Re: [squid-users] Compute digest as content is written to cache
2012/8/12 Amos Jeffries squ...@treenet.co.nz: On 11/08/2012 10:21 p.m., Jack Bates wrote: On 11/08/12 12:30 AM, Amos Jeffries wrote: On 11/08/2012 7:22 p.m., Jack Bates wrote: I am interested in intercepting content as it is written to the cache, and computing a digest from the content. Do you know if this can be done in some kind of add on, or would it require a change to the core? What type of digest and to what purpose? I was thinking of using OpenSSL SHA256_Init()/SHA256_Update()/SHA256_Final(). The purpose I have in mind is to detect identical content at different URLs Given a response with a Location: ... header and a Digest: SHA-256=... header (such as from MirrorBrain), if the URL in the Location: ... header is not already cached but the Digest: SHA-256=... header matches the content at some other URL that is already cached, then I want to update the Location: ... header with the cached URL. I think this should redirect clients to mirrors that are already cached Small problem there. The digest is not calculated/known until the object is finished arriving. By then it is too late to attach new headers. And way too late to decide whether to ask that source for it. Agree. Multiple different splashing headers with same content is really hard to store. Split headers/contents and store them respectively may works, and the headers should store as on-to-many mapping.
Re: [squid-users] Squid memory usage
2012/8/3 Hugo Deprez hugo.dep...@gmail.com: Dear community, I am running squid3 on Linux Debian squeeze.(3.1.6). I encounter a suddenly a high memory usage on my virtual machine don't really know why. Looking at the cacti memory graph is showing a memory jump from 1.5 Gb to 4GB and then ther server started to swap. For information the virtual machine has 4Gb of RAM. Here is the settings of squid.conf : cache_dir ufs /var/spool/squid3 100 16 256 cache_mem 100 MB Can you try tuning these options? memory_pools off memory_pools_limit 1 MB hierarchy_stoplist cgi-bin ? refresh_pattern ^ftp: 144020% 10080 refresh_pattern ^gopher:14400% 1440 refresh_pattern -i (/cgi-bin/|\?) 0 0% 0 refresh_pattern . 0 20% 4320 my squid3 process is using: 81% of my RAM. So arround 3,2Gb of memory. proxy25889 0.6 81.1 3937744 3299616 ? SAug02 9:34 (squid) -YC -f /etc/squid3/squid.conf I am currently having arround 50 users using it. I did have a look at the FAQ (http://wiki.squid-cache.org/SquidFaq/SquidMemory#how-much-ram), but I didn't find any tips for my situation in it. Have you got any idea ? How can I troubleshoot this ? Thanks ! -- 张绍文 gongfan...@gmail.com zhan...@gwbnsh.net.cn 18601633785
Re: [squid-users] squid load balancing
2011/9/20 nikko...@gmail.com nikko...@gmail.com: Hello, I would like to implement a proxy server in load balancing with 2 or more server proxy. It is possible to do this? What can I use? LVS? Ultramonkey? Other? keepalived uses LVS, very simple but strong implementation, PLUS CARP which give you more power.
Re: [squid-users] squid performance tunning
Median Service Times (seconds) 5 min 60 min: HTTP Requests (All): 0.00865 0.00865 Cache Misses: 0.01035 0.01035 Cache Hits: 0.0 0.0 Near Hits: 0.00091 0.00091 Not-Modified Replies: 0.0 0.0 DNS Lookups: 0.0 0.0 ICP Queries: 0.0 0.0 Response time is reasonable at this time, while, peak time capture is good for performance tunning. Try atop 1 at peak time, this magic tool can clear about bottleneck. Try multi-instance, which can improve throughput dramaticlly. Docs's here: http://wiki.squid-cache.org/MultipleInstances CARP is another choice for extreme perf demand. http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend
Re: [squid-users] squid performance tunning
2011/8/18 Chen Bangzhong bangzh...@gmail.com: My cached objects will expire after 10 minutes. Cache-Control:max-age=600 Static content like pictures should cache longer, like 1 day, 86400. I don't know why there are so many disk writes and there are so many objects on disk. In addtion, Disk hits as % of hit requests: 5min: 1.6%, 60min: 1.9% is very low. Maybe cause by disk read timeout. You used too much disk space, you can shrink it a little by a little, until disk busy percentage reduced to 80% or lower. Can I increase the cache_mem？ or not use disk cache at all? I used all memory I can use :-)
Re: [squid-users] squid performance tunning
2011/8/18 Amos Jeffries squ...@treenet.co.nz: On 18/08/11 19:40, Drunkard Zhang wrote: 2011/8/18 Chen Bangzhong: My cached objects will expire after 10 minutes. Cache-Control:max-age=600 Static content like pictures should cache longer, like 1 day, 86400. Could also be a whole year. If you control the origin website, set caching times as large as reasonably possible for each object. With revalidate settings relevant to its likely replacement needs. And always send a correct ETag. With those details Squid and other caches will take care of reducing caching times to suit the network and disk needs and updates/revalidation to suit your needs. So please set it large. I don't know why there are so many disk writes and there are so many objects on disk. All traffic goes through either RAM cache or if its bigger than maximum_object_size_in_memory will go through disks. From that info report ~60% of your traffic bytes are MISS responses. A large portion of that MISS traffic is likely not storable, so will be written to cache then discarded immediately. Squid is overall mostly-write with its disk behaviour. Likely your 10-minute age is affecting this in a big way. The cache will have a lot of storable object which are stale. Next request they will be fetched into memory, then replaced by a revalidation REFRESH (near-HIT) response, which writes new data back to disk later. In addtion, Disk hits as % of hit requests: 5min: 1.6%, 60min: 1.9% is very low. Maybe cause by disk read timeout. You used too much disk space, you can shrink it a little by a little, until disk busy percentage reduced to 80% or lower. Your Squid version is one which will promote HIT objects from disk and service repeat HITs from memory. Which reducing that disk-hit % a lot more than earlier squid versions would show it as. Can I increase the cache_mem？ or not use disk cache at all? I used all memory I can use :-) Indeed, the more the merrier. Unless it is swapping under high load. If that happens Squid speed goes terrible almost immediately. Actually I disabled swap at all, and use a script to start squid process immediately when killed by OS. OS will kill squid when OOM(Out of memory).
