenericCommand(buf, 3, argv);
    decrRefCount(argv[0]);
    decrRefCount(argv[2]);
    return buf;
}

void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
    sds buf = sdsempty();
    robj *tmpargv[3];

    /* The DB this command was targeting is not the same as the last command
     * we appendend. To issue a SELECT command is needed. */
    if (dictid != server.aof_selected_db) {
        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.aof_selected_db = dictid;
    }

    if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
        cmd->proc == expireatCommand) {
        /* Translate EXPIRE/PEXPIRE/EXPIREAT into PEXPIREAT */
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    } else if (cmd->proc == setexCommand || cmd->proc == psetexCommand) {
        /* Translate SETEX/PSETEX to SET and PEXPIREAT */
        tmpargv[0] = createStringObject("SET",3);
        tmpargv[1] = argv[1];
        tmpargv[2] = argv[3];
        buf = catAppendOnlyGenericCommand(buf,3,tmpargv);
        decrRefCount(tmpargv[0]);
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    } else {
        /* All the other commands don't need translation or need the
         * same translation already operated in the command vector
         * for the replication itself. */
        buf = catAppendOnlyGenericCommand(buf,argc,argv);
    }

    /* Append to the AOF buffer. This will be flushed on disk just before
     * of re-entering the event loop, so before the client will get a
     * positive reply about the operation performed. */
    if (server.aof_state == REDIS_AOF_ON)
        server.aof_buf = sdscatlen(server.aof_buf,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.aof_child_pid != -1)
        aofRewriteBufferAppend((unsigned char*)buf,(unsigned long)sdslen(buf));

    sdsfree(buf);
}

/* ----------------------------------------------------------------------------
 * AOF loading
 * ------------------------------------------------------------------------- */

/* In Redis commands are always executed in the context of a client, so in
 * order to load the append only file we need to create a fake client. */
struct redisClient *createFakeClient(void) {
    struct redisClient *c = zmalloc(sizeof(*c));

    selectDb(c,0);
    c->fd = -1;
    c->name = NULL;
    c->querybuf = sdsempty();
    c->querybuf_peak = 0;
    c->argc = 0;
    c->argv = NULL;
    c->bufpos = 0;
    c->flags = 0;
    /* We set the fake client as a slave waiting for the synchronization
     * so that Redis will not try to send replies to this client. */
    c->replstate = REDIS_REPL_WAIT_BGSAVE_START;
    c->reply = listCreate();
    c->reply_bytes = 0;
    c->obuf_soft_limit_reached_time = 0;
    c->watched_keys = listCreate();
    listSetFreeMethod(c->reply,decrRefCount);
    listSetDupMethod(c->reply,dupClientReplyValue);
    initClientMultiState(c);
    return c;
}

void freeFakeClient(struct redisClient *c) {
    sdsfree(c->querybuf);
    listRelease(c->reply);
    listRelease(c->watched_keys);
    freeClientMultiState(c);
    zfree(c);
}

/* Replay the append log file. On error REDIS_OK is returned. On non fatal
 * error (the append only file is zero-length) REDIS_ERR is returned. On
 * fatal error an error message is logged and the program exists. */
int loadAppendOnlyFile(char *filename) {
    struct redisClient *fakeClient;
#ifdef _WIN32
    FILE *fp = fopen(filename,"rb");
#else
    FILE *fp = fopen(filename,"r");
#endif
    struct redis_stat sb;
    int old_aof_state = server.aof_state;
    long loops = 0;

    if (fp && redis_fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {
        server.aof_current_size = 0;
        fclose(fp);
        return REDIS_ERR;
    }

    if (fp == NULL) {
        redisLog(REDIS_WARNING,"Fatal error: can't open the append log file for reading: %s",strerror(errno));
        exit(1);
    }

    /* Temporarily disable AOF, to prevent EXEC from feeding a MULTI
     * to the same file we're about to read. */
    server.aof_state = REDIS_AOF_OFF;

    fakeClient = createFakeClient();
    startLoading(fp);

    while(1) {
        int argc, j;
#ifdef _WIN32
        size_t len;
#else
        unsigned long len;
#endif
        robj **argv;
        char buf[128];
        sds argsds;
        struct redisCommand *cmd;

