Todd Lipcon has posted comments on this change. ( http://gerrit.cloudera.org:8080/12987 )
Change subject: IMPALA-8341: Data cache for remote reads ...................................................................... Patch Set 4: (1 comment) http://gerrit.cloudera.org:8080/#/c/12987/4/be/src/runtime/io/data-cache.h File be/src/runtime/io/data-cache.h: http://gerrit.cloudera.org:8080/#/c/12987/4/be/src/runtime/io/data-cache.h@88 PS4, Line 88: /// - bound number of backing files per partition by consolidating the content of very > Yeah this scenario is a bit concerning for me still since it's conceivable I think with our current assumption of 4TB of logical space per file, if you assume you're writing a relatively aggressive estimate of 100MB/sec to the cache in a super heavy workload, then you'll only need to roll to a new file every 11 hours. So, 1000 file descriptors will last you over a year. Given that fd counts can be set into the 100k range without any real issues, I don't think this is going to be too problematic under these assumptions. If we find that we need to support a smaller "rolling" interval than 4TB for some reason, we'll definitely need to address it, but it seems like a lot of complexity to take for now. -- To view, visit http://gerrit.cloudera.org:8080/12987 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-Project: Impala-ASF Gerrit-Branch: master Gerrit-MessageType: comment Gerrit-Change-Id: I734803c1c1787c858dc3ffa0a2c0e33e77b12edc Gerrit-Change-Number: 12987 Gerrit-PatchSet: 4 Gerrit-Owner: Michael Ho <k...@cloudera.com> Gerrit-Reviewer: David Rorke <dro...@cloudera.com> Gerrit-Reviewer: Impala Public Jenkins <impala-public-jenk...@cloudera.com> Gerrit-Reviewer: Joe McDonnell <joemcdonn...@cloudera.com> Gerrit-Reviewer: Lars Volker <l...@cloudera.com> Gerrit-Reviewer: Michael Ho <k...@cloudera.com> Gerrit-Reviewer: Sahil Takiar <stak...@cloudera.com> Gerrit-Reviewer: Thomas Marshall <tmarsh...@cloudera.com> Gerrit-Reviewer: Tim Armstrong <tarmstr...@cloudera.com> Gerrit-Reviewer: Todd Lipcon <t...@apache.org> Gerrit-Comment-Date: Thu, 25 Apr 2019 18:05:56 +0000 Gerrit-HasComments: Yes