Re: [squid-users] Resize coss online
2011/1/12 Amos Jeffries squ...@treenet.co.nz: On 12/01/11 20:12, Drunkard Zhang wrote: I'm testing squid-2.7STABLE9 + COSS + ext4 + SSD now. When enlarge the coss, eg: from 10240 to 20480, I can see success in cache.log, but the coss file on disk did not change, after 3 times of squid -k reconfigure the coss file size changed. How long did you wait? it could be that Squid was doing a long resize in the background. This is a guess supported by the change actually happening. But some times later, the squid process exited, with nothing left in cache.log. Just once in cache.log I found: 2011/01/12 11:10:04| assertion failed: coss/store_io_coss.c:215: cs-curstripe (cs-numstripes - 1) So, I wondering if resize of coss online is supported perfectly, that we can use it without anxiety. BTW, is shrink of coss filesystem is supported? If it is, do I have to do it online, or offline? By online, I means operates without restart squid process, and the offline means opposite. I think you need to try offline change. Via a stop, squid -z and restart sequence. Thanks, maybe I'm too hurry. With squid-2.7STABLE9 + COSS + btrfs + SSD, reload can cause process to stuck, with 100% CPU usage per squid process. I caught these info in cache.log once: 2011/01/09 14:56:44| Killing RunCache, pid 59502 2011/01/09 14:56:44| kill 59502: (1) Operation not permitted And kill of the process will make the process into a zombie. The defunct process still using 100% CPU, which wasn't show in ps. squid75 ~ # ps -eo pid,%cpu,cmd --sort=c 59343 2.7 [squid]defunct 59505 2.8 [squid]defunct 59380 2.9 [squid]defunct 59474 2.9 [squid]defunct 42558 3.4 [btrfs-endio-1] 43717 3.7 (squid) -YC -D -f squid73.conf 43925 4.0 (squid) -YC -D -f squid74.conf 42520 4.3 (squid) -YC -D -f squid75.conf 51532 4.4 (squid) -YC -D -f squid77.conf 18014 5.9 (squid) -YC -D -f squid72.conf FWIW; I think you will very much want to play with the squid-3.2 RockStore code being written by The Measurement Factory guys. Contact Alex for ways to get a current working version. We did a test on squid-3.2, but using of 3.2 make no difference to what we are doing now. SMP acts very similar to our multi-instance mode... but still looking forward.
[squid-users] Resize coss online
I'm testing squid-2.7STABLE9 + COSS + ext4 + SSD now. When enlarge the coss, eg: from 10240 to 20480, I can see success in cache.log, but the coss file on disk did not change, after 3 times of squid -k reconfigure the coss file size changed. But some times later, the squid process exited, with nothing left in cache.log. Just once in cache.log I found: 2011/01/12 11:10:04| assertion failed: coss/store_io_coss.c:215: cs-curstripe (cs-numstripes - 1) So, I wondering if resize of coss online is supported perfectly, that we can use it without anxiety. BTW, is shrink of coss filesystem is supported? If it is, do I have to do it online, or offline? By online, I means operates without restart squid process, and the offline means opposite. With squid-2.7STABLE9 + COSS + btrfs + SSD, reload can cause process to stuck, with 100% CPU usage per squid process. I caught these info in cache.log once: 2011/01/09 14:56:44| Killing RunCache, pid 59502 2011/01/09 14:56:44| kill 59502: (1) Operation not permitted And kill of the process will make the process into a zombie. The defunct process still using 100% CPU, which wasn't show in ps. squid75 ~ # ps -eo pid,%cpu,cmd --sort=c 59343 2.7 [squid] defunct 59505 2.8 [squid] defunct 59380 2.9 [squid] defunct 59474 2.9 [squid] defunct 42558 3.4 [btrfs-endio-1] 43717 3.7 (squid) -YC -D -f squid73.conf 43925 4.0 (squid) -YC -D -f squid74.conf 42520 4.3 (squid) -YC -D -f squid75.conf 51532 4.4 (squid) -YC -D -f squid77.conf 18014 5.9 (squid) -YC -D -f squid72.conf 19465 7.9 (squid) -YC -D -f squid76.conf 59833 8.9 (squid) -YC -D -f squid79.conf 59803 9.4 (squid) -YC -D -f squid78.conf 59744 9.7 [squid] defunct 4511 10.8 (squid) -YC -D -f squid81.conf 4563 10.9 (squid) -YC -D -f squid85.conf 59705 12.0 [squid] defunct 4524 12.8 (squid) -YC -D -f squid82.conf 4550 12.9 (squid) -YC -D -f squid84.conf 4537 13.2 (squid) -YC -D -f squid83.conf 4498 29.9 (squid) -YC -D -f squid80.conf squid75 ~ # ps auwx | grep -e defunct -e COMMAND$ USER PID %CPU %MEMVSZ RSS TTY STAT START TIME COMMAND squid59343 2.8 0.0 0 0 ?Zl Jan07 83:47 [squid] defunct squid59380 3.0 0.0 0 0 ?ZNl Jan07 88:37 [squid] defunct squid59474 3.0 0.0 0 0 ?ZNl Jan07 89:57 [squid] defunct squid59505 2.9 0.0 0 0 ?ZNl Jan07 86:20 [squid] defunct squid59705 12.0 0.0 0 0 ?Zl Jan07 355:56 [squid] defunct squid59744 9.7 0.0 0 0 ?ZNl Jan07 288:11 [squid] defunct
Re: [squid-users] Performance Extremely squid configuration advice
2011/1/7 Amos Jeffries squ...@treenet.co.nz: On 07/01/11 19:08, Drunkard Zhang wrote: In order to get squid server 400M+ traffic, I did these: 1. Memory only IO bottleneck is too hard to avoid at high traffic, so I did not use harddisk, use only memory for HTTP cache. 32GB or 64GB memory per box works good. NP: The problem in squid-2 is large objects in memory. Though the more objects you have cached the slower the index lookups (very, very minor impact). With 6-8GB memory, there's about 320K objects per instance, so no significant delay would yield. 2. Disable useless acl I did not use any acl, even default acls: 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 Safe_ports port 901 # SWAT http_access deny !Safe_ports http_access deny CONNECT !SSL_ports squid itself do not do any acls, security is ensured by other layers, like iptables or acls on routers. Having the routers etc assemble the packets and parse the HTTP-layer protocol to find these details may be a larger bottleneck than testing for them inside Squid where the parsing has to be done a second time anyway to pass the request on. We only do http cache on tcp port 80, and the incoming source IPs is controllable, so iptables should be OK. Note that the default port and method ACL in Squid are validating on the HTTP header content URLs not the packet destination port. 3. refresh_pattern, mainly cache for pictures Make squid cache as long as it can, so it looks likes this: refresh_pattern -i \.