        /* Serve the clients from time to time */
        if (!(loops++ % 1000)) {
            loadingProgress((off_t)ftello(fp));
            aeProcessEvents(server.el, AE_FILE_EVENTS|AE_DONT_WAIT);
        }

        if (fgets(buf,sizeof(buf),fp) == NULL) {
            if (feof(fp))
                break;
            else
                goto readerr;
        }
        if (buf[0] != '*') goto fmterr;
        argc = atoi(buf+1);
        if (argc < 1) goto fmterr;

        argv = zmalloc(sizeof(robj*)*argc);
        for (j = 0; j < argc; j++) {
            if (fgets(buf,sizeof(buf),fp) == NULL) goto readerr;
            if (buf[0] != '$') goto fmterr;
            len = strtol(buf+1,NULL,10);
            argsds = sdsnewlen(NULL,len);
            if (len && fread(argsds,len,1,fp) == 0) goto fmterr;
            argv[j] = createObject(REDIS_STRING,argsds);
            if (fread(buf,2,1,fp) == 0) goto fmterr; /* discard CRLF */
        }

        /* Command lookup */
        cmd = lookupCommand(argv[0]->ptr);
        if (!cmd) {
            redisLog(REDIS_WARNING,"Unknown command '%s' reading the append only file", argv[0]->ptr);
            exit(1);
        }
        /* Run the command in the context of a fake client */
        fakeClient->argc = argc;
        fakeClient->argv = argv;
        cmd->proc(fakeClient);

        /* The fake client should not have a reply */
        redisAssert(fakeClient->bufpos == 0 && listLength(fakeClient->reply) == 0);
        /* The fake client should never get blocked */
        redisAssert((fakeClient->flags & REDIS_BLOCKED) == 0);

        /* Clean up. Command code may have changed argv/argc so we use the
         * argv/argc of the client instead of the local variables. */
        for (j = 0; j < fakeClient->argc; j++)
            decrRefCount(fakeClient->argv[j]);
        zfree(fakeClient->argv);
    }

    /* This point can only be reached when EOF is reached without errors.
     * If the client is in the middle of a MULTI/EXEC, log error and quit. */
    if (fakeClient->flags & REDIS_MULTI) goto readerr;

    fclose(fp);
    freeFakeClient(fakeClient);
    server.aof_state = old_aof_state;
    stopLoading();
    aofUpdateCurrentSize();
    server.aof_rewrite_base_size = server.aof_current_size;
    return REDIS_OK;

readerr:
    if (feof(fp)) {
        redisLog(REDIS_WARNING,"Unexpected end of file reading the append only file");
    } else {
        redisLog(REDIS_WARNING,"Unrecoverable error reading the append only file: %s", strerror(errno));
    }
    exit(1);
fmterr:
    redisLog(REDIS_WARNING,"Bad file format reading the append only file: make a backup of your AOF file, then use ./redis-check-aof --fix <filename>");
    exit(1);
}

/* ----------------------------------------------------------------------------
 * AOF rewrite
 * ------------------------------------------------------------------------- */

/* Delegate writing an object to writing a bulk string or bulk long long.
 * This is not placed in rio.c since that adds the redis.h dependency. */
int rioWriteBulkObject(rio *r, robj *obj) {
    /* Avoid using getDecodedObject to help copy-on-write (we are often
     * in a child process when this function is called). */
    if (obj->encoding == REDIS_ENCODING_INT) {
        return (int)rioWriteBulkLongLong(r,(long)obj->ptr);
    } else if (obj->encoding == REDIS_ENCODING_RAW) {
        return (int)rioWriteBulkString(r,obj->ptr,sdslen(obj->ptr));
    } else {
        redisPanic("Unknown string encoding");
    }
}

