From 0ea1a9c452141671ee3f36dab08962d811596903 Mon Sep 17 00:00:00 2001 From: dvir volk Date: Fri, 8 Jun 2012 16:03:18 +0300 Subject: [PATCH 1/9] fixed server install script to rewrite the default configuration file and not a template, and removed the old config template --- utils/install_server.sh | 25 +- utils/redis.conf.tpl | 495 ---------------------------------------- 2 files changed, 18 insertions(+), 502 deletions(-) delete mode 100644 utils/redis.conf.tpl diff --git a/utils/install_server.sh b/utils/install_server.sh index 70f0adfe..789a9780 100755 --- a/utils/install_server.sh +++ b/utils/install_server.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # Copyright 2011 Dvir Volk . All rights reserved. # @@ -48,6 +48,7 @@ if [ `whoami` != "root" ] ; then exit 1 fi + #Read the redis port read -p "Please select the redis port for this instance: [$_REDIS_PORT] " REDIS_PORT if [ ! `echo $REDIS_PORT | egrep "^[0-9]+\$"` ] ; then @@ -99,7 +100,7 @@ fi #render the tmplates TMP_FILE="/tmp/$REDIS_PORT.conf" -TPL_FILE="./redis.conf.tpl" +DEFAULT_CONFIG="../redis.conf" INIT_TPL_FILE="./redis_init_script.tpl" INIT_SCRIPT_DEST="/etc/init.d/redis_$REDIS_PORT" PIDFILE="/var/run/redis_$REDIS_PORT.pid" @@ -112,9 +113,19 @@ if [ ! "$CLI_EXEC" ] ; then CLI_EXEC=`dirname $REDIS_EXECUTABLE`"/redis-cli" fi -#Generate config file from template +#Generate config file from the default config file as template +#changing only the stuff we're controlling from this script echo "## Generated by install_server.sh ##" > $TMP_FILE -cat $TPL_FILE | while read line; do eval "echo \"$line\"" >> $TMP_FILE; done + +SED_EXPR="s#^port [0-9]{4}\$#port ${REDIS_PORT}#;\ +s#^logfile .+\$#logfile ${REDIS_LOG_FILE}#;\ +s#^dir .+\$#dir ${REDIS_DATA_DIR}#;\ +s#^pidfile .+\$#pidfile ${PIDFILE}#;\ +s#^daemonize no\$#daemonize yes#;" +echo $SED_EXPR +sed -r "$SED_EXPR" $DEFAULT_CONFIG >> $TMP_FILE + +#cat $TPL_FILE | while read line; do eval "echo \"$line\"" >> $TMP_FILE; done cp -f $TMP_FILE $REDIS_CONFIG_FILE || exit 1 #Generate sample script from template file @@ -146,9 +157,9 @@ REDIS_CHKCONFIG_INFO=\ # Description: Redis daemon\n ### END INIT INFO\n\n" -if [[ ! `which chkconfig` ]] ; then +if [ !`which chkconfig` ] ; then #combine the header and the template (which is actually a static footer) - echo -e $REDIS_INIT_HEADER > $TMP_FILE && cat $INIT_TPL_FILE >> $TMP_FILE || die "Could not write init script to $TMP_FILE" + echo $REDIS_INIT_HEADER > $TMP_FILE && cat $INIT_TPL_FILE >> $TMP_FILE || die "Could not write init script to $TMP_FILE" else #if we're a box with chkconfig on it we want to include info for chkconfig echo -e $REDIS_INIT_HEADER $REDIS_CHKCONFIG_INFO > $TMP_FILE && cat $INIT_TPL_FILE >> $TMP_FILE || die "Could not write init script to $TMP_FILE" @@ -160,7 +171,7 @@ echo "Copied $TMP_FILE => $INIT_SCRIPT_DEST" #Install the service echo "Installing service..." -if [[ ! `which chkconfig` ]] ; then +if [ !`which chkconfig` ] ; then #if we're not a chkconfig box assume we're able to use update-rc.d update-rc.d redis_$REDIS_PORT defaults && echo "Success!" else diff --git a/utils/redis.conf.tpl b/utils/redis.conf.tpl deleted file mode 100644 index 33d99a50..00000000 --- a/utils/redis.conf.tpl +++ /dev/null @@ -1,495 +0,0 @@ -# Redis configuration file example - -# Note on units: when memory size is needed, it is possible to specify -# it in the usual form of 1k 5GB 4M and so forth: -# -# 1k => 1000 bytes -# 1kb => 1024 bytes -# 1m => 1000000 bytes -# 1mb => 1024*1024 bytes -# 1g => 1000000000 bytes -# 1gb => 1024*1024*1024 bytes -# -# units are case insensitive so 1GB 1Gb 1gB are all the same. - -# By default Redis does not run as a daemon. Use 'yes' if you need it. -# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. -daemonize yes - -# When running daemonized, Redis writes a pid file in /var/run/redis.pid by -# default. You can specify a custom pid file location here. -pidfile $PIDFILE - -# Accept connections on the specified port, default is 6379. -# If port 0 is specified Redis will not listen on a TCP socket. -port $REDIS_PORT - -# If you want you can bind a single interface, if the bind option is not -# specified all the interfaces will listen for incoming connections. -# -# bind 127.0.0.1 - -# Specify the path for the unix socket that will be used to listen for -# incoming connections. There is no default, so Redis will not listen -# on a unix socket when not specified. -# -# unixsocket /tmp/redis.sock -# unixsocketperm 755 - -# Close the connection after a client is idle for N seconds (0 to disable) -timeout 0 - -# Set server verbosity to 'debug' -# it can be one of: -# debug (a lot of information, useful for development/testing) -# verbose (many rarely useful info, but not a mess like the debug level) -# notice (moderately verbose, what you want in production probably) -# warning (only very important / critical messages are logged) -loglevel notice - -# Specify the log file name. Also 'stdout' can be used to force -# Redis to log on the standard output. Note that if you use standard -# output for logging but daemonize, logs will be sent to /dev/null -logfile $REDIS_LOG_FILE - -# To enable logging to the system logger, just set 'syslog-enabled' to yes, -# and optionally update the other syslog parameters to suit your needs. -# syslog-enabled no - -# Specify the syslog identity. -# syslog-ident redis - -# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. -# syslog-facility local0 - -# Set the number of databases. The default database is DB 0, you can select -# a different one on a per-connection basis using SELECT where -# dbid is a number between 0 and 'databases'-1 -databases 16 - -################################ SNAPSHOTTING ################################# -# -# Save the DB on disk: -# -# save -# -# Will save the DB if both the given number of seconds and the given -# number of write operations against the DB occurred. -# -# In the example below the behaviour will be to save: -# after 900 sec (15 min) if at least 1 key changed -# after 300 sec (5 min) if at least 10 keys