Re: [luminous 12.2.2] Cluster write performance degradation problem(possibly tcmalloc related)

["shadow_lin"<shadow_lin@xxxxxxx>]

I have disabled scrub before the test.

 

2017-12-27

---

shadow_lin

---

发件人：Webert de Souza Lima <webert.boss@xxxxxxxxx>

发送时间：2017-12-22 20:37

主题：Re: [ceph-users] [luminous 12.2.2] Cluster write performance degradation problem(possibly tcmalloc related)

收件人："ceph-users"<ceph-users@xxxxxxxxxxxxxx>

抄送：

 

On Thu, Dec 21, 2017 at 12:52 PM, shadow_lin <shadow_lin@xxxxxxx> wrote:

After 18:00 suddenly the write throughput dropped and the osd latency increased. TCmalloc started relcaim page heap freelist much more frequently.All of this happened very fast and every osd had the indentical pattern.

Could that be caused by OSD scrub?  Check your "osd_scrub_begin_hour"

 

  ceph daemon osd.$ID config show | grep osd_scrub

Regards,

Webert Lima

DevOps Engineer at MAV Tecnologia

Belo Horizonte - Brasil

IRC NICK - WebertRLZ

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com