/* Emit the commands needed to rebuild a list object.
 * The function returns 0 on error, 1 on success. */
int rewriteListObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = listTypeLength(o);

    if (o->encoding == REDIS_ENCODING_ZIPLIST) {
        unsigned char *zl = o->ptr;
        unsigned char *p = ziplistIndex(zl,0);
        unsigned char *vstr;
        unsigned int vlen;
        long long vlong;

#ifdef _WIN32
        cowUnlock();
#endif
        while(ziplistGet(p,&vstr,&vlen,&vlong)) {
            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"RPUSH",5) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (vstr) {
                if (rioWriteBulkString(r,(char*)vstr,vlen) == 0) return 0;
            } else {
                if (rioWriteBulkLongLong(r,vlong) == 0) return 0;
            }
            p = ziplistNext(zl,p);
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
#ifdef _WIN32
    } else if (o->encoding == REDIS_ENCODING_LINKEDLIST ||
               o->encoding == REDIS_ENCODING_LINKEDLISTARRAY) {
        roListIter li;
        listNode *ln;

        if (o->encoding == REDIS_ENCODING_LINKEDLIST) {
            list *list = o->ptr;
            roListRewind(list, NULL, &li);
        } else {
            cowListArray *ar = (cowListArray *)o->ptr;
            roListRewind(NULL, ar, &li);
        }
        cowUnlock();

        while((ln = roListNext(&li))) {
#else
    } else if (o->encoding == REDIS_ENCODING_LINKEDLIST) {
        list *list = o->ptr;
        listNode *ln;
        listIter li;

        listRewind(list,&li);
        while((ln = listNext(&li))) {
#endif
            robj *eleobj = listNodeValue(ln);

            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"RPUSH",5) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkObject(r,eleobj) == 0) return 0;
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
    } else {
#ifdef _WIN32
        cowUnlock();
#endif
        redisPanic("Unknown list encoding");
    }
    return 1;
}

/* Emit the commands needed to rebuild a set object.
 * The function returns 0 on error, 1 on success. */
int rewriteSetObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = setTypeSize(o);

    if (o->encoding == REDIS_ENCODING_INTSET) {
        int ii = 0;
        int64_t llval;

#ifdef _WIN32
        cowUnlock();
#endif
        while(intsetGet(o->ptr,ii++,&llval)) {
            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"SADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkLongLong(r,llval) == 0) return 0;
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
#ifdef _WIN32
    } else if (o->encoding == REDIS_ENCODING_HT ||
               o->encoding == REDIS_ENCODING_HTARRAY) {
        roDictIter *di;
        dictEntry *de;
        if (o->encoding == REDIS_ENCODING_HT) {
            di = roDictGetIterator(o->ptr, NULL);
        } else {
            cowDictArray *ar = (cowDictArray *)o->ptr;
            di = roDictGetIterator(NULL, ar);
        }
        cowUnlock();

        while((de = roDictNext(di)) != NULL) {
#else
    } else if (o->encoding == REDIS_ENCODING_HT) {
        dictIterator *di = dictGetIterator(o->ptr);
        dictEntry *de;

        while((de = dictNext(di)) != NULL) {
#endif
            robj *eleobj = dictGetKey(de);
            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items) == 0) return 0;
                if (rioWriteBulkString(r,"SADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkObject(r,eleobj) == 0) return 0;
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
#ifdef _WIN32
        roDictReleaseIterator(di);
#else
        dictReleaseIterator(di);
#endif
    } else {
#ifdef _WIN32
        cowUnlock();
#endif
        redisPanic("Unknown set encoding");
    }
    return 1;
}

/* Emit the commands needed to rebuild a sorted set object.
 * The function returns 0 on error, 1 on success. */
int rewriteSortedSetObject(rio *r, robj *key, robj *o) {
    long long count = 0, items = zsetLength(o);

    if (o->encoding == REDIS_ENCODING_ZIPLIST) {
        unsigned char *zl = o->ptr;
        unsigned char *eptr, *sptr;
        unsigned char *vstr;
        unsigned int vlen;
        long long vll;
        double score;

