From: Gregory Maxwell <gmaxwell@gmail•com>
To: Bitcoin Dev <bitcoin-development@lists•sourceforge.net>
Subject: [Bitcoin-development] Announcement: libcoin
Date: Thu, 2 Feb 2012 12:12:04 -0500 [thread overview]
Message-ID: <CAAS2fgR_r=NpFJJEQ=canx5noUeQDyJPYRJ4D5rzCGC_qLOgEg@mail.gmail.com> (raw)
In-Reply-To: <CAAS2fgSQZ1wv=OXnBnGbKnLTZXbn909umpPBaZDF2g6vy8katA@mail.gmail.com>
On Wed, Feb 1, 2012 at 9:18 AM, Michael Grønager
<gronager@ceptacle•com> > The libcoin/bitcoind client downloads the
entire block chain 3.5 times faster than the bitcoin/bitcoind client.
This is less than 90 minutes on a modern laptop!
I'm guessing that you benchmarked this against the version you forked
from rather than the current reference client?
If so— I suspect your speedup was almost entirely because you removed
the secure allocator and as a result fixed the mlock performance bug
[https://bitcointalk.org/index.php?topic=56491.0] as a side effect. On
some systems the mlock issue makes a very big difference (on other
systems not so much).
In any case, I finally got libbitcoin built and I'm disappointed to
report that in the same time it takes the reference client to fully
sync, libbitcoin only made it to height 138k (of course, because the
time is mostly spent late in the chain 138k is not very far along— I'm
guessing it's going to take libbitcoin 3x-4x longer all said)
I assume the reason it's actually slower is because it's CPU bound on
ECDSA checks, which are skipped in bitcoin in blocks up to the highest
hardcoded checkpoint. Without that difference I suspect libbitcoin
would be about the same speed— maybe a little faster because of the
other changes you mentioned (though, e.g. lock profiling shows hardly
any contention during sync).
I don't doubt your rpc performance is a lot better. There is a
longstanding pull request for async rpc for the reference client that
hasn't been merged.
next prev parent reply other threads:[~2012-02-02 17:12 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-01 14:18 Michael Grønager
2012-02-01 14:59 ` Gregory Maxwell
2012-02-01 15:50 ` Michael Grønager
2012-02-01 16:06 ` Jorge Timón
2012-02-01 15:02 ` Wladimir
2012-02-01 15:52 ` Michael Grønager
2012-02-01 15:09 ` slush
2012-02-01 15:57 ` Michael Grønager
2012-02-01 23:50 ` grarpamp
2012-02-02 8:32 ` Michael Grønager
2012-02-02 11:34 ` Craig B Agricola
2012-02-03 0:19 ` Pieter Wuille
2012-02-03 9:52 ` Michael Grønager
2012-02-01 15:26 ` Luke-Jr
2012-02-01 15:58 ` Michael Grønager
2012-02-01 16:15 ` Luke-Jr
2012-02-01 16:21 ` Michael Grønager
2012-02-01 16:23 ` Aidan Thornton
2012-02-01 16:20 ` Michael Grønager
2012-02-01 16:23 ` Luke-Jr
2012-02-01 17:37 ` Luke-Jr
2012-02-01 17:51 ` Michael Grønager
[not found] ` <CAAS2fgSQZ1wv=OXnBnGbKnLTZXbn909umpPBaZDF2g6vy8katA@mail.gmail.com>
2012-02-02 17:12 ` Gregory Maxwell [this message]
2012-02-02 17:36 ` Gregory Maxwell
2012-02-02 17:46 ` Gregory Maxwell
2012-02-23 17:31 ` Martinx - ジェームズ
2012-02-23 19:48 ` Michael Grønager
2012-02-23 20:01 ` Michael Grønager
2012-02-23 20:35 ` Michael Grønager
2012-02-23 23:29 ` Martinx - ジェームズ
2012-02-24 2:17 ` Martinx - ジェームズ
2012-02-24 7:44 ` Michael Grønager
2012-02-24 16:17 ` Michael Grønager
2012-02-24 18:49 ` Martinx - ジェームズ
2012-02-24 19:40 ` Michael Grønager
2012-02-24 19:57 ` Michael Grønager
2012-02-25 2:11 ` Martinx - ジェームズ
2012-02-26 17:57 ` Michael Grønager
2012-02-27 19:03 ` Martinx - ジェームズ
2012-02-27 21:03 ` Michael Grønager
2012-02-28 9:03 ` Michael Grønager
[not found] ` <CAJSM8J15LBiT9ojrPDE1-TXqmBLXcVvAmWw0e=5nQfLtMQ42Zg@mail.gmail.com>
[not found] ` <8CEEE576-37DF-4101-9593-73D5FB66D52F@ceptacle.com>
2012-03-22 10:48 ` Martinx - ジェームズ
2012-03-22 11:34 ` Michael Grønager
2012-03-28 7:59 ` Martinx - ジェームズ
2012-03-22 10:50 ` Martinx - ジェームズ
2012-03-22 11:35 ` Michael Grønager
2012-03-22 16:34 ` Peter Vessenes
2012-03-27 9:58 ` Martinx - ジェームズ
[not found] ` <B4616B21-7C05-4793-8452-376EE4122BEC@ceptacle.com>
2012-04-15 4:32 ` Martinx - ジェームズ
2012-07-16 20:14 ` Martinx - ジェームズ
2012-09-12 23:27 ` Martinx - ジェームズ
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAAS2fgR_r=NpFJJEQ=canx5noUeQDyJPYRJ4D5rzCGC_qLOgEg@mail.gmail.com' \
--to=gmaxwell@gmail$(echo .)com \
--cc=bitcoin-development@lists$(echo .)sourceforge.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox