[Dev] Feathercoin - P2Pool-Neoscrypt - Now Available

lizhi

My p2pool-neoscrypt work ! His status http://pool.ftc-c.com:19327/static/

You can mine testcoin in testnet.

minerd -o  http://pool.ftc-c.com:19327 -u ftcpool -p 12345 -a neoscrypt

feathercoind -testnet -daemon -debug -addnode=wb01.dtdns.net -addnode=271.253.100.231 -addnode=217.253.100.213

python run_p2pool.py --net feathercoin --testnet  --feathercoind-p2p-port 9336 --feathercoind-rpc-port 9337 ftcpool 6qXvFmctiX6pM1Bm5QPs8tEv7Th2R5HHKK

Wellenreiter

There is a problem that the wallet doesn’t accept the blocks found by the p2pool.

The current version on github has disabled a couple of sanity checks to get the communication between the miner and the pool working.

–debug option or the wallet shows in the log:

014-08-02 11:27:40 received block 379fff03f539c3d7276728de3335a65963ada29dc8bb1d153babbfb68210d7e3
2014-08-02 11:27:40 ERROR: CheckProofOfWork() : hash doesn’t match nBits
2014-08-02 11:27:40 ERROR: CheckBlock() : proof-of-work verification failed
2014-08-02 11:27:40 ERROR: ProcessBlock() : CheckBlock FAILED
2014-08-02 11:27:40 Warning: Local node 127.0.0.1:50510 misbehaving (delta: 50)!
2014-08-02 11:27:40 ThreadRPCServer method=submitblock
2014-08-02 11:27:40 ERROR: CheckProofOfWork() : hash doesn’t match nBits
2014-08-02 11:27:40 ERROR: CheckBlock() : proof-of-work verification failed
2014-08-02 11:27:40 ERROR: ProcessBlock() : CheckBlock FAILED

lizhi

Yes, same problem,why ?

2014-08-03 08:40:46 RETARGET: nActualTimespan = 65 after bounds
2014-08-03 08:40:46 RETARGET: nTargetTimespan = 60, nTargetTimespan/nActualTimespan = 0.9231
2014-08-03 08:40:46 GetNextWorkRequired RETARGET
2014-08-03 08:40:46 Before: 1e0fffff  00000fffff000000000000000000000000000000000000000000000000000000
2014-08-03 08:40:46 After:  1e0fffff  00000fffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
2014-08-03 08:40:46 ThreadRPCServer method=validateaddress
2014-08-03 08:40:46 RETARGET: nActualTimespan = 139 before bounds
2014-08-03 08:40:46 RETARGET: nActualTimespanShort = 218, nActualTimespanMedium = 139, nActualTimespanLong = 145, nActualTimeSpanAvg = 167, nActualTimespan (damped) = 86
2014-08-03 08:40:46 RETARGET: nActualTimespan = 65 after bounds
2014-08-03 08:40:46 RETARGET: nTargetTimespan = 60, nTargetTimespan/nActualTimespan = 0.9231
2014-08-03 08:40:46 GetNextWorkRequired RETARGET
2014-08-03 08:40:46 Before: 1e0fffff  00000fffff000000000000000000000000000000000000000000000000000000
2014-08-03 08:40:46 After:  1e0fffff  00000fffffffffffffffffffffffffffffffffffffffffffffffffffffffffff
2014-08-03 08:40:46 received: getheaders (37 bytes)
2014-08-03 08:40:46 getheaders 1607 to bde747cf86ad5513cab5e9f8ace55f8ce294e77429ad8522d063e1bf4350b8b2
2014-08-03 08:40:46 sending: headers (82 bytes)
2014-08-03 08:40:46 ThreadRPCServer method=submitblock
2014-08-03 08:40:46 ERROR: CheckProofOfWork() : hash doesn't match nBits
2014-08-03 08:40:46 ERROR: CheckBlock() : proof-of-work verification failed
2014-08-03 08:40:46 ERROR: ProcessBlock() : CheckBlock FAILED
2014-08-03 08:40:46 RETARGET: nActualTimespan = 139 before bounds
2014-08-03 08:40:46 RETARGET: nActualTimespanShort = 218, nActualTimespanMedium = 139, nActualTimespanLong = 145, nActualTimeSpanAvg = 167, nActualTimespan (damped) = 86

wrapper

Just some ideas to test.

Are some of the transaction validations scrypt specific? and need updating in the code.

Some of the p2pool settings are incorrect for the testnet, Lizhi, although you must have fixed that, to get it working at all.

these are the wrong ports for the testnet.