changed -# after 60 sec if at least 10000 keys changed -# -# Note: you can disable saving at all commenting all the "save" lines. -# -# It is also possible to remove all the previously configured save -# points by adding a save directive with a single empty string argument -# like in the following example: -# -# save "" - -save 900 1 -save 300 10 -save 60 10000 - -# By default Redis will stop accepting writes if RDB snapshots are enabled -# (at least one save point) and the latest background save failed. -# This will make the user aware (in an hard way) that data is not persisting -# on disk properly, otherwise chances are that no one will notice and some -# distater will happen. -# -# If the background saving process will start working again Redis will -# automatically allow writes again. -# -# However if you have setup your proper monitoring of the Redis server -# and persistence, you may want to disable this feature so that Redis will -# continue to work as usually even if there are problems with disk, -# permissions, and so forth. -stop-writes-on-bgsave-error yes - -# Compress string objects using LZF when dump .rdb databases? -# For default that's set to 'yes' as it's almost always a win. -# If you want to save some CPU in the saving child set it to 'no' but -# the dataset will likely be bigger if you have compressible values or keys. -rdbcompression yes - -# The filename where to dump the DB -dbfilename dump.rdb - -# The working directory. -# -# The DB will be written inside this directory, with the filename specified -# above using the 'dbfilename' configuration directive. -# -# Also the Append Only File will be created inside this directory. -# -# Note that you must specify a directory here, not a file name. -dir $REDIS_DATA_DIR - -################################# REPLICATION ################################# - -# Master-Slave replication. Use slaveof to make a Redis instance a copy of -# another Redis server. Note that the configuration is local to the slave -# so for example it is possible to configure the slave to save the DB with a -# different interval, or to listen to another port, and so on. -# -# slaveof - -# If the master is password protected (using the "requirepass" configuration -# directive below) it is possible to tell the slave to authenticate before -# starting the replication synchronization process, otherwise the master will -# refuse the slave request. -# -# masterauth - -# When a slave lost the connection with the master, or when the replication -# is still in progress, the slave can act in two different ways: -# -# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will -# still reply to client requests, possibly with out of date data, or the -# data set may just be empty if this is the first synchronization. -# -# 2) if slave-serve-stale data is set to 'no' the slave will reply with -# an error "SYNC with master in progress" to all the kind of commands -# but to INFO and SLAVEOF. -# -slave-serve-stale-data yes - -# Slaves send PINGs to server in a predefined interval. It's possible to change -# this interval with the repl_ping_slave_period option. The default value is 10 -# seconds. -# -# repl-ping-slave-period 10 - -# The following option sets a timeout for both Bulk transfer I/O timeout and -# master data or ping response timeout. The default value is 60 seconds. -# -# It is important to make sure that this value is greater than the value -# specified for repl-ping-slave-period otherwise a timeout will be detected -# every time there is low traffic between the master and the slave. -# -# repl-timeout 60 - -################################## SECURITY ################################### - -# Require clients to issue AUTH before processing any other -# commands. This might be useful in environments in which you do not trust -# others with access to the host running redis-server. -# -# This should stay commented out for backward compatibility and because most -# people do not need auth (e.g. they run their own servers). -# -# Warning: since Redis is pretty fast an outside user can try up to -# 150k passwords per second against a good box. This means that you should -# use a very strong password otherwise it will be very easy to break. -# -# requirepass foobared - -# Command renaming. -# -# It is possible to change the name of dangerous commands in a shared -# environment. For instance the CONFIG command may be renamed into something -# of hard to guess so that it will be still available for internal-use -# tools but not available for general clients. -# -# Example: -# -# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52 -# -# It is also possible to completely kill a command renaming it into -# an empty string: -# -# rename-command CONFIG "" - -################################### LIMITS #################################### - -# Set the max number of connected clients at the same time. By default -# this limit is set to 10000 clients, however if the Redis server is not -# able ot configure the process file limit to allow for the specified limit -# the max number of allowed clients is set to the current file limit -# minus 32 (as Redis reserves a few file descriptors for internal uses). -# -# Once the limit is reached Redis will close all the new connections sending -# an error 'max number of clients reached'. -# -# maxclients 10000 - -# Don't use more memory than the specified amount of bytes. -# When the memory limit is reached Redis will try to remove keys -# accordingly to the eviction policy selected (see maxmemmory-policy). -# -# If Redis can't remove keys according to the policy, or if the policy is -# set to 'noeviction', Redis will start to reply with errors to commands -# that would use more memory, like SET, LPUSH, and so on, and will continue -# to reply to read-only commands like GET. -# -# This option is usually useful when using Redis as an LRU cache, or to set -# an hard memory limit for an instance (using the 'noeviction' policy). -# -# WARNING: If you have slaves attached to an instance with maxmemory on, -# the size of the