23.07.2014 Views

Lustre 1.6 Operations Manual

Lustre 1.6 Operations Manual

Lustre 1.6 Operations Manual

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

9.1.3 Resetting the Quota<br />

To reset the quota that was previously established for a user, run:<br />

# setquota -u $user 0 0 0 0 /srv/testfs<br />

Then run:<br />

# setquota -u $user a b c d /srv/testfs<br />

Caution – Do not use # lfs setquota to reset the previously-established quota.<br />

9.1.4 Quota Allocation<br />

The Linux kernel sets a default quota size of 1 MB. (For a block, the default is 100<br />

MB. For files, the default is 5000.) <strong>Lustre</strong> handles quota allocation in a different<br />

manner. A quota must be set properly or users may experience unnecessary failures.<br />

The filesystem block quota is divided up among the OSTs within the filesystem.<br />

Each OST requests an allocation which is increased up to the quota limit. The quota<br />

allocation is then quantized to reduce the number of quota-related request traffic. By<br />

default, <strong>Lustre</strong> supports both user and group quotas to limit disk usage and file<br />

counts.<br />

The quota system in <strong>Lustre</strong> is completely compatible with the quota systems used on<br />

other file systems. The <strong>Lustre</strong> quota system distributes quotas from the quota master.<br />

Generally, the MDS is the quota master for both inodes and blocks. All OSTs and the<br />

MDS are quota slaves to the OSS nodes. The minimum transfer unit is 100 MB, to<br />

avoid performance impacts for quota adjustments. The filesystem block quota is<br />

divided up among the OSTs and the MDS within the file system. Only the MDS uses<br />

the filesystem inode quota.<br />

This means that the minimum quota for block is 100 MB* (the number of OSTs + the<br />

number of MDSs), which is 100 MB* (number of OSTs + 1). The minimum quota for<br />

inode is the inode qunit. If you attempt to assign a smaller quota, users maybe not<br />

be able to create files. The default is established at filesystem creation time, but can<br />

be tuned via /proc values (described below). The inode quota is also allocated in a<br />

quantized manner on the MDS.<br />

9-6 <strong>Lustre</strong> <strong>1.6</strong> <strong>Operations</strong> <strong>Manual</strong> • September 2008

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!