Redis 7.0 Multi Part AOF的设计和实现

aof_pending_rewrite:0
aof_buffer_length:35500
aof_rewrite_buffer_length:34000
aof_pending_bio_fsync:0

3351:M 25 Jan 2022 09:55:39.655 * Background append only file rewriting started by pid 6817
3351:M 25 Jan 2022 09:57:51.864 * AOF rewrite child asks to stop sending diffs.
6817:C 25 Jan 2022 09:57:51.864 * Parent agreed to stop sending diffs. Finalizing AOF...
6817:C 25 Jan 2022 09:57:51.864 * Concatenating 2135.60 MB of AOF diff received from parent.
3351:M 25 Jan 2022 09:57:56.545 * Background AOF buffer size: 100 MB

/* Append data to the AOF rewrite buffer, allocating new blocks if needed. */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) {
    // 此处省略其他细节...

    /* Install a file event to send data to the rewrite child if there is
     * not one already. */
    if (!server.aof_stop_sending_diff &&
        aeGetFileEvents(server.el,server.aof_pipe_write_data_to_child) == 0)
    {
        aeCreateFileEvent(server.el, server.aof_pipe_write_data_to_child,
            AE_WRITABLE, aofChildWriteDiffData, NULL);
    } 

    // 此处省略其他细节...
}

int rewriteAppendOnlyFile(char *filename) {
     // 此处省略其他细节...

    /* Read again a few times to get more data from the parent.
     * We can't read forever (the server may receive data from clients
     * faster than it is able to send data to the child), so we try to read
     * some more data in a loop as soon as there is a good chance more data
     * will come. If it looks like we are wasting time, we abort (this
     * happens after 20 ms without new data). */
    int nodata = 0;
    mstime_t start = mstime();
    while(mstime()-start < 1000 && nodata < 20) {
        if (aeWait(server.aof_pipe_read_data_from_parent, AE_READABLE, 1) <= 0)
        {
            nodata++;
            continue;
        }
        nodata = 0; /* Start counting from zero, we stop on N *contiguous*
                       timeouts. */
        aofReadDiffFromParent();
    }

    // 此处省略其他细节...
}

void backgroundRewriteDoneHandler(int exitcode, int bysignal) {
    // 此处省略其他细节...

    /* Flush the differences accumulated by the parent to the rewritten AOF. */
    if (aofRewriteBufferWrite(newfd) == -1) {
        serverLog(LL_WARNING,
                "Error trying to flush the parent diff to the rewritten AOF: %s", strerror(errno));
        close(newfd);
        goto cleanup;
     }

     // 此处省略其他细节...
}

/* AOF pipes used to communicate between parent and child during rewrite. */
 int aof_pipe_write_data_to_child;
 int aof_pipe_read_data_from_parent;
 int aof_pipe_write_ack_to_parent;
 int aof_pipe_read_ack_from_child;
 int aof_pipe_write_ack_to_child;
 int aof_pipe_read_ack_from_parent;

typedef struct {
    sds           file_name;  /* file name */
    long long     file_seq;   /* file sequence */
    aof_file_type file_type;  /* file type */
} aofInfo;

typedef struct {
    aofInfo     *base_aof_info;       /* BASE file information. NULL if there is no BASE file. */
    list        *incr_aof_list;       /* INCR AOFs list. We may have multiple INCR AOF when rewrite fails. */
    list        *history_aof_list;    /* HISTORY AOF list. When the AOFRW success, The aofInfo contained in
                                         `base_aof_info` and `incr_aof_list` will be moved to this list. We
                                         will delete these AOF files when AOFRW finish. */
    long long   curr_base_file_seq;   /* The sequence number used by the current BASE file. */
    long long   curr_incr_file_seq;   /* The sequence number used by the current INCR file. */
    int         dirty;                /* 1 Indicates that the aofManifest in the memory is inconsistent with
                                         disk, we need to persist it immediately. */
} aofManifest;

struct redisServer {
    // 此处省略其他细节...

    aofManifest *aof_manifest;       /* Used to track AOFs. */

    // 此处省略其他细节...
}

file appendonly.aof.1.base.rdb seq 1 type b
file appendonly.aof.1.incr.aof seq 1 type i
file appendonly.aof.2.incr.aof seq 2 type i

file appendonly.aof.1.base.rdb seq 1 type b newkey newvalue
file appendonly.aof.1.incr.aof type i seq 1 
# this is annotations
seq 2 type i file appendonly.aof.2.incr.aof

#define BASE_FILE_SUFFIX           ".base"
#define INCR_FILE_SUFFIX           ".incr"
#define RDB_FORMAT_SUFFIX          ".rdb"
#define AOF_FORMAT_SUFFIX          ".aof"
#define MANIFEST_NAME_SUFFIX       ".manifest"

appendonly.aof.1.base.rdb // 开启RDB preamble
appendonly.aof.1.base.aof // 关闭RDB preamble
appendonly.aof.1.incr.aof
appendonly.aof.2.incr.aof

/* Load the AOF files according the aofManifest pointed by am. */
int loadAppendOnlyFiles(aofManifest *am) {
    // 此处省略其他细节...

