[PROXYPER] LIFO/FIFO Buffers (was Proxyper 300+ a lemon?7
j-zbiciak1 at ti.com
Mon Feb 22 08:41:31 EST 1999
'Karl Tremain' said previously:
| I have observed my buffer, and i am now convinced that the perproxy buffers
| are lifo.
I believe they are FIFO, with some caveats, as mentioned below.
| The evidence that i have to support this is the fact that when i am on the
| internet for a while, the PP uploads my blocks the moment they are
| completed, and therefore downloads more blocks to refill its in buffer,
| usually only getting iter 1 or 2 blocks.
I seem to recall someone mentioning that proxies prefer to hand out
partial blocks (smaller than 16*2^28) before handing out complete
blocks, so as to keep these smaller blocks from clogging the proxy.
What this implies is that the buffers are FIFO _within a given block
size_, which, over very short periods of time, could appear to behave
like a LIFO, if the blocks that are fetched are smaller than the ones
that are currently present in the proxy's buffers.
Does anyone _in the know_ care to substantiate/refute/elaborate?
--- Joseph Zbiciak ---- #include <std_disc.h> ---- j-zbiciak1 at ti.com ---
"It's only fun until someone loses an eye. Then you have to send that --
person home before you can start having fun again." -- John Hubner --
To unsubscribe, send 'unsubscribe proxyper' to majordomo at lists.distributed.net
More information about the proxyper