Thanks Amos. We are already on a Production, cant really think about
upgrading without knowing the impact and benefits, for now.
On the other hand, i picked up the "TCP_HIT" from my production box
that is a lot used, seem to have many there.
1368107093 000000 10.56.9.27 TCP_HIT/200 738 GET
http://wikid.domain.com/wikid/skins/common/images/Arr_.png -
HIER_NONE/- image/png
1368110324 000001 10.56.9.27 TCP_HIT/200 5143 GET
http://wikid.domain.com/wikid/skins/common/images/spinner.gif -
HIER_NONE/- image/gif
1368110509 000001 10.56.9.27 TCP_HIT/200 2169 GET
http://wikid.domain.com/wikid/skins/monobook/IE60Fixes.css? -
HIER_NONE/- text/css
1368110510 000001 10.56.9.27 TCP_HIT/200 557 GET
http://wikid.domain.com/wikid/skins/monobook/external.png -
HIER_NONE/- image/png
1368113664 000001 10.56.9.27 TCP_HIT/200 897 GET
http://wikid.eng.domain.com/wikid/skins/common/images/button_image.png
- HIER_NONE/- image/png
1368113664 000000 10.56.9.27 TCP_HIT/200 639 GET
http://wikid.eng.domain.com/wikid/skins/common/images/button_hr.png -
HIER_NONE/- image/png
1368115000 000000 10.56.9.27 TCP_HIT/200 475 GET
http://wikid.domain.com/lucene-wikid/skins/monobook/FF2Fixes.css -
HIER_NONE/- text/css
1368117520 000001 10.56.9.27 TCP_HIT/200 1311 GET
http://wikid.domain.com/lucene-wikid/skins/monobook/lock_icon.gif? -
HIER_NONE/- image/gif
1368123877 000001 10.56.9.27 TCP_HIT/200 4099 GET
http://wikid/wikid/skins/common/images/poweredby_mediawiki_88x31.png -
HIER_NONE/- image/png
1368130149 000000 10.56.9.27 TCP_HIT/200 3998 GET
http://wikid.eng.domain.com/wikid/skins/common/images/poweredby_mediawiki_88x31.png
- HIER_NONE/- image/png
Basically, Out of over 8 lac lines in the access.log of production,
here is what the count for each of the type of requests it has
received ..
TCP_CLIENT_REFRESH_MISS/200 :69
TCP_CLIENT_REFRESH_MISS_ABORTED/200 :1
TCP_HIT/200 :173
TCP_HIT_ABORTED/000 :45
TCP_HIT_ABORTED/200 :1
TCP_IMS_HIT/304 :9126
TCP_MEM_HIT/200 :16172
TCP_MEM_HIT_ABORTED/200 :42
TCP_MISS/200 :282417
TCP_MISS/206 :200
TCP_MISS/301 :3110
TCP_MISS/302 :383503
TCP_MISS/304 :52580
TCP_MISS/400 :10
TCP_MISS/403 :14
TCP_MISS/404 :42825
TCP_MISS/405 :221
TCP_MISS/500 :2
TCP_MISS/502 :3
TCP_MISS/503 :19
TCP_MISS_ABORTED/000 :5559
TCP_MISS_ABORTED/200 :2882
TCP_MISS_ABORTED/206 :1
TCP_MISS_ABORTED/302 :2
TCP_MISS_ABORTED/404 :2
TCP_REFRESH_FAIL/200 :1
TCP_REFRESH_MODIFIED/200 :158
TCP_REFRESH_MODIFIED/206 :13
TCP_REFRESH_MODIFIED/404 :2
TCP_REFRESH_UNMODIFIED/200 :31737
TCP_REFRESH_UNMODIFIED/206 :144
TCP_REFRESH_UNMODIFIED/304 :10355
TCP_REFRESH_UNMODIFIED_ABORTED/200 :14
Do you see anything fishy in here ?
Here is what the squid.conf of the production box look like and it
runs the same squid version.
