Closed Bug 878111 Opened 12 years ago Closed 11 years ago

Increase memcache/membase capacity to allow for client writethrough cache

Categories

(Cloud Services :: Operations: Miscellaneous, task)

Product:
Cloud Services
Component:
Operations: Miscellaneous
Platform:
x86
macOS
Type:
task
Priority:
Not set
Severity:
normal

Tracking

(Not tracked)

Status:
VERIFIED FIXED

People

(Reporter: telliott, Assigned: bobm)

References

Details

(Whiteboard: [qa+])

Calls to the client collection account for ~ 25% of our database read requests. Given that it's a small collection (rarely > 3 records, usually one), it's a good candidate for a writethrough cache. However, bobm suggests that we're experiencing some memory pressure on the current memcache cluster. Since it's important that this not crowd out any info/collections calls, we should make sure we have the increased capacity to handle that.
QA Contact: jbonacci
Whiteboard: [qa+]
Taking this bug.
Assignee: nobody → bobm
Status: NEW → ASSIGNED
The caching tier has been expanding. It's presently around 50% capacity.
Status: ASSIGNED → RESOLVED
Closed: 11 years ago
Resolution: --- → FIXED
Cleaning out ye olde bugs...
Status: RESOLVED → VERIFIED
Component: Operations: Hardware → Operations
You need to log in before you can comment on or make changes to this bug.