Re: incomplete loads

At 01:56 22.10.99 +0200, Henrik Nordstrom wrote:
>Tilman Schmidt wrote:
>
>> and I am rather frequently seeing files being incompletely loaded - ie. HTML
>> pages breaking of in mid-text or images showing only the top part.
[...]
>It would be interesting to see the store.log entries for these requests.

I had store.log deactivated but I have since activated it and here is a
new example (a JPEG image this time):

access.log

940604339.776 8767 HeartOfGold.sema.de TCP_MISS/000 19164 GET http://www.sommerfeldt.com/screen.jpg - FIRST_PARENT_MISS/www-cache.xlink.net -
940604351.801 90 HeartOfGold.sema.de TCP_IMS_HIT/304 196 GET http://www.sommerfeldt.com/screen.jpg - NONE/- image/jpeg
940604372.938 11753 HeartOfGold.sema.de TCP_MISS/200 30465 GET http://www.sommerfeldt.com/screen.jpg - TIMEOUT_FIRST_PARENT_MISS/www-cache.xlink.net image/jpeg

store.log

940604339.934 SWAPOUT 00009085 200 940604332 934832385 -1 image/jpeg 20550/20550 GET http://www.sommerfeldt.com/screen.jpg
940604351.801 RELEASE FFFFFFFF 304 940604332 934832385 -1 image/jpeg -1/0 GET http://www.sommerfeldt.com/screen.jpg
940604372.938 SWAPOUT 00009086 200 940603980 939763524 -1 image/jpeg 30111/30111 GET http://www.sommerfeldt.com/screen.jpg

cache.log

1999/10/22 16:29:58| Detected DEAD Parent: www-cache.xlink.net/3128/3130
1999/10/22 16:29:58| Detected REVIVED Parent: www-cache.xlink.net/3128/3130
1999/10/22 16:34:59| Detected DEAD Parent: www-cache.xlink.net/3128/3130
1999/10/22 16:34:59| Detected REVIVED Parent: www-cache.xlink.net/3128/3130
1999/10/22 16:56:25| Detected DEAD Parent: www-cache.xlink.net/3128/3130
1999/10/22 16:56:25| Detected REVIVED Parent: www-cache.xlink.net/3128/3130

>Your parent seems to have servere performance problems. It is not
>answering ICP queries in a timely manner and also sporadically refusing
>TCP connections on the proxy port.

I see. It is our ISP's cache and I am not obliged to use it. Would I
perhaps be better off just running without a parent? I think I'll
comment out the cache_peer entry for a while and see if that has any
influence on the problem.

-- 
Tilman Schmidt          E-Mail: Tilman.Schmidt@sema.de (office)
Sema Group Koeln, Germany       tilman@schmidt.bn.uunet.de (private)