====
cache_mgr enghelp_at_domain.com
cache_effective_user squid
cache_effective_group squid
visible_hostname wikid.domain.com
http_port 80 accel defaultsite=wikid.domain.com vhost
cache_peer 10.56.9.38 parent 443 0 originserver login=PASS
name=engwikiweb1 sourcehash ssl sslflags=DONT_VERIFY_PEER
cache_peer 10.56.9.39 parent 443 0 login=PASS name=engwikiweb2
sourcehash ssl sslflags=DONT_VERIFY_PEER
acl wikid dstdomain wikid.domain.com
cache_peer_access engwikiweb1 allow wikid
cache_peer_access engwikiweb2 allow wikid
cache_peer_access engwikiweb1 allow all
cache_peer_access engwikiweb2 allow all
never_direct allow wikid
http_access allow wikid
http_access allow all
cache_replacement_policy heap LRU
memory_replacement_policy heap LRU
cache_dir ufs /wikiweb/squid-cache/var/cache/engwikilb1 2048 16 64
cache_swap_low 90
cache_swap_high 95
cache_mem 1024 MB
maximum_object_size_in_memory 4096 KB
maximum_object_size 32768 KB
logfile_rotate 3
forwarded_for on
cache_store_log none
logformat squid %ts %06tr %>a %Ss/%03>Hs %<st %rm %ru %un %Sh/%<A %mt
refresh_pattern -i \.css\?.*$ 1440 50% 2880 reload-into-ims
refresh_pattern -i \.js\?.*$ 1440 50% 2880 reload-into-ims
refresh_pattern -i \.css$ 1440 50% 2880 reload-into-ims
refresh_pattern -i \.js$ 1440 50% 2880 reload-into-ims
refresh_pattern (/skins/) 1440 50% 2880 reload-into-ims
refresh_pattern -i gen=css 1440 50% 2880 reload-into-ims
refresh_pattern -i gen=js 1440 50% 2880 reload-into-ims
refresh_pattern . 0 0% 0
===
Do you still see something wrong with this squid version or anything
to do with its config file that we can tweak to see ?
-PK
On Mon, May 13, 2013 at 6:10 AM, Amos Jeffries <squid3_at_treenet.co.nz> wrote:
> On 12/05/2013 7:04 p.m., paramkrish wrote:
>>
>> Additional info:
>>
>> Squid Cache: Version 3.2.3
>> configure options: '--prefix=/usr/local/squid' '--enable-ssl'
>> '--enable-removal-policies=lru heap' '--enable-ltdl-convenience'
>>
>> squid.conf :
>>
>> cache_mgr enghelp_at_domain.com
>> cache_effective_user squid
>> cache_effective_group squid
>>
>> visible_hostname wikid-dev.domain.com
>>
>> http_port 80 accel defaultsite=wikid-dev.domain.com vhost
>>
>> cache_peer 10.56.102.92 parent 443 0 login=PASS name=engwikiweb1dev
>> sourcehash ssl sslflags=DONT_VERIFY_PEER
>> cache_peer 10.56.102.93 parent 443 0 login=PASS name=engwikiweb2dev
>> sourcehash ssl sslflags=DONT_VERIFY_PEER
>>
>>
>> acl wikid-dev dstdomain wikid-dev.domain.com
>> cache_peer_access engwikiweb1dev allow wikid-dev
>> #cache_peer_access engwikiweb2dev allow wikid-dev
>> cache_peer_access engwikiweb1dev allow all
>> #cache_peer_access engwikiweb2dev allow all
>> never_direct allow wikid-dev
>>
>> acl LUCENE url_regex lucene
>> cache deny LUCENE
>>
>> http_access allow wikid-dev
>> http_access allow all
>>
>> cache_replacement_policy heap LRU
>> memory_replacement_policy heap LRU
>>
>> cache_dir ufs /wikiweb-dev/squid-cache/var/engwikilb1/cache 2048 16 64
>>
>> cache_swap_low 90
>> cache_swap_high 95
>>
>> cache_mem 1024 MB
>> maximum_object_size_in_memory 4096 KB
>> maximum_object_size 32768 KB
>>
>> logfile_rotate 3
>> forwarded_for truncate
>>
>> cache_store_log
>> /wikiweb-dev/squid-cache/var/engwikilb1/logs/cache_store.log
>> logformat squid %ts %06tr %>a %Ss/%03>Hs %<st %rm %ru %un %Sh/%<A %mt
>>
>> refresh_pattern -i \.css\?.*$ 1440 50% 2880 reload-into-ims
>> refresh_pattern -i \.js\?.*$ 1440 50% 2880 reload-into-ims
>> refresh_pattern -i \.css$ 1440 50% 2880 reload-into-ims
>> refresh_pattern -i \.js$ 1440 50% 2880 reload-into-ims
>> refresh_pattern (/skins/) 1440 50% 2880 reload-into-ims
>> refresh_pattern -i gen=css 1440 50% 2880 reload-into-ims
>> refresh_pattern -i gen=js 1440 50% 2880 reload-into-ims
>> refresh_pattern . 0 0% 0
>>
>>
>> I would like if there is anything wrong in my config that makes not to
>> cache
>> all the pages as i see only TCP_MISS statements in my access.log
>
>
> That . refresh_pattern is making Squid discard all content with incomplete
> or missing expiry and age information headers. It could be related to your
> problem.The default refresh_pattern we publish with Squid sets a 3 day
> caching period for those objects (max fields set to 4320 minutes).
>
> It could also be some weird caching bugs we had in the early 3.2 releases,
> your version is early enough to be an affected one. Upgrade to 3.3.4 will
> show whether that was the problem or not.
>
> Amos
Received on Mon May 13 2013 - 05:08:19 MDT
This archive was generated by hypermail 2.2.0 : Mon May 13 2013 - 12:00:05 MDT