Thanks Yongming �C our team in China will take a look at the blog. Our site is like yours- our images are tiny… maybe we should decrease the size?
-Steve Steve Lerner | Sr. Member of Technical Staff, Network Engineering | M 212 495 9212 | [email protected]<mailto:[email protected]> | Skype: steve.lerner [Description: logo] From: Yongming Zhao [mailto:[email protected]] Sent: Saturday, November 15, 2014 12:36 AM To: [email protected] Subject: Re: proxy.config.cache.ram_cache.size query from eBay there is a blog in Chinese by 仝渊, which may help you calculate the memory needed by ATS: https://blog.zymlinux.net/index.php/archives/1038 well, you have big storage, then you want to cache big files? if so, please increase the average size, that will help reduce the index memory. FYI - Yongming Zhao 赵永明 在 2014年11月15日，上午10:32，Lerner, Steve <[email protected]<mailto:[email protected]>> 写道： James, Makes perfect sense- thanks! In the mix of ye olde alchemy are there any favorite levers to pull for ATS that are known to impact overall RAM use? We won’t bother the list anymore about this after this question :) Thanks for the help! -Steve Steve Lerner | Sr. Member of Technical Staff, Network Engineering | M 212 495 9212 | [email protected]<mailto:[email protected]> | Skype: steve.lerner <image001.jpg> From: James Peach [mailto:[email protected]] Sent: Friday, November 14, 2014 7:07 PM To: [email protected]<mailto:[email protected]> Subject: Re: proxy.config.cache.ram_cache.size query from eBay On Nov 13, 2014, at 6:40 PM, Lerner, Steve <[email protected]<mailto:[email protected]>> wrote: Hi gang- Phil Sorber referred me to this list. We are setting up clusters of Apache Traffic Server to beef up the front end of our image services which are… large in terms of volume… to say the least. We hope to be the big users of ATS and be a strong reference customer- so any help with is appreciated! Our first test cluster consistes of 23 machines, ubuntu12.04, Intel(R) 2x Xeon(R) CPU E5-2670 v2 @ 2.50GHz, 128G ram, 95T disk Here is our query: We are setting records.config as: CONFIG proxy.config.cache.ram_cache.size INT 64G But we find that trafficserver ignores this limit and grows at the default rate of 1MB RAM / 1GB disk. proxy.config.cache.ram_cache.size just sets how much memory to use in the RAM cache, as YongMing points out, there's lots of other things in the system that will consume RAM. Unfortunately tuning the RAM usage seems to be a bit of a black art :-/ Example of a current process: traffic_line -r proxy.config.cache.ram_cache.size returns 68,719,476,736 Which is about 64GB- correct! But looking at the process: 86050 nobody 20 0 108g 102g 4912 S 54 81.3 1523:33 /ebay/local/trafficserver/bin/traffic_server -M --httpport 80:fd=7 So basically we’ve set the process to only consume 64GB but its consuming 108GB… Does anyone have any ideas on why this happens or a way to fix it? We want to have constrained RAM but tons of disk- we’d much rather have the cache serve from disk then start swapping RAM Thanks in advance, Steve Steve Lerner | Sr. Member of Technical Staff, Network Engineering | M 212 495 9212 | [email protected]<mailto:[email protected]> | Skype: steve.lerner <image001.jpg>
