multi-threaded memcached

I discovered while compiling Wafflegrid today that by default, the Ubuntu binaries for memcached are not-multithreaded.

Following the installation of memcached from apt-get and libmemcached I ran memslap for:

$ memslap -s localhost
    Threads connecting to servers 1
    Took 1.633 seconds to load data

$ memstat -s localhost
Listing 1 Server

Server: localhost (11211)
     pid: 23868
     uptime: 54
     time: 1244575816
     version: 1.2.2
     pointer_size: 32
     rusage_user: 0.90000
     rusage_system: 0.120000
     curr_items: 10000
     total_items: 10000
     bytes: 5430000
     curr_connections: 1
     total_connections: 3
     connection_structures: 2
     cmd_get: 0
     cmd_set: 10000
     get_hits: 0
     get_misses: 0
     evictions: 0
     bytes_read: 5430000
     bytes_written: 5430000
     limit_maxbytes: 0
     threads: 1

By installed the Latest RC 1.4.0 we see.

memslap -s localhost
    Threads connecting to servers 1
    Took 0.866 seconds to load data

memstat -s localhost

Listing 1 Server

Server: localhost (11211)
     pid: 8651
     uptime: 375
     time: 1244577237
     version: 1.4.0-rc1
     pointer_size: 32
     rusage_user: 0.110000
     rusage_system: 0.130000
     curr_items: 10000
     total_items: 10000
     bytes: 5510000
     curr_connections: 5
     total_connections: 8
     connection_structures: 6
     cmd_get: 0
     cmd_set: 10000
     get_hits: 0
     get_misses: 0
     evictions: 0
     bytes_read: 5510000
     bytes_written: 5510000
     limit_maxbytes: 0
     threads: 5

Thanks Matt for pointing that one out.

Tagged with: Databases General Linux Memcached MySQL Open Source Ubuntu Wafflegrid

Related Posts

Why INSERT IGNORE should not be used

Why INSERT IGNORE should not be used

Let’s say you’re building a reference table from source data, e.g. a silver medallion table from a primary source. In this example I am using a file of random locations on the globe extracted from OpenStreetMap (OSM) as my primary source.

Read more
What Constitutes Clean Data?

What Constitutes Clean Data?

Clean data is one of those terms everyone uses and few define precisely. Row counts match? No nulls in key columns? Values within expected ranges? All useful checks — and all insufficient once you move from a table view to a visualization view.

Read more
Curated MySQL Data Sets for Realistic Testing

Curated MySQL Data Sets for Realistic Testing

Synthetic benchmarks have their place, but I have always preferred working with real data. Not client production data — that stays private — but publicly available datasets that reflect the messy shapes, skewed distributions, and indexing challenges you encounter in the wild.

Read more