[ARVADOS] updated: 9ddb8e3b5106f885401927a513ac0d94a59133ed
Git user
git at public.curoverse.com
Wed Mar 2 12:18:21 EST 2016
Summary of changes:
sdk/cli/bin/crunch-job | 590 +++++++++++++++++++---------------
sdk/cli/test/binstub_clean_fail/mount | 2 +-
sdk/cli/test/test_crunch-job.rb | 2 +-
3 files changed, 334 insertions(+), 260 deletions(-)
via 9ddb8e3b5106f885401927a513ac0d94a59133ed (commit)
via 19cb98ad222177fb7dd3613282446060e74dd2ce (commit)
via 395d48a60ed557318833a5272ab00dce270cec40 (commit)
via fbd54468b13466839c24d880a3d041d0a49371af (commit)
via ad48bb33bf49e3fec668a0ccf788ad9b2ffcaa80 (commit)
via 3c90228c2e0466b2e69c08e0ad610dd5d619b4f8 (commit)
via d41563d9a62450f86214c4feac774dd82fc4311c (commit)
via f9d868590efb81cee078d19d3be91ef297634499 (commit)
from b026643583d835a15d3baf6edef2df16ce678307 (commit)
Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.
commit 9ddb8e3b5106f885401927a513ac0d94a59133ed
Merge: b026643 19cb98a
Author: Tom Clegg <tom at curoverse.com>
Date: Wed Mar 2 12:16:27 2016 -0500
Merge branch '8099-babysit-all-srun' closes #8099
commit 19cb98ad222177fb7dd3613282446060e74dd2ce
Merge: 395d48a b026643
Author: Tom Clegg <tom at curoverse.com>
Date: Wed Mar 2 12:16:19 2016 -0500
Merge branch 'master' into 8099-babysit-all-srun
Conflicts:
sdk/cli/bin/crunch-job
diff --cc sdk/cli/bin/crunch-job
index 14dac6a,ca6c47b..1a9dac3
--- a/sdk/cli/bin/crunch-job
+++ b/sdk/cli/bin/crunch-job
@@@ -1472,11 -1482,11 +1474,11 @@@ sub preprocess_stder
ban_node_by_slot($job_slot_index);
}
elsif ($line =~ /srun: error: (Unable to create job step|.*: Communication connection failure)/) {
- $jobstep[$job]->{tempfail} = 1;
- ban_node_by_slot($jobstep[$job]->{slotindex});
+ $jobstep[$jobstepidx]->{tempfail} = 1;
+ ban_node_by_slot($jobstep[$jobstepidx]->{slotindex});
}
- elsif ($line =~ /arvados\.errors\.Keep/) {
+ elsif ($line =~ /\bKeep(Read|Write|Request)Error:/) {
- $jobstep[$job]->{tempfail} = 1;
+ $jobstep[$jobstepidx]->{tempfail} = 1;
}
}
}
commit 395d48a60ed557318833a5272ab00dce270cec40
Author: Tom Clegg <tom at curoverse.com>
Date: Wed Mar 2 12:14:08 2016 -0500
8099: Remove duplicated line
diff --git a/sdk/cli/bin/crunch-job b/sdk/cli/bin/crunch-job
index ca9db1d..14dac6a 100755
--- a/sdk/cli/bin/crunch-job
+++ b/sdk/cli/bin/crunch-job
@@ -1467,7 +1467,6 @@ sub preprocess_stderr
}
elsif ($line =~ /srun: error: (Node failure on|Aborting, .*\bio error\b)/) {
my $job_slot_index = $jobstep[$jobstepidx]->{slotindex};
- my $job_slot_index = $jobstep[$jobstepidx]->{slotindex};
$slot[$job_slot_index]->{node}->{fail_count}++;
$jobstep[$jobstepidx]->{tempfail} = 1;
ban_node_by_slot($job_slot_index);
-----------------------------------------------------------------------
hooks/post-receive
--
More information about the arvados-commits
mailing list