Redis多線程演進(jìn)
點(diǎn)擊關(guān)注公眾號(hào),Java干貨及時(shí)送達(dá)
轉(zhuǎn)自:景同學(xué)
鏈接:https://juejin.cn/post/6928407842009546766
Redis作為一個(gè)基于內(nèi)存的緩存系統(tǒng),一直以高性能著稱,因沒有上下文切換以及無鎖操作,即使在單線程處理情況下,讀速度仍可達(dá)到11萬次/s,寫速度達(dá)到8.1萬次/s。但是,單線程的設(shè)計(jì)也給Redis帶來一些問題:
只能使用CPU一個(gè)核; 如果刪除的鍵過大(比如Set類型中有上百萬個(gè)對(duì)象),會(huì)導(dǎo)致服務(wù)端阻塞好幾秒; QPS難再提高。
針對(duì)上面問題,Redis在4.0版本以及6.0版本分別引入了Lazy Free以及多線程IO,逐步向多線程過渡,下面將會(huì)做詳細(xì)介紹。
| 單線程原理
都說Redis是單線程的,那么單線程是如何體現(xiàn)的?如何支持客戶端并發(fā)請(qǐng)求的?為了搞清這些問題,首先來了解下Redis是如何工作的。
Redis服務(wù)器是一個(gè)事件驅(qū)動(dòng)程序,服務(wù)器需要處理以下兩類事件:
文件事件:Redis服務(wù)器通過套接字與客戶端(或者其他Redis服務(wù)器)進(jìn)行連接,而文件事件就是服務(wù)器對(duì)套接字操作的抽象;服務(wù)器與客戶端的通信會(huì)產(chǎn)生相應(yīng)的文件事件,而服務(wù)器則通過監(jiān)聽并處理這些事件來完成一系列網(wǎng)絡(luò)通信操作,比如連接accept,read,write,close等;時(shí)間事件:Redis服務(wù)器中的一些操作(比如serverCron函數(shù))需要在給定的時(shí)間點(diǎn)執(zhí)行,而時(shí)間事件就是服務(wù)器對(duì)這類定時(shí)操作的抽象,比如過期鍵清理,服務(wù)狀態(tài)統(tǒng)計(jì)等。
如上圖,Redis將文件事件和時(shí)間事件進(jìn)行抽象,時(shí)間輪訓(xùn)器會(huì)監(jiān)聽I/O事件表,一旦有文件事件就緒,Redis就會(huì)優(yōu)先處理文件事件,接著處理時(shí)間事件。在上述所有事件處理上,Redis都是以單線程形式處理,所以說Redis是單線程的。此外,如下圖,Redis基于Reactor模式開發(fā)了自己的I/O事件處理器,也就是文件事件處理器,Redis在I/O事件處理上,采用了I/O多路復(fù)用技術(shù),同時(shí)監(jiān)聽多個(gè)套接字,并為套接字關(guān)聯(lián)不同的事件處理函數(shù),通過一個(gè)線程實(shí)現(xiàn)了多客戶端并發(fā)處理。

正因?yàn)檫@樣的設(shè)計(jì),在數(shù)據(jù)處理上避免了加鎖操作,既使得實(shí)現(xiàn)上足夠簡潔,也保證了其高性能。當(dāng)然,Redis單線程只是指其在事件處理上,實(shí)際上,Redis也并不是單線程的,比如生成RDB文件,就會(huì)fork一個(gè)子進(jìn)程來實(shí)現(xiàn),當(dāng)然,這不是本文要討論的內(nèi)容。
| Lazy Free機(jī)制
如上所知,Redis在處理客戶端命令時(shí)是以單線程形式運(yùn)行,而且處理速度很快,期間不會(huì)響應(yīng)其他客戶端請(qǐng)求,但若客戶端向Redis發(fā)送一條耗時(shí)較長的命令,比如刪除一個(gè)含有上百萬對(duì)象的Set鍵,或者執(zhí)行flushdb,flushall操作,Redis服務(wù)器需要回收大量的內(nèi)存空間,導(dǎo)致服務(wù)器卡住好幾秒,對(duì)負(fù)載較高的緩存系統(tǒng)而言將會(huì)是個(gè)災(zāi)難。為了解決這個(gè)問題,在Redis 4.0版本引入了Lazy Free,將慢操作異步化,這也是在事件處理上向多線程邁進(jìn)了一步。
如作者在其博客中所述,要解決慢操作,可以采用漸進(jìn)式處理,即增加一個(gè)時(shí)間事件,比如在刪除一個(gè)具有上百萬個(gè)對(duì)象的Set鍵時(shí),每次只刪除大鍵中的一部分?jǐn)?shù)據(jù),最終實(shí)現(xiàn)大鍵的刪除。但是,該方案可能會(huì)導(dǎo)致回收速度趕不上創(chuàng)建速度,最終導(dǎo)致內(nèi)存耗盡。因此,Redis最終實(shí)現(xiàn)上是將大鍵的刪除操作異步化,采用非阻塞刪除(對(duì)應(yīng)命令UNLINK),大鍵的空間回收交由單獨(dú)線程實(shí)現(xiàn),主線程只做關(guān)系解除,可以快速返回,繼續(xù)處理其他事件,避免服務(wù)器長時(shí)間阻塞。
