Modeling Performance of Microservices Systems with Growth Theory.

CONTEXT: The microservices architectural style is gaining momentum in the IT industry. This style does not guarantee that a target system can continuously meet acceptable performance levels. The ability to study the violations of performance requirements and eventually predict them would help practitioners to tune techniques like dynamic load balancing or horizontal scaling to achieve the resilience property. OBJECTIVE: The goal of this work is to study the violations of performance requirements of microservices through time series analysis and provide practical instruments that can detect resilient and non-resilient microservices and possibly predict their performance behavior. METHOD: We introduce a new method based on growth theory to model the occurrences of violations of performance requirements as a stochastic process. We applied our method to an in-vitro e-commerce benchmark and an in-production real-world telecommunication system. We interpreted the resulting growth models to characterize the microservices in terms of their transient performance behavior. RESULTS: Our empirical evaluation shows that, in most of the cases, the non-linear S-shaped growth models capture the occurrences of performance violations of resilient microservices with high accuracy. The bounded nature associated with this models tell that the performance degradation is limited and thus the microservice is able to come back to an acceptable performance level even under changes in the nominal number of concurrent users. We also detect cases where linear models represent a better description. These microservices are not resilient and exhibit constant growth and unbounded performance violations over time. The application of our methodology to a real in-production system identified additional resilience profiles that were not observed in the in-vitro experiments. These profiles show the ability of services to react differently to the same solicitation. We found that when a service is resilient it can either decrease the rate of the violations occurrences in a continuous manner or with repeated attempts (periodical or not). CONCLUSIONS: We showed that growth theory can be successfully applied to study the occurences of performance violations of in-vitro and in-production real-world systems. Furthermore, the cost of our model calibration heuristics, based on the mathematical expression of the selected non-linear growth models, is limited. We discussed how the resulting models can shed some light on the trend of performance violations and help engineers to spot problematic microservice operations that exhibit performance issues. Thus, meaningful insights from the application of growth theory have been derived to characterize the behavior of (non) resilient microservices operations.

Assessment of nocturnal hypertension by ambulatory blood pressure monitoring at the forearm in people with morbid obesity.

Blood pressure (BP) measurement at the forearm (FA) has been proposed as alternative site to upper arm (UA) in people with morbid obesity (MO). We compared nocturnal BP readings simultaneously taken at FA and UA by ambulatory blood pressure monitoring (ABPM). Fourteen individuals with MO and seven normal-weight controls underwent nocturnal ABPM with two devices placed at the UA and contralateral FA, respectively. Agreement between FA-UA BP, diagnosis of nocturnal hypertension, and potential determinants of BP differences were evaluated. BP at the FA was significantly higher than UA in both people with MO and controls. FA-UA differences in systolic and diastolic BP were similar in people with MO and controls. Nocturnal hypertension was diagnosed in 10 subjects (48%) according to UA BP and in 13 subjects (62%) according to FA BP (concordance 76%, moderate agreement). ΔFA-UA systolic BP was associated with ratio between FA/UA circumferences (R = 0.45, P < .05) and with cuff-UA slant angle difference (R = 0.44, P < .05). In conclusions, in people with MO, the agreement between FA and UA nighttime BP measured by ABPM is sub-optimal. Our results raise uncertainty in using ABPM at the FA as an alternative to UA placement in people with MO for the diagnosis of nocturnal hypertension.

Sleeve Gastrectomy Efficacy on Metabolic and Cardiovascular Dysfunction With a Focus on the Role of Comorbidities.

We evaluated the effects of sleeve gastrectomy (SG) on metabolic/cardiovascular parameters according to weight loss, visceral fat area (VFA), and homeostasis model assessment (HOMA)-insulin resistance index; we also assessed the influence of SG on comorbidities (diabetes/hypertension). At baseline and 10 to 12 months after SG, we assessed anthropometric and biochemical parameters, bioimpedentiometry, ultrasonographic VFA, liver steatosis, flow-mediated dilation, and echocardiography in 110 patients with obesity. We found that 23 (21%) patients had diabetes. Diabetic patients who normalized their glycated hemoglobin A1C (HbA1C) level experienced greater total weight loss (TWL), and the probability of normalizing HbA1C levels directly correlated with TWL. Diabetic patients experienced a greater improvement in systolic blood pressure, VFA, and high-density lipoprotein cholesterol than nondiabetics, while patients with hypertension experienced a greater improvement in VFA, triglycerides, HOMA, and HbA1C than nonhypertensive patients. The most important determinant of glucose control in diabetic patients was weight loss. Patients with diabetes and hypertension experienced a greater improvement in vascular and metabolic status after SG.