Ask Your Question

Ivan Pustovalov's profile - activity

2016-08-26 11:32:33 -0500 received badge  Taxonomist
2015-05-29 02:09:38 -0500 received badge  Famous Question (source)
2015-05-29 02:09:38 -0500 received badge  Notable Question (source)
2015-05-29 02:09:38 -0500 received badge  Popular Question (source)
2014-10-09 09:31:50 -0500 answered a question Openstack Swift Connection and Lock Timeouts on account and object server

Still no answers or questions? There is no person interested in swift development? Does anyone know a faster way to get answers?

2014-10-09 06:30:10 -0500 received badge  Editor (source)
2014-10-06 01:35:25 -0500 asked a question Openstack Swift Connection and Lock Timeouts on account and object server

Hi, we are having a problem with connection and lock timeouts on 5-nodes 3-replicas swift cluster. Each account and object server has SSD, each object node has 12 SATA hard drives. Current system info: 1 account, 1.5 million containers, 40 million objects (distributed uniformly), 3 TB used.

And logs have a lot of connection and lock timeouts for account (0.5s, 10s) and container (1s, 10s) servers. Importantly, object replicators are disabled because it gives an increased load (perhaps, this is a topic for another question).

2014-06-13 15:02:53 -0500 received badge  Nice Question (source)
2014-05-14 23:27:46 -0500 received badge  Famous Question (source)
2014-03-31 00:39:59 -0500 received badge  Notable Question (source)
2014-03-19 00:20:49 -0500 received badge  Enthusiast
2014-03-17 08:22:13 -0500 commented question openstack swift small objects put performance

1 SATA drive is for daemons. And 1 SATA drive is for object storage. During testing, we found that disabling supporting daemons(e.g. container-updater) may increase performance.

2014-03-17 03:46:22 -0500 received badge  Popular Question (source)
2014-03-07 14:51:40 -0500 received badge  Student (source)
2014-03-07 01:36:41 -0500 asked a question openstack swift small objects put performance

HI! I have a cluster of 5 nodes with 3 replicas. All of the servers (e.g. proxy, account, object, container ) are installed on a single server, and I have 5 of these servers. I send put object requests from one testing thread and check client response time from cluster. And obtained results did not satisfy me. When I was researching tcp traffic, I found time loss on waiting HTTP 100 from object servers, 10-15 ms on each and 10 ms on proxy while checking quorum.

In my case, users can put small objects (e.g. 16 kbytes) into the cloud and I look forward to a load of 2000 requests per second. This time loss significantly reduces cloud performance. How I can reduce this time loss and what are best practices for tuning(tuning from deployment guide was already provided)?