Varnish dumping cache?
Skye Poier Nott
skye at F4.ca
Mon Apr 14 20:55:27 CEST 2008
Hello,
I'm a new Varnish user (coming from Squid - glad to be rid of it) but
I'm seeing some strange behaviour when I test load a Varnish server.
I have a configuration of 4 machines with 250 http client test threads
each requesting a set of 46 files from 2,000 virtual hosts (92,000
objects total). But while it's running, I see the following:
# while ((1)); do
date
varnishstat -1 | grep n_object
sleep 5
done
n_object will climb steadily and then all of a sudden, it all goes away:
n_objecthead 86765 . N struct objecthead
Mon Apr 14 11:51:06 PDT 2008
n_object 86780 . N struct object
n_objecthead 86782 . N struct objecthead
Mon Apr 14 11:51:11 PDT 2008
n_object 358 . N struct object
n_objecthead 358 . N struct objecthead
Mon Apr 14 11:51:16 PDT 2008
n_object 358 . N struct object
n_objecthead 358 . N struct objecthead
I don't see anything in varnishlog -i Error when this happens but I'm
not sure where to look.
Here's my config:
param.show
200 783
user nobody (65534)
group nogroup (65533)
default_ttl 86400 [seconds]
thread_pools 1 [pools]
thread_pool_max 1000 [threads]
thread_pool_min 1 [threads]
thread_pool_timeout 120 [seconds]
overflow_max 100 [%]
http_workspace 8192 [bytes]
sess_timeout 5 [seconds]
pipe_timeout 60 [seconds]
send_timeout 600 [seconds]
auto_restart on [bool]
fetch_chunksize 128 [kilobytes]
sendfile_threshold unlimited [bytes]
vcl_trace off [bool]
listen_address ":80"
listen_depth 1024 [connections]
srcaddr_hash 1049 [buckets]
srcaddr_ttl 30 [seconds]
backend_http11 off [bool]
client_http11 off [bool]
ping_interval 3 [seconds]
storage is varnishd_storage="file,/var/cache/varnish,128G" (pre-alloced)
on FreeBSD 6.3-RELEASE
Thanks for helping this Varnish newbie. Great daemon!
Skye
More information about the varnish-misc
mailing list