redis数据结构源码分析——压缩列表ziplist(II)API详解+级联更新

前面我们聊了压缩列表的源码解析，留了一个坑，就是API当中的新增、删除和查找，那么本篇我们就来深入分析下这三个API

API详解

API中，插入删除更新的源码比较复杂，我们本篇深入讲解下这三个API

ziplistInsert(插入)

首先看到插入方法，是直接调用了另外一个插入，我们直接来看这个方法

unsigned char *__ziplistInsert(unsigned char *zl, unsigned char *p, unsigned char *s, unsigned int slen) {
    size_t curlen = intrev32ifbe(ZIPLIST_BYTES(zl)), reqlen, newlen;
    unsigned int prevlensize, prevlen = 0;
    size_t offset;
    int nextdiff = 0;
    unsigned char encoding = 0;
    long long value = 123456789; /* initialized to avoid warning. Using a value
                                    that is easy to see if for some reason
                                    we use it uninitialized. */
    zlentry tail;

    /* Find out prevlen for the entry that is inserted. */
    if (p[0] != ZIP_END) {
        ZIP_DECODE_PREVLEN(p, prevlensize, prevlen);
    } else {
        unsigned char *ptail = ZIPLIST_ENTRY_TAIL(zl);
        if (ptail[0] != ZIP_END) {
            prevlen = zipRawEntryLengthSafe(zl, curlen, ptail);
        }
    }

    /* See if the entry can be encoded */
    if (zipTryEncoding(s,slen,&value,&encoding)) {
        /* 'encoding' is set to the appropriate integer encoding */
        reqlen = zipIntSize(encoding);
    } else {
        /* 'encoding' is untouched, however zipStoreEntryEncoding will use the
         * string length to figure out how to encode it. */
        reqlen = slen;
    }
    /* We need space for both the length of the previous entry and
     * the length of the payload. */
    reqlen += zipStorePrevEntryLength(NULL,prevlen);
    reqlen += zipStoreEntryEncoding(NULL,encoding,slen);

    /* When the insert position is not equal to the tail, we need to
     * make sure that the next entry can hold this entry's length in
     * its prevlen field. */
    int forcelarge = 0;
    nextdiff = (p[0] != ZIP_END) ? zipPrevLenByteDiff(p,reqlen) : 0;
    if (nextdiff == -4 && reqlen < 4) {
        nextdiff = 0;
        forcelarge = 1;
    }

    /* Store offset because a realloc may change the address of zl. */
    offset = p-zl;
    newlen = curlen+reqlen+nextdiff;
    zl = ziplistResize(zl,newlen);
    p = zl+offset;

    /* Apply memory move when necessary and update tail offset. */
    if (p[0] != ZIP_END) {
        /* Subtract one because of the ZIP_END bytes */
        memmove(p+reqlen,p-nextdiff,curlen-offset-1+nextdiff);

        /* Encode this entry's raw length in the next entry. */
        if (forcelarge)
            zipStorePrevEntryLengthLarge(p+reqlen,reqlen);
        else
            zipStorePrevEntryLength(p+reqlen,reqlen);

        /* Update offset for tail */
        ZIPLIST_TAIL_OFFSET(zl) =
            intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+reqlen);

        /* When the tail contains more than one entry, we need to take
         * "nextdiff" in account as well. Otherwise, a change in the
         * size of prevlen doesn't have an effect on the *tail* offset. */
        assert(zipEntrySafe(zl, newlen, p+reqlen, &tail, 1));
        if (p[reqlen+tail.headersize+tail.len] != ZIP_END) {
            ZIPLIST_TAIL_OFFSET(zl) =
                intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+nextdiff);
        }
    } else {
        /* This element will be the new tail. */
        ZIPLIST_TAIL_OFFSET(zl) = intrev32ifbe(p-zl);
    }

    /* When nextdiff != 0, the raw length of the next entry has changed, so
     * we need to cascade the update throughout the ziplist */
    if (nextdiff != 0) {
        offset = p-zl;
        zl = __ziplistCascadeUpdate(zl,p+reqlen);
        p = zl+offset;
    }

    /* Write the entry */
    p += zipStorePrevEntryLength(p,prevlen);
    p += zipStoreEntryEncoding(p,encoding,slen);
    if (ZIP_IS_STR(encoding)) {
        memcpy(p,s,slen);
    } else {
        zipSaveInteger(p,value,encoding);
    }
    ZIPLIST_INCR_LENGTH(zl,1);
    return zl;
}

这里的代码较长，我们分三个阶段来做分析：
1、编码

2、重新分配空间

3、数据复制

这里的级联更新我们下面会讲到

ziplistDelete(删除)

