From 186c03c2b9e1b08e4298383fc6593d1b2c3a5dd8 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 25 Sep 2018 15:44:39 -0700 Subject: start organizing notes into subdirectories --- notes/bootstrap/import_timing_20180920.txt | 96 ++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 notes/bootstrap/import_timing_20180920.txt (limited to 'notes/bootstrap/import_timing_20180920.txt') diff --git a/notes/bootstrap/import_timing_20180920.txt b/notes/bootstrap/import_timing_20180920.txt new file mode 100644 index 00000000..a57ffd77 --- /dev/null +++ b/notes/bootstrap/import_timing_20180920.txt @@ -0,0 +1,96 @@ + +This was on fatcat-prod-vm (2TB disk). + + time ./fatcat_import.py import-issn /srv/fatcat/datasets/journal_extra_metadata.csv + + Processed 53300 lines, inserted 53283, updated 0. + real 0m32.463s + user 0m8.716s + sys 0m0.284s + + time parallel --bar --pipepart -j8 -a /srv/fatcat/datasets/public_profiles_1_2_json.all.json ./fatcat_import.py import-orcid - + + Processed 48900 lines, inserted 48731, updated 0. <= these numbers times 80x + 100% 80:0=0s + + real 10m20.598s + user 26m16.544s + sys 1m40.284s + + time xzcat /srv/fatcat/datasets/crossref-works.2018-01-21.json.xz | time parallel -j20 --round-robin --pipe ./fatcat_import.py import-crossref - /srv/fatcat/datasets/20180216.ISSN-to-ISSN-L.txt /srv/fatcat/datasets/release_ids.ia_munge_20180908.sqlite3 + + Processed 4679900 lines, inserted 3755867, updated 0. + 107730.08user 4110.22system 16:31:25elapsed 188%CPU (0avgtext+0avgdata 447496maxresident)k + 77644160inputs+361948352outputs (105major+49094767minor)pagefaults 0swaps + + => 16.5 hours, faster! + + select count(id) from release_ident; => 75106713 + + kernel/system crashed after first file import (!), so don't have numbers from that. + +Table sizes at this point: + + select count(id) from file_ident; => 6334606 + + Size: 389.25G + + table_name | table_size | indexes_size | total_size +--------------------------------------------------------------+------------+--------------+------------ + "public"."release_ref" | 170 GB | 47 GB | 217 GB + "public"."release_rev" | 44 GB | 21 GB | 65 GB + "public"."release_contrib" | 19 GB | 20 GB | 39 GB + "public"."release_edit" | 6671 MB | 6505 MB | 13 GB + "public"."work_edit" | 6671 MB | 6505 MB | 13 GB + "public"."release_ident" | 4892 MB | 5875 MB | 11 GB + "public"."work_ident" | 4892 MB | 5874 MB | 11 GB + "public"."work_rev" | 3174 MB | 2936 MB | 6109 MB + "public"."file_rev_url" | 3634 MB | 1456 MB | 5090 MB + "public"."file_rev" | 792 MB | 1281 MB | 2073 MB + "public"."abstracts" | 1665 MB | 135 MB | 1800 MB + "public"."file_edit" | 565 MB | 561 MB | 1126 MB + "public"."file_release" | 380 MB | 666 MB | 1045 MB + "public"."file_ident" | 415 MB | 496 MB | 911 MB + "public"."creator_rev" | 371 MB | 457 MB | 828 MB + "public"."creator_edit" | 347 MB | 353 MB | 700 MB + "public"."creator_ident" | 255 MB | 305 MB | 559 MB + "public"."release_rev_abstract" | 183 MB | 237 MB | 421 MB + "public"."changelog" | 122 MB | 126 MB | 247 MB + "public"."editgroup" | 138 MB | 81 MB | 219 MB + "public"."container_rev" | 52 MB | 38 MB | 89 MB + "public"."container_edit" | 32 MB | 30 MB | 62 MB + "public"."container_ident" | 24 MB | 28 MB | 52 MB + + + relname | too_much_seq | case | rel_size | seq_scan | idx_scan +----------------------+--------------+------+--------------+----------+---------- + release_edit | 0 | OK | 6993084416 | 0 | 0 + container_rev | 0 | OK | 54124544 | 0 | 0 + creator_ident | 0 | OK | 266919936 | 0 | 0 + creator_edit | 0 | OK | 363921408 | 0 | 0 + work_rev | 0 | OK | 3327262720 | 0 | 0 + creator_rev | 0 | OK | 388726784 | 0 | 0 + work_ident | 0 | OK | 5128560640 | 0 | 0 + work_edit | 0 | OK | 6993108992 | 0 | 0 + container_ident | 0 | OK | 25092096 | 0 | 0 + file_edit | 0 | OK | 598278144 | 0 | 0 + container_edit | 0 | OK | 33857536 | 0 | 0 + changelog | 0 | OK | 127549440 | 0 | 0 + abstracts | -4714 | OK | 1706713088 | 0 | 4714 + file_release | -13583 | OK | 401752064 | 0 | 13583 + file_rev_url | -13583 | OK | 3832389632 | 0 | 13583 + editgroup | -74109 | OK | 144277504 | 0 | 74109 + release_contrib | -76699 | OK | 20357849088 | 0 | 76699 + release_ref | -76700 | OK | 183009157120 | 3 | 76703 + release_rev_abstract | -76939 | OK | 192102400 | 0 | 76939 + release_rev | -77965 | OK | 47602647040 | 0 | 77965 + file_ident | -100089 | OK | 438255616 | 3 | 100092 + release_ident | -152809 | OK | 5128617984 | 0 | 152809 + file_rev | -440780 | OK | 837705728 | 0 | 440780 +(23 rows) + +Continuing imports: + + zcat /srv/fatcat/datasets/2018-08-27-2352.17-matchcrossref.insertable.json.gz | pv -l | time parallel -j12 --round-robin --pipe ./fatcat_import.py import-matched - + => HTTP response body: {"message":"duplicate key value violates unique constraint \"file_edit_editgroup_id_ident_id_key\""} + -- cgit v1.2.3