You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
So far I haven't changed a single config of the servers, so they are far from the ideal setup for production env.
By first round I mean that since we do not have any traffic or data, the best we can do for now is guess (based on gut/experience) the best tunable values. Once we do have some data we can proceed to the second round of optimization.
Special stuff that comes to mind: sysctl, user limit, networking stack, ZFS compression/dedup.
Service-specific optimizations (nginx, haproxy, pg) are out of scope for this issue, but a new one should be create (at least to assess how well optimized they are).
The text was updated successfully, but these errors were encountered:
So far I haven't changed a single config of the servers, so they are far from the ideal setup for production env.
By first round I mean that since we do not have any traffic or data, the best we can do for now is guess (based on gut/experience) the best tunable values. Once we do have some data we can proceed to the second round of optimization.
Special stuff that comes to mind: sysctl, user limit, networking stack, ZFS compression/dedup.
Service-specific optimizations (nginx, haproxy, pg) are out of scope for this issue, but a new one should be create (at least to assess how well optimized they are).
The text was updated successfully, but these errors were encountered: