unofficial mirror of meta@public-inbox.org
 help / color / mirror / Atom feed
* [WIP PATCH 0/12] v2: git repo rotation + parallel Xapian indexing
@ 2018-02-22 21:42 Eric Wong (Contractor, The Linux Foundation)
  2018-02-22 21:42 ` [PATCH 01/12] import: allow the epoch (0s) as a valid time Eric Wong (Contractor, The Linux Foundation)
                   ` (12 more replies)
  0 siblings, 13 replies; 14+ messages in thread
From: Eric Wong (Contractor, The Linux Foundation) @ 2018-02-22 21:42 UTC (permalink / raw)
  To: meta

The key thing is sharding git and sharding of Xapian are not
tied together:

git repos are sharded to reduce clone/repack costs; so we shard
them based on size (currently 1G or so).

Xapian DBs are sharded to take advantage of SMP during the indexing
phase.

Current import times are as follows:

                  git-only:  ~1 minute
                git+SQLite: ~12 minutes
 git+Xapian+SQLite  serial: ~45 minutes
 git+Xapian+SQLite 4 parts: ~15 minutes (2 + 2 hyperthread)

More cores will help since the Xapian text+term indexing is the
slowest and the only partitioned work.

I also tested just the December 2017 archives on an 8-core AMD
FX-8320.  I forget the specifics, but I seem to recall half the
cores on that chip are not full power:

	4 parts: 58s
	8 parts: 45s

Note: I use eatmydata (LD_PRELOAD to disable sync/fsync) for development
and I consider it perfectly safe to use for offline updates/reindexing.


^ permalink raw reply	[flat|nested] 14+ messages in thread

end of thread, other threads:[~2018-02-23  1:22 UTC | newest]

Thread overview: 14+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2018-02-22 21:42 [WIP PATCH 0/12] v2: git repo rotation + parallel Xapian indexing Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 01/12] import: allow the epoch (0s) as a valid time Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 02/12] extmsg: fix broken Xapian MID lookup Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 03/12] search: stop assuming Message-ID is unique Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 04/12] www: stop assuming mainrepo == git_dir Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 05/12] v2writable: initial cut for repo-rotation Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 06/12] git: reload alternates file on missing blob Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 07/12] v2: support Xapian + SQLite indexing Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 08/12] import_vger_from_inbox: allow "-V" option Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 09/12] import_vger_from_mbox: use PublicInbox::MIME and avoid clobbering Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 10/12] v2: parallelize Xapian indexing Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 11/12] v2writable: round-robin to partitions based on article number Eric Wong (Contractor, The Linux Foundation)
2018-02-22 21:42 ` [PATCH 12/12] searchidxpart: increase pipe size for partitions Eric Wong (Contractor, The Linux Foundation)
2018-02-23  1:22 ` [WIP PATCH 0/12] v2: git repo rotation + parallel Xapian indexing Eric Wong

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).