clusterdata
clusterdata copied to clipboard
alibaba
cluster data collected from production clusters in Alibaba for cluster management research
dose it mean "used percent of requested disk space"? does it consider the "writes_bytes" and "reads_bytes"? does it normalize to "the requested disk space of the container" or "the machine's...
I want to konw the difference between failed and terminated in the instance,thank you very munch!
Seems only instance ID is related and know of the disk space. I would like to know the disk space needed by a job or a task.
As mentioned in title, here is an example: in container_meta.csv, we have entries about c_1 with various timestamp, thus I expect that there are three instances of container "c_1" is...
Hi, when dealing with the `task_name` column of `batch_task.csv` in cluster-trace-v2018, I found two anomalies: 1. Some task names contain "Stg", e.g. J10_7_9_Stg4 (belonging to job j_9395). Judging from the...
What is the meaning of the normalized in coming network traffic? What does 100% correspond to? Is it the bandwidth allocated to the container? Or is it the bandwidth available...
My question is in column `plan_mem` in `batch_task.csv`. I am still a little bit confused about the normalization standard. The schema mentions this column, plan_mem, specifies normalized memory requested for...
Hi, may I ask how cpu_util_percent calculates?Cpu_util_percent is normalized to [0,100], but some invalid values are set to -1 or 101.What value is classified as invalid?What value is assigned to...
Hi,I want to know how the M, R, and J in the task name are named. What does it mean? There are 12 types of tasks, which are they? And...
"M5_3_4: means that task5 depends on both task3 and task4, that is, task5 cannot start before all instances of both task3 and task4 are completed.", which is read from "trace_2018.md(2.3...