以刪除(DEL命令)為例,看看Redis是如何實(shí)現(xiàn)的,下面就是刪除函數(shù)的入口,其中,lazyfree_lazy_user_del是是否修改DEL命令的默認(rèn)行為,一旦開啟,執(zhí)行DEL時(shí)將會(huì)以UNLINK形式執(zhí)行。
void?delCommand(client?*c)?{
????delGenericCommand(c,server.lazyfree_lazy_user_del);
}
/*?This?command?implements?DEL?and?LAZYDEL.?*/
void?delGenericCommand(client?*c,?int?lazy)?{
????int?numdel?=?0,?j;
????for?(j?=?1;?j?argc;?j++)?{
????????expireIfNeeded(c->db,c->argv[j]);
????????//?根據(jù)配置確定DEL在執(zhí)行時(shí)是否以lazy形式執(zhí)行
????????int?deleted??=?lazy???dbAsyncDelete(c->db,c->argv[j])?:
??????????????????????????????dbSyncDelete(c->db,c->argv[j]);
????????if?(deleted)?{
????????????signalModifiedKey(c,c->db,c->argv[j]);
????????????notifyKeyspaceEvent(NOTIFY_GENERIC,
????????????????"del",c->argv[j],c->db->id);
????????????server.dirty++;
????????????numdel++;
????????}
????}
????addReplyLongLong(c,numdel);
}
同步刪除很簡單,只要把key和value刪除,如果有內(nèi)層引用,則進(jìn)行遞歸刪除,這里不做介紹。下面看下異步刪除,Redis在回收對(duì)象時(shí),會(huì)先計(jì)算回收收益,只有回收收益在超過一定值時(shí),采用封裝成Job加入到異步處理隊(duì)列中,否則直接同步回收,這樣效率更高。回收收益計(jì)算也很簡單,比如String類型,回收收益值就是1,而Set類型,回收收益就是集合中元素個(gè)數(shù)。
/*?Delete?a?key,?value,?and?associated?expiration?entry?if?any,?from?the?DB.
?*?If?there?are?enough?allocations?to?free?the?value?object?may?be?put?into
?*?a?lazy?free?list?instead?of?being?freed?synchronously.?The?lazy?free?list
?*?will?be?reclaimed?in?a?different?bio.c?thread.?*/
#define?LAZYFREE_THRESHOLD?64
int?dbAsyncDelete(redisDb?*db,?robj?*key)?{
????/*?Deleting?an?entry?from?the?expires?dict?will?not?free?the?sds?of
?????*?the?key,?because?it?is?shared?with?the?main?dictionary.?*/
????if?(dictSize(db->expires)?>?0)?dictDelete(db->expires,key->ptr);
????/*?If?the?value?is?composed?of?a?few?allocations,?to?free?in?a?lazy?way
?????*?is?actually?just?slower...?So?under?a?certain?limit?we?just?free
?????*?the?object?synchronously.?*/
????dictEntry?*de?=?dictUnlink(db->dict,key->ptr);
????if?(de)?{
????????robj?*val?=?dictGetVal(de);
????????//?計(jì)算value的回收收益
????????size_t?free_effort?=?lazyfreeGetFreeEffort(val);
????????/*?If?releasing?the?object?is?too?much?work,?do?it?in?the?background
?????????*?by?adding?the?object?to?the?lazy?free?list.
