#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;
/* 释放旧的链表,初始化新的链表,用于AOF重写缓存的初始化*/
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);
}
/* 返回当前的链表的总大小 */
unsigned long aofRewriteBufferSize(void) {
listNode *ln;
listIter li;
unsigned long size = 0;
listRewind(server.aof_rewrite_buf_blocks,&li);
while((ln = listNext(&li))) {
aofrwblock *block = listNodeValue(ln);
size += block->used;
}
return size;
}
/* Event handler used to send data to the child process doing the AOF
* rewrite. We send pieces of our AOF differences buffer so that the final
* write when the child finishes the rewrite will be small. */
void aofChildWriteDiffData(aeEventLoop *el, int fd, void *privdata, int mask) {
listNode *ln;
aofrwblock *block;
ssize_t nwritten;
UNUSED(el);
UNUSED(fd);
UNUSED(privdata);
UNUSED(mask);
while(1) {
ln = listFirst(server.aof_rewrite_buf_blocks);
block = ln ? ln->value : NULL;
if (server.aof_stop_sending_diff || !block) {
aeDeleteFileEvent(server.el,server.aof_pipe_write_data_to_child,
AE_WRITABLE);
return;
}
if (block->used > 0) {
nwritten = write(server.aof_pipe_write_data_to_child,
block->buf,block->used);
if (nwritten <= 0) return;
memmove(block->buf,block->buf+nwritten,block->used-nwritten);
block->used -= nwritten;
}
if (block->used == 0) listDelNode(server.aof_rewrite_buf_blocks,ln);
}
}
/* 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 ? LL_WARNING :
LL_NOTICE;
serverLog(level,"Background AOF buffer size: %lu MB",
aofRewriteBufferSize()/(1024*1024));
}
}
}
/* Install a file event to send data to the rewrite child if there is
* not one already. */
if (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);
}
}
/* Write the buffer (possibly composed of multiple blocks) into the specified
* fd. If a 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) {
nwritten = write(fd,block->buf,block->used);
if (nwritten != (ssize_t)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) {
bioCreateBackgroundJob(BIO_AOF_FSYNC,(void*)(long)fd,NULL,NULL);
}
/* Called when the user switches from "appendonly yes" to "appendonly no"
* at runtime using the CONFIG command. */
void stopAppendOnly(void) {
serverAssert(server.aof_state != 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 = AOF_OFF;
/* rewrite operation in progress? kill it, wait child exit */
if (server.aof_child_pid != -1) {
int statloc;
serverLog(LL_NOTICE,"Killing running AOF rewrite child: %ld",
(long) server.aof_child_pid);
if (kill(server.aof_child_pid,SIGUSR1) != -1) {
while(wait3(&statloc,0,NULL) != server.aof_child_pid);
}
/* 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;
/* close pipes used for IPC between the two processes. */
aofClosePipes();
}
}
/* Called when the user switches from "appendonly no" to "appendonly yes"
* at runtime using the CONFIG command. */
int startAppendOnly(void) {
char cwd[MAXPATHLEN]; /* Current working dir path for error messages. */
server.aof_last_fsync = server.unixtime;
server.aof_fd = open(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
serverAssert(server.aof_state == AOF_OFF);
if (server.aof_fd == -1) {
char *cwdp = getcwd(cwd,MAXPATHLEN);
serverLog(LL_WARNING,
"Redis needs to enable the AOF but can't open the "
"append only file %s (in server root dir %s): %s",
server.aof_filename,
cwdp ? cwdp : "unknown",
strerror(errno));
return C_ERR;
}
if (server.rdb_child_pid != -1) {
server.aof_rewrite_scheduled = 1;
serverLog(LL_WARNING,"AOF was enabled but there is already a child process saving an RDB file on disk. An AOF background was scheduled to start when possible.");
} else if (rewriteAppendOnlyFileBackground() == C_ERR) {
