I watched a phenomenon in my production env. A redis master used memory as follows:
used_memory: 144537448
used_memory_human: 137.84M
used_memory_rss: 159195136
used_memory_peak: 166693568
used_memory_peak_human: 158.97M
used_memory_lua: 33792
mem_fragmentation_ratio: 1.10
mem_allocator: jemalloc-3.2.0
but the slave used memory as follows:
used_memory: 4992912
used_memory_human: 4.76M
used_memory_rss: 12337152
used_memory_peak: 17586480
used_memory_peak_human: 16.77M
used_memory_lua: 33792
mem_fragmentation_ratio: 2.47
mem_allocator: jemalloc-3.2.0
The redis version is 2.8.9, i'm confused with this.
Comment From: badboy
Please show the complete INFO output
Comment From: mindwind
The master INFO complete output
redis 172.xx.xx.xx:6381> info
# Server
redis_version:2.8.9
redis_git_sha1:00000000
redis_git_dirty:0
redis_build_id:d9ddbfb45faa4dd8
redis_mode:standalone
os:Linux 2.6.32-358.el6.x86_64 x86_64
arch_bits:64
multiplexing_api:epoll
gcc_version:4.4.7
process_id:6088
run_id:3663168932b75d4017846a9beee79f7fcb94bc47
tcp_port:6381
uptime_in_seconds:2423216
uptime_in_days:28
hz:10
lru_clock:11780148
config_file:/export/servers/redis-2.8.9/conf/redis_6381.conf
# Clients
connected_clients:292
client_longest_output_list:0
client_biggest_input_buf:0
blocked_clients:0
# Memory
used_memory:146330632
used_memory_human:139.55M
used_memory_rss:153825280
used_memory_peak:166693568
used_memory_peak_human:158.97M
used_memory_lua:33792
mem_fragmentation_ratio:1.05
mem_allocator:jemalloc-3.2.0
# Persistence
loading:0
rdb_changes_since_last_save:374252931
rdb_bgsave_in_progress:0
rdb_last_save_time:1401868981
rdb_last_bgsave_status:ok
rdb_last_bgsave_time_sec:0
rdb_current_bgsave_time_sec:-1
aof_enabled:0
aof_rewrite_in_progress:0
aof_rewrite_scheduled:0
aof_last_rewrite_time_sec:-1
aof_current_rewrite_time_sec:-1
aof_last_bgrewrite_status:ok
aof_last_write_status:ok
# Stats
total_connections_received:2086842
total_commands_processed:912258912
instantaneous_ops_per_sec:1300
rejected_connections:0
sync_full:1
sync_partial_ok:0
sync_partial_err:0
expired_keys:95400
evicted_keys:0
keyspace_hits:655903770
keyspace_misses:43474587
pubsub_channels:0
pubsub_patterns:0
latest_fork_usec:747
# Replication
role:master
connected_slaves:1
slave0:ip=172.xx.xx.xx,port=6382,state=online,offset=43142077109,lag=1
master_repl_offset:43142133024
repl_backlog_active:1
repl_backlog_size:134217728
repl_backlog_first_byte_offset:43007915297
repl_backlog_histlen:134217728
# CPU
used_cpu_sys:19631.60
used_cpu_user:12294.03
used_cpu_sys_children:0.00
used_cpu_user_children:0.00
# Keyspace
db0:keys=9091,expires=9091,avg_ttl=765988756
The slave INFO complete output
redis 172.xx.xx.xx:6382> info
# Server
redis_version:2.8.9
redis_git_sha1:00000000
redis_git_dirty:0
redis_build_id:c16bcda3d9345354
redis_mode:standalone
os:Linux 2.6.32-358.el6.x86_64 x86_64
arch_bits:64
multiplexing_api:epoll
gcc_version:4.4.7
process_id:8972
run_id:63296d1ed6b7f8e661182125f9f92d7f62ab7d22
tcp_port:6382
uptime_in_seconds:2423377
uptime_in_days:28
hz:10
lru_clock:11780314
config_file:/export/servers/redis-2.8.9/conf/redis_6382.conf
# Clients
connected_clients:8
client_longest_output_list:0
client_biggest_input_buf:0
blocked_clients:0
# Memory
used_memory:5026464
used_memory_human:4.79M
used_memory_rss:12267520
used_memory_peak:17586480
used_memory_peak_human:16.77M
used_memory_lua:33792
mem_fragmentation_ratio:2.44
mem_allocator:jemalloc-3.2.0
# Persistence
loading:0
rdb_changes_since_last_save:374425013
rdb_bgsave_in_progress:0
rdb_last_save_time:1401865865
rdb_last_bgsave_status:ok
rdb_last_bgsave_time_sec:-1
rdb_current_bgsave_time_sec:-1
aof_enabled:1
aof_rewrite_in_progress:0
aof_rewrite_scheduled:0
aof_last_rewrite_time_sec:0
aof_current_rewrite_time_sec:-1
aof_last_bgrewrite_status:ok
aof_last_write_status:ok
aof_current_size:28610748
aof_base_size:3364328
aof_pending_rewrite:0
aof_buffer_length:0
aof_rewrite_buffer_length:0
aof_pending_bio_fsync:0
aof_delayed_fsync:0
# Stats
total_connections_received:784275
total_commands_processed:385478374
instantaneous_ops_per_sec:386
rejected_connections:0
sync_full:0
sync_partial_ok:0
sync_partial_err:0
expired_keys:0
evicted_keys:0
keyspace_hits:187050671
keyspace_misses:0
pubsub_channels:0
pubsub_patterns:0
latest_fork_usec:936
# Replication
role:slave
master_host:172.22.146.153
master_port:6381
master_link_status:up
master_last_io_seconds_ago:0
master_sync_in_progress:0
slave_repl_offset:43150944977
slave_priority:100
slave_read_only:1
connected_slaves:0
master_repl_offset:0
repl_backlog_active:0
repl_backlog_size:134217728
repl_backlog_first_byte_offset:0
repl_backlog_histlen:0
# CPU
used_cpu_sys:10217.29
used_cpu_user:6234.36
used_cpu_sys_children:3.91
used_cpu_user_children:17.93
# Keyspace
db0:keys=9094,expires=9094,avg_ttl=0
Comment From: idning
try this::
config set hz 200
here is a explain (in chinese): http://idning.github.io/redis-config-hz.html
Comment From: mindwind
3ks
Comment From: sayap
The difference is mostly caused by the 128 MB replication backlog buffer (repl_backlog_size:134217728), which was a master-only thing until version 4.0 (2669fb83)