#ifdef _WIN32
        cowUnlock();
#endif
        eptr = ziplistIndex(zl,0);
        redisAssert(eptr != NULL);
        sptr = ziplistNext(zl,eptr);
        redisAssert(sptr != NULL);

        while (eptr != NULL) {
            redisAssert(ziplistGet(eptr,&vstr,&vlen,&vll));
            score = zzlGetScore(sptr);

            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
                if (rioWriteBulkString(r,"ZADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkDouble(r,score) == 0) return 0;
            if (vstr != NULL) {
                if (rioWriteBulkString(r,(char*)vstr,vlen) == 0) return 0;
            } else {
                if (rioWriteBulkLongLong(r,vll) == 0) return 0;
            }
            zzlNext(zl,&eptr,&sptr);
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
#ifdef _WIN32
    } else if (o->encoding == REDIS_ENCODING_SKIPLIST ||
               o->encoding == REDIS_ENCODING_HTZARRAY) {
        roZDictIter *di;
        dictEntry *de;

        if (o->encoding == REDIS_ENCODING_SKIPLIST) {
            zset *zs = o->ptr;
            di = roZDictGetIterator(zs->dict, NULL);
        } else {
            cowDictZArray *ar = (cowDictZArray *)o->ptr;
            di = roZDictGetIterator(NULL, ar);
        }

        cowUnlock();
        while((de = roZDictNext(di)) != NULL) {
#else
    } else if (o->encoding == REDIS_ENCODING_SKIPLIST) {
        zset *zs = o->ptr;
        dictIterator *di = dictGetIterator(zs->dict);
        dictEntry *de;

        while((de = dictNext(di)) != NULL) {
#endif
            robj *eleobj = dictGetKey(de);
            double *score = dictGetVal(de);

            if (count == 0) {
                int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                    REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

                if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
                if (rioWriteBulkString(r,"ZADD",4) == 0) return 0;
                if (rioWriteBulkObject(r,key) == 0) return 0;
            }
            if (rioWriteBulkDouble(r,*score) == 0) return 0;
            if (rioWriteBulkObject(r,eleobj) == 0) return 0;
            if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
            items--;
        }
#ifdef _WIN32
        roZDictReleaseIterator(di);
#else
        dictReleaseIterator(di);
#endif
    } else {
#ifdef _WIN32
        cowUnlock();
#endif
        redisPanic("Unknown sorted zset encoding");
    }
    return 1;
}

/* Write either the key or the value of the currently selected item of an hash.
 * The 'hi' argument passes a valid Redis hash iterator.
 * The 'what' filed specifies if to write a key or a value and can be
 * either REDIS_HASH_KEY or REDIS_HASH_VALUE.
 *
 * The function returns 0 on error, non-zero on success. */
static int rioWriteHashIteratorCursor(rio *r, hashTypeIterator *hi, int what) {
    if (hi->encoding == REDIS_ENCODING_ZIPLIST) {
        unsigned char *vstr = NULL;
        unsigned int vlen = UINT_MAX;
        long long vll = LLONG_MAX;

        hashTypeCurrentFromZiplist(hi, what, &vstr, &vlen, &vll);
        if (vstr) {
            return (int)rioWriteBulkString(r, (char*)vstr, vlen);
        } else {
            return (int)rioWriteBulkLongLong(r, vll);
        }

    } else if (hi->encoding == REDIS_ENCODING_HT) {
        robj *value;

        hashTypeCurrentFromHashTable(hi, what, &value);
        return rioWriteBulkObject(r, value);
    }

    redisPanic("Unknown hash encoding");
    return 0;
}

#ifdef _WIN32
/* Wrap rioWriteHashIteratorCursor to handle the read only array if appropriate
 *
 * The function returns 0 on error, non-zero on success. */
static int rioWriteRoHashIteratorCursor(rio *r, roHashIter *rohi, int what) {
    int enc = roHashGetEncoding(rohi);
    if (enc == REDIS_ENCODING_HTARRAY) {
        robj *value;

