git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / code / Atom feed
* RFC: auto-enabling parallel-checkout on NFS
@ 2020-11-15 19:43 Matheus Tavares
  2020-11-16 15:19 ` Jeff Hostetler
  2020-11-19  9:01 ` Ævar Arnfjörð Bjarmason
  0 siblings, 2 replies; 10+ messages in thread
From: Matheus Tavares @ 2020-11-15 19:43 UTC (permalink / raw)
  To: git; +Cc: gerardu

Hi, everyone

I've been testing the parallel checkout code on some different machines,
to benchmark its performance against the sequential version. As
discussed in [1], the biggest speedups, on Linux, are usually seen on
SSDs and NFS volumes. (I haven't got the chance to benchmark on
Windows or OSX yet.)

Regarding NFS, I got some 2~3.4x speedups even when the NFS client and
server were both running on single-core machines. Here are some runtimes
for a linux-v5.8 clone (means of 5 cold-cache executions):

    nfs 3.0              nfs 4.0              nfs 4.1
1:  183.708 s ± 3.290 s  205.851 s ± 0.844 s  217.317 s ± 3.047 s
2:  130.510 s ± 3.917 s  139.124 s ± 0.772 s  142.963 s ± 0.765 s
4:   89.611 s ± 1.032 s  102.701 s ± 1.665 s   94.728 s ± 1.014 s
8:   68.097 s ± 0.820 s  104.914 s ± 1.239 s   69.359 s ± 0.619 s
16:  63.999 s ± 0.820 s  104.808 s ± 2.279 s   64.843 s ± 0.587 s
32:  62.316 s ± 2.095 s  102.105 s ± 1.537 s   64.122 s ± 0.374 s
64:  63.699 s ± 0.841 s  103.103 s ± 1.319 s   63.532 s ± 0.734 s

The parallel version was also faster for some smaller checkouts. For
example, the following numbers come from a bat-v0.16.0 clone
(251 files, ~3MB):

     nfs 3.0             nfs 4.0             nfs 4.1
1:   0.853 s ± 0.080 s   0.814 s ± 0.020 s   0.876 s ± 0.065 s
2:   0.671 s ± 0.020 s   0.702 s ± 0.030 s   0.705 s ± 0.030 s
4:   0.530 s ± 0.024 s   0.595 s ± 0.020 s   0.570 s ± 0.030 s
8:   0.470 s ± 0.033 s   0.609 s ± 0.025 s   0.510 s ± 0.031 s
16:  0.469 s ± 0.037 s   0.616 s ± 0.022 s   0.513 s ± 0.030 s
32:  0.487 s ± 0.030 s   0.639 s ± 0.018 s   0.527 s ± 0.028 s
64:  0.520 s ± 0.022 s   0.680 s ± 0.028 s   0.562 s ± 0.026 s

While looking at these numbers with Geert (in CC), he had the idea that
we could try to detect when the checkout path is within an NFS mount,
and auto-enable paralellism for this case. This way, users in NFS would
get the best performance by default. And it seems that using ~16 workers
would produce good results regardless of the NFS version that they might
be running.

The major downside is that detecting the file system type is quite
platform-dependent, so there is no simple and portable solution. (Also,
I'm not sure if the optimal number of workers would be the same on
different OSes). But we decided to give it a try, so this is a
rough prototype that would work for Linux:
https://github.com/matheustavares/git/commit/2e2c787e2a1742fed8c35dba185b7cd208603de9

Any thoughts on this idea? Or alternative suggestions?

Thanks,
Matheus

[1]: https://lore.kernel.org/git/815137685ac3e41444201316f537db9797dcacd2.1604521276.git.matheus.bernardino@usp.br/

^ permalink raw reply	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2020-11-24 13:00 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-11-15 19:43 RFC: auto-enabling parallel-checkout on NFS Matheus Tavares
2020-11-16 15:19 ` Jeff Hostetler
2020-11-19  4:01   ` Matheus Tavares
2020-11-19 14:04     ` Jeff Hostetler
2020-11-20 12:10       ` Ævar Arnfjörð Bjarmason
2020-11-23 23:18       ` Geert Jansen
2020-11-19  9:01 ` Ævar Arnfjörð Bjarmason
2020-11-19 14:11   ` Jeff Hostetler
2020-11-23 23:37   ` Geert Jansen
2020-11-24 12:58     ` Ævar Arnfjörð Bjarmason

Code repositories for project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).