close(server.aof_fd);
serverLog(LL_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 C_ERR;
}
/* We correctly switched on AOF, now wait for the rewrite to be complete
* in order to append data on disk. */
server.aof_state = AOF_WAIT_REWRITE;
return C_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. */
#define AOF_WRITE_LOG_ERROR_RATE 30 /* Seconds between errors logging. */
void flushAppendOnlyFile(int force) {
ssize_t nwritten;
int sync_in_progress = 0;
mstime_t latency;
if (sdslen(server.aof_buf) == 0) return;
if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
sync_in_progress = bioPendingJobsOfType(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 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 */
latencyStartMonitor(latency);
nwritten = write(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 (server.aof_child_pid != -1 || server.rdb_child_pid != -1) {
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 != (signed)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, and we
* have the contract with the user that on acknowledged write data
* is synced on disk. */
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();
}
/* 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. */
latencyStartMonitor(latency);
aof_fsync(server.aof_fd); /* Let's try to get this data on the disk */
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("aof-fsync-always",latency);
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 strtoll */
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 appended. 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 == 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,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 client *createFakeClient(void) {
struct client *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;
c->btype = BLOCKED_NONE;
/* 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 = SLAVE_STATE_WAIT_BGSAVE_START;
c->reply = listCreate();
c->reply_bytes = 0;
c->obuf_soft_limit_reached_time = 0;
c->watched_keys = listCreate();
c->peerid = NULL;
listSetFreeMethod(c->reply,decrRefCountVoid);
listSetDupMethod(c->reply,dupClientReplyValue);
initClientMultiState(c);
return c;
}
void freeFakeClientArgv(struct client *c) {
int j;
for (j = 0; j < c->argc; j++)
decrRefCount(c->argv[j]);
zfree(c->argv);
}
void freeFakeClient(struct client *c) {
sdsfree(c->querybuf);
listRelease(c->reply);
listRelease(c->watched_keys);
freeClientMultiState(c);
zfree(c);
}
/* aof数据恢复过程 */
int loadAppendOnlyFile(char *filename) {
struct client *fakeClient;//客户端
FILE *fp = fopen(filename,"r");//打开aof文件
struct redis_stat sb;
int old_aof_state = server.aof_state;
long loops = 0;
off_t valid_up_to = 0; /* Offset of the latest well-formed command loaded. */
// int fileno(FILE *stream):用来取得参数stream指定的文件流所使用的文件描述词返回值
// int fstat(int filedes, struct stat *buf): 获取文件描述符的状态
if (fp && redis_fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {//aof文件大小为0
server.aof_current_size = 0;
fclose(fp);
return C_ERR;
}
if (fp == NULL) {// 检查文件是否正常打开
serverLog(LL_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.
暂时关闭aof,防止在执行multi时exec命令被传播到同一文件
*/
server.aof_state = AOF_OFF;
fakeClient = createFakeClient();//创建伪客户端
startLoading(fp);//记录开始时间,总数据大小
while(1) {
int argc, j;
unsigned long len;
robj **argv;
char buf[128];
sds argsds;
struct redisCommand *cmd;
/*
间隔性地处理客户端发送来的请求
* 因为服务器正处于载入状态，所以能正常执行的只有 PUBSUB 等模块
*/
if (!(loops++ % 1000)) {
loadingProgress(ftello(fp));//记录已加载的数据量,更新最大内存使用量
processEventsWhileBlocked();
}
if (fgets(buf,sizeof(buf),fp) == NULL) {//读一行数据
if (feof(fp))
break;
