Hacker News new | ask | show | jobs
by silvestrov 688 days ago
On my M1 mac "dd ... | cksum" takes 3 seconds while "dd | shasum" (sha1) takes 2 seconds. So cksum might not be the best tool for performance checking.

There is CPU specific code in the PG source in src/include/storage/checksum_impl.h

It is written as a plain nested loop in C. So performance is fully dependent on the compiler being able to parallelize or vectorize the code.

I would not be surprised if manually written SIMD code would be faster.
2 comments
anarazel 687 days ago
The bottleneck isn't at all the checksum computation itself. It's that to keep checksums valid we need to protect against the potential of torn pages even in cases where it doesn't matter without checksums (i.e. were just individual bits are flipped). That in turn means we need to WAL log changes we don't need to without checksums - which can be painful.
link
Joe_Cool 687 days ago
Interesting. I guess M1 doesn't have the 'crc32' "acceleration" that is included in SSE4.2.
link
loeg 687 days ago
M1 has CRC32 acceleration intrinsics.

https://dougallj.wordpress.com/2022/05/22/faster-crc32-on-th...

https://github.com/corsix/fast-crc32?tab=readme-ov-file#appl...

link
silvestrov 687 days ago
So when using these intrinsics an Intel Core i7 can do 30 GB/s but the performance check linked above (by isosphere ) says only 300 MB/s, i.e. 1%

Something is amiss here.

If a CPU can do 30 GB/s then a CRC check should not have any real performance impact.

link
loeg 687 days ago
I don't know where you're getting 300 MB/s from.
link
silvestrov 687 days ago
Page 5 of https://www-staging.commandprompt.com/uploads/images/Command... says "This system can checksum data at about 300 MB/s per core."

It lacks page numbers. Page 5 is first page with gray box at the top of the page.

link
loeg 686 days ago
That's measuring 'cksum', which must have an awfully slow implementation. The document notes that this is distinct from measuring PG's checksum performance. (I think it's a pretty useless measurement.)

Earlier (page 4):

> How much CPU time does it take to checksum...

> ...a specific amount of data? This is easy to estimate because PostgreSQL uses the crc32 algorithm which is very simple, and (GNU) Linux has a command line program that does the same thing: cksum.

Yeah, using cksum as an estimate here appears to be very flawed.

link