这里我们也直接看__ziplistDelete方法

unsigned char * __ziplistDelete(unsigned char *zl, unsigned char *p, unsigned int num) {
    unsigned int i, totlen, deleted = 0;
    size_t offset;
    int nextdiff = 0;
    zlentry first, tail;
    size_t zlbytes = intrev32ifbe(ZIPLIST_BYTES(zl));

    zipEntry(p, &first); /* no need for "safe" variant since the input pointer was validated by the function that returned it. */
    for (i = 0; p[0] != ZIP_END && i < num; i++) {
        p += zipRawEntryLengthSafe(zl, zlbytes, p);
        deleted++;
    }

    assert(p >= first.p);
    totlen = p-first.p; /* Bytes taken by the element(s) to delete. */
    if (totlen > 0) {
        uint32_t set_tail;
        if (p[0] != ZIP_END) {
            /* Storing `prevrawlen` in this entry may increase or decrease the
             * number of bytes required compare to the current `prevrawlen`.
             * There always is room to store this, because it was previously
             * stored by an entry that is now being deleted. */
            nextdiff = zipPrevLenByteDiff(p,first.prevrawlen);

            /* Note that there is always space when p jumps backward: if
             * the new previous entry is large, one of the deleted elements
             * had a 5 bytes prevlen header, so there is for sure at least
             * 5 bytes free and we need just 4. */
            p -= nextdiff;
            assert(p >= first.p && p<zl+zlbytes-1);
            zipStorePrevEntryLength(p,first.prevrawlen);

            /* Update offset for tail */
            set_tail = intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))-totlen;

            /* When the tail contains more than one entry, we need to take
             * "nextdiff" in account as well. Otherwise, a change in the
             * size of prevlen doesn't have an effect on the *tail* offset. */
            assert(zipEntrySafe(zl, zlbytes, p, &tail, 1));
            if (p[tail.headersize+tail.len] != ZIP_END) {
                set_tail = set_tail + nextdiff;
            }

            /* Move tail to the front of the ziplist */
            /* since we asserted that p >= first.p. we know totlen >= 0,
             * so we know that p > first.p and this is guaranteed not to reach
             * beyond the allocation, even if the entries lens are corrupted. */
            size_t bytes_to_move = zlbytes-(p-zl)-1;
            memmove(first.p,p,bytes_to_move);
        } else {
            /* The entire tail was deleted. No need to move memory. */
            set_tail = (first.p-zl)-first.prevrawlen;
        }

        /* Resize the ziplist */
        offset = first.p-zl;
        zlbytes -= totlen - nextdiff;
        zl = ziplistResize(zl, zlbytes);
        p = zl+offset;

        /* Update record count */
        ZIPLIST_INCR_LENGTH(zl,-deleted);

        /* Set the tail offset computed above */
        assert(set_tail <= zlbytes - ZIPLIST_END_SIZE);
        ZIPLIST_TAIL_OFFSET(zl) = intrev32ifbe(set_tail);

        /* When nextdiff != 0, the raw length of the next entry has changed, so
         * we need to cascade the update throughout the ziplist */
        if (nextdiff != 0)
            zl = __ziplistCascadeUpdate(zl,p);
    }
    return zl;
}

1、先计算出要删除的元素的长度，这里的逻辑是比较简单的
大致步骤为：解码待删除元素-遍历所有待删除元素-计算待删除元素长度
2、数据复制

3、重新分配空间

ziplistFind(查找)

查找的方法其实相对插入和删除来说简单的多

unsigned char *ziplistFind(unsigned char *zl, unsigned char *p, unsigned char *vstr, unsigned int vlen, unsigned int skip) {
    int skipcnt = 0;
    unsigned char vencoding = 0;
    long long vll = 0;
    size_t zlbytes = ziplistBlobLen(zl);

    while (p[0] != ZIP_END) {
        struct zlentry e;
        unsigned char *q;

        assert(zipEntrySafe(zl, zlbytes, p, &e, 1));
        q = p + e.prevrawlensize + e.lensize;

        if (skipcnt == 0) {
            /* Compare current entry with specified entry */
            if (ZIP_IS_STR(e.encoding)) {
                if (e.len == vlen && memcmp(q, vstr, vlen) == 0) {
                    return p;
                }
            } else {
                /* Find out if the searched field can be encoded. Note that
                 * we do it only the first time, once done vencoding is set
                 * to non-zero and vll is set to the integer value. */
                if (vencoding == 0) {
                    if (!zipTryEncoding(vstr, vlen, &vll, &vencoding)) {
                        /* If the entry can't be encoded we set it to
                         * UCHAR_MAX so that we don't retry again the next
                         * time. */
                        vencoding = UCHAR_MAX;
                    }
                    /* Must be non-zero by now */
                    assert(vencoding);
                }

                /* Compare current entry with specified entry, do it only
                 * if vencoding != UCHAR_MAX because if there is no encoding
                 * possible for the field it can't be a valid integer. */
                if (vencoding != UCHAR_MAX) {
                    long long ll = zipLoadInteger(q, e.encoding);
                    if (ll == vll) {
                        return p;
                    }
                }
            }

            /* Reset skip count */
            skipcnt = skip;
        } else {
            /* Skip entry */
            skipcnt--;
        }

        /* Move to next entry */
        p = q + e.len;
    }

    return NULL;
}

1、计算节点属性
2、判断节点类型
3、如果是字符串，对比内容
4、如果是整数，对比数值
5、找到就返回，找不到就指向下一个
这里的逻辑不算复杂，我们整合为一个图来讲解