else
goto readerr;
}
if (buf[0] != '*') goto fmterr;//第一行开头必须是一个*号
if (buf[1] == '\0') goto readerr;
argc = atoi(buf+1);//第一行第二个字符以后是一个数字,表示以下命令分几部分
if (argc < 1) goto fmterr;
argv = zmalloc(sizeof(robj*)*argc);
fakeClient->argc = argc;
fakeClient->argv = argv;
for (j = 0; j < argc; j++) {
if (fgets(buf,sizeof(buf),fp) == NULL) {//依次读取命令的各个参数,每个一行
fakeClient->argc = j; /* Free up to j-1. */
freeFakeClientArgv(fakeClient);
goto readerr;
}
if (buf[0] != '$') goto fmterr;//命令参数开头是一个$
len = strtol(buf+1,NULL,10);//命令参数第二个字符是一个数字,表示本参数的字节数
argsds = sdsnewlen(NULL,len);
if (len && fread(argsds,len,1,fp) == 0) {//没读到预期的字节数,则报错
sdsfree(argsds);
fakeClient->argc = j; /* Free up to j-1. */
freeFakeClientArgv(fakeClient);
goto readerr;
}
argv[j] = createObject(OBJ_STRING,argsds);
if (fread(buf,2,1,fp) == 0) {//读取剩下的/r/n
fakeClient->argc = j+1; /* Free up to j. */
freeFakeClientArgv(fakeClient);
goto readerr; /* discard CRLF */
}
}
cmd = lookupCommand(argv[0]->ptr);//查找命令
if (!cmd) {
serverLog(LL_WARNING,"Unknown command '%s' reading the append only file", (char*)argv[0]->ptr);
exit(1);
}
/* Run the command in the context of a fake client */
cmd->proc(fakeClient);
/* The fake client should not have a reply */
serverAssert(fakeClient->bufpos == 0 && listLength(fakeClient->reply) == 0);
/* The fake client should never get blocked */
serverAssert((fakeClient->flags & CLIENT_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. */
freeFakeClientArgv(fakeClient);
if (server.aof_load_truncated) valid_up_to = ftello(fp);
}
/* 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 & CLIENT_MULTI) goto uxeof;
loaded_ok: /* DB loaded, cleanup and return C_OK to the caller. */
fclose(fp);// 关闭 AOF 文件
freeFakeClient(fakeClient);//释放伪客户端
server.aof_state = old_aof_state;//记录旧的aof状态
stopLoading();//停止加载
aofUpdateCurrentSize();//更新读入数据
server.aof_rewrite_base_size = server.aof_current_size;//更新上次读入aof的大小
return C_OK;
readerr: /* Read error. If feof(fp) is true, fall through to unexpected EOF. */
if (!feof(fp)) {
if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
serverLog(LL_WARNING,"Unrecoverable error reading the append only file: %s", strerror(errno));
exit(1);
}
uxeof: /* Unexpected AOF end of file. */
if (server.aof_load_truncated) {
serverLog(LL_WARNING,"!!! Warning: short read while loading the AOF file !!!");
serverLog(LL_WARNING,"!!! Truncating the AOF at offset %llu !!!",
(unsigned long long) valid_up_to);
if (valid_up_to == -1 || truncate(filename,valid_up_to) == -1) {
if (valid_up_to == -1) {
serverLog(LL_WARNING,"Last valid command offset is invalid");
} else {
serverLog(LL_WARNING,"Error truncating the AOF file: %s",
strerror(errno));
}
} else {
/* Make sure the AOF file descriptor points to the end of the
* file after the truncate call. */
if (server.aof_fd != -1 && lseek(server.aof_fd,0,SEEK_END) == -1) {
serverLog(LL_WARNING,"Can't seek the end of the AOF file: %s",
strerror(errno));
} else {
serverLog(LL_WARNING,
"AOF loaded anyway because aof-load-truncated is enabled");
goto loaded_ok;
}
}
}
if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
serverLog(LL_WARNING,"Unexpected end of file reading the append only file. You can: 1) Make a backup of your AOF file, then use ./redis-check-aof --fix <filename>. 2) Alternatively you can set the 'aof-load-truncated' configuration option to yes and restart the server.");
exit(1);
fmterr: /* Format error. */
if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
serverLog(LL_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 server.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 == OBJ_ENCODING_INT) {