    /* If the 'server.aof_filename' file exists in dir, we may be starting
     * from an old redis version. We will use enter upgrade mode in three situations.
     *
     * 1. If the 'server.aof_dirname' directory not exist
     * 2. If the 'server.aof_dirname' directory exists but the manifest file is missing
     * 3. If the 'server.aof_dirname' directory exists and the manifest file it contains
     *    has only one base AOF record, and the file name of this base AOF is 'server.aof_filename',
     *    and the 'server.aof_filename' file not exist in 'server.aof_dirname' directory
     * */
    if (fileExist(server.aof_filename)) {
        if (!dirExists(server.aof_dirname) ||
            (am->base_aof_info == NULL && listLength(am->incr_aof_list) == 0) ||
            (am->base_aof_info != NULL && listLength(am->incr_aof_list) == 0 &&
             !strcmp(am->base_aof_info->file_name, server.aof_filename) && !aofFileExist(server.aof_filename)))
        {
            aofUpgradePrepare(am);
        }
    }

    // 此处省略其他细节...
  }

void aofUpgradePrepare(aofManifest *am) {
    // 此处省略其他细节...

    /* 1. Manually construct a BASE type aofInfo and add it to aofManifest. */
    if (am->base_aof_info) aofInfoFree(am->base_aof_info);
    aofInfo *ai = aofInfoCreate();
    ai->file_name = sdsnew(server.aof_filename);
    ai->file_seq = 1;
    ai->file_type = AOF_FILE_TYPE_BASE;
    am->base_aof_info = ai;
    am->curr_base_file_seq = 1;
    am->dirty = 1;

    /* 2. Persist the manifest file to AOF directory. */
    if (persistAofManifest(am) != C_OK) {
        exit(1);
    }

    /* 3. Move the old AOF file to AOF directory. */
    sds aof_filepath = makePath(server.aof_dirname, server.aof_filename);
    if (rename(server.aof_filename, aof_filepath) == -1) {
        sdsfree(aof_filepath);
        exit(1);;
    }

    // 此处省略其他细节...
}

int loadAppendOnlyFiles(aofManifest *am) {
    // 此处省略其他细节...

    /* Here we calculate the total size of all BASE and INCR files in
     * advance, it will be set to `server.loading_total_bytes`. */
    total_size = getBaseAndIncrAppendOnlyFilesSize(am);
    startLoading(total_size, RDBFLAGS_AOF_PREAMBLE, 0);

    /* Load BASE AOF if needed. */
    if (am->base_aof_info) {
        aof_name = (char*)am->base_aof_info->file_name;
        updateLoadingFileName(aof_name);
        loadSingleAppendOnlyFile(aof_name);
    }

    /* Load INCR AOFs if needed. */
    if (listLength(am->incr_aof_list)) {
        listNode *ln;
        listIter li;

        listRewind(am->incr_aof_list, &li);
        while ((ln = listNext(&li)) != NULL) {
            aofInfo *ai = (aofInfo*)ln->value;
            aof_name = (char*)ai->file_name;
            updateLoadingFileName(aof_name);
            loadSingleAppendOnlyFile(aof_name);
        }
    }

    server.aof_current_size = total_size;
    server.aof_rewrite_base_size = server.aof_current_size;
    server.aof_fsync_offset = server.aof_current_size;

    stopLoading();

    // 此处省略其他细节...
}

le appendonly.aof.1.base.rdb seq 1 type b
file appendonly.aof.1.incr.aof seq 1 type i

file appendonly.aof.1.base.rdb seq 1 type b
file appendonly.aof.1.incr.aof seq 1 type i
file appendonly.aof.2.incr.aof seq 2 type i

file appendonly.aof.2.base.rdb seq 2 type b
file appendonly.aof.1.base.rdb seq 1 type h
file appendonly.aof.1.incr.aof seq 1 type h
file appendonly.aof.2.incr.aof seq 2 type i

void backgroundRewriteDoneHandler(int exitcode, int bysignal) {
    snprintf(tmpfile, 256, "temp-rewriteaof-bg-%d.aof",
        (int)server.child_pid);

    /* 1. Dup a temporary aof_manifest for subsequent modifications. */
    temp_am = aofManifestDup(server.aof_manifest);

    /* 2. Get a new BASE file name and mark the previous (if we have)
     * as the HISTORY type. */
    new_base_filename = getNewBaseFileNameAndMarkPreAsHistory(temp_am);

    /* 3. Rename the temporary aof file to 'new_base_filename'. */
    if (rename(tmpfile, new_base_filename) == -1) {
        aofManifestFree(temp_am);
        goto cleanup;
    }

    /* 4. Change the AOF file type in 'incr_aof_list' from AOF_FILE_TYPE_INCR
     * to AOF_FILE_TYPE_HIST, and move them to the 'history_aof_list'. */
    markRewrittenIncrAofAsHistory(temp_am);

    /* 5. Persist our modifications. */
    if (persistAofManifest(temp_am) == C_ERR) {
        bg_unlink(new_base_filename);
        aofManifestFree(temp_am);
        goto cleanup;
    }

    /* 6. We can safely let `server.aof_manifest` point to 'temp_am' and free the previous one. */
    aofManifestFreeAndUpdate(temp_am);

    /* 7. We don't care about the return value of `aofDelHistoryFiles`, because the history
     * deletion failure will not cause any problems. */
    aofDelHistoryFiles();
}

if (ftruncate(server.aof_fd, server.aof_last_incr_size) == -1) {
      //此处省略其他细节...
 }

if (server.aof_state == AOF_ON &&
    !hasActiveChildProcess() &&
    server.aof_rewrite_perc &&
    server.aof_current_size > server.aof_rewrite_min_size &&
    !aofRewriteLimited())
{
    long long base = server.aof_rewrite_base_size ?
        server.aof_rewrite_base_size : 1;
    long long growth = (server.aof_current_size*100/base) - 100;
    if (growth >= server.aof_rewrite_perc) {
        rewriteAppendOnlyFileBackground();
    }
}