        roHashGetCurrentFromArray(rohi, what, &value);
        return rioWriteBulkObject(r, value);
    } else {
        hashTypeIterator * hi = (hashTypeIterator *)roHashGetHashIter(rohi);
        return rioWriteHashIteratorCursor(r, hi, what);
    }

    return 0;
}

/* Emit the commands needed to rebuild a hash object.
 * The function returns 0 on error, 1 on success. */
int rewriteHashObject(rio *r, robj *key, robj *o) {
    roHashIter *rohi;
    long long count = 0, items = hashTypeLength(o);

    if (o->encoding == REDIS_ENCODING_HTARRAY) {
        cowDictArray *ar = (cowDictArray *)o->ptr;
        rohi = roHashGetIterator(NULL, ar);
    } else {
        rohi = roHashGetIterator(o, NULL);
    }
    while (roHashNext(rohi) != REDIS_ERR) {
        if (count == 0) {
            int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                REDIS_AOF_REWRITE_ITEMS_PER_CMD : (int)items;

            if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
            if (rioWriteBulkString(r,"HMSET",5) == 0) return 0;
            if (rioWriteBulkObject(r,key) == 0) return 0;
        }

        if (rioWriteRoHashIteratorCursor(r, rohi, REDIS_HASH_KEY) == 0) return 0;
        if (rioWriteRoHashIteratorCursor(r, rohi, REDIS_HASH_VALUE) == 0) return 0;
        if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
        items--;
    }

    roHashReleaseIterator(rohi);

    return 1;
}
#else
/* Emit the commands needed to rebuild a hash object.
 * The function returns 0 on error, 1 on success. */
int rewriteHashObject(rio *r, robj *key, robj *o) {
    hashTypeIterator *hi;
    long long count = 0, items = hashTypeLength(o);

    hi = hashTypeInitIterator(o);
    while (hashTypeNext(hi) != REDIS_ERR) {
        if (count == 0) {
            int cmd_items = (items > REDIS_AOF_REWRITE_ITEMS_PER_CMD) ?
                REDIS_AOF_REWRITE_ITEMS_PER_CMD : items;

            if (rioWriteBulkCount(r,'*',2+cmd_items*2) == 0) return 0;
            if (rioWriteBulkString(r,"HMSET",5) == 0) return 0;
            if (rioWriteBulkObject(r,key) == 0) return 0;
        }

        if (rioWriteHashIteratorCursor(r, hi, REDIS_HASH_KEY) == 0) return 0;
        if (rioWriteHashIteratorCursor(r, hi, REDIS_HASH_VALUE) == 0) return 0;
        if (++count == REDIS_AOF_REWRITE_ITEMS_PER_CMD) count = 0;
        items--;
    }

    hashTypeReleaseIterator(hi);

    return 1;
}
#endif

/* Write a sequence of commands able to fully rebuild the dataset into
 * "filename". Used both by REWRITEAOF and BGREWRITEAOF.
 *
 * In order to minimize the number of commands needed in the rewritten
 * log Redis uses variadic commands when possible, such as RPUSH, SADD
 * and ZADD. However at max REDIS_AOF_REWRITE_ITEMS_PER_CMD items per time
 * are inserted using a single command. */
int rewriteAppendOnlyFile(char *filename) {
#ifdef _WIN32
    roDictIter *di = NULL;
#else
    dictIterator *di = NULL;
#endif
    dictEntry *de;
    rio aof;
    FILE *fp;
    char tmpfile[256];
    int j;
    long long now = mstime();
    dictIterator * expIter = NULL;

    /* Note that we have to use a different temp name here compared to the
     * one used by rewriteAppendOnlyFileBackground() function. */
    snprintf(tmpfile,256,"temp-rewriteaof-%d.aof", (int) getpid());
#ifdef _WIN32
    fp = fopen(tmpfile,"wb");
#else
    fp = fopen(tmpfile,"w");
#endif
    if (!fp) {
        redisLog(REDIS_WARNING, "Opening the temp file for AOF rewrite in rewriteAppendOnlyFile(): %s", strerror(errno));
        return REDIS_ERR;
    }

    rioInitWithFile(&aof,fp);
    if (server.aof_rewrite_incremental_fsync)
        rioSetAutoSync(&aof,REDIS_AOF_AUTOSYNC_BYTES);
    for (j = 0; j < server.dbnum; j++) {
        char selectcmd[] = "*2\r\n$6\r\nSELECT\r\n";
        redisDb *db = server.db+j;
        dict *d;