return rioWriteBulkLongLong(r,(long)obj->ptr);
} else if (sdsEncodedObject(obj)) {
return rioWriteBulkString(r,obj->ptr,sdslen(obj->ptr));
} else {
serverPanic("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 == OBJ_ENCODING_QUICKLIST) {
quicklist *list = o->ptr;
quicklistIter *li = quicklistGetIterator(list, AL_START_HEAD);
quicklistEntry entry;
while (quicklistNext(li,&entry)) {
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
AOF_REWRITE_ITEMS_PER_CMD : 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 (entry.value) {
if (rioWriteBulkString(r,(char*)entry.value,entry.sz) == 0) return 0;
} else {
if (rioWriteBulkLongLong(r,entry.longval) == 0) return 0;
}
if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
quicklistReleaseIterator(li);
} else {
serverPanic("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 == OBJ_ENCODING_INTSET) {
int ii = 0;
int64_t llval;
while(intsetGet(o->ptr,ii++,&llval)) {
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
AOF_REWRITE_ITEMS_PER_CMD : 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 == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
} else if (o->encoding == OBJ_ENCODING_HT) {
dictIterator *di = dictGetIterator(o->ptr);
dictEntry *de;
while((de = dictNext(di)) != NULL) {
robj *eleobj = dictGetKey(de);
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
AOF_REWRITE_ITEMS_PER_CMD : 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 == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
dictReleaseIterator(di);
} else {
serverPanic("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 == OBJ_ENCODING_ZIPLIST) {
unsigned char *zl = o->ptr;
unsigned char *eptr, *sptr;
unsigned char *vstr;
unsigned int vlen;
long long vll;
double score;
eptr = ziplistIndex(zl,0);
serverAssert(eptr != NULL);
sptr = ziplistNext(zl,eptr);
serverAssert(sptr != NULL);
while (eptr != NULL) {
serverAssert(ziplistGet(eptr,&vstr,&vlen,&vll));
score = zzlGetScore(sptr);
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
AOF_REWRITE_ITEMS_PER_CMD : 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 == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
} else if (o->encoding == OBJ_ENCODING_SKIPLIST) {
zset *zs = o->ptr;
dictIterator *di = dictGetIterator(zs->dict);
dictEntry *de;
while((de = dictNext(di)) != NULL) {
robj *eleobj = dictGetKey(de);
double *score = dictGetVal(de);
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
AOF_REWRITE_ITEMS_PER_CMD : 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 == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
dictReleaseIterator(di);
} else {
serverPanic("Unknown sorted zset encoding");
}
return 1;
}
/* Write either the key or the value of the currently selected item of a 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 OBJ_HASH_KEY or OBJ_HASH_VALUE.
*
* The function returns 0 on error, non-zero on success. */
static int rioWriteHashIteratorCursor(rio *r, hashTypeIterator *hi, int what) {
if (hi->encoding == OBJ_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 rioWriteBulkString(r, (char*)vstr, vlen);
} else {
return rioWriteBulkLongLong(r, vll);
}
} else if (hi->encoding == OBJ_ENCODING_HT) {
robj *value;
hashTypeCurrentFromHashTable(hi, what, &value);
return rioWriteBulkObject(r, value);
}
serverPanic("Unknown hash encoding");
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) {
hashTypeIterator *hi;
long long count = 0, items = hashTypeLength(o);
hi = hashTypeInitIterator(o);
while (hashTypeNext(hi) != C_ERR) {
if (count == 0) {
int cmd_items = (items > AOF_REWRITE_ITEMS_PER_CMD) ?