(jpg|jpeg|gif|png|swf|htm|html|bmp)(\?.*)?$ 21600 100% 21600 reload-into-ims ignore-reload ignore-no-cache ignore-auth ignore-private 4. multi-instance I can't get single squid process runs over 200M, so multi-instance make perfect sense. Congratulations, most can't get Squid to go over 50MBps per instance. Both CARP frontend and backend (for store HTTP files) need to be multi-instanced. Frontend configuration is here: http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend I heard that squid is still can't process huge memory properly, so I splited big memory into 6-8GB per instance, which listens at ports lower than 80. And on a box with 32GB memory CARP frontend configs like this: cache_peer 192.168.1.73 parent 76 0 carp name=73-76 proxy-only cache_peer 192.168.1.73 parent 77 0 carp name=73-77 proxy-only cache_peer 192.168.1.73 parent 78 0 carp name=73-78 proxy-only cache_peer 192.168.1.73 parent 79 0 carp name=73-79 proxy-only 5. CARP frontend - cache_mem 0 MB I used to use cache_mem 0 MB, time flies, I think that files smaller than 1.5KB would be waste if GET from CARP backend, am I right? I use these now: cache_mem 5 MB maximum_object_size_in_memory 1.5 KB The best value here differs on every network so we can't answer your question with details. Here's my idea: did 3 times of tcp hand shake, and transfered data in ONE packet is silly, so let it store locally. According to my observation, no more than 500 StoreEntries per CARP frontend. Log analysis of live traffic will show you the amount of objects your Squid are handling in each size bracket. That will determine where the best place to set this limit at to reduce the lag on small items versus your available cache_mem memory.
Re: [squid-users] Performance Extremely squid configuration advice
2011/1/8 Mohsen Saeedi mohsen.sae...@gmail.com: and now which filesystem has better performance. aufs or diskd? on the SAS hdd for example. Neither of them, we are using coss on SATA. And coss on SSD is under testing, looks good still. On Fri, Jan 7, 2011 at 7:56 PM, Drunkard Zhang gongfan...@gmail.com wrote: 2011/1/7 Amos Jeffries squ...@treenet.co.nz: On 07/01/11 19:08, Drunkard Zhang wrote: In order to get squid server 400M+ traffic, I did these: 1. Memory only IO bottleneck is too hard to avoid at high traffic, so I did not use harddisk, use only memory for HTTP cache. 32GB or 64GB memory per box works good. NP: The problem in squid-2 is large objects in memory. Though the more objects you have cached the slower the index lookups (very, very minor impact). With 6-8GB memory, there's about 320K objects per instance, so no significant delay would yield. 2. Disable useless acl I did not use any acl, even default acls: 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 Safe_ports port 901 # SWAT http_access deny !Safe_ports http_access deny CONNECT !SSL_ports squid itself do not do any acls, security is ensured by other layers, like iptables or acls on routers. Having the routers etc assemble the packets and parse the HTTP-layer protocol to find these details may be a larger bottleneck than testing for them inside Squid where the parsing has to be done a second time anyway to pass the request on. We only do http cache on tcp port 80, and the incoming source IPs is controllable, so iptables should be OK. Note that the default port and method ACL in Squid are validating on the HTTP header content URLs not the packet destination port. 3. refresh_pattern, mainly cache for pictures Make squid cache as long as it can, so it looks likes this: refresh_pattern -i \.(jpg|jpeg|gif|png|swf|htm|html|bmp)(\?.*)?$ 21600 100% 21600 reload-into-ims ignore-reload ignore-no-cache ignore-auth ignore-private 4. multi-instance I can't get single squid process runs over 200M, so multi-instance make perfect sense. Congratulations, most can't get Squid to go over 50MBps per instance. Both CARP frontend and backend (for store HTTP files) need to be multi-instanced. Frontend configuration is here: http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend I heard that squid is still can't process huge memory properly, so I splited big memory into 6-8GB per instance, which listens at ports lower than 80. And on a box with 32GB memory CARP frontend configs like this: cache_peer 192.168.1.73 parent 76 0 carp name=73-76 proxy-only cache_peer 192.168.1.73 parent 77 0 carp name=73-77 proxy-only cache_peer 192.168.1.73 parent 78 0 carp name=73-78 proxy-only cache_peer 192.168.1.73 parent 79 0 carp name=73-79 proxy-only 5. CARP frontend - cache_mem 0 MB I used to use cache_mem 0 MB, time flies, I think that files smaller than 1.5KB would be waste if GET from CARP backend, am I right? I use these now: cache_mem 5 MB maximum_object_size_in_memory 1.5 KB The best value here differs on every network so we can't answer your question with details. Here's my idea: did 3 times of tcp hand shake, and transfered data in ONE packet is silly, so let it store locally. According to my observation, no more than 500 StoreEntries per CARP frontend. Log analysis of live traffic will show you the amount of objects your Squid are handling in each size bracket. That will determine where the best place to set this limit at to reduce the lag on small items versus your available cache_mem memory.
