Documentation #2983: doc: write performance monitoring - Ceph - Ceph

Actions

Copy link

Documentation #2983

closed

doc: write performance monitoring

Added by Ross Turk over 11 years ago. Updated over 5 years ago.

Status:

Rejected

Priority:

Normal

Assignee:

John Wilkins

Category:

Target version:

% Done:

Tags:

Backport:

Reviewed:

Affected Versions:

Pull request ID:

Actions

Copy link

Updated by Ross Turk over 11 years ago

Translation missing: en.field_position deleted (14)
Translation missing: en.field_position set to 8

Actions

Copy link

Updated by Ross Turk over 11 years ago

Translation missing: en.field_position deleted (11)
Translation missing: en.field_position set to 11

Actions

Copy link

Updated by Sage Weil over 11 years ago

Translation missing: en.field_position deleted (15)
Translation missing: en.field_position set to 16

Actions

Copy link

Updated by Ross Turk over 11 years ago

From Sage:

-- osds --

overall throughput
osd.op
osd.op_r
osd.op_w
osd.op_in_bytes
osd.op_out_bytes
filestore.bytes
filestore.ops

interesting for performance
osd.op_latency (average)
osd.op_r_latency (average)
osd.op_w_latency (average)
osd.opq queue length
osd.op_wip writes in progress
osd.recovery_ops
osd.numpg

fs performance
filestore.commitcycle_interval (average)
filestore.commitcycle_latency (average)

-- monitors --

overall cluster state
cluster.num_mon
cluster.num_mon_quorum
cluster.num_osd
cluster.num_osd_up
cluster.num_osd_in
cluster.num_pg
cluster.num_pg_active
cluster.num_pg_active_clean
cluster.num_objects
cluster.num_object_degraded
cluster.num_bytes
cluster.osd_kb
cluster.osd_kb_used
cluster.osd_kb_avail