#ifdef _WIN32
        cowLock();
        if (server.isBackgroundSaving == 1) {
            /* use background DB copy */
            db = server.cowSaveDb+j;
        }
        d = db->dict;
        if (dictSize(d) == 0) {
            cowUnlock();
            continue;
        }
        di = roDBGetIterator(j);
        /* to prevent rehash of expires from background thread, get safe iterator */
        expIter = dictGetSafeIterator(db->expires);
        cowUnlock();
#else
        d = db->dict;
        if (dictSize(d) == 0) continue;
        di = dictGetSafeIterator(d);
#endif
        if (!di) {
            fclose(fp);
            return REDIS_ERR;
        }

        /* SELECT the new DB */
        if (rioWrite(&aof,selectcmd,sizeof(selectcmd)-1) == 0) goto werr;
        if (rioWriteBulkLongLong(&aof,j) == 0) goto werr;

        /* Iterate this DB writing every entry */
#ifdef _WIN32
        while((de = roDictNext(di)) != NULL) {
#else
        while((de = dictNext(di)) != NULL) {
#endif
            sds keystr;
            robj key, *o;
            long long expiretime;

            keystr = dictGetKey(de);
            o = dictGetVal(de);
            initStaticStringObject(key,keystr);
#ifdef _WIN32
            expiretime = getExpireForSave(db,&key);
#else
            expiretime = getExpire(db,&key);
#endif

            /* If this key is already expired skip it */
            if (expiretime != -1 && expiretime < now) continue;

#ifdef _WIN32
            cowLock();
            if (o->type == REDIS_LIST ||
                o->type == REDIS_SET ||
                o->type == REDIS_ZSET ||
                o->type == REDIS_HASH) {
                    o = (robj *)getRoConvertedObj(keystr, o);
            }
            cowUnlock();
#endif
            /* Save the key and associated value */
            if (o->type == REDIS_STRING) {
                /* Emit a SET command */
                char cmd[]="*3\r\n$3\r\nSET\r\n";
                if (rioWrite(&aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                /* Key and value */
                if (rioWriteBulkObject(&aof,&key) == 0) goto werr;
                if (rioWriteBulkObject(&aof,o) == 0) goto werr;
            } else if (o->type == REDIS_LIST) {
                if (rewriteListObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_SET) {
                if (rewriteSetObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_ZSET) {
                if (rewriteSortedSetObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_HASH) {
                if (rewriteHashObject(&aof,&key,o) == 0) goto werr;
            } else {
                redisPanic("Unknown object type");
            }
            /* Save the expire time */
            if (expiretime != -1) {
                char cmd[]="*3\r\n$9\r\nPEXPIREAT\r\n";
                if (rioWrite(&aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                if (rioWriteBulkObject(&aof,&key) == 0) goto werr;
                if (rioWriteBulkLongLong(&aof,expiretime) == 0) goto werr;
            }
        }
#ifdef _WIN32
        if (expIter) dictReleaseIterator(expIter);
        roDictReleaseIterator(di);
#else
        dictReleaseIterator(di);
#endif
    }

    /* Make sure data will not remain on the OS's output buffers */
    fflush(fp);
    aof_fsync(fileno(fp));
    fclose(fp);

