<font size=2 face="sans-serif">Please clarify and elaborate .... When
you write "a full backup ... takes 60 days" - that seems
very poor indeed.</font><br><font size=2 face="sans-serif">BUT you haven't stated how much data
is being copied to what kind of backup media nor how much equipment or
what types you are using... Nor which backup software... </font><br><br><font size=2 face="sans-serif">We have Spectrum Scale installation
doing nightly backups of huge file systems using the mmbackup command with
TivoliStorageManager backup, using IBM branded or approved equipment and
software.</font><br><br><br><br><font size=1 color=#5f5f5f face="sans-serif">From:
</font><font size=1 face="sans-serif">"Tomasz.Wolski@ts.fujitsu.com"
<Tomasz.Wolski@ts.fujitsu.com></font><br><font size=1 color=#5f5f5f face="sans-serif">To:
</font><font size=1 face="sans-serif">"gpfsug-discuss@spectrumscale.org"
<gpfsug-discuss@spectrumscale.org></font><br><font size=1 color=#5f5f5f face="sans-serif">Date:
</font><font size=1 face="sans-serif">02/08/2018 05:50 AM</font><br><font size=1 color=#5f5f5f face="sans-serif">Subject:
</font><font size=1 face="sans-serif">[gpfsug-discuss]
Inode scan optimization</font><br><font size=1 color=#5f5f5f face="sans-serif">Sent by:
</font><font size=1 face="sans-serif">gpfsug-discuss-bounces@spectrumscale.org</font><br><hr noshade><br><br><br><font size=2 face="Calibri">Hello All,</font><br><font size=2 face="Calibri"> </font><br><font size=2 face="Calibri">A full backup of an 2 billion inodes spectrum
scale file system on V4.1.1.16 takes 60 days.</font><br><font size=2 face="Calibri"> </font><br><font size=2 face="Calibri">We try to optimize and using inode scans
seems to improve, even when we are using a directory scan and the inode
scan just for having a better performance concerning stat (using gpfs_stat_inode_with_xattrs64).
With 20 processes in parallel doing dir scans (+ inode scans for stat info)
we have decreased the time to 40 days.</font><br><font size=2 face="Calibri">All NSDs are dataAndMetadata type.</font><br><font size=2 face="Calibri"> </font><br><font size=2 face="Calibri">I have the following questions:</font><br><font size=2 face="Symbol">· </font><font size=2 face="Calibri">Is
there a way to increase the inode scan cache (we may use 32 GByte)? </font><br><font size=2 face="Courier New">o </font><font size=2 face="Calibri">Can
we us the \u201chidden\u201d config parameters</font><br><font size=2 face="Wingdings">§ </font><font size=2 face="Calibri"> iscanPrefetchAggressiveness 2</font><br><font size=2 face="Wingdings">§ </font><font size=2 face="Calibri"> iscanPrefetchDepth 0</font><br><font size=2 face="Wingdings">§ </font><font size=2 face="Calibri"> iscanPrefetchThreadsPerNode 0</font><br><font size=2 face="Symbol">· </font><font size=2 face="Calibri">Is
there a documentation concerning cache behavior?</font><br><font size=2 face="Courier New">o </font><font size=2 face="Calibri">if
no, is the inode scan cache process or node specific?</font><br><font size=2 face="Courier New">o </font><font size=2 face="Calibri">Is
there a suggestion to optimize the termIno parameter in the gpfs_stat_inode_with_xattrs64()
in such a use case?</font><br><font size=2 face="Calibri"> </font><br><font size=2 face="Calibri">Thanks! </font><br><font size=2 face="Calibri"> </font><br><font size=2 face="Calibri">Best regards,</font><br><font size=2 face="Calibri">Tomasz Wolski</font><tt><font size=2>_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org<br></font></tt><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-siA1ZOg&r=cvpnBBH0j41aQy0RPiG2xRL_M8mTc1izuQD3_PmtjZ8&m=mWxVB2lS_snDiYR4E348tnzbQTSuuWSrRiBDhJPjyh8&s=FG9fDxbmiCuSh0cvt4hsQS0bKdGHjI7loVGEKO0eTf0&e="><tt><font size=2>https://urldefense.proofpoint.com/v2/url?u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-siA1ZOg&r=cvpnBBH0j41aQy0RPiG2xRL_M8mTc1izuQD3_PmtjZ8&m=mWxVB2lS_snDiYR4E348tnzbQTSuuWSrRiBDhJPjyh8&s=FG9fDxbmiCuSh0cvt4hsQS0bKdGHjI7loVGEKO0eTf0&e=</font></tt></a><tt><font size=2><br></font></tt><br><br><BR>