级联更新

出现原因

出现级联更新，主要是因为prevlensize，假设我们要删除某个entry，prevlensize是会变更的。
我们参照这张图举个例子：

假设此时我们需要删除entryX，entryX是128字节，entyrX-1为512字节，entyrX+1为253字节。我们上文讲过prevlensize，这里entryX的prevlensize为1，而现在prevlensize变为了5，而这样就需要给entyrX+1后的所有节点全部向后移，也就是nextdiff。

流程

我们先看下代码

unsigned char *__ziplistCascadeUpdate(unsigned char *zl, unsigned char *p) {
    zlentry cur;
    size_t prevlen, prevlensize, prevoffset; /* Informat of the last changed entry. */
    size_t firstentrylen; /* Used to handle insert at head. */
    size_t rawlen, curlen = intrev32ifbe(ZIPLIST_BYTES(zl));
    size_t extra = 0, cnt = 0, offset;
    size_t delta = 4; /* Extra bytes needed to update a entry's prevlen (5-1). */
    unsigned char *tail = zl + intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl));

    /* Empty ziplist */
    if (p[0] == ZIP_END) return zl;

    zipEntry(p, &cur); /* no need for "safe" variant since the input pointer was validated by the function that returned it. */
    firstentrylen = prevlen = cur.headersize + cur.len;
    prevlensize = zipStorePrevEntryLength(NULL, prevlen);
    prevoffset = p - zl;
    p += prevlen;

    /* Iterate ziplist to find out how many extra bytes do we need to update it. */
    while (p[0] != ZIP_END) {
        assert(zipEntrySafe(zl, curlen, p, &cur, 0));

        /* Abort when "prevlen" has not changed. */
        if (cur.prevrawlen == prevlen) break;

        /* Abort when entry's "prevlensize" is big enough. */
        if (cur.prevrawlensize >= prevlensize) {
            if (cur.prevrawlensize == prevlensize) {
                zipStorePrevEntryLength(p, prevlen);
            } else {
                /* This would result in shrinking, which we want to avoid.
                 * So, set "prevlen" in the available bytes. */
                zipStorePrevEntryLengthLarge(p, prevlen);
            }
            break;
        }

        /* cur.prevrawlen means cur is the former head entry. */
        assert(cur.prevrawlen == 0 || cur.prevrawlen + delta == prevlen);

        /* Update prev entry's info and advance the cursor. */
        rawlen = cur.headersize + cur.len;
        prevlen = rawlen + delta; 
        prevlensize = zipStorePrevEntryLength(NULL, prevlen);
        prevoffset = p - zl;
        p += rawlen;
        extra += delta;
        cnt++;
    }

    /* Extra bytes is zero all update has been done(or no need to update). */
    if (extra == 0) return zl;

    /* Update tail offset after loop. */
    if (tail == zl + prevoffset) {
        /* When the last entry we need to update is also the tail, update tail offset
         * unless this is the only entry that was updated (so the tail offset didn't change). */
        if (extra - delta != 0) {
            ZIPLIST_TAIL_OFFSET(zl) =
                intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+extra-delta);
        }
    } else {
        /* Update the tail offset in cases where the last entry we updated is not the tail. */
        ZIPLIST_TAIL_OFFSET(zl) =
            intrev32ifbe(intrev32ifbe(ZIPLIST_TAIL_OFFSET(zl))+extra);
    }

    /* Now "p" points at the first unchanged byte in original ziplist,
     * move data after that to new ziplist. */
    offset = p - zl;
    zl = ziplistResize(zl, curlen + extra);
    p = zl + offset;
    memmove(p + extra, p, curlen - offset - 1);
    p += extra;

    /* Iterate all entries that need to be updated tail to head. */
    while (cnt) {
        zipEntry(zl + prevoffset, &cur); /* no need for "safe" variant since we already iterated on all these entries above. */
        rawlen = cur.headersize + cur.len;
        /* Move entry to tail and reset prevlen. */
        memmove(p - (rawlen - cur.prevrawlensize), 
                zl + prevoffset + cur.prevrawlensize, 
                rawlen - cur.prevrawlensize);
        p -= (rawlen + delta);
        if (cur.prevrawlen == 0) {
            /* "cur" is the previous head entry, update its prevlen with firstentrylen. */
            zipStorePrevEntryLength(p, firstentrylen);
        } else {
            /* An entry's prevlen can only increment 4 bytes. */
            zipStorePrevEntryLength(p, cur.prevrawlen+delta);
        }
        /* Forward to previous entry. */
        prevoffset -= cur.prevrawlen;
        cnt--;
    }
    return zl;
}

__ziplistCascadeUpdate方法，这里的逻辑我们就直接放在一张图里

其实大家有注意到的话，可以看到，插入和删除的方法里，都会用到这个方法，所以其实是可以串联起来的，也建议大家去翻看源码稍微过一下。
感谢阅读，如果有任何疑问或不同意见，欢迎留言讨论。