mirror of
https://github.com/status-im/nimbus-eth2.git
synced 2025-01-09 05:52:45 +00:00
aabdd34704
Era files contain 8192 blocks and a state corresponding to the length of the array holding block roots in the state, meaning that each block is verifiable using the pubkeys and block roots from the state. Of course, one would need to know the root of the state as well, which is available in the first block of the _next_ file - or known from outside. This PR also adds an implementation to write e2s, e2i and era files, as well as a python script to inspect them. All in all, the format is very similar to what goes on in the network requests meaning it can trivially serve as a backing format for serving said requests. Mainnet, up to the first 671k slots, take up 3.5gb - in each era file, the BeaconState contributes about 9mb at current validator set sizes, up from ~3mb in the early blocks, for a grand total of ~558mb for the 82 eras tested - this overhead could potentially be calculated but one would lose the ability to verify individual blocks (eras could still be verified using historical roots). ``` -rw-rw-r--. 1 arnetheduck arnetheduck 16 5 mar 11.47 ethereum2-mainnet-00000000-00000001.e2i -rw-rw-r--. 1 arnetheduck arnetheduck 1,8M 5 mar 11.47 ethereum2-mainnet-00000000-00000001.e2s -rw-rw-r--. 1 arnetheduck arnetheduck 65K 5 mar 11.47 ethereum2-mainnet-00000001-00000001.e2i -rw-rw-r--. 1 arnetheduck arnetheduck 18M 5 mar 11.47 ethereum2-mainnet-00000001-00000001.e2s ... -rw-rw-r--. 1 arnetheduck arnetheduck 65K 5 mar 11.52 ethereum2-mainnet-00000051-00000001.e2i -rw-rw-r--. 1 arnetheduck arnetheduck 68M 5 mar 11.52 ethereum2-mainnet-00000051-00000001.e2s -rw-rw-r--. 1 arnetheduck arnetheduck 61K 5 mar 11.11 ethereum2-mainnet-00000052-00000001.e2i -rw-rw-r--. 1 arnetheduck arnetheduck 62M 5 mar 11.11 ethereum2-mainnet-00000052-00000001.e2s ```
50 lines
1.3 KiB
Python
50 lines
1.3 KiB
Python
import sys, struct
|
|
|
|
def read_e2store(name):
|
|
with open(name, "rb") as f:
|
|
header = f.read(8)
|
|
typ = header[0:2] # First 2 bytes for type
|
|
|
|
if typ != b"e2":
|
|
raise RuntimeError("this is not an e2store file")
|
|
|
|
while True:
|
|
header = f.read(8) # Header is 8 bytes
|
|
if not header: break
|
|
|
|
typ = header[0:2] # First 2 bytes for type
|
|
dlen = struct.unpack("<q", header[2:8] + b"\0\0")[0] # 6 bytes of little-endian length
|
|
|
|
data = f.read(dlen)
|
|
if len(data) != dlen: # Don't trust the given length, specially when pre-allocating
|
|
raise RuntimeError("File is missing data")
|
|
|
|
if typ == b"i2":
|
|
raise RuntimeError("Cannot switch to index mode")
|
|
elif typ == b"e2":
|
|
pass # Ignore extra headers
|
|
|
|
yield (typ, data)
|
|
|
|
def find_offset(name, slot):
|
|
# Find the offset of a given slot
|
|
with open(name, "rb") as f:
|
|
header = f.read(8)
|
|
typ = header[0:2] # First 2 bytes for type
|
|
|
|
if typ != b"i2":
|
|
raise RuntimeError("this is not an e2store file")
|
|
|
|
start_slot = struct.unpack("<q", f.read(8))[0]
|
|
|
|
f.seek(8 * (slot - start_slot) + 16)
|
|
|
|
return struct.unpack("<q", f.read(8))[0]
|
|
|
|
name = sys.argv[1]
|
|
if name.endswith(".e2i"):
|
|
print(find_offset(name, int(sys.argv[2])))
|
|
else:
|
|
for typ, data in read_e2store(name):
|
|
print("typ", typ, "data", len(data))
|