?????????*?Note?that?if?the?object?is?shared,?to?reclaim?it?now?it?is?not
?????????*?possible.?This?rarely?happens,?however?sometimes?the?implementation
?????????*?of?parts?of?the?Redis?core?may?call?incrRefCount()?to?protect
?????????*?objects,?and?then?call?dbDelete().?In?this?case?we'll?fall
?????????*?through?and?reach?the?dictFreeUnlinkedEntry()?call,?that?will?be
?????????*?equivalent?to?just?calling?decrRefCount().?*/
????????//?只有回收收益超過一定值,才會(huì)執(zhí)行異步刪除,否則還是會(huì)退化到同步刪除
????????if?(free_effort?>?LAZYFREE_THRESHOLD?&&?val->refcount?==?1)?{
????????????atomicIncr(lazyfree_objects,1);
????????????bioCreateBackgroundJob(BIO_LAZY_FREE,val,NULL,NULL);
????????????dictSetVal(db->dict,de,NULL);
????????}
????}
????/*?Release?the?key-val?pair,?or?just?the?key?if?we?set?the?val
?????*?field?to?NULL?in?order?to?lazy?free?it?later.?*/
????if?(de)?{
????????dictFreeUnlinkedEntry(db->dict,de);
????????if?(server.cluster_enabled)?slotToKeyDel(key->ptr);
????????return?1;
????}?else?{
????????return?0;
????}
}
通過引入a threaded lazy free,Redis實(shí)現(xiàn)了對(duì)于Slow Operation的Lazy操作,避免了在大鍵刪除,FLUSHALL,FLUSHDB時(shí)導(dǎo)致服務(wù)器阻塞。當(dāng)然,在實(shí)現(xiàn)該功能時(shí),不僅引入了lazy free線程,也對(duì)Redis聚合類型在存儲(chǔ)結(jié)構(gòu)上進(jìn)行改進(jìn)。因?yàn)镽edis內(nèi)部使用了很多共享對(duì)象,比如客戶端輸出緩存。當(dāng)然,Redis并未使用加鎖來避免線程沖突,鎖競(jìng)爭(zhēng)會(huì)導(dǎo)致性能下降,而是去掉了共享對(duì)象,直接采用數(shù)據(jù)拷貝,如下,在3.x和6.x中ZSet節(jié)點(diǎn)value的不同實(shí)現(xiàn)。
//?3.2.5版本ZSet節(jié)點(diǎn)實(shí)現(xiàn),value定義robj?*obj
/*?ZSETs?use?a?specialized?version?of?Skiplists?*/
typedef?struct?zskiplistNode?{
????robj?*obj;
????double?score;
????struct?zskiplistNode?*backward;
????struct?zskiplistLevel?{
????????struct?zskiplistNode?*forward;
????????unsigned?int?span;
????}?level[];
}?zskiplistNode;
//?6.0.10版本ZSet節(jié)點(diǎn)實(shí)現(xiàn),value定義為sds?ele
/*?ZSETs?use?a?specialized?version?of?Skiplists?*/
typedef?struct?zskiplistNode?{
????sds?ele;
????double?score;
????struct?zskiplistNode?*backward;
????struct?zskiplistLevel?{
????????struct?zskiplistNode?*forward;
????????unsigned?long?span;
????}?level[];
}?zskiplistNode;
去掉共享對(duì)象,不但實(shí)現(xiàn)了lazy free功能,也為Redis向多線程跨進(jìn)帶來了可能,正如作者所述:
Now that values of aggregated data types are fully unshared, and client output buffers don’t contain shared objects as well, there is a lot to exploit. For example it is finally possible to implement threaded I/O in Redis, so that different clients are served by different threads. This means that we’ll have a global lock only when accessing the database, but the clients read/write syscalls and even the parsing of the command the client is sending, can happen in different threads.
| 多線程I/O及其局限性
Redis在4.0版本引入了Lazy Free,自此Redis有了一個(gè)Lazy Free線程專門用于大鍵的回收,同時(shí),也去掉了聚合類型的共享對(duì)象,這為多線程帶來可能,Redis也不負(fù)眾望,在6.0版本實(shí)現(xiàn)了多線程I/O。
實(shí)現(xiàn)原理
正如官方以前的回復(fù),Redis的性能瓶頸并不在CPU上,而是在內(nèi)存和網(wǎng)絡(luò)上。因此6.0發(fā)布的多線程并未將事件處理改成多線程,而是在I/O上,此外,如果把事件處理改成多線程,不但會(huì)導(dǎo)致鎖競(jìng)爭(zhēng),而且會(huì)有頻繁的上下文切換,即使用分段鎖來減少競(jìng)爭(zhēng),對(duì)Redis內(nèi)核也會(huì)有較大改動(dòng),性能也不一定有明顯提升。

如上圖紅色部分,就是Redis實(shí)現(xiàn)的多線程部分,利用多核來分擔(dān)I/O讀寫負(fù)荷。在事件處理線程每次獲取到可讀事件時(shí),會(huì)將所有就緒的讀事件分配給I/O線程,并進(jìn)行等待,在所有I/O線程完成讀操作后,事件處理線程開始執(zhí)行任務(wù)處理,在處理結(jié)束后,同樣將寫事件分配給I/O線程,等待所有I/O線程完成寫操作。
以讀事件處理為例,看下事件處理線程任務(wù)分配流程:
int?handleClientsWithPendingReadsUsingThreads(void)?{
????...
????/*?Distribute?the?clients?across?N?different?lists.?*/
????listIter?li;
????listNode?*ln;
????listRewind(server.clients_pending_read,&li);
????int?item_id?=?0;
????//?將等待處理的客戶端分配給I/O線程
????while((ln?=?listNext(&li)))?{
????????client?*c?=?listNodeValue(ln);
????????int?target_id?=?item_id?%?server.io_threads_num;
????????listAddNodeTail(io_threads_list[target_id],c);
????????item_id++;
????}
????...