    /* Use RENAME to make sure the DB file is changed atomically only
     * if the generate DB file is ok. */
    if (rename(tmpfile,filename) == -1) {
        redisLog(REDIS_WARNING,"Error moving temp append only file on the final destination: %s", strerror(errno));
        unlink(tmpfile);
        return REDIS_ERR;
    }
    redisLog(REDIS_NOTICE,"SYNC append only file rewrite performed");
    return REDIS_OK;

werr:
    fclose(fp);
    unlink(tmpfile);
    redisLog(REDIS_WARNING,"Write error writing append only file on disk: %s", strerror(errno));
#ifdef _WIN32
    if (expIter) dictReleaseIterator(expIter);
    if (di) roDictReleaseIterator(di);
#else
    if (di) dictReleaseIterator(di);
#endif
    return REDIS_ERR;
}

/* This is how rewriting of the append only file in background works:
 *
 * 1) The user calls BGREWRITEAOF
 * 2) Redis calls this function, that forks():
 *    2a) the child rewrite the append only file in a temp file.
 *    2b) the parent accumulates differences in server.aof_rewrite_buf.
 * 3) When the child finished '2a' exists.
 * 4) The parent will trap the exit code, if it's OK, will append the
 *    data accumulated into server.aof_rewrite_buf into the temp file, and
 *    finally will rename(2) the temp file in the actual file name.
 *    The the new file is reopened as the new append only file. Profit!
 */
#ifdef _WIN32
int rewriteAppendOnlyFileBackground(void) {
    pid_t childpid;
    char tmpfile[256];

    if (server.aof_child_pid != -1) return REDIS_ERR;
    if (server.rdb_child_pid != -1) return REDIS_ERR;

    childpid = getpid();
    snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", childpid);
    server.aof_rewrite_scheduled = 0;
    server.aof_child_pid = childpid;
    updateDictResizePolicy();
    server.aof_selected_db = -1;

    if (bkgdsave_start(tmpfile, rewriteAppendOnlyFile) == -1) {
        server.rdbbkgdfsave.background = 0;
        redisLog(REDIS_NOTICE,
            "Foreground append only file rewriting started by pid %d", childpid);

        if (rewriteAppendOnlyFile(tmpfile) == REDIS_OK) {
            backgroundRewriteDoneHandler(0, 0);
            return REDIS_OK;
        } else {
            backgroundRewriteDoneHandler(0, 255);
            redisLog(REDIS_WARNING,
                "Can't rewrite append only file in background: spoon: %s",
                strerror(errno));
            return REDIS_ERR;
        }
    }
    return REDIS_OK; /* unreached */
}

#else
int rewriteAppendOnlyFileBackground(void) {
    pid_t childpid;
    long long start;

    if (server.aof_child_pid != -1) return REDIS_ERR;
    start = ustime();
    if ((childpid = fork()) == 0) {
        char tmpfile[256];

        /* Child */
        if (server.ipfd > 0) close(server.ipfd);
        if (server.sofd > 0) close(server.sofd);
        snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) getpid());
        if (rewriteAppendOnlyFile(tmpfile) == REDIS_OK) {
            size_t private_dirty = zmalloc_get_private_dirty();

            if (private_dirty) {
                redisLog(REDIS_NOTICE,
                    "AOF rewrite: %lu MB of memory used by copy-on-write",
                    private_dirty/(1024*1024));
            }
            exitFromChild(0);
        } else {
            exitFromChild(1);
        }
    } else {
        /* Parent */
        server.stat_fork_time = ustime()-start;
        if (childpid == -1) {
            redisLog(REDIS_WARNING,
                "Can't rewrite append only file in background: fork: %s",
                strerror(errno));
            return REDIS_ERR;
        }
        redisLog(REDIS_NOTICE,
            "Background append only file rewriting started by pid %d",childpid);
        server.aof_rewrite_scheduled = 0;
        server.aof_rewrite_time_start = time(NULL);
        server.aof_child_pid = childpid;
        updateDictResizePolicy();
        /* We set appendseldb to -1 in order to force the next call to the
         * feedAppendOnlyFile() to issue a SELECT command, so the differences
         * accumulated by the parent into server.aof_rewrite_buf will start
         * with a SELECT statement and it will be safe to merge. */
        server.aof_selected_db = -1;
        return REDIS_OK;
    }
    return REDIS_OK; /* unreached */
}
#endif