Re: [squid-users] Performance Extremely squid configuration advice
2011/1/8 Mohsen Saeedi mohsen.sae...@gmail.com: I know about coss. it's great. but i have squid 3.1 and i think it's unstable in 3.x version. that's correct? I need null for memory-only cache, which is not provided in squid-3, so it's all squid-2.x in product environment. Of cource, we tested every squid-3.x, many bugs and poor performance to squid-2.x. We tested squid-2.HEAD too, it's worth to try. aufs acts very bad under high presure, with 8GB memory and least SATA aufs space per instance, it's still too hard to over 180Mbps. I haven't try diskd yet. On Fri, Jan 7, 2011 at 8:05 PM, Drunkard Zhang gongfan...@gmail.com wrote: 2011/1/8 Mohsen Saeedi mohsen.sae...@gmail.com: and now which filesystem has better performance. aufs or diskd? on the SAS hdd for example. Neither of them, we are using coss on SATA. And coss on SSD is under testing, looks good still. On Fri, Jan 7, 2011 at 7:56 PM, Drunkard Zhang gongfan...@gmail.com wrote: 2011/1/7 Amos Jeffries squ...@treenet.co.nz: On 07/01/11 19:08, Drunkard Zhang wrote: In order to get squid server 400M+ traffic, I did these: 1. Memory only IO bottleneck is too hard to avoid at high traffic, so I did not use harddisk, use only memory for HTTP cache. 32GB or 64GB memory per box works good. NP: The problem in squid-2 is large objects in memory. Though the more objects you have cached the slower the index lookups (very, very minor impact). With 6-8GB memory, there's about 320K objects per instance, so no significant delay would yield. 2. Disable useless acl I did not use any acl, even default acls: 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 Safe_ports port 901 # SWAT http_access deny !Safe_ports http_access deny CONNECT !SSL_ports squid itself do not do any acls, security is ensured by other layers, like iptables or acls on routers. Having the routers etc assemble the packets and parse the HTTP-layer protocol to find these details may be a larger bottleneck than testing for them inside Squid where the parsing has to be done a second time anyway to pass the request on. We only do http cache on tcp port 80, and the incoming source IPs is controllable, so iptables should be OK. Note that the default port and method ACL in Squid are validating on the HTTP header content URLs not the packet destination port. 3. refresh_pattern, mainly cache for pictures Make squid cache as long as it can, so it looks likes this: refresh_pattern -i \.(jpg|jpeg|gif|png|swf|htm|html|bmp)(\?.*)?$ 21600 100% 21600 reload-into-ims ignore-reload ignore-no-cache ignore-auth ignore-private 4. multi-instance I can't get single squid process runs over 200M, so multi-instance make perfect sense. Congratulations, most can't get Squid to go over 50MBps per instance. Both CARP frontend and backend (for store HTTP files) need to be multi-instanced. Frontend configuration is here: http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend I heard that squid is still can't process huge memory properly, so I splited big memory into 6-8GB per instance, which listens at ports lower than 80. And on a box with 32GB memory CARP frontend configs like this: cache_peer 192.168.1.73 parent 76 0 carp name=73-76 proxy-only cache_peer 192.168.1.73 parent 77 0 carp name=73-77 proxy-only cache_peer 192.168.1.73 parent 78 0 carp name=73-78 proxy-only cache_peer 192.168.1.73 parent 79 0 carp name=73-79 proxy-only 5. CARP frontend - cache_mem 0 MB I used to use cache_mem 0 MB, time flies, I think that files smaller than 1.5KB would be waste if GET from CARP backend, am I right? I use these now: cache_mem 5 MB maximum_object_size_in_memory 1.5 KB The best value here differs on every network so we can't answer your question with details. Here's my idea: did 3 times of tcp hand shake, and transfered data in ONE packet is silly, so let it store locally. According to my observation, no more than 500 StoreEntries per CARP frontend. Log analysis of live traffic will show you the amount of objects your Squid are handling in each size bracket. That will determine where the best place to set this limit at to reduce the lag on small items versus your available cache_mem memory. -- Seyyed Mohsen Saeedi سید محسن سعیدی -- 张绍文 gongfan...@gmail.com zhan...@gwbnsh.net.cn 18601633785
Re: [squid-users] Performance Extremely squid configuration advice
2011/1/8 Amos Jeffries squ...@treenet.co.nz: On 08/01/11 06:22, Drunkard Zhang wrote: 2011/1/8 Mohsen Saeedimohsen.sae...@gmail.com: I know about coss. it's great. but i have squid 3.1 and i think it's unstable in 3.x version. that's correct? I need null for memory-only cache, which is not provided in squid-3, so it's all squid-2.x in product environment. The memory cache has been made default in Squid-3. Removing all cache_dir entries moves squid-3 to the same operational state as squid-2 with a fake null directory. My fault :-). Thanks. Of cource, we tested every squid-3.x, many bugs and poor performance to squid-2.x. We tested squid-2.HEAD too, it's worth to try. Which 3.x? We just had reports that 3.1.10 is faster than 2.7.STABLE9 (in RPS). Prior to that it has been slower. If there are any bugs you are aware of that are not already reported or fixed in bugzilla please report. Also, please add your additional knowledge to the bugzilla entries to aid a faster fix. aufs acts very bad under high presure, with 8GB memory and least SATA aufs space per instance, it's still too hard to over 180Mbps. I haven't try diskd yet. Thanks for this.
