Tag
load-balancing
- Jul 25, 2026 Load Balancing Policy and Effective Capacity How assignment policy, connection reuse, and request-class knowledge change the throughput a pool can sustain, and why a policy tuned for latency can reduce total capacity. performance engineering
- Jun 22, 2026 CPU Affinity Masks and What Pinning Actually Costs How a task affinity mask restricts the scheduler, why pinning a thread can lower latency and raise queueing at the same time, and what the load balancer does when every task is pinned. memory systems
- Jun 17, 2026 Work Stealing and the Cost of Task Granularity How per-worker deques with stealing keep locality for producers and absorb imbalance, why the victim is chosen at the tail, and where the stealing overhead overtakes the gain. performance engineering
- Jan 18, 2026 Link Aggregation and the Hash That Chooses a Member How LACP bundles links, why the distributor hashes rather than round-robins, and the ordering guarantee that constrains every possible choice. networking
- Dec 8, 2025 Power of Two Choices and the Cost of a Random Probe Why sampling two backends and picking the less loaded one beats both random assignment and global state, and how stale or misleading load signals degrade the guarantee. backend systems
- Aug 11, 2025 Partitioning Work Across Devices and the Cost of Every Dependency How to split a computation across several devices without drowning it in synchronization, and why the cost of a dependency is set by the slowest participant. gpu computing
- Jul 23, 2025 Weighted Canary Routing at the Edge and What the Weight Measures Whether a traffic weight applies to connections, requests, or users, how hashing turns percentages into fixed partitions, and why small canaries cannot resolve small error differences. devops
- Apr 30, 2025 Load Balancing and Thread Migration on Symmetric Multiprocessors How per-CPU run queues are kept in balance without a global lock, when a thread is worth moving, and why affinity and NUMA topology constrain the answer. operating systems
- Dec 27, 2024 UDP Source Port Entropy and Underlay ECMP Why a tunnel collapses many flows onto one underlay path, how deriving the outer source port from an inner-header hash restores path diversity, and when the hash runs out of entropy. networking
- Dec 19, 2024 Blue-Green Cutover Mechanics at the Routing Layer Where the traffic switch actually happens, why DNS record changes make poor cutover levers, and what the standby fleet must be able to carry before and after the switch. devops
- Dec 13, 2024 Work Distribution, Join Barriers, and Idle Time at the End of a Stage Why splitting a stage across parallel workers shortens the mean but lengthens the tail, what a join barrier does to a request that has one slow participant, and the arithmetic of straggler cost. performance engineering
- Nov 19, 2024 Load Balancer Session Affinity and Its Failure Modes How sticky routing is implemented at layer 4 and layer 7, why consistent hashing limits the damage of a node loss, and which failures affinity cannot prevent. backend systems
- Oct 16, 2024 Load Balancer Listeners and Target Selection How a listener decides to accept a connection, how a target is chosen from a registered set, and why the balancer terminates the client connection instead of forwarding packets. cloud infrastructure
- Sep 22, 2024 Work-Stealing Deques and Why the Thief Takes the Oldest Task Per-worker deques with LIFO local execution and FIFO stealing keep hot data on one core, and the memory-ordering requirements that make the concurrent deque correct are narrower than they look. language runtimes
- Sep 14, 2023 Work Stealing: Per-Processor Deques and Why Thieves Take the Oldest Task How a work-stealing scheduler keeps locality by pushing and popping on one end of a deque while idle processors take from the other, and where the contention lands. algorithms
- Dec 26, 2022 Variance and the Effective Capacity of a Replica Pool How service-time variance and partially correlated demand shrink the throughput a pool can sustain at a latency target, and why replica count, not average load, sets the tail. performance engineering
- Oct 31, 2022 Least-Outstanding Routing When Request Costs Vary Round robin assumes equal service cost and equal replica capacity. Token generation breaks both assumptions, so routers score replicas by work in flight instead of counting requests. inference systems
- Aug 7, 2022 Hot Keys, Skew, and Load Imbalance in Hash Partitioning Why a partitioner that distributes keys evenly can still produce one task with sixty times the average work, and the static and sampled fixes that spread that load. data engineering