–feathercoind-p2p-port 9336 --feathercoind-rpc-port 9337

I also had problems because there are requirements to the p2pool - rpc password, its got to have numbers and letters, of which some have to be capital letters. I don’t know if “12345” works

ghostlander

Disable submitblock and let it use getblocktemplate to return block data. There is also getblockex, but it seems deprecated and unsupported now.

lizhi

Thank wrapper, I think I fixed the problem.

fix .feathercoin/feathercoin.conf

rpcuser=ftcpool
rpcpassword=6qXvFmctiX6pM1Bm5QPs8tEv7Th2R5HHKK
daemon=1
server=1
rpcport=19337
port=19336

start p2pool:

python run_p2pool.py --net feathercoin --testnet  --feathercoind-p2p-port 19336 --feathercoind-rpc-port 19337 ftcpool 6qXvFmctiX6pM1Bm5QPs8tEv7Th2R5HHKK

miner command:

minerd -o http://pool.ftc-c.com:19327 -u ftcpool -p 123 -a neoscrypt

lizhi

A new problem. It will not work in mining three minutes later.

after three minutes , Minerd.exe stop .

some error information in p2pool log:

2014-08-03 20:01:29.794448 > ---  ---
2014-08-03 20:01:29.794660 >   File "/usr/lib/python2.7/dist-packages/twisted/internet/defer.py", line 1039, in _inlineCallbacks
2014-08-03 20:01:29.794859 >     result = g.send(result)
2014-08-03 20:01:29.795101 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/web.py", line 189, in render_GET
2014-08-03 20:01:29.795300 >     res = yield self.func(*self.args)
2014-08-03 20:01:29.795506 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/web.py", line 194, in 
2014-08-03 20:01:29.795714 >     web_root.putChild('rate', WebInterface(lambda: p2pool_data.get_pool_attempts_per_second(node.tracker, node.best_share_var.value, decent_height())/(1-p2pool_data.get_average_stale_prop(node.tracker, node.best_share_var.value, decent_height()))))
2014-08-03 20:01:29.795933 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/data.py", line 547, in get_pool_attempts_per_second
2014-08-03 20:01:29.796147 >     assert dist >= 2
2014-08-03 20:01:29.796346 > exceptions.AssertionError: 
2014-08-03 20:01:37.216029 P2Pool: 0 shares in chain (0 verified/0 total) Peers: 0 (0 incoming)
2014-08-03 20:01:37.216498  Local: 1388H/s in last 10.0 minutes Local dead on arrival: ~0.3% (0-2%) Expected time to share: 48.2 minutes
2014-08-03 20:01:39.807271 > Error in DeferredResource handler:
2014-08-03 20:01:39.807743 > Traceback (most recent call last):
2014-08-03 20:01:39.808046 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/util/deferred_resource.py", line 24, in render
2014-08-03 20:01:39.808327 >     defer.maybeDeferred(resource.Resource.render, self, request).addCallbacks(finish, finish_error)
2014-08-03 20:01:39.808621 >   File "/usr/lib/python2.7/dist-packages/twisted/internet/defer.py", line 134, in maybeDeferred
2014-08-03 20:01:39.808927 >     result = f(*args, **kw)
2014-08-03 20:01:39.809153 >   File "/usr/lib/python2.7/dist-packages/twisted/web/resource.py", line 216, in render
2014-08-03 20:01:39.809357 >     return m(request)
2014-08-03 20:01:39.809557 >   File "/usr/lib/python2.7/dist-packages/twisted/internet/defer.py", line 1181, in unwindGenerator
2014-08-03 20:01:39.809813 >     return _inlineCallbacks(None, gen, Deferred())
2014-08-03 20:01:39.810029 > ---  ---
2014-08-03 20:01:39.810288 >   File "/usr/lib/python2.7/dist-packages/twisted/internet/defer.py", line 1039, in _inlineCallbacks
2014-08-03 20:01:39.810492 >     result = g.send(result)
2014-08-03 20:01:39.810693 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/web.py", line 189, in render_GET
2014-08-03 20:01:39.810938 >     res = yield self.func(*self.args)
2014-08-03 20:01:39.811144 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/web.py", line 194, in 
2014-08-03 20:01:39.811350 >     web_root.putChild('rate', WebInterface(lambda: p2pool_data.get_pool_attempts_per_second(node.tracker, node.best_share_var.value, decent_height())/(1-p2pool_data.get_average_stale_prop(node.tracker, node.best_share_var.value, decent_height()))))
2014-08-03 20:01:39.811594 >   File "/data/ftcc/p2pool-neoscrypt/p2pool/data.py", line 547, in get_pool_attempts_per_second
2014-08-03 20:01:39.811815 >     assert dist >= 2
2014-08-03 20:01:39.812024 > exceptions.AssertionError:

Wellenreiter

Lizhi, the errors regarding webroot.putchild are normal as long as no other p2pool node has a worker connected. It simply can’t determine the global pool hash rate.

To give an update on my tests:

neoscrypt module for p2pool installed in python with profile 0
used ghostlanders neoscrypt p2pool as basis and added the feathercoin infos in networks.py and bitcoin/networks.py
forced the pool to use getblocktemplate, as suggested by ghostlander
current log shows:

2014-08-05 19:06:05.383892 Worker mrKP5thmnTRxV2Em8x3d8pamPXWHtv2Ed submitted share with hash > target:
2014-08-05 19:06:05.384129 Hash: 67146109f860500455e07f9c06a298ec2bd85202c42c18bd0bd63bf0cb059a5e
2014-08-05 19:06:05.384219 Target: a6c64b37894160e5d022dbf97e6abc74931804560e2db29defa7c64b378941
implemented reversebyte to change from big endian to little endian for target.

this changes the target, but as the Pow_hash has 2 bytes more than the target, it is always bigger than the target.

