1 / 17

Inherent Limitations on Disjoint-Access Parallel Transactional Memory

Inherent Limitations on Disjoint-Access Parallel Transactional Memory. Hagit Attiya, Eshcar Hillel, Alessia Milani Technion. Complexity Bounds for STMs: Why?. Indicate futile design choices Elucidate expectations (specification) Spell out assumptions (models of the architecture).

freira
Download Presentation

Inherent Limitations on Disjoint-Access Parallel Transactional Memory

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Inherent Limitations on Disjoint-Access Parallel Transactional Memory Hagit Attiya, Eshcar Hillel, Alessia MilaniTechnion Inherent limitations on DAP TMs

  2. Complexity Bounds for STMs: Why? • Indicate futile design choices • Elucidate expectations (specification) • Spell out assumptions (models of the architecture) Inherent limitations on DAP TMs

  3. DAP: Disjoint Access Parallelism T1 T3 T1 Read(Y) Write(X1) Write(X2) T2 T3 Read(X2) Read(X1) Improves scalability for large data structures by reducing interference Y X1 X2 Disjoint data sets  no contention Data sets are connected  may contend 3 3 Inherent limitations on DAP TMs

  4. Optimizing for Read-Only Transactions Transactions that do not modify the data should Be invisible (not write to low-level objects) Avoid contention for the memory Always terminate successfully (wait-free) 4 4 Inherent limitations on DAP TMs

  5. Some Known STMs… Coincidence or inherent tradeoff ? 5 5 Inherent limitations on DAP TMs

  6. Inherent Tradeoff Theorem. There is no TM implementation that is DAP and has invisible & wait-free read-only transactions The paper also shows a lower bound: Theorem. A transaction with a data set of size t must write to t-1 base objects Both proofs utilize the flippable execution, used to prove lower bounds for atomic snapshot objects [Israeli & Shirazi] [Attiya, Ellen & Fatourou] 6 6 Inherent limitations on DAP TMs

  7. Flippable Execution w/ 2 Updaters U0 … Ul-1 … Uk p1 Ek U1 …Ul … p2 s1 … sl-1sl … sk q A complete transaction in which p1 writes l-1 to X1 A read-only transaction by q that reads X1 , X2 Inherent limitations on DAP TMs

  8. U0 … Ul-1 … Uk p1 U1 …Ul … p2 s1 … sl-1sl … sk q Flippable Execution w/ 2 Updaters Ek Indistinguishable from executions where the order of (each pair of) updates is flipped… In one of two ways (forward and backward). Inherent limitations on DAP TMs

  9. U0 … Ul-1 … Uk p1 U1 …Ul … p2 s1 … sl-1sl … sk q Flippable Execution: Backward Flip Ek Backward Flip U0 … Ul-1 … Uk p1 U1 …Ul … p2 s1 … sl-1sl … sk q Inherent limitations on DAP TMs

  10. Why Flippable Executions? Lemma 1. The read-only transaction of q cannot terminate successfully Relies on strict serializabitly (~linearizability) • The serialization of committed transactions must preserve the real-time order of non-overlapping transactions Inherent limitations on DAP TMs

  11. U0 Ul-1 Uk U1 …Ul … Serialization of Ek U0 … Ul-1 … Uk p1 Ek U1 …Ul … p2 Returns (l-1,l-2) s1 … sl-1sl … sk q Serialization of Ek: Serialization point Inherent limitations on DAP TMs

  12. U0 U0 Ul-1 Uk U1 …Ul Ul-1 … Uk U1 …Ul … Nowhere to Serialize U0 … Ul-1 … Uk p1 Indistinguishable from some flip (say, backward) Ek U1 …Ul … p2 Returns (l-1,l-2) s1 … sl-1sl … sk q Serialization U0 … Ul-1 … Uk p1 BW Flip Still returns (l-1,l-2) U1 …Ul … p2 s1 … sl-1sl … sk q Serialization Inherent limitations on DAP TMs

  13. Completing the Proof Show that a flippable execution exists The read-only transaction is invisible its steps can be removed Transactions Ul & Ul-1have disjoint data sets  Ul & Ul-1do not “communicate” (by DAP)  Ul & Ul-1can be flipped By Lemma 1, the read-only transaction cannot terminate successfully If aborts, can apply the same argument again… 13 Inherent limitations on DAP TMs

  14. Complexity Bounds for STMs: What are the implications? • Adapt your expectations • What STM guarantees (e.g. consistency) • What you measure: • Best case, average case • Special workloads Inherent limitations on DAP TMs

  15. Weaker Liveness Condition If a transaction runs alone from a quiescent configuration then it terminates successfully Weakly progressive blocking implementation [Guerraoui & Kapalka] OUR RESULTS STILL HOLD Inherent limitations on DAP TMs

  16. Serializability Snapshot Isolation Virtual world consistency Causal consistency Causal serializability Weaker Consistency Conditions OUR RESULTS STILL HOLD OPEN PROBLEM 16 Inherent limitations on DAP TMs

  17. Thank you![paper in SPAA 09] Inherent limitations on DAP TMs

More Related