[squid-users] Vary object loop returns

Yuri Voinov yvoinov at gmail.com
Tue Jun 7 11:59:42 UTC 2016

Hash: SHA256
I want to give one example on the topic.

Here is from one of my cache:

/data/cache/d2/00/02/000004C3   0   102502
/data/cache/d2/00/01/0000031D   0   161421
/data/cache/d1/00/2E/00005C04   0    33274

Just take a look on file sizes. This is only favicon. 100 kbytes for
favicon only! (on Microsoft I've seen 470 kbytes favicon once upon time).

When we take a look into access.log, we often see several URL's for favicon:


Good site, isn't it? Loading 100 kbytes every time every client surf any
site page.

When I was doing research, it became clear that, in most cases, these
same favicon were one and the same content. As an example, a client with
a smartphone like to download 100 kB - and this is only a small portion
of the page! - everytime?

100 kb of mobile data traffic in most countries of the world - decent money.

Yes, usually from the client browser cache.

What about the number of clients and the access point, which pays
terabytes non-peering traffic?

The same tricks I've seen with a user-agent. With Vary.

07.06.2016 16:36, Amos Jeffries пишет:
> On 7/06/2016 8:48 p.m., Yuri Voinov wrote:
>> 07.06.2016 4:57, Amos Jeffries пишет:
>>> On 7/06/2016 5:55 a.m., Yuri Voinov wrote:
>>>> So.
>>>> Squid DOES NOT and DON'T BE support gzip. The only way to do it - use
>>>> ecap + desupported ecap gzip adapter. Let's accept this. We can support
>>>> gzip. With restrictions. Ok.
>>>> any other compression - false. No. No way. Get out. and so on.
>>>>  identity - this is uncompressed type.
>>>> That's all, folks.
>>>> Finally. As Joe does, we can remain only gzip and identity in
>>>> Accept-Encoding and truncate all remaining.
>>> Locking the entire Internet to using your personal choice of gzip
>>> compression or none.
>>> gzip is the slowest and more resource hungry type of compression there
>>> is. deflate is actually faster for clients and just as widely supported.
>> Unfortunately, Amos, no one has written any other compression algorithms
>> support module. We have to eat what they give.
> Like I said deflate is widely available. Heiler's recent info shows that
> lzma is becomming more visible on the public web, which should help fix
> the one issue deflate has.
> And noone appears to be fixing the remaining issues in the Squid gzip
> eCAP module.
> There also seems to be a big push back from browser and some server
> vendors about compression in general. We had a fairly major fight in
> IETF to get HTTP/2 to contain data compression at all. It is still only
> in there as an optional extension that some are openly refusing to
> implement.
>>>> Without any problem. Moreover, this type of can be push to all brunches
>>>> of squid without any problem, because of this dramatically increases
>>>> byte HIT.
>>> Responding with a single object to all requests makes your HIT ratio
>>> 100% guaranteed. The clients wont like you though if all they ever see
>>> is the same cat picture.
>>> It sounds ridiculous when put that way, but that is what these patches
>>> are doing for a unknown number of those "gained" HITs. See my previous
>>> post about how none of these patches are changing the request the server
>>> gets.
>> But no one asked the question - why Squid in production installations
>> has such a low hit ratio
> Yes that has been asked, even investigated. The reason(s) are many
> complex details and small issues adding together to a big loss.
> They range from protocol things like Vary not being fine-grained enough
> (Key header being developed fixes that), through to client behaviour
> (Chrome sdch doubles the variant count - almost halving useful cache
> space), to server behaviour (Apache changing Vary header).
> What your testing of joes patches is showing is that the sdch effect
> Chrome has is probably way bigger than one would expect to be reasonable.
>> that raises the question of expediency of
>> application caching proxy. We do believe that this is a caching proxy?
>>> You are once again sweeping asside the critical requirement of content
>>> integrity to achieve high HIT ratio. Which is not something that I can
>>> accept into Squid as a default action.
>> I continue to believe that 20% is unacceptably low cache hit ratio,
>> given the very aggressive settings and the active use of Store ID. Which
>> brings us back to the idea of the feasibility of using the SQUID as a
> That kind of "unacceptable" statement simply cannot be made about cache
> HIT ratio. It is what it is. One cannot change the speed of light
> because it takes unacceptable long to travel through space.
> Two properly working caches in serial will have extremely different
> caching ratios. The one with most direct client connections trends
> towards 50-100% and the upstream one towards the servers will trend
> towards zero. The total cacheable ratio is unchanged, but each cache
> sees a different proportion of it and so shows different HIT ratios
> relative to their clients portion.
> Also, don't forget that browser cache disk space available are
> increasingly large as well. So their caches are growing in size and
> taking up a larger share of the total achievable HIT ratios in recent
> Amos
> _______________________________________________
> squid-users mailing list
> squid-users at lists.squid-cache.org
> http://lists.squid-cache.org/listinfo/squid-users

Version: GnuPG v2

-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0x613DEC46.asc
Type: application/pgp-keys
Size: 2437 bytes
Desc: not available
URL: <http://lists.squid-cache.org/pipermail/squid-users/attachments/20160607/a0a1ef66/attachment.key>

More information about the squid-users mailing list