[squid-users] Performance Extremely squid configuration advice
In order to get squid server 400M+ traffic, I did these: 1. Memory only IO bottleneck is too hard to avoid at high traffic, so I did not use harddisk, use only memory for HTTP cache. 32GB or 64GB memory per box works good. 2. Disable useless acl I did not use any acl, even default acls: 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 Safe_ports port 901 # SWAT http_access deny !Safe_ports http_access deny CONNECT !SSL_ports squid itself do not do any acls, security is ensured by other layers, like iptables or acls on routers. 3. refresh_pattern, mainly cache for pictures Make squid cache as long as it can, so it looks likes this: refresh_pattern -i \.(jpg|jpeg|gif|png|swf|htm|html|bmp)(\?.*)?$ 21600 100% 21600 reload-into-ims ignore-reload ignore-no-cache ignore-auth ignore-private 4. multi-instance I can't get single squid process runs over 200M, so multi-instance make perfect sense. Both CARP frontend and backend (for store HTTP files) need to be multi-instanced. Frontend configuration is here: http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend I heard that squid is still can't process huge memory properly, so I splited big memory into 6-8GB per instance, which listens at ports lower than 80. And on a box with 32GB memory CARP frontend configs like this: cache_peer 192.168.1.73 parent 76 0 carp name=73-76 proxy-only cache_peer 192.168.1.73 parent 77 0 carp name=73-77 proxy-only cache_peer 192.168.1.73 parent 78 0 carp name=73-78 proxy-only cache_peer 192.168.1.73 parent 79 0 carp name=73-79 proxy-only 5. CARP frontend - cache_mem 0 MB I used to use cache_mem 0 MB, time flies, I think that files smaller than 1.5KB would be waste if GET from CARP backend, am I right? I use these now: cache_mem 5 MB maximum_object_size_in_memory 1.5 KB 6. LAN, WAN seperates Again, to split load on NIC. Use LAN for clients and CARP interaction, WAN to fetch content from internet. 7. Using official NIC driver. Sometimes chip vender's official driver acts better behavior than builtin driver, so it's worth to try. 8. Based on gentoo Using gentoo, we can strip useless function as much as possible, make the cache system thinner, and faster. 9. Strip useless compile options and runtime options Proper CFLAGS and LDFLAGS are needed, here's one good doc: http://en.gentoo-wiki.com/wiki/Safe_Cflags ~ # squid -v Squid Cache: Version 2.7.STABLE9 configure options: '--prefix=/usr' '--build=x86_64-pc-linux-gnu' '--host=x86_64-pc-linux-gnu' '--mandir=/usr/share/man' '--infodir=/usr/share/info' '--datadir=/usr/share' '--sysconfdir=/etc' '--localstatedir=/var/lib' '--libdir=/usr/lib64' '--sysconfdir=/etc/squid' '--libexecdir=/usr/libexec/squid' '--localstatedir=/var' '--datadir=/usr/share/squid' '--disable-auth' '--disable-delay-pools' '--enable-removal-policies=lru,heap' '--enable-ident-lookups' '--enable-useragent-log' '--enable-cache-digests' '--enable-referer-log' '--enable-http-violations' '--with-pthreads' '--with-large-files' '--enable-wccpv2' '--enable-htcp' '--enable-carp' '--enable-icmp' '--enable-follow-x-forwarded-for' '--enable-x-accelerator-vary' '--enable-kill-parent-hack' '--enable-cachemgr-hostname=squid37' '--enable-err-languages=English' '--enable-default-err-language=English' '--with-maxfd=65535' '--without-libcap' '--disable-snmp' '--disable-ssl' '--enable-storeio=ufs,diskd,coss,aufs,null' '--enable-async-io' '--enable-linux-netfilter' '--disable-linux-tproxy' '--enable-epoll' 'build_alias=x86_64-pc-linux-gnu' 'host_alias=x86_64-pc-linux-gnu' 'CC=x86_64-pc-linux-gnu-gcc' 'CFLAGS=-march=barcelona -mtune=barcelona -O2 -pipe' 'LDFLAGS=-Wl,-O1 -Wl,--as-needed' 10. sysctl tune net.ipv4.ip_forward = 0 net.ipv4.conf.default.rp_filter = 1 net.ipv4.conf.default.accept_source_route = 0 kernel.sysrq = 0 kernel.core_uses_pid = 1 net.ipv4.tcp_syncookies = 1 net.ipv4.tcp_syn_retries = 3 net.ipv4.tcp_synack_retries = 3 net.ipv4.tcp_max_syn_backlog = 4096 net.core.netdev_max_backlog = 4096 net.ipv4.ip_local_port_range = 1024 65534 net.netfilter.nf_conntrack_max = 1048576 net.netfilter.nf_conntrack_tcp_timeout_established = 1000 net.ipv4.tcp_timestamps = 0 net.ipv4.tcp_sack = 0 net.ipv4.tcp_low_latency = 1 net.ipv4.tcp_fin_timeout = 15 net.ipv4.tcp_keepalive_intvl = 30 net.ipv4.tcp_keepalive_probes = 3 net.ipv4.tcp_keepalive_time = 1800 net.ipv4.tcp_max_orphans = 16384 net.ipv4.tcp_orphan_retries = 1 net.ipv4.ipfrag_high_thresh = 524288 net.ipv4.ipfrag_low_thresh = 262144 kernel.pid_max = 65535 vm.swappiness = 1 net.ipv4.tcp_mem = 6085248 8113664 12170496 net.ipv4.tcp_wmem = 4096 65536 8388608
[squid-users] Performance Extremely squid configuration advice
In order to get squid server 400M+ traffic, I did these: 1. Memory only IO bottleneck is too hard to avoid at high traffic, so I did not use harddisk, use only memory for HTTP cache. 32GB or 64GB memory per box works good. 2. Disable useless acl I did not use any acl, even default acls: 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 Safe_ports port 901 # SWAT http_access deny !Safe_ports http_access deny CONNECT !SSL_ports squid itself do not do any acls, security is ensured by other layers, like iptables or acls on routers. 3. refresh_pattern, mainly cache for pictures Make squid cache as long as it can, so it looks likes this: refresh_pattern -i \.(jpg|jpeg|gif|png|swf|htm|html|bmp)(\?.*)?