output buffers needed to feed the slaves are subtracted -# from the used memory count, so that network problems / resyncs will -# not trigger a loop where keys are evicted, and in turn the output -# buffer of slaves is full with DELs of keys evicted triggering the deletion -# of more keys, and so forth until the database is completely emptied. -# -# In short... if you have slaves attached it is suggested that you set a lower -# limit for maxmemory so that there is some free RAM on the system for slave -# output buffers (but this is not needed if the policy is 'noeviction'). -# -# maxmemory - -# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory -# is reached? You can select among five behavior: -# -# volatile-lru -> remove the key with an expire set using an LRU algorithm -# allkeys-lru -> remove any key accordingly to the LRU algorithm -# volatile-random -> remove a random key with an expire set -# allkeys-random -> remove a random key, any key -# volatile-ttl -> remove the key with the nearest expire time (minor TTL) -# noeviction -> don't expire at all, just return an error on write operations -# -# Note: with all the kind of policies, Redis will return an error on write -# operations, when there are not suitable keys for eviction. -# -# At the date of writing this commands are: set setnx setex append -# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd -# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby -# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby -# getset mset msetnx exec sort -# -# The default is: -# -# maxmemory-policy volatile-lru - -# LRU and minimal TTL algorithms are not precise algorithms but approximated -# algorithms (in order to save memory), so you can select as well the sample -# size to check. For instance for default Redis will check three keys and -# pick the one that was used less recently, you can change the sample size -# using the following configuration directive. -# -# maxmemory-samples 3 - -############################## APPEND ONLY MODE ############################### - -# By default Redis asynchronously dumps the dataset on disk. If you can live -# with the idea that the latest records will be lost if something like a crash -# happens this is the preferred way to run Redis. If instead you care a lot -# about your data and don't want to that a single record can get lost you should -# enable the append only mode: when this mode is enabled Redis will append -# every write operation received in the file appendonly.aof. This file will -# be read on startup in order to rebuild the full dataset in memory. -# -# Note that you can have both the async dumps and the append only file if you -# like (you have to comment the "save" statements above to disable the dumps). -# Still if append only mode is enabled Redis will load the data from the -# log file at startup ignoring the dump.rdb file. -# -# IMPORTANT: Check the BGREWRITEAOF to check how to rewrite the append -# log file in background when it gets too big. - -appendonly no - -# The name of the append only file (default: "appendonly.aof") -# appendfilename appendonly.aof - -# The fsync() call tells the Operating System to actually write data on disk -# instead to wait for more data in the output buffer. Some OS will really flush -# data on disk, some other OS will just try to do it ASAP. -# -# Redis supports three different modes: -# -# no: don't fsync, just let the OS flush the data when it wants. Faster. -# always: fsync after every write to the append only log . Slow, Safest. -# everysec: fsync only if one second passed since the last fsync. Compromise. -# -# The default is "everysec" that's usually the right compromise between -# speed and data safety. It's up to you to understand if you can relax this to -# "no" that will let the operating system flush the output buffer when -# it wants, for better performances (but if you can live with the idea of -# some data loss consider the default persistence mode that's snapshotting), -# or on the contrary, use "always" that's very slow but a bit safer than -# everysec. -# -# If unsure, use "everysec". - -# appendfsync always -appendfsync everysec -# appendfsync no - -# When the AOF fsync policy is set to always or everysec, and a background -# saving process (a background save or AOF log background rewriting) is -# performing a lot of I/O against the disk, in some Linux configurations -# Redis may block too long on the fsync() call. Note that there is no fix for -# this currently, as even performing fsync in a different thread will block -# our synchronous write(2) call. -# -# In order to mitigate this problem it's possible to use the following option -# that will prevent fsync() from being called in the main process while a -# BGSAVE or BGREWRITEAOF is in progress. -# -# This means that while another child is saving the durability of Redis is -# the same as "appendfsync none", that in practical terms means that it is -# possible to lost up to 30 seconds of log in the worst scenario (with the -# default Linux settings). -# -# If you have latency problems turn this to "yes". Otherwise leave it as -# "no" that is the safest pick from the point of view of durability. -no-appendfsync-on-rewrite no - -# Automatic rewrite of the append only file. -# Redis is able to automatically rewrite the log file implicitly calling -# BGREWRITEAOF when the AOF log size will growth by the specified percentage. -# -# This is how it works: Redis remembers the size of the AOF file after the -# latest rewrite (or if no rewrite happened since the restart, the size of -# the AOF at startup is used). -# -# This base size is compared to the current size. If the current size is -# bigger than the specified percentage, the rewrite is triggered. Also -# you need to specify a minimal size for the AOF file to be rewritten, this -# is useful to avoid rewriting the AOF file even if the percentage increase -# is reached but it is still pretty small. -# -# Specify a percentage of zero in order to disable the automatic AOF -# rewrite feature. - -auto-aof-rewrite-percentage 