I noticed, that Ghoslander has aa pcx p2pool running on his testnet, which is on neoscrypt, so I send him a message to ask what he has modified to get it running.

Wellenreiter

new commit on github, including reversebyte.py, which was missing.

Still not working

wrapper

Great work guys!

lizhi

oh, it not work :-

Wellenreiter

I spend half a day on the p2pool stuff again
no results
what I noticed is, that the p2pool neoscrypt module produces wrong results while the same code runs fine in the wallet, so it may be ‘just’ a problem of function calls and parameter transfer between python and C++.

also if I read it right, the Wallet code passes variables to the neoscrypt procedure, as in GetPowHash() in main.h, while the python passes pointer to structures??

Eample from wallet main.h:

/* Calculates block proof-of-work hash using either NeoScrypt or Scrypt */
uint256 GetPoWHash() const {
unsigned int profile = 0x0;
uint256 hash;

/* All blocks generated up to this time point are Scrypt only */
if((fTestNet && (nTime < nTestnetSwitchV2)) ||
(!fTestNet && (nTime < nSwitchV2))) {
profile = 0x3;
} else {
/* All these blocks must be v2+ with valid nHeight */
int nHeight = GetBlockHeight();
if(fTestNet) {
if(nHeight < nTestnetFork)
profile = 0x3;
} else {
if(nHeight < nForkFour)
profile = 0x3;
}
}

neoscrypt((unsigned char *) &nVersion, (unsigned char *) &hash, profile);

return hash;
}

Example from p2pool/work.py:

 
pow_hash = self.node.net.PARENT.POW_FUNC(bitcoin_data.block_header_type.pack(header))

Where header is a dict in python.

uncle_muddy

Wellen,

I’m at the same point as you now :(

I get everything looking like it’s running well but nothing is accepted by the wallet, I’ll keep pluggin away but I’m some what in the dark here as my coding skills are limited in this area :(

UM

Wellenreiter

The miner says ’ hash accepted’ , but in the p2pool log you will see entries like ‘worker xyz submitted share with hash > target’

lizhi

I spend half a day on the p2pool stuff again
no results
what I noticed is, that the p2pool neoscrypt module produces wrong results while the same code runs fine in the wallet, so it may be ‘just’ a problem of function calls and parameter transfer between python and C++.

also if I read it right, the Wallet code passes variables to the neoscrypt procedure, as in GetPowHash() in main.h, while the python passes pointer to structures??

Eample from wallet main.h:
/* Calculates block proof-of-work hash using either NeoScrypt or Scrypt */
uint256 GetPoWHash() const {
unsigned int profile = 0x0;
uint256 hash;

/* All blocks generated up to this time point are Scrypt only */
if((fTestNet && (nTime < nTestnetSwitchV2)) ||
(!fTestNet && (nTime < nSwitchV2))) {
profile = 0x3;
} else {
/* All these blocks must be v2+ with valid nHeight */
int nHeight = GetBlockHeight();
if(fTestNet) {
if(nHeight < nTestnetFork)
profile = 0x3;
} else {
if(nHeight < nForkFour)
profile = 0x3;
}
}

neoscrypt((unsigned char *) &nVersion, (unsigned char *) &hash, profile);

return hash;
} 
Example from p2pool/work.py:
 
pow_hash = self.node.net.PARENT.POW_FUNC(bitcoin_data.block_header_type.pack(header))
Where header is a dict in python.

I think it is in main.py.

if share.pow_hash

Wellenreiter

For testing I temporarily modified the neoscrypt.c of the p2pool neoscrypt module and defined the input value of the hashing procedure as constant in the c-code. It seems to calculate correctly.

Also the target on p2pool measured against seems to be fine.

I assume, that the return value from the neoscrypt module either has an overflow or is interpreted wrong. may be wrong type, little/big endian problem or whatever.

------------- Edit---------------

Checked type of pow_hash and target in work.py -> both variables have type ‘long’

ghostlander

If you switch CPUminer in debug mode with -D, you can see P2Pool asking for incorrect targets:

[2014-08-10 21:21:12] 1 miner threads started, using 'neoscrypt' algorithm.
[2014-08-10 21:21:15] Long-polling activated for http://prometheus.phoenixcoin.org:20554/long-polling
[2014-08-10 21:21:15] DEBUG: got new work in 3062 ms
[2014-08-10 21:21:16] DEBUG (little endian): hash

Wellenreiter

It is working now for long-poll.

No support for stratum at the moment, even if work is distributed, no valid blocks can be mined via stratum.

A new version is on github

lizhi

Yes, It work! >:D

wrapper

neoscrypt p2pool dev testing cpu mine phoenixcoin

http://95.85.57.10:10554

Longpoll works, so start minerd with ‘–no-stratum’

useing Ghostlander’s Github (for minerd)

https://github.com/g…r-neoscrypt.git