$ 21600 100% 21600 reload-into-ims ignore-reload ignore-no-cache ignore-auth ignore-private 4. multi-instance I can't get single squid process runs over 200M, so multi-instance make perfect sense. Both CARP frontend and backend (for store HTTP files) need to be multi-instanced. Frontend configuration is here: http://wiki.squid-cache.org/ConfigExamples/ExtremeCarpFrontend I heard that squid is still can't process huge memory properly, so I splited big memory into 6-8GB per instance, which listens at ports lower than 80. And on a box with 32GB memory CARP frontend configs like this: cache_peer 192.168.1.73 parent 76 0 carp name=73-76 proxy-only cache_peer 192.168.1.73 parent 77 0 carp name=73-77 proxy-only cache_peer 192.168.1.73 parent 78 0 carp name=73-78 proxy-only cache_peer 192.168.1.73 parent 79 0 carp name=73-79 proxy-only 5. CARP frontend - cache_mem 0 MB I used to use cache_mem 0 MB, time flies, I think that files smaller than 1.5KB would be waste if GET from CARP backend, am I right? I use these now: cache_mem 5 MB maximum_object_size_in_memory 1.5 KB 6. LAN, WAN seperates Again, to split load on NIC. Use LAN for clients and CARP interaction, WAN to fetch content from internet. 7. Using official NIC driver. Sometimes chip vender's official driver acts better behavior than builtin driver, so it's worth to try. 8. Based on gentoo Using gentoo, we can strip useless function as much as possible, make the cache system thinner, and faster. 9. Strip useless compile options and runtime options Proper CFLAGS and LDFLAGS are needed, here's one good doc: http://en.gentoo-wiki.com/wiki/Safe_Cflags ~ # squid -v Squid Cache: Version 2.7.STABLE9 configure options: '--prefix=/usr' '--build=x86_64-pc-linux-gnu' '--host=x86_64-pc-linux-gnu' '--mandir=/usr/share/man' '--infodir=/usr/share/info' '--datadir=/usr/share' '--sysconfdir=/etc' '--localstatedir=/var/lib' '--libdir=/usr/lib64' '--sysconfdir=/etc/squid' '--libexecdir=/usr/libexec/squid' '--localstatedir=/var' '--datadir=/usr/share/squid' '--disable-auth' '--disable-delay-pools' '--enable-removal-policies=lru,heap' '--enable-ident-lookups' '--enable-useragent-log' '--enable-cache-digests' '--enable-referer-log' '--enable-http-violations' '--with-pthreads' '--with-large-files' '--enable-wccpv2' '--enable-htcp' '--enable-carp' '--enable-icmp' '--enable-follow-x-forwarded-for' '--enable-x-accelerator-vary' '--enable-kill-parent-hack' '--enable-cachemgr-hostname=squid37' '--enable-err-languages=English' '--enable-default-err-language=English' '--with-maxfd=65535' '--without-libcap' '--disable-snmp' '--disable-ssl' '--enable-storeio=ufs,diskd,coss,aufs,null' '--enable-async-io' '--enable-linux-netfilter' '--disable-linux-tproxy' '--enable-epoll' 'build_alias=x86_64-pc-linux-gnu' 'host_alias=x86_64-pc-linux-gnu' 'CC=x86_64-pc-linux-gnu-gcc' 'CFLAGS=-march=barcelona -mtune=barcelona -O2 -pipe' 'LDFLAGS=-Wl,-O1 -Wl,--as-needed' 10. sysctl tune net.ipv4.ip_forward = 0 net.ipv4.conf.default.rp_filter = 1 net.ipv4.conf.default.accept_source_route = 0 kernel.sysrq = 0 kernel.core_uses_pid = 1 net.ipv4.tcp_syncookies = 1 net.ipv4.tcp_syn_retries = 3 net.ipv4.tcp_synack_retries = 3 net.ipv4.tcp_max_syn_backlog = 4096 net.core.netdev_max_backlog = 4096 net.ipv4.ip_local_port_range = 1024 65534 net.netfilter.nf_conntrack_max = 1048576 net.netfilter.nf_conntrack_tcp_timeout_established = 1000 net.ipv4.tcp_timestamps = 0 net.ipv4.tcp_sack = 0 net.ipv4.tcp_low_latency = 1 net.ipv4.tcp_fin_timeout = 15 net.ipv4.tcp_keepalive_intvl = 30 net.ipv4.tcp_keepalive_probes = 3 net.ipv4.tcp_keepalive_time = 1800 net.ipv4.tcp_max_orphans = 16384 net.ipv4.tcp_orphan_retries = 1 net.ipv4.ipfrag_high_thresh = 524288 net.ipv4.ipfrag_low_thresh = 262144 kernel.pid_max = 65535 vm.swappiness = 1 net.ipv4.tcp_mem = 6085248 8113664 12170496 net.ipv4.tcp_wmem = 4096 65536 8388608
[squid-users] squid with coss can not write to SSD
My configuration: cache_dir coss /mnt/c/72 10240 max-size=524288 max-stripe-waste=32768 block-size=4096 maxfullbufs=10 cache_swap_log /mnt/s/%s /mnt/c/72 is a file on btrfs + SSD. The btrfs is created by: mkfs.btrfs /dev/sdb1 /dev/sdc1, so it will spanning across two SSDs. But squid did not write anything to disk, here's info in cache.log 2011/01/07 14:36:42| WARNING: failed to unpack meta data 2011/01/07 14:36:42| storeCossWriteMemBufDone: got failure (-6) 2011/01/07 14:36:42| FD 9, size=1048576 2011/01/07 14:36:42| WARNING: failed to unpack meta data Why? squid can't work with btrfs? or SSD? or my way using it?
Re: [squid-users] how much traffic can squid handle?
2010/8/12 Matus UHLAR - fantomas uh...@fantomas.sk: On Wed, Aug 11, 2010 at 1:09 AM, Drunkard Zhang gongfan...@gmail.com wrote: With same multi-squid-instance configuration, same Linux distro, and different hardware, AMD Opteron gets more balanced CPU usage, while on Intel Xeon just one CPU core running out, others still too idle, about 5%-15%. When that core runs out, simple TCP SYN check on service failed occasional. I'm still trying to get this problem resolved...:-( Now I'm trying linux-2.6.35 kernel :-). On 11.08.10 19:24, Jose Ildefonso Camargo Tolosa wrote: So, the only logical conclusion is: AMD rules! :) Actually, since there's different hardware, I can even thing of APIC problems on the intel machine... I‘m trying new kernel 2.6.35 since yesterday, it looks like CPU usage balanced better. Has anyone did the same thing? Or it's just my illusion of loving linux, :-( I read this: http://www.linuxfordevices.com/c/a/News/Linux-2635-and-early-days-of-Linux/ (I actually like AMD, but I have never faced this kind of problem with Xeon, or maybe I'm just not paying attention, will make a few test myself, and see how it ends). I like AMD too, but the hardware is way hard to obtain to Intel in China... Tragic!
Re: [squid-users] how much traffic can squid handle?
2010/8/11 Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com: Hi! On Tue, Aug 10, 2010 at 12:27 AM, Stand H hstan...@yahoo.com wrote: --- On Mon, 8/9/10, Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com wrote: From: Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com Subject: Re: [squid-users] how much traffic can squid handle? To: Drunkard Zhang gongfan...@gmail.com Cc: Stand H hstan...@yahoo.com, squid-users@squid-cache.org Date: Monday, August 9, 2010, 6:26 PM Hi! On Mon, Aug 9, 2010 at 8:18 PM, Drunkard Zhang gongfan...@gmail.com wrote: BTW, may bonding of multiple NICs helps on too many interrupts. Or maybe just a good NIC, or a GOOD NIC + bonding :) Can you recommend a good NIC? Most Intel have behaved really well with me. As for Broadcom: bad luck, I had to disable most of the hardware assistance, and thus: add more load to the server, I'm currently on a avoid Broadcom policy, but that could change in the future (I'll try them again sometime). I got bottle on forcedeth shipped with nVidia MCP55 chipset, not got problem on Intel e1000e yet, but CPU usage on Intel cores balanced badly. On the other hand CPU time usage on AMD Opteron cores balanced very good with same configuration, so confuse about this.
Re: [squid-users] how much traffic can squid handle?
2010/8/11 Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com: On Tue, Aug 10, 2010 at 10:19 PM, Drunkard Zhang gongfan...@gmail.com wrote: 2010/8/11 Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com: Hi! On Tue, Aug 10, 2010 at 12:27 AM, Stand H hstan...@yahoo.com wrote: --- On Mon, 8/9/10, Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com wrote: From: Jose Ildefonso Camargo Tolosa ildefonso.cama...@gmail.com Subject: Re: [squid-users] how much traffic can squid handle? To: Drunkard Zhang gongfan...@gmail.com Cc: Stand H hstan...@yahoo.com, squid-users@squid-cache.org Date: Monday, August 9, 2010, 6:26 PM Hi! On Mon, Aug 9, 2010 at 8:18 PM, Drunkard Zhang gongfan...@gmail.com wrote: BTW, may bonding of multiple NICs helps on too many interrupts. Or maybe just a good NIC, or a GOOD NIC + bonding :) Can you recommend a good NIC? Most Intel have behaved really well with me. As for Broadcom: bad luck, I had to disable most of the hardware assistance, and thus: add more load to the server, I'm currently on a avoid Broadcom policy, but that could change in the future (I'll try them again sometime). I got bottle on forcedeth shipped with nVidia MCP55 chipset, not got problem on Intel e1000e yet, but CPU usage on Intel cores balanced badly. On the other hand CPU time usage on AMD Opteron cores balanced very good with same configuration, so confuse about this. Yeah, e1000 have worked very well for me. Ok, so, you saw that CPU usage on Intel tends to be inclined to one of the cores? and on AMD it gets more balanced? Also, are talking about network related load here? or just about any processes running on Intel multi-core and AMD multicore. With same multi-squid-instance configuration, same Linux distro, and different hardware, AMD Opteron gets more balanced CPU usage, while on Intel Xeon just one CPU core running out, others still too idle, about 5%-15%. When that core runs out, simple TCP SYN check on service failed occasional. I'm still trying to get this problem resolved...:-( Now I'm trying linux-2.6.35 kernel :-).
Re: [squid-users] how much traffic can squid handle?
2010/8/9 Stand H hstan...@yahoo.com: Hi all, If configured properly, how much traffic can a server with 16GB RAM, 3.0Ghz CPU, and 5 x 500GB SAS drive can handle? Anyone has a squid box that can handle more than 300Mbps traffic? From my experience and configuration, it can handle around 80Mbps only. Thank you. Stand With multi-instances of squid, I'm running a couple of servers handle 300-400Mbps traffic. We use memory only, 32GB.
Re: [squid-users] how much traffic can squid handle?
2010/8/9 Stand H hstan...@yahoo.com: If configured properly, how much traffic can a server with 16GB RAM, 3.0Ghz CPU, and 5 x 500GB SAS drive can handle? Anyone has a squid box that can handle more than 300Mbps traffic? From my experience and configuration, it can handle around 80Mbps only. Thank you. Stand With multi-instances of squid, I'm running a couple of servers handle 300-400Mbps traffic. We use memory only, 32GB. Do you mean multiple instances on a single physical server with 32GB memory? What type of disk and how many you have? Thanks, We don't use any disk for cache, just cache_dir null /tmp, the following option controls how much memory squid uses: memory_pools off memory_pools_limit 1 MB cache_mem 6500 MB maximum_object_size_in_memory 4096 KB memory_replacement_policy heap LFUDA In this case, CPU is not bottleneck generally, I THINK dual-channel memory and FSB speed is much more important. NIC(network card) could be bottleneck too, at least we encountered, too many interrupt from NIC limited the traffic no more than 550Mbps. I have not touch that line in production enviroment, but it is possible. BTW, may bonding of multiple NICs helps on too many interrupts.