100 -auto-aof-rewrite-min-size 64mb - -################################ LUA SCRIPTING ############################### - -# Max execution time of a Lua script in milliseconds. -# -# If the maximum execution time is reached Redis will log that a script is -# still in execution after the maximum allowed time and will start to -# reply to queries with an error. -# -# When a long running script exceed the maximum execution time only the -# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be -# used to stop a script that did not yet called write commands. The second -# is the only way to shut down the server in the case a write commands was -# already issue by the script but the user don't want to wait for the natural -# termination of the script. -# -# Set it to 0 or a negative value for unlimited execution without warnings. -lua-time-limit 5000 - -################################## SLOW LOG ################################### - -# The Redis Slow Log is a system to log queries that exceeded a specified -# execution time. The execution time does not include the I/O operations -# like talking with the client, sending the reply and so forth, -# but just the time needed to actually execute the command (this is the only -# stage of command execution where the thread is blocked and can not serve -# other requests in the meantime). -# -# You can configure the slow log with two parameters: one tells Redis -# what is the execution time, in microseconds, to exceed in order for the -# command to get logged, and the other parameter is the length of the -# slow log. When a new command is logged the oldest one is removed from the -# queue of logged commands. - -# The following time is expressed in microseconds, so 1000000 is equivalent -# to one second. Note that a negative number disables the slow log, while -# a value of zero forces the logging of every command. -slowlog-log-slower-than 10000 - -# There is no limit to this length. Just be aware that it will consume memory. -# You can reclaim memory used by the slow log with SLOWLOG RESET. -slowlog-max-len 1024 - -############################### ADVANCED CONFIG ############################### - -# Hashes are encoded using a memory efficient data structure when they have a -# small number of entries, and the biggest entry does not exceed a given -# threshold. These thresholds can be configured using the following directives. -hash-max-ziplist-entries 512 -hash-max-ziplist-value 64 - -# Similarly to hashes, small lists are also encoded in a special way in order -# to save a lot of space. The special representation is only used when -# you are under the following limits: -list-max-ziplist-entries 512 -list-max-ziplist-value 64 - -# Sets have a special encoding in just one case: when a set is composed -# of just strings that happens to be integers in radix 10 in the range -# of 64 bit signed integers. -# The following configuration setting sets the limit in the size of the -# set in order to use this special memory saving encoding. -set-max-intset-entries 512 - -# Similarly to hashes and lists, sorted sets are also specially encoded in -# order to save a lot of space. This encoding is only used when the length and -# elements of a sorted set are below the following limits: -zset-max-ziplist-entries 128 -zset-max-ziplist-value 64 - -# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in -# order to help rehashing the main Redis hash table (the one mapping top-level -# keys to values). The hash table implementation Redis uses (see dict.c) -# performs a lazy rehashing: the more operation you run into an hash table -# that is rehashing, the more rehashing "steps" are performed, so if the -# server is idle the rehashing is never complete and some more memory is used -# by the hash table. -# -# The default is to use this millisecond 10 times every second in order to -# active rehashing the main dictionaries, freeing memory when possible. -# -# If unsure: -# use "activerehashing no" if you have hard latency requirements and it is -# not a good thing in your environment that Redis can reply form time to time -# to queries with 2 milliseconds delay. -# -# use "activerehashing yes" if you don't have such hard requirements but -# want to free memory asap when possible. -activerehashing yes - -# The client output buffer limits can be used to force disconnection of clients -# that are not reading data from the server fast enough for some reason (a -# common reason is that a Pub/Sub client can't consume messages as fast as the -# publisher can produce them). -# -# The limit can be set differently for the three different classes of clients: -# -# normal -> normal clients -# slave -> slave clients and MONITOR clients -# pubsub -> clients subcribed to at least one pubsub channel or pattern -# -# The syntax of every client-output-buffer-limit directive is the following: -# -# client-output-buffer-limit -# -# A client is immediately disconnected once the hard limit is reached, or if -# the soft limit is reached and remains reached for the specified number of -# seconds (continuously). -# So for instance if the hard limit is 32 megabytes and the soft limit is -# 16 megabytes / 10 seconds, the client will get disconnected immediately -# if the size of the output buffers reach 32 megabytes, but will also get -# disconnected if the client reaches 16 megabytes and continuously overcomes -# the limit for 10 seconds. -# -# By default normal clients are not limited because they don't receive data -# without asking (in a push way), but just after a request, so only -# asynchronous clients may create a scenario where data is requested faster -# than it can read. -# -# Instead there is a default limit for pubsub and slave clients, since -# subscribers and slaves receive data in a push fashion. -# -# Both the hard or the soft limit can be disabled just setting it to zero. -client-output-buffer-limit normal 0 0 0 -client-output-buffer-limit slave 256mb 64mb 60 -client-output-buffer-limit pubsub 32mb 8mb 60 - -################################## INCLUDES ################################### - -# Include one or more other config files here. This is useful if you -# have a standard template that goes to all Redis server but also need -# to customize a few per-server settings. Include files can include -# other files, so use this wisely. -# -# include /path/to/local.conf -# include /path/to/other.conf From 2ba962714aaba78921ce18a65628f71f350be460 Mon Sep 17 00:00:00 2001 From: antirez Date: Wed, 3 Oct 2012 11:41:08 +0200 Subject: [PATCH 2/9] "SORT by nosort" (skip sorting) respect sorted set ordering. When SORT is called with the option BY set to a string constant not inclduing the wildcard character "*", there is no way to sort the output so any ordering is valid. This allows the SORT internals to optimize its work and don't really sort the output at all. However it was odd that this option was not able to retain the natural order of a sorted set. This feature was requested by users multiple times as sometimes to call SORT with GET against sorted sets as a way to mass-fetch objects can be handy. This commit introduces two things: 1) The ability of SORT to return sorted sets elements in their natural ordering when `BY nosort` is specified, accordingly to `DESC / ASC` options. 2) The ability of SORT to optimize this case further if LIMIT is passed as well, avoiding to really fetch the whole sorted set, but directly obtaining the specified range. Because in this case the sorting is always deterministic, no post-sorting activity is performed when SORT is called from a Lua script. This commit fixes issue #98. --- src/sort.c | 108 ++++++++++++++++++++++++++++++++++++-------- tests/unit/sort.tcl | 41 +++++++++++++++++ 2 files changed, 129 insertions(+), 20 deletions(-) diff --git a/src/sort.c b/src/sort.c index e5178cd0..d18a5295 100644 --- a/src/sort.c +++ b/src/sort.c @@ -2,6 +2,8 @@ #include "pqsort.h" /* Partial qsort for SORT+LIMIT */ #include /* isnan() */ +zskiplistNode* zslGetElementByRank(zskiplist *zsl, unsigned long rank); + redisSortOperation *createSortOperation(int type, robj *pattern) { redisSortOperation *so = zmalloc(sizeof(*so)); so->type = type; @@ -156,8 +158,9 @@ void sortCommand(redisClient *c) { /* Lookup the key to sort. It must be of the right types */ sortval = lookupKeyRead(c->db,c->argv[1]); - if (sortval && sortval->type != REDIS_SET && sortval->type != REDIS_LIST && - sortval->type != REDIS_ZSET) + if (sortval && sortval->type != REDIS_SET && + sortval->type != REDIS_LIST && + sortval->type != REDIS_ZSET) { addReply(c,shared.wrongtypeerr); return; @@ -167,7 +170,7 @@ void sortCommand(redisClient *c) { * Operations can be GET/DEL/INCR/DECR */ operations = listCreate(); listSetFreeMethod(operations,zfree); - j = 2; + j = 2; /* options start at argv[2] */ /* Now we need to protect sortval incrementing its count, in the future * SORT may have options able to overwrite/delete keys during the sorting @@ -213,13 +216,18 @@ void sortCommand(redisClient *c) { j++; } - /* If we have STORE we need to force sorting for deterministic output - * and replication. We use alpha sorting since this is guaranteed to - * work with any input. + /* For the STORE option, or when SORT is called from a Lua script, + * we want to force a specific ordering even when no explicit ordering + * was asked (SORT BY nosort). This guarantees that replication / AOF + * is deterministic. * - * We also want determinism when SORT is called from Lua scripts, so - * in this case we also force alpha sorting. */ - if ((storekey || c->flags & REDIS_LUA_CLIENT) && dontsort) { + * However in the case 'dontsort' is true, but the type to sort is a + * sorted set, we don't need to do anything as ordering is guaranteed + * in this special case. */ + if ((storekey || c->flags & REDIS_LUA_CLIENT) && + (dontsort && sortval->type != REDIS_ZSET)) + { + /* Force ALPHA sorting */ dontsort = 0; alpha = 1; sortby = NULL; @@ -229,13 +237,41 @@ void sortCommand(redisClient *c) { if (sortval->type == REDIS_ZSET) zsetConvert(sortval, REDIS_ENCODING_SKIPLIST); - /* Load the sorting vector with all the objects to sort */ + /* Objtain the length of the object to sort. */ switch(sortval->type) { case REDIS_LIST: vectorlen = listTypeLength(sortval); break; case REDIS_SET: vectorlen = setTypeSize(sortval); break; case REDIS_ZSET: vectorlen = dictSize(((zset*)sortval->ptr)->dict); break; default: vectorlen = 0; redisPanic("Bad SORT type"); /* Avoid GCC warning */ } + + /* Perform LIMIT start,count sanity checking. */ + start = (limit_start < 0) ? 0 : limit_start; + end = (limit_count < 0) ? vectorlen-1 : start+limit_count-1; + if (start >= vectorlen) { + start = vectorlen-1; + end = vectorlen-2; + } + if (end >= vectorlen) end = vectorlen-1; + + /* Optimization: + * + * 1) if the object to sort is a sorted set. + * 2) There is nothing to sort as dontsort is true (BY ). + * 3) We have a LIMIT option that actually reduces the number of elements + * to fetch. + * + * In this case to load all the objects in the vector is a huge waste of + * resources. We just allocate a vector that is big enough for the selected + * range length, and make sure to load just this part in the vector. */ + if (sortval->type == REDIS_ZSET && + dontsort && + (start != 0 || end != vectorlen-1)) + { + vectorlen = end-start+1; + } + + /* Load the sorting vector with all the objects to sort */ vector = zmalloc(sizeof(redisSortObject)*vectorlen); j = 0; @@ -259,6 +295,48 @@ void sortCommand(redisClient *c) { j++; } setTypeReleaseIterator(si); + } else if (sortval->type == REDIS_ZSET && dontsort) { + /* Special handling for a sorted set, if 'dontsort' is true. + * This makes sure we return elements in the sorted set original + * ordering, accordingly to DESC / ASC options. + * + * Note that in this case we also handle LIMIT here in a direct + * way, just getting the required range, as an optimization. */ + + zset *zs = sortval->ptr; + zskiplist *zsl = zs->zsl; + zskiplistNode *ln; + robj *ele; + int rangelen = vectorlen; + + /* Check if starting point is trivial, before doing log(N) lookup. */ + if (desc) { + long zsetlen = dictSize(((zset*)sortval->ptr)->dict); + + ln = zsl->tail; + if (start > 0) + ln = zslGetElementByRank(zsl,zsetlen-start); + } else { + ln = zsl->header->level[0].forward; + if (start > 0) + ln = zslGetElementByRank(zsl,start+1); + } + + while(rangelen--) { + redisAssertWithInfo(c,sortval,ln != NULL); + ele = ln->obj; + vector[j].obj = ele; + vector[j].u.score = 0; + vector[j].u.cmpobj = NULL; + j++; + ln = desc ? ln->backward : ln->level[0].forward; + } + /* The code producing the output does not know that in the case of + * sorted set, 'dontsort', and LIMIT, we are able to get just the + * range, already sorted, so we need to adjust "start" and "end" + * to make sure start is set to 0. */ + end -= start; + start = 0; } else if (sortval->type == REDIS_ZSET) { dict *set = ((zset*)sortval->ptr)->dict; dictIterator *di; @@ -319,16 +397,6 @@ void sortCommand(redisClient *c) { } } - /* We are ready to sort the vector... perform a bit of sanity check - * on the LIMIT option too. We'll use a partial version of quicksort. */ - start = (limit_start < 0) ? 0 : limit_start; - end = (limit_count < 0) ? vectorlen-1 : start+limit_count-1; - if (start >= vectorlen) { - start = vectorlen-1; - end = vectorlen-2; - } - if (end >= vectorlen) end = vectorlen-1; - if (dontsort == 0) { server.sort_desc = desc; server.sort_alpha = alpha; diff --git a/tests/unit/sort.tcl b/tests/unit/sort.tcl index 5a181641..6c5644a7 100644 --- a/tests/unit/sort.tcl +++ b/tests/unit/sort.tcl @@ -118,6 +118,47 @@ start_server { r sort zset alpha desc } {e d c b a} + test "SORT sorted set BY nosort should retain ordering" { + r del zset + r zadd zset 1 a + r zadd zset 5 b + r zadd zset 2 c + r zadd zset 10 d + r zadd zset 3 e + r multi + r sort zset by nosort asc + r sort zset by nosort desc + r exec + } {{a c e b d} {d b e c a}} + + test "SORT sorted set BY nosort + LIMIT" { + r del zset + r zadd zset 1 a + r zadd zset 5 b + r zadd zset 2 c + r zadd zset 10 d + r zadd zset 3 e + assert_equal [r sort zset by nosort asc limit 0 1] {a} + assert_equal [r sort zset by nosort desc limit 0 1] {d} + assert_equal [r sort zset by nosort asc limit 0 2] {a c} + assert_equal [r sort zset by nosort desc limit 0 2] {d b} + assert_equal [r sort zset by nosort limit 5 10] {} + assert_equal [r sort zset by nosort limit -10 100] {a c e b d} + } + + test "SORT sorted set BY nosort works as expected from scripts" { + r del zset + r zadd zset 1 a + r zadd zset 5 b + r zadd zset 2 c + r zadd zset 10 d + r zadd zset 3 e + r eval { + return {redis.call('sort','zset','by','nosort','asc'), + redis.call('sort','zset','by','nosort','desc')} + } 0 + } {{a c e b d} {d b e c a}} + test "SORT sorted set: +inf and -inf handling" { r del zset r zadd zset -100 a From 0c19880ce61bb4516346288a33797ec650e13842 Mon Sep 17 00:00:00 2001 From: antirez Date: Thu, 4 Oct 2012 11:49:17 +0200 Subject: [PATCH 3/9] "Timeout receiving bulk data" error message modified. The new message now contains an hint about modifying the repl-timeout configuration directive if the problem persists. This should normally not be needed, because while the master generates the RDB file it makes sure to send newlines to the replication channel to prevent timeouts. However there are times when masters running on very slow systems can completely stop for seconds during the RDB saving process. In such a case enlarging the timeout value can fix the problem. See issue #695 for an example of this problem in an EC2 deployment. --- src/replication.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/replication.c b/src/replication.c index 871ce95a..c1e46191 100644 --- a/src/replication.c +++ b/src/replication.c @@ -721,7 +721,7 @@ void replicationCron(void) { if (server.masterhost && server.repl_state == REDIS_REPL_TRANSFER && (time(NULL)-server.repl_transfer_lastio) > server.repl_timeout) { - redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER..."); + redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER... If the problem persists try to set the 'repl-timeout' parameter in redis.conf to a larger value."); replicationAbortSyncTransfer(); } From e480c279bc28832ca78a33f7f52c0b57ae5a16f1 Mon Sep 17 00:00:00 2001 From: Jokea Date: Thu, 30 Aug 2012 15:08:19 +0800 Subject: [PATCH 4/9] Force expire all timer events when system clock skew is detected. When system time changes back, the timer will not worker properly hence some core functionality of redis will stop working(e.g. replication, bgsave, etc). See issue #633 for details. The patch saves the previous time and when a system clock skew is detected, it will force expire all timers. Modiifed by @antirez: the previous time was moved into the eventLoop structure to make sure the library is still thread safe as long as you use different event loops into different threads (otherwise you need some synchronization). More comments added about the reasoning at the base of the patch, that's worth reporting here: /* If the system clock is moved to the future, and then set back to the * right value, time events may be delayed in a random way. Often this * means that scheduled operations will not be performed soon enough. * * Here we try to detect system clock skews, and force all the time * events to be processed ASAP when this happens: the idea is that * processing events earlier is less dangerous than delaying them * indefinitely, and practice suggests it is. */ --- src/ae.c | 19 +++++++++++++++++++ src/ae.h | 1 + 2 files changed, 20 insertions(+) diff --git a/src/ae.c b/src/ae.c index ba53b456..ee483802 100644 --- a/src/ae.c +++ b/src/ae.c @@ -67,6 +67,7 @@ aeEventLoop *aeCreateEventLoop(int setsize) { eventLoop->fired = zmalloc(sizeof(aeFiredEvent)*setsize); if (eventLoop->events == NULL || eventLoop->fired == NULL) goto err; eventLoop->setsize = setsize; + eventLoop->lastTime = time(NULL); eventLoop->timeEventHead = NULL; eventLoop->timeEventNextId = 0; eventLoop->stop = 0; @@ -236,6 +237,24 @@ static int processTimeEvents(aeEventLoop *eventLoop) { int processed = 0; aeTimeEvent *te; long long maxId; + time_t