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, OBJ_HASH_KEY) == 0) return 0;
if (rioWriteHashIteratorCursor(r, hi, OBJ_HASH_VALUE) == 0) return 0;
if (++count == AOF_REWRITE_ITEMS_PER_CMD) count = 0;
items--;
}
hashTypeReleaseIterator(hi);
return 1;
}
/* This function is called by the child rewriting the AOF file to read
* the difference accumulated from the parent into a buffer, that is
* concatenated at the end of the rewrite. */
ssize_t aofReadDiffFromParent(void) {
char buf[65536]; /* Default pipe buffer size on most Linux systems. */
ssize_t nread, total = 0;
while ((nread =
read(server.aof_pipe_read_data_from_parent,buf,sizeof(buf))) > 0) {
server.aof_child_diff = sdscatlen(server.aof_child_diff,buf,nread);
total += nread;
}
return total;
}
/* 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 AOF_REWRITE_ITEMS_PER_CMD items per time
* are inserted using a single command. */
int rewriteAppendOnlyFile(char *filename) {
dictIterator *di = NULL;
dictEntry *de;
rio aof;
FILE *fp;
char tmpfile[256];
int j;
long long now = mstime();
char byte;
size_t processed = 0;
/* 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());
fp = fopen(tmpfile,"w");
if (!fp) {
serverLog(LL_WARNING, "Opening the temp file for AOF rewrite in rewriteAppendOnlyFile(): %s", strerror(errno));
return C_ERR;
}
server.aof_child_diff = sdsempty();
rioInitWithFile(&aof,fp);
if (server.aof_rewrite_incremental_fsync)
rioSetAutoSync(&aof,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 = db->dict;
if (dictSize(d) == 0) continue;
di = dictGetSafeIterator(d);
if (!di) {
fclose(fp);
return C_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 */
while((de = dictNext(di)) != NULL) {
sds keystr;
robj key, *o;
long long expiretime;
keystr = dictGetKey(de);
o = dictGetVal(de);
initStaticStringObject(key,keystr);
expiretime = getExpire(db,&key);
/* If this key is already expired skip it */
if (expiretime != -1 && expiretime < now) continue;
/* Save the key and associated value */
if (o->type == OBJ_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 == OBJ_LIST) {
if (rewriteListObject(&aof,&key,o) == 0) goto werr;
} else if (o->type == OBJ_SET) {
if (rewriteSetObject(&aof,&key,o) == 0) goto werr;
} else if (o->type == OBJ_ZSET) {
if (rewriteSortedSetObject(&aof,&key,o) == 0) goto werr;
} else if (o->type == OBJ_HASH) {
if (rewriteHashObject(&aof,&key,o) == 0) goto werr;
} else {
serverPanic("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;
}
/* Read some diff from the parent process from time to time. */
if (aof.processed_bytes > processed+1024*10) {
processed = aof.processed_bytes;
aofReadDiffFromParent();
}
}
dictReleaseIterator(di);
di = NULL;
}
/* Do an initial slow fsync here while the parent is still sending
* data, in order to make the next final fsync faster. */
if (fflush(fp) == EOF) goto werr;
if (fsync(fileno(fp)) == -1) goto werr;
/* 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();
}
/* Ask the master to stop sending diffs. */
if (write(server.aof_pipe_write_ack_to_parent,"!",1) != 1) goto werr;
if (anetNonBlock(NULL,server.aof_pipe_read_ack_from_parent) != ANET_OK)
goto werr;
/* We read the ACK from the server using a 10 seconds timeout. Normally
* it should reply ASAP, but just in case we lose its reply, we are sure
* the child will eventually get terminated. */
if (syncRead(server.aof_pipe_read_ack_from_parent,&byte,1,5000) != 1 ||
byte != '!') goto werr;
serverLog(LL_NOTICE,"Parent agreed to stop sending diffs. Finalizing AOF...");
/* Read the final diff if any. */
aofReadDiffFromParent();
/* Write the received diff to the file. */
serverLog(LL_NOTICE,
"Concatenating %.2f MB of AOF diff received from parent.",
(double) sdslen(server.aof_child_diff) / (1024*1024));
if (rioWrite(&aof,server.aof_child_diff,sdslen(server.aof_child_diff)) == 0)
goto werr;
/* Make sure data will not remain on the OS's output buffers */