Re: [squid-users] How much ram
2010/7/28 Marcello Romani mrom...@ottotecnica.com: Tóth Tibor Péter ha scritto: It was just a curiosity. I am interested what other people use in their cache server as far as ram goes. :) That's all. -Original Message- From: Marcello Romani [mailto:mrom...@ottotecnica.com] Sent: Wednesday, July 28, 2010 11:48 AM To: squid-users@squid-cache.org Cc: Tóth Tibor Péter Subject: Re: [squid-users] How much ram Tóth Tibor Péter ha scritto: Hi Guys! How much ram do you have in your squids? We have 8GB, and it's all being used. Proc usage is low, but ram seems to be never enough. Just interested. Tibby What OS are you using ? Under Linux, using top it's easy to see that all the memory that's not allocated to processes is used by the OS as disk cache and buffers. Their sisze is automatically managed by the kernel and given enough time will fill up the entire ram however big. After all, you don't want to pay for precious ram just to have it unused, right ? I was just responding to ram seems to be never enough, and perhaps I should've put a :-) after the question mark. Agree, my servers got 16GB, 24GB, 32GB to 64GB ram, seems hit ratio increased tiny...
Re: [squid-users] SQUID3: Access denied connecting to one site
2010/4/20 Alexandr Dmitriev alexandr.dmitr...@mos.lv: Hello, I have ubuntu 9.10 runing with squid 3.0.STABLE18-1 and squidGuard. Squid is set up as a transparent proxy - everything is working just fine, except I can't access one site (www.airbaltic.lv). Squid drops me an error - Access denied. Try this: echo 0 /proc/sys/net/ipv4/tcp_ecn I tried to disable squidGuard - it did not help, but when I connect without squid (disabling transparent access) - I can visit airbaltic.lv Here are records from access.log: 1271761294.299 5 192.168.1.64 TCP_MISS/403 2834 GET http://www.airbaltic.lv/ - DIRECT/87.110.220.160 text/html 1271761305.202 0 192.168.1.64 TCP_NEGATIVE_HIT/403 2842 GET http://www.airbaltic.lv/ - NONE/- text/html And here is my squid.conf: 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 192.168.1.0/24 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 localhost http_access allow localnet http_access deny all icp_access deny all htcp_access deny all http_port 3128 transparent hierarchy_stoplist cgi-bin ? access_log /var/log/squid3/access.log squid refresh_pattern ^ftp: 1440 20% 10080 refresh_pattern ^gopher: 1440 0% 1440 refresh_pattern (cgi-bin|\?) 0 0% 0 refresh_pattern . 0 20% 4320 coredump_dir /var/spool/squid3 redirect_program /usr/bin/squidGuard -c /etc/squid/squidGuard.conf Any ideas? Best regards, -- Alexandr Dmitrijev Head of IT Department Fashion Retail Ltd. Phone: +371 67560501 Fax: +371 67560502 GSM: +371 2771 E-mail: alexandr.dmitr...@mos.lv
[squid-users] Is this REAL squid-CARP cluster?
I'm using a squid cluster with CARP configured, they works great. I'm not sure if all the CARP frontend distributed URLs based on the _same_ hash value, here's result queried by squidclient: 16:00:25 ~ $ for i in 66 67 68 71; do ask_squid $i carp | grep -A7 Hostname; done Hostname Hash Multiplier Factor Actual 150.164.100.65 d6945438 1.00 0.142857 0.459355 150.164.100.69 89857dc5 1.00 0.142857 0.212488 150.164.100.70 239c90ac 1.00 0.142857 0.161517 150.164.100.72 7d152572 1.00 0.142857 0.153253 150.164.100.72 7d152572 1.00 0.142857 0.004496 150.164.100.72 7d152572 1.00 0.142857 0.004460 150.164.100.72 7d152572 1.00 0.142857 0.004431 Hostname Hash Multiplier Factor Actual 150.164.100.65 d6945438 1.00 0.142857 0.348483 150.164.100.69 89857dc5 1.00 0.142857 0.272565 150.164.100.70 239c90ac 1.00 0.142857 0.184725 150.164.100.72 7d152572 1.00 0.142857 0.151390 150.164.100.72 7d152572 1.00 0.142857 0.014509 150.164.100.72 7d152572 1.00 0.142857 0.014176 150.164.100.72 7d152572 1.00 0.142857 0.014151 Hostname Hash Multiplier Factor Actual 150.164.100.65 d6945438 1.00 0.142857 0.309244 150.164.100.69 89857dc5 1.00 0.142857 0.257143 150.164.100.70 239c90ac 1.00 0.142857 0.206424 150.164.100.72 7d152572 1.00 0.142857 0.209645 150.164.100.72 7d152572 1.00 0.142857 0.005738 150.164.100.72 7d152572 1.00 0.142857 0.005962 150.164.100.72 7d152572 1.00 0.142857 0.005844 Hostname Hash Multiplier Factor Actual 150.164.100.65 d6945438 1.00 0.142857 0.300572 150.164.100.69 89857dc5 1.00 0.142857 0.266725 150.164.100.70 239c90ac 1.00 0.142857 0.203087 150.164.100.72 7d152572 1.00 0.142857 0.214236 150.164.100.72 7d152572 1.00 0.142857 0.005091 150.164.100.72 7d152572 1.00 0.142857 0.005338 150.164.100.72 7d152572 1.00 0.142857 0.004951 ps: the last one: 150.164.100.72 has 64GB memory, so I setup 4 squid processes which listening on 80 81 82 83 ports. If the column Hash identified hashed URLs chuck, is it good; if not, how can I make several CARP-frontend distribute the SAME hashed URL chunk to one squid box; I'm using squid-2.6 and squid-2.7. -- gongfan...@gmail.com zhan...@gwbnsh.net.cn 18601633785
Re: [squid-users] Is this REAL squid-CARP cluster?
2010/4/14 Amos Jeffries squ...@treenet.co.nz: On Tue, 13 Apr 2010 22:10:38 +0800, Drunkard Zhang gongfan...@gmail.com wrote: I'm using a squid cluster with CARP configured, they works great. I'm not sure if all the CARP frontend distributed URLs based on the _same_ hash value, here's result queried by squidclient: Bug http://bugs.squid-cache.org/show_bug.cgi?id=2153 already fixed. Thanks! Despite this, am I configured CARP right? I'm not very sure about this. -- gongfan...@gmail.com zhan...@gwbnsh.net.cn 18601633785