void bgrewriteaofCommand(redisClient *c) {
    if (server.aof_child_pid != -1) {
        addReplyError(c,"Background append only file rewriting already in progress");
    } else if (server.rdb_child_pid != -1) {
        server.aof_rewrite_scheduled = 1;
        addReplyStatus(c,"Background append only file rewriting scheduled");
    } else if (rewriteAppendOnlyFileBackground() == REDIS_OK) {
        addReplyStatus(c,"Background append only file rewriting started");
    } else {
        addReply(c,shared.err);
    }
}

void aofRemoveTempFile(pid_t childpid) {
    char tmpfile[256];

    snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) childpid);
    unlink(tmpfile);
}

/* Update the server.aof_current_size filed explicitly using stat(2)
 * to check the size of the file. This is useful after a rewrite or after
 * a restart, normally the size is updated just adding the write length
 * to the current length, that is much faster. */
void aofUpdateCurrentSize(void) {
    struct redis_stat sb;

#ifdef _WIN32
    if (server.aof_fd == -1) {
        redisLog(REDIS_NOTICE,"Unable to check the AOF length: %s", "appendfd is -1");
        return;
    }
#endif
    if (redis_fstat(server.aof_fd,&sb) == -1) {
        redisLog(REDIS_WARNING,"Unable to obtain the AOF file length. stat: %s",
            strerror(errno));
    } else {
        server.aof_current_size = sb.st_size;
    }
}

/* 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();
#ifdef _WIN32
        char tmpfile_old[256];
#endif

        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);
#ifdef _WIN32
        newfd = open(tmpfile,O_WRONLY|O_APPEND|O_CREAT|_O_BINARY,_S_IREAD|_S_IWRITE);
#else
        newfd = open(tmpfile,O_WRONLY|O_APPEND);
#endif
        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. */
#ifdef _WIN32
        oldfd = -1; /* We'll set this to the current AOF filedes later. */

        /* Close files before renaming */
        close(newfd);
        if (server.aof_fd != -1) close(server.aof_fd);
        /* now rename the existing file to allow new file to be renamed */
        snprintf(tmpfile_old,256,"temp-rewriteaof-old-%d.aof",
            (int)server.aof_child_pid);
        if (server.aof_fd != -1) {
            if (rename(server.aof_filename, tmpfile_old) == -1) {
                redisLog(REDIS_WARNING,
                    "Error trying to rename the existing AOF to old tempfile: %s", strerror(errno));
            }
        }
        if (rename(tmpfile,server.aof_filename) == -1) {
            redisLog(REDIS_WARNING,
                "Error trying to rename the temporary AOF: %s", strerror(errno));
            if (server.aof_fd != -1) {
                if (rename(tmpfile_old, server.aof_filename) == -1) {
                    redisLog(REDIS_WARNING,
                        "Error trying to rename the existing AOF from old tempfile: %s", strerror(errno));
                }
            }
            if (oldfd != -1) close(oldfd);
            goto cleanup;
        }
        /* now open the files again with new names */
        newfd = open(server.aof_filename, O_WRONLY|O_APPEND|_O_BINARY);
        if (newfd == -1) {
            /* Windows fix: More info */
            redisLog(REDIS_WARNING, "Not able to reopen the temporary AOF file after rename");
            goto cleanup;
        }
        if (server.aof_fd != -1) {
            server.aof_fd = open(tmpfile_old, O_WRONLY|O_APPEND|O_CREAT|_O_BINARY,0644);
        }
#else
        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;
        }
#endif

        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. */
#ifdef _WIN32
        if (oldfd != -1) bioCreateBackgroundJob(REDIS_BIO_CLOSE_FILE,(void*)(size_t)oldfd,NULL,NULL);
#else
        if (oldfd != -1) bioCreateBackgroundJob(REDIS_BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL);
#endif

        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);
#ifdef _WIN32
    server.rdbbkgdfsave.state = BKSAVE_IDLE;
    /* turn off copy on write */
    cowBkgdSaveStop();
#endif
    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;
}