if (fflush(fp) == EOF) goto werr;
if (fsync(fileno(fp)) == -1) goto werr;
if (fclose(fp) == EOF) goto werr;
/* Use RENAME to make sure the DB file is changed atomically only
* if the generate DB file is ok. */
if (rename(tmpfile,filename) == -1) {
serverLog(LL_WARNING,"Error moving temp append only file on the final destination: %s", strerror(errno));
unlink(tmpfile);
return C_ERR;
}
serverLog(LL_NOTICE,"SYNC append only file rewrite performed");
return C_OK;
werr:
serverLog(LL_WARNING,"Write error writing append only file on disk: %s", strerror(errno));
fclose(fp);
unlink(tmpfile);
if (di) dictReleaseIterator(di);
return C_ERR;
}
/* ----------------------------------------------------------------------------
* AOF rewrite pipes for IPC
* -------------------------------------------------------------------------- */
/* This event handler is called when the AOF rewriting child sends us a
* single '!' char to signal we should stop sending buffer diffs. The
* parent sends a '!' as well to acknowledge. */
void aofChildPipeReadable(aeEventLoop *el, int fd, void *privdata, int mask) {
char byte;
UNUSED(el);
UNUSED(privdata);
UNUSED(mask);
if (read(fd,&byte,1) == 1 && byte == '!') {
serverLog(LL_NOTICE,"AOF rewrite child asks to stop sending diffs.");
server.aof_stop_sending_diff = 1;
if (write(server.aof_pipe_write_ack_to_child,"!",1) != 1) {
/* If we can't send the ack, inform the user, but don't try again
* since in the other side the children will use a timeout if the
* kernel can't buffer our write, or, the children was
* terminated. */
serverLog(LL_WARNING,"Can't send ACK to AOF child: %s",
strerror(errno));
}
}
/* Remove the handler since this can be called only one time during a
* rewrite. */
aeDeleteFileEvent(server.el,server.aof_pipe_read_ack_from_child,AE_READABLE);
}
/* Create the pipes used for parent - child process IPC during rewrite.
* We have a data pipe used to send AOF incremental diffs to the child,
* and two other pipes used by the children to signal it finished with
* the rewrite so no more data should be written, and another for the
* parent to acknowledge it understood this new condition. */
int aofCreatePipes(void) {
int fds[6] = {-1, -1, -1, -1, -1, -1};
int j;
if (pipe(fds) == -1) goto error; /* parent -> children data. */
if (pipe(fds+2) == -1) goto error; /* children -> parent ack. */
if (pipe(fds+4) == -1) goto error; /* children -> parent ack. */
/* Parent -> children data is non blocking. */
if (anetNonBlock(NULL,fds[0]) != ANET_OK) goto error;
if (anetNonBlock(NULL,fds[1]) != ANET_OK) goto error;
if (aeCreateFileEvent(server.el, fds[2], AE_READABLE, aofChildPipeReadable, NULL) == AE_ERR) goto error;
server.aof_pipe_write_data_to_child = fds[1];
server.aof_pipe_read_data_from_parent = fds[0];
server.aof_pipe_write_ack_to_parent = fds[3];
server.aof_pipe_read_ack_from_child = fds[2];
server.aof_pipe_write_ack_to_child = fds[5];
server.aof_pipe_read_ack_from_parent = fds[4];
server.aof_stop_sending_diff = 0;
return C_OK;
error:
serverLog(LL_WARNING,"Error opening /setting AOF rewrite IPC pipes: %s",
strerror(errno));
for (j = 0; j < 6; j++) if(fds[j] != -1) close(fds[j]);
return C_ERR;
}
void aofClosePipes(void) {
aeDeleteFileEvent(server.el,server.aof_pipe_read_ack_from_child,AE_READABLE);
aeDeleteFileEvent(server.el,server.aof_pipe_write_data_to_child,AE_WRITABLE);
close(server.aof_pipe_write_data_to_child);
close(server.aof_pipe_read_data_from_parent);
close(server.aof_pipe_write_ack_to_parent);
close(server.aof_pipe_read_ack_from_child);
close(server.aof_pipe_write_ack_to_child);
close(server.aof_pipe_read_ack_from_parent);
}
/* ----------------------------------------------------------------------------
* AOF background rewrite
* ------------------------------------------------------------------------- */
/* 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!