now = time(NULL); + + /* If the system clock is moved to the future, and then set back to the + * right value, time events may be delayed in a random way. Often this + * means that scheduled operations will not be performed soon enough. + * + * Here we try to detect system clock skews, and force all the time + * events to be processed ASAP when this happens: the idea is that + * processing events earlier is less dangerous than delaying them + * indefinitely, and practice suggests it is. */ + if (now < eventLoop->lastTime) { + te = eventLoop->timeEventHead; + while(te) { + te->when_sec = 0; + te = te->next; + } + } + eventLoop->lastTime = now; te = eventLoop->timeEventHead; maxId = eventLoop->timeEventNextId-1; diff --git a/src/ae.h b/src/ae.h index e1dccfc7..f52a075e 100644 --- a/src/ae.h +++ b/src/ae.h @@ -88,6 +88,7 @@ typedef struct aeEventLoop { int maxfd; /* highest file descriptor currently registered */ int setsize; /* max number of file descriptors tracked */ long long timeEventNextId; + time_t lastTime; /* Used to detect system clock skew */ aeFileEvent *events; /* Registered events */ aeFiredEvent *fired; /* Fired events */ aeTimeEvent *timeEventHead; From e2f2dab3efbe2ffdcad013eaa9131529c82b6fd4 Mon Sep 17 00:00:00 2001 From: antirez Date: Fri, 5 Oct 2012 10:10:34 +0200 Subject: [PATCH 5/9] Include time.h in ae.c as we now use time(). --- src/ae.c | 1 + 1 file changed, 1 insertion(+) diff --git a/src/ae.c b/src/ae.c index ee483802..d2faed32 100644 --- a/src/ae.c +++ b/src/ae.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "ae.h" #include "zmalloc.h" From 05e06e154332cf107d30092dddb94b6b35967ce5 Mon Sep 17 00:00:00 2001 From: antirez Date: Fri, 5 Oct 2012 10:48:49 +0200 Subject: [PATCH 6/9] Warn when configured maxmemory value seems odd. This commit warns the user with a log at "warning" level if: 1) After the server startup the maxmemory limit was found to be < 1MB. 2) After a CONFIG SET command modifying the maxmemory setting the limit is set to a value that is smaller than the currently used memory. The behaviour of the Redis server is unmodified, and this wil not make the CONFIG SET command or a wrong configuration in redis.conf less likely to create problems, but at least this will make aware most users about a possbile error they committed without resorting to external help. However no warning is issued if, as a result of loading the AOF or RDB file, we are very near the maxmemory setting, or key eviction will be needed in order to go under the specified maxmemory setting. The reason is that in servers configured as a cache with an aggressive maxmemory-policy most of the times restarting the server will cause this condition to happen if persistence is not switched off. This fixes issue #429. --- src/config.c | 7 ++++++- src/redis.c | 5 +++++ 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/src/config.c b/src/config.c index 768db1e9..a36eb9a3 100644 --- a/src/config.c +++ b/src/config.c @@ -438,7 +438,12 @@ void configSetCommand(redisClient *c) { if (getLongLongFromObject(o,&ll) == REDIS_ERR || ll < 0) goto badfmt; server.maxmemory = ll; - if (server.maxmemory) freeMemoryIfNeeded(); + if (server.maxmemory) { + if (server.maxmemory < zmalloc_used_memory()) { + redisLog(REDIS_WARNING,"WARNING: the new maxmemory value set via CONFIG SET is smaller than the current memory usage. This will result in keys eviction and/or inability to accept new write commands depending on the maxmemory-policy."); + } + freeMemoryIfNeeded(); + } } else if (!strcasecmp(c->argv[2]->ptr,"maxmemory-policy")) { if (!strcasecmp(o->ptr,"volatile-lru")) { server.maxmemory_policy = REDIS_MAXMEMORY_VOLATILE_LRU; diff --git a/src/redis.c b/src/redis.c index 0656d7c2..aa5a73f2 100644 --- a/src/redis.c +++ b/src/redis.c @@ -2578,6 +2578,11 @@ int main(int argc, char **argv) { redisLog(REDIS_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket); } + /* Warning the user about suspicious maxmemory setting. */ + if (server.maxmemory > 0 && server.maxmemory < 1024*1024) { + redisLog(REDIS_WARNING,"WARNING: You specified a maxmemory value that is less than 1MB (current value is %llu bytes). Are you sure this is what you really want?", server.maxmemory); + } + aeSetBeforeSleepProc(server.el,beforeSleep); aeMain(server.el); aeDeleteEventLoop(server.el); From 99c3338c23ba0d4ca4ecb85e0f23ff3f3c3e81f3 Mon Sep 17 00:00:00 2001 From: antirez Date: Wed, 3 Oct 2012 19:14:46 +0200 Subject: [PATCH 7/9] Hash function switched to murmurhash2. The previously used hash function, djbhash, is not secure against collision attacks even when the seed is randomized as there are simple ways to find seed-independent collisions. The new hash function appears to be safe (or much harder to exploit at least) in this case, and has better distribution. Better distribution does not always means that's better. For instance in a fast benchmark with "DEBUG POPULATE 1000000" I obtained the following results: 1.6 seconds with djbhash 2.0 seconds with murmurhash2 This is due to the fact that djbhash will hash objects that follow the pattern `prefix:` and where the id is numerically near, to near buckets. This improves the locality. However in other access patterns with keys that have no relation murmurhash2 has some (apparently minimal) speed advantage. On the other hand a better distribution should significantly improve the quality of the distribution of elements returned with dictGetRandomKey() that is used in SPOP, SRANDMEMBER, RANDOMKEY, and other commands. Everything considered, and under the suspect that this commit fixes a security issue in Redis, we are switching to the new hash function. If some serious speed regression will be found in the future we'll be able to step back easiliy. This commit fixes issue #663. --- src/dict.c | 68 ++++++++++++++++++++++++++++++++++++++++++++---------- src/dict.h | 2 +- 2 files changed, 57 insertions(+), 13 deletions(-) diff --git a/src/dict.c b/src/dict.c index 66bb983a..ec58e820 100644 --- a/src/dict.c +++ b/src/dict.c @@ -85,29 +85,73 @@ unsigned int dictIdentityHashFunction(unsigned