1. 12 Aug, 2013 1 commit
    • antirez's avatar
      Replication: better way to send a preamble before RDB payload. · 89ffba91
      antirez authored
      During the replication full resynchronization process, the RDB file is
      transfered from the master to the slave. However there is a short
      preamble to send, that is currently just the bulk payload length of the
      file in the usual Redis form $..length..<CR><LF>.
      
      This preamble used to be sent with a direct write call, assuming that
      there was alway room in the socket output buffer to hold the few bytes
      needed, however this does not scale in case we'll need to send more
      stuff, and is not very robust code in general.
      
      This commit introduces a more general mechanism to send a preamble up to
      2GB in size (the max length of an sds string) in a non blocking way.
      89ffba91
  2. 06 Aug, 2013 2 commits
  3. 05 Aug, 2013 1 commit
    • antirez's avatar
      Draft #1 of a new expired keys collection algorithm. · b09ea1bd
      antirez authored
      The main idea here is that when we are no longer to expire keys at the
      rate the are created, we can't block more in the normal expire cycle as
      this would result in too big latency spikes.
      
      For this reason the commit introduces a "fast" expire cycle that does
      not run for more than 1 millisecond but is called in the beforeSleep()
      hook of the event loop, so much more often, and with a frequency bound
      to the frequency of executed commnads.
      
      The fast expire cycle is only called when the standard expiration
      algorithm runs out of time, that is, consumed more than
      REDIS_EXPIRELOOKUPS_TIME_PERC of CPU in a given cycle without being able
      to take the number of already expired keys that are yet not collected
      to a number smaller than 25% of the number of keys.
      
      You can test this commit with different loads, but a simple way is to
      use the following:
      
      Extreme load with pipelining:
      
      redis-benchmark -r 100000000 -n 100000000  \
              -P 32 set ele:rand:000000000000 foo ex 2
      
      Remove the -P32 in order to avoid the pipelining for a more real-world
      load.
      
      In another terminal tab you can monitor the Redis behavior with:
      
      redis-cli -i 0.1 -r -1 info keyspace
      
      and
      
      redis-cli --latency-history
      
      Note: this commit will make Redis printing a lot of debug messages, it
      is not a good idea to use it in production.
      b09ea1bd
  4. 22 Jul, 2013 1 commit
    • antirez's avatar
      Introduction of a new string encoding: EMBSTR · 894eba07
      antirez authored
      Previously two string encodings were used for string objects:
      
      1) REDIS_ENCODING_RAW: a string object with obj->ptr pointing to an sds
      stirng.
      
      2) REDIS_ENCODING_INT: a string object where the obj->ptr void pointer
      is casted to a long.
      
      This commit introduces a experimental new encoding called
      REDIS_ENCODING_EMBSTR that implements an object represented by an sds
      string that is not modifiable but allocated in the same memory chunk as
      the robj structure itself.
      
      The chunk looks like the following:
      
      +--------------+-----------+------------+--------+----+
      | robj data... | robj->ptr | sds header | string | \0 |
      +--------------+-----+-----+------------+--------+----+
                           |                       ^
                           +-----------------------+
      
      The robj->ptr points to the contiguous sds string data, so the object
      can be manipulated with the same functions used to manipulate plan
      string objects, however we need just on malloc and one free in order to
      allocate or release this kind of objects. Moreover it has better cache
      locality.
      
      This new allocation strategy should benefit both the memory usage and
      the performances. A performance gain between 60 and 70% was observed
      during micro-benchmarks, however there is more work to do to evaluate
      the performance impact and the memory usage behavior.
      894eba07
  5. 16 Jul, 2013 1 commit
  6. 12 Jul, 2013 2 commits
    • antirez's avatar
      SORT ALPHA: use collation instead of binary comparison. · cf1579a7
      antirez authored
      Note that we only do it when STORE is not used, otherwise we want an
      absolutely locale independent and binary safe sorting in order to ensure
      AOF / replication consistency.
      
      This is probably an unexpected behavior violating the least surprise
      rule, but there is currently no other simple / good alternative.
      cf1579a7
    • antirez's avatar
      Fixed compareStringObject() and introduced collateStringObject(). · 81e55ec0
      antirez authored
      compareStringObject was not always giving the same result when comparing
      two exact strings, but encoded as integers or as sds strings, since it
      switched to strcmp() when at least one of the strings were not sds
      encoded.
      
      For instance the two strings "123" and "123\x00456", where the first
      string was integer encoded, would result into the old implementation of
      compareStringObject() to return 0 as if the strings were equal, while
      instead the second string is "greater" than the first in a binary
      comparison.
      
      The same compasion, but with "123" encoded as sds string, would instead
      return a value < 0, as it is correct. It is not impossible that the
      above caused some obscure bug, since the comparison was not always
      deterministic, and compareStringObject() is used in the implementation
      of skiplists, hash tables, and so forth.
      