*/
int rewriteAppendOnlyFileBackground(void) {
pid_t childpid;
long long start;
if (server.aof_child_pid != -1 || server.rdb_child_pid != -1) return C_ERR;
if (aofCreatePipes() != C_OK) return C_ERR;
start = ustime();
if ((childpid = fork()) == 0) {
char tmpfile[256];
/* Child */
closeListeningSockets(0);
redisSetProcTitle("redis-aof-rewrite");
snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) getpid());
if (rewriteAppendOnlyFile(tmpfile) == C_OK) {
size_t private_dirty = zmalloc_get_private_dirty();
if (private_dirty) {
serverLog(LL_NOTICE,
"AOF rewrite: %zu 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;
server.stat_fork_rate = (double) zmalloc_used_memory() * 1000000 / server.stat_fork_time / (1024*1024*1024); /* GB per second. */
latencyAddSampleIfNeeded("fork",server.stat_fork_time/1000);
if (childpid == -1) {
serverLog(LL_WARNING,
"Can't rewrite append only file in background: fork: %s",
strerror(errno));
return C_ERR;
}
serverLog(LL_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;
replicationScriptCacheFlush();
return C_OK;
}
return C_OK; /* unreached */
}
void bgrewriteaofCommand(client *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() == C_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 field 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;
mstime_t latency;
latencyStartMonitor(latency);
if (redis_fstat(server.aof_fd,&sb) == -1) {
serverLog(LL_WARNING,"Unable to obtain the AOF file length. stat: %s",
strerror(errno));
} else {
server.aof_current_size = sb.st_size;
}
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("aof-fstat",latency);
}
/* 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();
mstime_t latency;
serverLog(LL_NOTICE,
"Background AOF rewrite terminated with success");
/* Flush the differences accumulated by the parent to the
* rewritten AOF. */
latencyStartMonitor(latency);
snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof",
(int)server.aof_child_pid);
newfd = open(tmpfile,O_WRONLY|O_APPEND);
if (newfd == -1) {
serverLog(LL_WARNING,
"Unable to open the temporary AOF produced by the child: %s", strerror(errno));
goto cleanup;
}
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;
}
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("aof-rewrite-diff-write",latency);
serverLog(LL_NOTICE,
"Residual parent diff successfully flushed to the rewritten AOF (%.2f MB)", (double) aofRewriteBufferSize() / (1024*1024));
/* 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. */
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". */
latencyStartMonitor(latency);
if (rename(tmpfile,server.aof_filename) == -1) {
serverLog(LL_WARNING,
"Error trying to rename the temporary AOF file %s into %s: %s",
tmpfile,
server.aof_filename,
strerror(errno));
close(newfd);
if (oldfd != -1) close(oldfd);
goto cleanup;
}
latencyEndMonitor(latency);
latencyAddSampleIfNeeded("aof-rename",latency);
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 = C_OK;
serverLog(LL_NOTICE, "Background AOF rewrite finished successfully");
/* Change state from WAIT_REWRITE to ON if needed */
if (server.aof_state == AOF_WAIT_REWRITE)
server.aof_state = AOF_ON;
/* Asynchronously close the overwritten AOF. */
if (oldfd != -1) bioCreateBackgroundJob(BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL);
serverLog(LL_VERBOSE,
"Background AOF rewrite signal handler took %lldus", ustime()-now);
} else if (!bysignal && exitcode != 0) {
/* SIGUSR1 is whitelisted, so we have a way to kill a child without
* tirggering an error conditon. */
if (bysignal != SIGUSR1)
server.aof_lastbgrewrite_status = C_ERR;
serverLog(LL_WARNING,
"Background AOF rewrite terminated with error");
} else {
server.aof_lastbgrewrite_status = C_ERR;
serverLog(LL_WARNING,
"Background AOF rewrite terminated by signal %d", bysignal);
}
cleanup:
aofClosePipes();
aofRewriteBufferReset();
aofRemoveTempFile(server.aof_child_pid);
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 == AOF_WAIT_REWRITE)
server.aof_rewrite_scheduled = 1;
}
1085
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
