On 11-Aug-07 My Secret NSA Wiretap Overheard Adrian Chadd Saying : > On Sat, Aug 11, 2007, Michel Santos wrote: > >> I must admit I can't talk in there because I never could test it really >> but I do not convinve myself easy by reading papers. > > Good! Thats why you take the papers and try to duplicate/build from them > to convince yourself. Google for "UCFS web cache", should bring out one > of the papers in question. 2 to 3 times the small object performance is > what people are seeing in COSS under certain circumstances as it eliminates > the multiple seeks required in the worst cases for "normal" UNIX filesystems. > It also reduces write overhead and fragmentation issues by writing in > larger chunks. Issuing a 512 byte write vs a 16k write to the same sector > of disk is pretty much an equivalent operation in terms of time taken. > > The stuff to do, basically, involves: > > * planning out better object memory cache management; > * sorting out a smarter method of writing stuff to disk - ie, exploit > locality; > * don't write everything cachable to disk! only write stuff that has > a good chance of being read again; > * do your IO ops in larger chunks than 512 bytes - I think the sweet > spot from my own semi-scientific tests is ~64k but what I needed to > do is try to detect the physical geometry of the disk and make sure > my write sizes match physical sector sizes (ie, so my X kbyte writes > aren't kicking off a seek to an adjacent sector, and another rotation > to reposition the head where it needs to be.) > * handle larger objects / partial object replies better > > I think I've said most/all of that before. We've identified what needs > doing - what we lack is people to do it and/or to fund it. In fact, > I'd be happy to do all the work as long as I had money available once > it was done (so I'm not paid for the "hope" that the work is done.) > Trouble is, we're coders, not sales/marketing people, and sometimes > I think thats sorely what the Squid project needs to get itself back > into the full swing of things. > > > > Adrian Hi Adrian, I think we live in a McDonalds world. We walk up, look at what we want, see the price and decide what we can buy. Perhaps what would help projects in open source projects like squid would be a web page of such items that need work, who could work on them and possible prices/donations whatever would aid in them. It may be, that just saying, we know what needs to be done, needs to be matched better with those who could do it, and some projected costs. Thus make it a bit more like shopping. Also, I have seen some FreeBSD developers advertise on lists. "Hi i'm between jobs and Blah needs work on BSD. I think if I worked full time on it I could have it running better/fixed etc in X months. If I can raise Y dollars to support myself durring that time, that is what I will do." And money has flowed in. Obviously for those who have a known track record of work to do things much desired. I can bet, if someone said/advertised. I can fix diskD (up) or I can make Coss really kick ass in 2 months, (pick your need/ability) if I can raise X money. You would likely be able to raise it. You would just have to find a way to do so honestly and spread the need across various donations. But putting a price to a product would likely greatly help. It has been found that people are more likely to donate money for something specific than for a general cause. Just a thought. Nicole