int key) return key; } -static int dict_hash_function_seed = 5381; +static uint32_t dict_hash_function_seed = 5381; -void dictSetHashFunctionSeed(unsigned int seed) { +void dictSetHashFunctionSeed(uint32_t seed) { dict_hash_function_seed = seed; } -unsigned int dictGetHashFunctionSeed(void) { +uint32_t dictGetHashFunctionSeed(void) { return dict_hash_function_seed; } -/* Generic hash function (a popular one from Bernstein). - * I tested a few and this was the best. */ -unsigned int dictGenHashFunction(const unsigned char *buf, int len) { - unsigned int hash = dict_hash_function_seed; +/* MurmurHash2, by Austin Appleby + * Note - This code makes a few assumptions about how your machine behaves - + * 1. We can read a 4-byte value from any address without crashing + * 2. sizeof(int) == 4 + * + * And it has a few limitations - + * + * 1. It will not work incrementally. + * 2. It will not produce the same results on little-endian and big-endian + * machines. + */ +unsigned int dictGenHashFunction(const void *key, int len) { + /* 'm' and 'r' are mixing constants generated offline. + They're not really 'magic', they just happen to work well. */ + uint32_t seed = dict_hash_function_seed; + const uint32_t m = 0x5bd1e995; + const int r = 24; - while (len--) - hash = ((hash << 5) + hash) + (*buf++); /* hash * 33 + c */ - return hash; + /* Initialize the hash to a 'random' value */ + uint32_t h = seed ^ len; + + /* Mix 4 bytes at a time into the hash */ + const unsigned char *data = (const unsigned char *)key; + + while(len >= 4) { + uint32_t k = *(uint32_t*)data; + + k *= m; + k ^= k >> r; + k *= m; + + h *= m; + h ^= k; + + data += 4; + len -= 4; + } + + /* Handle the last few bytes of the input array */ + switch(len) { + case 3: h ^= data[2] << 16; + case 2: h ^= data[1] << 8; + case 1: h ^= data[0]; h *= m; + }; + + /* Do a few final mixes of the hash to ensure the last few + * bytes are well-incorporated. */ + h ^= h >> 13; + h *= m; + h ^= h >> 15; + + return (unsigned int)h; } -/* And a case insensitive version */ +/* And a case insensitive hash function (based on djb hash) */ unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len) { - unsigned int hash = dict_hash_function_seed; + unsigned int hash = (unsigned int)dict_hash_function_seed; while (len--) hash = ((hash << 5) + hash) + (tolower(*buf++)); /* hash * 33 + c */ diff --git a/src/dict.h b/src/dict.h index 5f856953..f480ae53 100644 --- a/src/dict.h +++ b/src/dict.h @@ -155,7 +155,7 @@ dictEntry *dictNext(dictIterator *iter); void dictReleaseIterator(dictIterator *iter); dictEntry *dictGetRandomKey(dict *d); void dictPrintStats(dict *d); -unsigned int dictGenHashFunction(const unsigned char *buf, int len); +unsigned int dictGenHashFunction(const void *key, int len); unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len); void dictEmpty(dict *d); void dictEnableResize(void); From 500dddc26499319a7e60be996487078e07e921ac Mon Sep 17 00:00:00 2001 From: antirez Date: Fri, 5 Oct 2012 19:08:55 +0200 Subject: [PATCH 8/9] Redis 2.6.0 RC8 (2.5.14) --- 00-RELEASENOTES | 12 ++++++++++++ src/version.h | 2 +- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/00-RELEASENOTES b/00-RELEASENOTES index 12f1e3d1..02a3db3a 100644 --- a/00-RELEASENOTES +++ b/00-RELEASENOTES @@ -14,6 +14,18 @@ HIGH: There is a critical bug that may affect a subset of users. Upgrade! CRITICAL: There is a critical bug affecting MOST USERS. Upgrade ASAP. -------------------------------------------------------------------------------- +---[ Redis 2.5.14 (2.6 Release Candidate 8) ] + +* [BUGFIX] Fixed compilation on FreeBSD. +* [IMPROVED] SRANDMEMBER that returns multiple random elements. +* [IMPROVED] Sentinel backported to 2.6. It will be taken in sync with 2.8. +* [IMPROVED] Helper function for scripting to return errors and status replies. +* [IMPROVED] SORT by nosort [ASC|DESC] uses sorted set elements ordering. +* [BUGFIX] Better resistence to system clock skew. +* [IMPROVED] Warn the user when the configured maxmemory seems odd. +* [BUGFIX] Hashing function is now murmurhash2 for security purposes. +* [IMPROVED] Install script no longer uses a template but redis.conf itself. + ---[ Redis 2.5.13 (2.6 Release Candidate 7) ] UPGRADE URGENCY: HIGH diff --git a/src/version.h b/src/version.h index 6329f488..9e21cb96 100644 --- a/src/version.h +++ b/src/version.h @@ -1 +1 @@ -#define REDIS_VERSION "2.5.13" +#define REDIS_VERSION "2.5.14" From f4eb4b335264f2a88316a7fd8752d740f1a3cb63 Mon Sep 17 00:00:00 2001 From: antirez Date: Sat, 6 Oct 2012 12:04:27 +0200 Subject: [PATCH 9/9] CONTRIBUTING file updated. --- CONTRIBUTING | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/CONTRIBUTING b/CONTRIBUTING index 623c5a6e..1ecd1394 100644 --- a/CONTRIBUTING +++ b/CONTRIBUTING @@ -1,8 +1,22 @@ -1. Enter irc.freenode.org #redis and start talking with 'antirez' and/or 'pietern' to check if there is interest for such a feature and to understand the probability of it being merged. We'll try hard to keep Redis simple... so you'll likely encounter high resistance. +# IMPORTANT: HOW TO USE REDIS GITHUB ISSUES -2. Drop a message to the Redis Google Group with a proposal of semantics/API. +* Github issues SHOULD ONLY BE USED to report bugs, and for DETAILED feature + requests. Everything else belongs to the Redis Google Group. -3. If steps 1 and 2 are ok, use the following procedure to submit a patch: + PLEASE DO NOT POST GENERAL QUESTIONS that are not about bugs or suspected + bugs in the Github issues system. We'll be very happy to help you and provide + all the support in the Redis Google Group. + + Redis Google Group address: + + https://groups.google.com/forum/?fromgroups#!forum/redis-db + +# How to provide a patch for a new feature + +1. Drop a message to the Redis Google Group with a proposal of semantics/API. + +2. If in steps 1 you get an acknowledge from the project leaders, use the + following procedure to submit a patch: a. Fork Redis on github ( http://help.github.com/fork-a-repo/ ) b. Create a topic branch (git checkout -b my_branch)