      At the same time, collateStringObject() was introduced by this commit, so
      that can be used by SORT command to return sorted strings usign
      collation instead of binary comparison. See next commit.
      81e55ec0
  7. 09 Jul, 2013 3 commits
  8. 08 Jul, 2013 2 commits
    • Geoff Garside's avatar
      Update REDIS_CLUSTER_IPLEN to INET6_ADDRSTRLEN. · 6181455a
      Geoff Garside authored
      Change REDIS_CLUSTER_IPLEN to INET6_ADDRSTRLEN so that the clusterNode
      ip character buffer is big enough to hold an IPv6 address.
      6181455a
    • Geoff Garside's avatar
      Add macro to define clusterNode.ip buffer size. · 9cfa02fe
      Geoff Garside authored
      Add REDIS_CLUSTER_IPLEN macro to define the size of the clusterNode ip
      character array. Additionally use this macro in inet_ntop(3) calls where
      the size of the array was being defined manually.
      
      The REDIS_CLUSTER_IPLEN is defined as INET_ADDRSTRLEN which defines the
      correct size of a buffer to store an IPv4 address in. The
      INET_ADDRSTRLEN macro itself is defined in the <netinet/in.h> header
      file and should be portable across the majority of systems.
      9cfa02fe
  9. 05 Jul, 2013 1 commit
  10. 04 Jul, 2013 1 commit
  11. 28 Jun, 2013 1 commit
  12. 26 Jun, 2013 2 commits
  13. 24 Jun, 2013 2 commits
    • antirez's avatar
      Use the RSC to replicate EVALSHA unmodified. · f0bf5fd8
      antirez authored
      This commit uses the Replication Script Cache in order to avoid
      translating EVALSHA into EVAL whenever possible for both the AOF and
      slaves.
      f0bf5fd8
    • antirez's avatar
      Replication of scripts as EVALSHA: sha1 caching implemented. · 94ec7db4
      antirez authored
      This code is only responsible to take an LRU-evicted fixed length cache
      of SHA1 that we are sure all the slaves received.
      
      In this commit only the implementation is provided, but the Redis core
      does not use it to actually send EVALSHA to slaves when possible.
      94ec7db4
  14. 21 Jun, 2013 1 commit
    • antirez's avatar
      New API to force propagation. · 515a26bb
      antirez authored
      The old REDIS_CMD_FORCE_REPLICATION flag was removed from the
      implementation of Redis, now there is a new API to force specific
      executions of a command to be propagated to AOF / Replication link:
      
          void forceCommandPropagation(int flags);
      
      The new API is also compatible with Lua scripting, so a script that will
      execute commands that are forced to be propagated, will also be
      propagated itself accordingly even if no change to data is operated.
      
      As a side effect, this new design fixes the issue with scripts not able
      to propagate PUBLISH to slaves (issue #873).
      515a26bb
  15. 20 Jun, 2013 1 commit
    • antirez's avatar
      PUBSUB command implemented. · 455563fa
      antirez authored
      Currently it implements three subcommands:
      
      PUBSUB CHANNELS [<pattern>]    List channels with non-zero subscribers.
      PUBSUB NUMSUB [channel_1 ...]  List number of subscribers for channels.
      PUBSUB NUMPAT                  Return number of subscribed patterns.
      455563fa
  16. 12 Jun, 2013 1 commit
  17. 30 May, 2013 1 commit
  18. 27 May, 2013 3 commits
  19. 17 May, 2013 1 commit
  20. 15 May, 2013 1 commit
    • antirez's avatar
      Added a define for most configuration defaults. · 310dbba0
      antirez authored
      Also the logfile option was modified to always have an explicit value
      and to log to stdout when an empty string is used as log file.
      
      Previously there was special handling of the string "stdout" that set
      the logfile to NULL, this always required some special handling.
      310dbba0
  21. 13 May, 2013 2 commits
  22. 09 May, 2013 1 commit
  23. 08 May, 2013 1 commit
    • antirez's avatar
      Revert "use long long instead of size_t make it more safe" · 0ae1b5b0
      antirez authored
      This reverts commit 2c75f2cf.
      
      After further analysis, it is very unlikely that we'll raise the
      string size limit to > 512MB, and at the same time such big strings
      will be used in 32 bit systems.
      
      Better to revert to size_t so that 32 bit processors will not be
      forced to use a 64 bit counter in normal operations, that is currently
      completely useless.
      0ae1b5b0
  24. 07 May, 2013 2 commits
  25. 03 May, 2013 1 commit
    • antirez's avatar
      Cluster: link reconnection on delayed PONG reply. · 5c9f6d4f
      antirez authored
      When the PONG delay is half the cluster node timeout, the link gets
      disconnected (and later automatically reconnected) in order to ensure
      that it's not just a dead connection issue.
      
      However this operation is only performed if the link is old enough, in
      order to avoid to disconnect the same link again and again (and among
      the other problems, never receive the PONG because of that).
      
      Note: when the link is reconnected, the 'ping_sent' field is not updated
      even if a new ping is sent using the new connection, so we can still
      reliably detect a node ping timeout.
      5c9f6d4f
  26. 24 Apr, 2013 2 commits
  27. 09 Apr, 2013 2 commits
    • antirez's avatar
      Cluster: use server.cluster_node_timeout directly. · 68cf249f
      antirez authored
      We used to copy this value into the server.cluster structure, however this
      was not necessary.
      
      The reason why we don't directly use server.cluster->node_timeout is
      that things that can be configured via redis.conf need to be directly
      available in the server structure as server.cluster is allocated later
      only if needed in order to reduce the memory footprint of non-cluster
      instances.
      68cf249f
    • antirez's avatar
      ef4f25ff