????/*?Wait?for?all?the?other?threads?to?end?their?work.?*/
????//?輪訓(xùn)等待所有I/O線程處理完
????while(1)?{
????????unsigned?long?pending?=?0;
????????for?(int?j?=?1;?j?????????????pending?+=?io_threads_pending[j];
????????if?(pending?==?0)?break;
????}
????...
????return?processed;
}
I/O線程處理流程:
void?*IOThreadMain(void?*myid)?{
????...
????while(1)?{
????????...
????????//?I/O線程執(zhí)行讀寫操作
????????while((ln?=?listNext(&li)))?{
????????????client?*c?=?listNodeValue(ln);
????????????//?io_threads_op判斷是讀還是寫事件
????????????if?(io_threads_op?==?IO_THREADS_OP_WRITE)?{
????????????????writeToClient(c,0);
????????????}?else?if?(io_threads_op?==?IO_THREADS_OP_READ)?{
????????????????readQueryFromClient(c->conn);
????????????}?else?{
????????????????serverPanic("io_threads_op?value?is?unknown");
????????????}
????????}
????????listEmpty(io_threads_list[id]);
????????io_threads_pending[id]?=?0;
????????if?(tio_debug)?printf("[%ld]?Done\n",?id);
????}
}
局限性
從上面實(shí)現(xiàn)上看,6.0版本的多線程并非徹底的多線程,I/O線程只能同時(shí)執(zhí)行讀或者同時(shí)執(zhí)行寫操作,期間事件處理線程一直處于等待狀態(tài),并非流水線模型,有很多輪訓(xùn)等待開銷。
Tair多線程實(shí)現(xiàn)原理
相較于6.0版本的多線程,Tair的多線程實(shí)現(xiàn)更加優(yōu)雅。如下圖,Tair的Main Thread負(fù)責(zé)客戶端連接建立等,IO Thread負(fù)責(zé)請(qǐng)求讀取、響應(yīng)發(fā)送、命令解析等,Worker Thread線程專門用于事件處理。IO Thread讀取用戶的請(qǐng)求并進(jìn)行解析,之后將解析結(jié)果以命令的形式放在隊(duì)列中發(fā)送給Worker Thread處理。Worker Thread將命令處理完成后生成響應(yīng),通過另一條隊(duì)列發(fā)送給IO Thread。為了提高線程的并行度,IO Thread和Worker Thread之間采用無鎖隊(duì)列?和管道?進(jìn)行數(shù)據(jù)交換,整體性能會(huì)更好。

| 小結(jié)
Redis 4.0引入Lazy Free線程,解決了諸如大鍵刪除導(dǎo)致服務(wù)器阻塞問題,在6.0版本引入了I/O Thread線程,正式實(shí)現(xiàn)了多線程,但相較于Tair,并不太優(yōu)雅,而且性能提升上并不多,壓測(cè)看,多線程版本性能是單線程版本的2倍,Tair多線程版本則是單線程版本的3倍。在作者看來,Redis多線程無非兩種思路,I/O threading和Slow commands threading,正如作者在其博客中所說:
I/O threading is not going to happen in Redis AFAIK, because after much consideration I think it’s a lot of complexity without a good reason. Many Redis setups are network or memory bound actually. Additionally I really believe in a share-nothing setup, so the way I want to scale Redis is by improving the support for multiple Redis instances to be executed in the same host, especially via Redis Cluster.
What instead I really want a lot is slow operations threading, and with the Redis modules system we already are in the right direction. However in the future (not sure if in Redis 6 or 7) we’ll get key-level locking in the module system so that threads can completely acquire control of a key to process slow operations. Now modules can implement commands and can create a reply for the client in a completely separated way, but still to access the shared data set a global lock is needed: this will go away.
Redis作者更傾向于采用集群方式來解決I/O threading,尤其是在6.0版本發(fā)布的原生Redis Cluster Proxy背景下,使得集群更加易用。此外,作者更傾向于slow operations threading(比如4.0版本發(fā)布的Lazy Free)來解決多線程問題。后續(xù)版本,是否會(huì)將IO Thread實(shí)現(xiàn)的更加完善,采用Module實(shí)現(xiàn)對(duì)慢操作的優(yōu)化,著實(shí)值得期待。
往 期 推 薦
1、致歉!抖音Semi Design承認(rèn)參考阿里Ant Design
2、對(duì)比7種分布式事務(wù)方案,還是偏愛阿里開源的Seata,真香!
點(diǎn)分享
點(diǎn)收藏
點(diǎn)點(diǎn)贊
點(diǎn)在看





