Re: [squid-users] Squid high bandwidth IO issue (ramdisk SSD)

From: smaugadi <adi_at_binat.net.il>
Date: Sun, 2 Aug 2009 00:26:20 -0700 (PDT)

Dear Adrian,
During the implementation we encountered issues with all kind of variables
such as:
Limit of file descriptors (now the squid is using 204800).
TCP port range was low (increased to 1024 65535) TCP timers (changed them)
The ip_conntrack and hash size were low (now 524288 262144 respectively)

Now we are at a point that IO is the only issue.

Adi

Adrian Chadd-3 wrote:
>
> Have you actually done any system profiling to get an understanding of
> what wall(s) you're hitting?
>
> For example, is there perhaps some strange issue you're hitting with
> the disk controller?
>
> I'm pushing around 100-150mbit at peak through one server right now
> but I've not yet finished deploying COSS. But then, I'm hitting other
> issues with TCP stack tuning and CPU use.
>
>
>
> Adrian
>
> 2009/8/2 smaugadi <adi_at_binat.net.il>:
>>
>> Dear ALL,
>> We have a squid server with high volume of traffic, 200 – 300 MB.
>> The server is in transparent mode and using 18GB of ramdisk. With this
>> configuration performance is very good (after optimizing the squid and
>> the
>> linux machine).
>> The problem is the small size of cache directory.
>> Since IO is a big issue with squid we purchased the intel ssd x25-m 160gb
>> with hope that a flash drive will overcome the IO problems.
>> Unfortunately we failed. After adding the SSD disk and configuring squid
>> to
>> use another cache directory we encountered high IO that led to
>> performance
>> degradation.
>>
>> We have tried using AUFS and even downgrading to version 2.6 and using
>> COSS
>> with no success.
>> Does any one have an idea how to overcome the IO problems?
>> Do you have a suggestion to configuring squid in a big enterprise with
>> big
>> traffic volume?
>>
>> We have searched the WEB and used as reference links such as:
>> http://www.freeproxies.org/blog/2007/10/03/squid-cache-disk-io-performance-enhancements/
>> http://blog.last.fm/2007/08/30/squid-optimization-guide
>>
>> Platform: x3455 – 2 x dual core opteron 2.5Ghz
>> OS Memory: 32GB (24GB to ramdisk)
>> OS: Linux RHEL 5.0
>>
>> Squid configuration:
>>
>> acl manager proto cache_object
>> acl localhost src 127.0.0.1/32
>> acl to_localhost dst 127.0.0.0/8
>> acl localnet src 10.0.0.0/8     # RFC1918 possible internal network
>> acl localnet src 172.16.0.0/12  # RFC1918 possible internal network
>> acl localnet src 192.168.0.0/16 # RFC1918 possible internal network
>> acl ib src XXXXXXXXXXXXXX
>> acl mgt src XXXXXXXXXXXXX
>> acl SSL_ports port 443
>> acl Safe_ports port 80          # http
>> acl Safe_ports port 21          # ftp
>> acl Safe_ports port 443         # https
>> acl Safe_ports port 70          # gopher
>> acl Safe_ports port 210         # wais
>> acl Safe_ports port 1025-65535  # unregistered ports
>> acl Safe_ports port 280         # http-mgmt
>> acl Safe_ports port 488         # gss-http
>> acl Safe_ports port 591         # filemaker
>> acl Safe_ports port 777         # multiling http
>> acl CONNECT method CONNECT
>> http_access allow manager localhost
>> http_access deny manager
>> http_access deny !Safe_ports
>> http_access deny CONNECT !SSL_ports
>> http_access allow ib
>> icp_access allow localnet
>> icp_access deny all
>> htcp_access allow localnet
>> htcp_access allow all
>> http_port 3128 transparent
>> hierarchy_stoplist cgi-bin ?
>> cache_mem 100 MB
>> maximum_object_size_in_memory 34 KB
>> cache_replacement_policy heap LFUDA
>> cache_dir ufs /tmp/ramdiskt 18000 16 256
>> maximum_object_size 8 MB
>> cache_swap_low 90
>> cache_swap_high 95
>> access_log none
>> cache_store_log none
>> refresh_pattern ^ftp:           1440    20%     10080
>> refresh_pattern ^gopher:        1440    0%      1440
>> refresh_pattern (cgi-bin|\?)    0       0%      0
>> refresh_pattern .               0       20%     4320
>> half_closed_clients off
>> shutdown_lifetime 10 seconds
>> snmp_access allow ibsnmp mgt
>> snmp_access allow ibsnmp
>> snmp_access deny all
>> snmp_incoming_address 0.0.0.0
>> snmp_outgoing_address 255.255.255.255
>> icp_port 0
>> log_icp_queries off
>> dns_nameservers XXXXXXXX
>> hosts_file /etc/hosts
>> client_db off
>> coredump_dir /var/spool/squid
>> pipeline_prefetch on
>>
>> Regards.
>> --
>> View this message in context:
>> http://www.nabble.com/Squid-high-bandwidth-IO-issue-%28ramdisk-SSD%29-tp24775448p24775448.html
>> Sent from the Squid - Users mailing list archive at Nabble.com.
>>
>>
>
>

-- 
View this message in context: http://www.nabble.com/Squid-high-bandwidth-IO-issue-%28ramdisk-SSD%29-tp24775448p24775522.html
Sent from the Squid - Users mailing list archive at Nabble.com.
Received on Sun Aug 02 2009 - 07:26:22 MDT

This archive was generated by hypermail 2.2.0 : Sun Aug 02 2009 - 12:00:02 MDT