 | | | ext3: 40 sec i/o hesitations with data=journal | ext3: 40 sec i/o hesitations with data=journal 2004-02-10 - By Paul M Meyers
Back
2.4.20-28.7 kernel. ext3: 384Meg journal data=journal.
We run large journal sizes and sometimes see a few seconds of
hesitation when it is flushed. We can and do optimize by tweaking
bdflush times (down)on our servers....but
We have one interesting case that is defiant or is exhibiting some
other journal problem (then flush) where we are seeing a huge
hesitation (40 seconds) of i/o block. The hesitation happens aprox 7
times a day, and is consistantly 40 seconds and consistantly
(according to iostat) in a write "storm " of about 60Megs across the 40
seconds (60 Megs in 40 secs is not exactly a storm).
If this was a journal flush would 'nt I expect 384Megs (the actual size
of this particular journal) writing out? Nothing is writing to the
disk, so it has to be the journal, but what it is doing if not
flushing?
I have set it to data=ordered and the 40 second hesitation goes away
100%. We most often write to the middle of a file (without recreating
the file) so data=journal should be our choice (from what I gather).
Paul M Meyers
Systems Administrator
Community Computer Service
(315)-255-0900
--
This message and any attachments may contain information that is protected
by law as privileged and confidential, and is transmitted for the sole use
of the intended recipient(s). If you are not the intended recipient, you
are hereby notified that any use, dissemination, copying or retention of
this e-mail or the information contained herein is strictly prohibited. If
you have received this e-mail in error, please immediately notify the
sender by e-mail, and permanently delete this e-mail.
--
This message has been scanned for viruses and
dangerous content by MailScanner.
--
redhat-list mailing list
unsubscribe mailto:redhat-list-request@(protected)?subject=unsubscribe
https://www.redhat.com/mailman/listinfo/redhat-list
|
|
|